The modern development of Medicine and Healthcare is primarily based on the automation of various processes to support the correct and timely medical decisions. A doctor or other medical staff's fast, accurate, reliable diagnosis, prevention, and treatment processes are the keys to quality patient care. This aim can be achieved by developing reliable, intelligent Healthcare and medicine service systems for various purposes. The Special Issue covers science-intensive real-time solutions that underlie smart systems and data-driven services in Healthcare and Medicine.

Segmentation of the liver and tumours from computed tomography (CT) scans is an important task in hepatic surgical planning. Manual segmentation of the liver and tumours is a time-consuming and labour-intensive task; therefore, a fully automated method for performing this segmentation is particularly desired. An automatic two-step liver and tumour segmentation method is presented in this paper. A cascade framework is used during the segmentation process, and a fully connected conditional random field (CRF) method is used to refine the tumour segmentation result. First, the proposed fractal residual U-Net (FRA-UNet) is used to locate and initially segment the liver. Then, FRA-UNet is further used to predict liver tumours from the liver region of interest (ROI). Finally, a three-dimensional (3D) CRF is used to refine the tumour segmentation results. The improved fractal residual (FR) structure effectively retains more effective features for improving the segmentation performance of deeper networks, the improved deep residual block can utilise the feature information more effectively, and the 3D CRF method smooths the contours and avoids the tumour oversegmentation problem. FRA-UNet is tested on the Liver Tumour Segmentation challenge dataset (LiTS) and the 3D Image Reconstruction for Comparison of Algorithm Database dataset (3DIRCADb), achieving 97.13% and 97.18% Dice similarity coefficients (DSCs) for liver segmentation and 71.78% and 68.97% DSCs for tumour segmentation, respectively, outperforming most state-of-the-art networks.

BACKGROUND AND OBJECTIVE: Detection of the Optic Disc (OD) in retinal fundus image is crucial in identifying diverse abnormal conditions in the retina such as diabetic retinopathy. Previous systems are oriented to the OD detection and segmentation. Most research failed to locate the OD in the case when the image does not have a criterion appearance. The objective of the proposed work is to precisely define a new and robust OD segmentation in color retinal fundus images. METHODS: The proposed algorithm is composed of two stages: OD localization and segmentation. The first phase consists in the OD localization through: 1) a preprocessing step; 2) vessel extraction and elimination, and 3) a geometric analysis allowing to decide the OD location. For the second phase, a set of is computed in order to produce various candidates. A combination of these candidates accurately forms a completed contour of the OD. RESULTS: The proposed method is evaluated using 10 publicly available databases as well as a local database. Accuracy rates in the RimOne and IDRID databases are 98.06% and 99.71%, respectively, and 100% for the Chase, Drive, HRF, Drishti, Drions, Bin Rushed, Magrabia, Messidor and LocalDB databases with an overall success rate of 99.80% and specificity rates of 99.44%, 99.64%, 99.66%, 99.66%, 99.70%, 99.87%, 99.72%, 99.83% and 99.82% for the Rim One, Drions, IDRID, Drishti, HRF, Bin Rushed, Magrabia, Messidor and proprietary databases. CONCLUSION: The main advantage of the proposed approach is the robustness and the excellent performances even with critical cases of retinal images. The proposed method achieves the state-of-the-art performances with regards to the OD detection and segmentation. It is also of a great interest for clinical usage without the expert intervention to treat each image.

BACKGROUND: Wearable multi-modal time-series classification applications outperform their best uni-modal counterparts and hold great promise. A modality that directly measures electrical correlates from the brain is electroencephalography. Due to varying noise sources, different key brain regions, key frequency bands, and signal characteristics like non-stationarity, techniques for data pre-processing and classification algorithms are task-dependent. METHOD: Here, a systematic literature review on mental state classification for wearable electroencephalography is presented. Four search terms in different combinations were used for an in-title search. The search was executed on the 29th of June 2022, across Google Scholar, PubMed, IEEEXplore, and ScienceDirect. 76 most relevant publications were set into context as the current state-of-the-art in mental state time-series classification. RESULTS: Pre-processing techniques, features, and time-series classification models were analyzed. Across publications, a window length of one second was mainly chosen for classification and spectral features were utilized the most. The achieved performance per time-series classification model is analyzed, finding linear discriminant analysis, decision trees, and k-nearest neighbors models outperform support-vector machines by a factor of up to 1.5. A historical analysis depicts future trends while under-reported aspects relevant to practical applications are discussed. CONCLUSIONS: Five main conclusions are given, covering utilization of available area for electrode placement on the head, most often or scarcely utilized features and time-series classification model architectures, baseline reporting practices, as well as explainability and interpretability of Deep Learning. The importance of a 'test battery' assessing the influence of data pre-processing and multi-modality on time-series classification performance is emphasized.

Currently, glaucoma is one of the leading causes of irreversible vision loss. So far, glaucoma is incurable, but early treatment can stop the progression of the condition and slow down the speed and extent of vision loss. Early detection and treatment are crucial to prevent glaucoma from developing into blindness. It is an effective method for glaucoma diagnosis to measure Cup to Disc Ratio (CDR) by the segmentation of Optic Disc (OD) and Optic Cup (OC). Compared with OD segmentation, OC segmentation still faces difficulties in segmentation accuracy. In this paper, a deep learning architecture named FAU-Net (feature fusion and attention U-Net) is proposed for the joint segmentation of OD and OC. It is an improved architecture based on U-Net. By adding a feature fusion module in U-Net, information loss in feature extraction can be reduced. The channel and spatial attention mechanisms are combined to highlight the important features related to the segmentation task and suppress the expression of irrelevant regional features. Finally, a multi-label loss is used to generate the final joint segmentation of OD and OC. Experimental results show that the proposed FAU-Net outperforms the state-of-the-art segmentation of OD and OC on Drishti-GS1, REFUGE, RIM-ONE and ODIR datasets.

The discovery of cancer subtypes based on unsupervised clustering helps in providing a precise diagnosis, guide treatment, and improve patients' prognoses. Instead of single-omics data, multi-omics data can improve the clustering performance because it obtains a comprehensive landscape for understanding biological systems and mechanisms. However, heterogeneous data from multiple sources raises high complexity and different kinds of noise, which are detrimental to the extraction of clustering information. We propose an end-to-end deep learning based method, called Multi-omics Clustering Variational Autoencoders (MCluster-VAEs), that can extract cluster-friendly representations on multi-omics data. First, a unified network architecture with an attention mechanism was developed for accurately modeling multi-omics data. Then, using a novel objective function built from the Variational Bayes technique, the model was trained to effectively obtain the posterior estimation of the clustering assignments. Compared with 12 other state-of-the-art multi-omics clustering methods, MCluster-VAEs achieved an outstanding performance on benchmark datasets from the TCGA database. On the Pan Cancer dataset, MCluster-VAEs achieved an adjusted Rand index of approximately 0.78 for cancer category recognition, an increase of more than 18% compared with other methods. Furthermore, a survival analysis and clinical parameter enrichment tests conducted on 10 cancer datasets demonstrated that MCluster-VAEs provides comparable and even better results than many common integrative approaches. These results demonstrate that MCluster-VAEs are a powerful new tool for dissecting complex multi-omics relationships and providing new insights for cancer subtype discovery.

Liver fibrosis staging is clinically important for liver disease progression prediction. As the portal tract fibrotic quantity and size in a liver biopsy correlate with the fibrosis stage, an accurate analysis of portal tract regions is clinically critical. Manual annotations of portal tract regions, however, are time-consuming and subject to large inter- and intra-observer variability. To address such a challenge, we develop a Multiple Up-sampling and Spatial Attention guided UNet model (MUSA-UNet) to segment liver portal tract regions in whole-slide images of liver tissue slides. To enhance the segmentation performance, we propose to use depth-wise separable convolution, the spatial attention mechanism, the residual connection, and multiple up-sampling paths in the developed model. This study includes 53 histopathology whole slide images from patients who received liver transplantation. In total, 6,012 patches derived from 30 images are used for our deep learning model training and validation. The remaining 23 whole slide images are utilized for the model testing. The average liver portal tract segmentation performance of the developed MUSA-UNet is 0.94 (Precision), 0.85 (Recall), 0.89 (F1 Score), 0.89 (Accuracy), 0.80 (Jaccard Index), and 0.91 (Fowlkes-Mallows Index), respectively. The clinical Scheuer fibrosis stage presents a strong correlation with the resulting average portal tract fibrotic area (R = 0.681, p<0.001) and portal tract percentage (R = 0.335, p = 0.02) computed from the MUSA-UNet segmentation results. In conclusion, our developed deep learning model MUSA-UNet can accurately segment portal tract regions from whole-slide images of liver tissue biopsies, presenting its promising potential to assist liver disease diagnosis in a computational manner.

In recent years, deep learning (DL) has been recognized very useful in the semantic segmentation of biomedical images. Such an application, however, is significantly hindered by the lack of pixel-wise annotations. In this work, we propose a data pair generative adversarial network (DPGAN) for the purpose of synthesizing concurrently the diverse biomedical images and the segmentation labels from random latent vectors. First, a hierarchical structure is constructed consisting of three variational auto-encoder generative adversarial networks (VAEGANs) with an extra discriminator. Subsequently, to alleviate the influence from the imbalance between lesions and non-lesions areas in biomedical segmentation data sets, we divide the DPGAN into three stages, namely, background stage, mask stage and advanced stage, with each stage deploying a VAEGAN. In such a way, a large number of new segmentation data pairs are generated from random latent vectors and then used to augment the original data sets. Finally, to validate the effectiveness of the proposed DPGAN, experiments are carried out on a vestibular schwannoma data set, a kidney tumor data set and a skin cancer data set. The results indicate that, in comparison to other state-of-the-art GAN-based methods, the proposed DPGAN shows better performance in the generative quality, and meanwhile, gains an effective boost on semantic segmentation of class imbalanced biomedical images.

Since December 2019, coronavirus SARS-CoV-2 (COVID-19) has rapidly developed into a global epidemic, with millions of patients affected worldwide. As part of the diagnostic pathway, computed tomography (CT) scans are used to help patient management. However, parenchymal imaging findings in COVID-19 are non-specific and can be seen in other diseases. In this work, we propose to first segment lesions from CT images, and further, classify COVID-19 patients from healthy persons and common pneumonia patients. In detail, a novel Dynamic Fusion Segmentation Network (DFSN) that automatically segments infection-related pixels is first proposed. Within this network, low-level features are aggregated to high-level ones to effectively capture context characteristics of infection regions, and high-level features are dynamically fused to model multi-scale semantic information of lesions. Based on DFSN, Dynamic Transfer-learning Classification Network (DTCN) is proposed to distinguish COVID-19 patients. Within DTCN, a pre-trained DFSN is transferred and used as the backbone to extract pixel-level information. Then the pixel-level information is dynamically selected and used to make a diagnosis. In this way, the pre-trained DFSN is utilized through transfer learning, and clinical significance of segmentation results is comprehensively considered. Thus DTCN becomes more sensitive to typical signs of COVID-19. Extensive experiments are conducted to demonstrate effectiveness of the proposed DFSN and DTCN frameworks. The corresponding results indicate that these two models achieve state-of-the-art performance in terms of segmentation and classification.

AIM: Corona Virus Disease 2019 (COVID-19) was a lung disease with high mortality and was highly contagious. Early diagnosis of COVID-19 and distinguishing it from pneumonia was beneficial for subsequent treatment. OBJECTIVES: Recently, Graph Convolutional Network (GCN) has driven a significant contribution to disease diagnosis. However, limited by the nature of the graph convolution algorithm, deep GCN has an over-smoothing problem. Most of the current GCN models are shallow neural networks, which do not exceed five layers. Furthermore, the objective of this study is to develop a novel deep GCN model based on the DenseGCN and the pre-trained model of deep Convolutional Neural Network (CNN) to complete the diagnosis of chest X-ray (CXR) images. METHODS: We apply the pre-trained model of deep CNN to perform feature extraction on the data to complete the extraction of pixel-level features in the image. And then, to extract the potential relationship between the obtained features, we propose Neighbourhood Feature Reconstruction Algorithm to reconstruct them into graph-structured data. Finally, we design a deep GCN model that exploits the graph-structured data to diagnose COVID-19 effectively. In the deep GCN model, we propose a Node-Self Convolution Algorithm (NSC) based on feature fusion to construct a deep GCN model called NSCGCN (Node-Self Convolution Graph Convolutional Network). RESULTS: Experiments were carried out on the Computed Tomography (CT) and CXR datasets. The results on the CT dataset confirmed that: compared with the six state-of-the-art (SOTA) shallow GCN models, the accuracy and sensitivity of the proposed NSCGCN had improve 8% as sensitivity (Sen.) = 87.50%, F1 score = 97.37%, precision (Pre.) = 89.10%, accuracy (Acc.) = 97.50%, area under the ROC curve (AUC) = 97.09%. Moreover, the results on the CXR dataset confirmed that: compared with the fourteen SOTA GCN models, sixteen SOTA CNN transfer learning models and eight SOTA COVID-19 diagnosis methods on the COVID-19 dataset. Our proposed method had best performances as Sen. = 96.45%, F1 score = 96.45%, Pre. = 96.61%, Acc. = 96.45%, AUC = 99.22%. CONCLUSION: Our proposed NSCGCN model is effective and performed better than the thirty-eight SOTA methods. Thus, the proposed NSC could help build deep GCN models. Our proposed COVID-19 diagnosis method based on the NSCGCN model could help radiologists detect pneumonia from CXR images and distinguish COVID-19 from Ordinary Pneumonia (OPN). The source code of this work will be publicly available at https://github.com/TangChaosheng/NSCGCN.

Histopathological image classification has become one of the most challenging tasks among researchers due to the fine-grained variability of the disease. However, the rapid development of deep learning-based models such as the Convolutional Neural Network (CNN) has propelled much attentiveness to the classification of complex biomedical images. In this work, we propose a novel end-to-end deep learning model, named Multi-scale Dual Residual Recurrent Network (MTRRE-Net), for breast cancer classification from histopathological images. This model introduces a contrasting approach of dual residual block combined with the recurrent network to overcome the vanishing gradient problem even if the network is significantly deep. The proposed model has been evaluated on a publicly available standard dataset, namely BreaKHis, and achieved impressive accuracy in overcoming state-of-the-art models on all the images considered at various magnification levels.

Non-specific sympathetic arousal responses to different stressful elicitations can be easily recognized from the analysis of physiological signals. However, neural patterns of sympathetic arousal during physical and mental fatigue are clearly not unitary. In the context of physiological monitoring through wearable and non-invasive devices, electrodermal activity (EDA) is the most effective and widely used marker of sympathetic activation. This study presents ComEDA, a novel approach for the characterization of complex dynamics of EDA. ComEDA overcomes the methodological limitations related to the application of nonlinear analysis to EDA dynamics, is not parameter-sensitive and is suitable for the analysis of ultra-short time series. We validated the proposed algorithm using synthetic series of white noise and 1/f noise, varying the number of samples from 50 to 5000. By applying our approach, we were able to discriminate a statistically significant increase of complexity in the 1/f noise with respect to white noise, obtaining p-values in the range [4.35 × 10-6, 0.03] after the Mann-Whitney test. Then, we tested ComEDA on both EDA signal and its tonic and phasic components, acquired from healthy subjects during four experimental protocols: two inducing a sympathetic activation through physical efforts and two based on mentally stressful tasks. Results are encouraging and promising, outperforming state of the art metrics such as the Sample Entropy. ComEDA shows good performance not only in discriminating between stressful tasks and resting state (p-value < 0.01 after the Wilcoxon non-parametric statistical test applied to EDA signals of all the four datasets), but also in differentiating different trends of complexity of EDA dynamics when induced by physical and mental stressors. These findings suggest future applications to automatically detect and selectively identify threats due to overwhelming stress impacting both physical and mental health or in the field of telemedicine to monitor autonomic diseases correlated to atypical sympathetic activation. The Matlab code implementing the ComEDA algorithm is available online.

BACKGROUND AND OBJECTIVE: Semi-supervised learning for medical image segmentation is an important area of research for alleviating the huge cost associated with the construction of reliable large-scale annotations in the medical domain. Recent semi-supervised approaches have demonstrated promising results by employing consistency regularization, pseudo-labeling techniques, and adversarial learning. These methods primarily attempt to learn the distribution of labeled and unlabeled data by enforcing consistency in the predictions or embedding context. However, previous approaches have focused only on local discrepancy minimization or context relations across single classes. METHODS: In this paper, we introduce a novel adversarial learning-based semi-supervised segmentation method that effectively embeds both local and global features from multiple hidden layers and learns context relations between multiple classes. Our voxel-wise adversarial learning method utilizes a voxel-wise feature discriminator, which considers multilayer voxel-wise features (involving both local and global features) as an input by embedding class-specific voxel-wise feature distribution. Furthermore, our previous representation learning method is improved by overcoming information loss and learning stability problems, which enables rich representations of labeled data. RESULT: In the experiments, we used the Left Atrial Segmentation Challenge dataset and the Abdominal Multi-Organ dataset to prove the effectiveness of our method in both single class and multiclass segmentation. The experimental results demonstrate that our method outperforms current best-performing state-of-the-art semi-supervised learning approaches. Our proposed adversarial learning-based semi-supervised segmentation method successfully leveraged unlabeled data to improve the network performance by 2% in Dice score coefficient for multi-organ dataset. CONCLUSION: We compare our approach to a wide range of medical datasets, and showed our method can be adapted to embed class-specific features. Furthermore, visual interpretation of the feature space demonstrates that our proposed method enables a well-distributed and separated feature space from both labeled and unlabeled data, which improves the overall prediction results.

The diagnosis of Coronavirus Disease 2019 (COVID-19) exploiting machine learning algorithms based on chest computed tomography (CT) images has become an important technology. Though many excellent computer-aided methods leveraging CT images have been designed, they do not possess sufficiently high recognition accuracy. Besides, these methods entail vast amounts of training data, which might be difficult to be satisfied in some real-world applications. To address these two issues, this paper proposes a novel COVID-19 recognition system based on CT images, which has high recognition accuracy, while only requiring a small amount of training data. Specifically, the system possesses the following three improvements: 1) Data: a novel redesigned BCELoss that incorporates Label Smoothing, Focal Loss, and Label Weighting Regularization (LSFLLW-R) technique for optimizing the solution space and preventing overfitting, 2) Model: a backbone network processed by two-phase contrastive self-supervised learning for classifying multiple labels, and 3) Method: a decision-fusing ensemble learning method for getting a more stable system, with balanced metric values. Our proposed system is evaluated on the small-scale expanded COVID-CT dataset, achieving an accuracy of 94.3%, a precision of 94.1%, a recall (sensitivity) of 93.4%, an F1-score of 94.7%, and an Area Under the Curve (AUC) of 98.9%, for COVID-19 diagnosis, respectively. These experimental results verify that our system can not only identify pathological locations effectively, but also achieve better performance in terms of accuracy, generalizability, and stability, compared with several other state-of-the-art COVID-19 diagnosis methods.

OBJECTIVE: Sudden cardiac death (SCD) is a serious public health burden. This study aims to find prognostic biomarkers of SCD using machine learning. METHODS: The myocardial samples from 21 accidental death and 82 sudden death donors were compared to seek for differential genes. Enriched active genes were found according to the PPI interaction network. GSEA analyzed differences in function and pathway between control and experimental groups. Related diseases caused by active genes are mainly exhibited through DO enrichment. Prognostic biomarkers for SCD are identified via two machine learning algorithms. The CIBERSORT method was used to compare the immune microenvironment changes in patients with SCD. RESULTS: SCD was mainly associated with heart and kidney diseases caused by atherosclerosis. DEFA1B, BGN, SERPINE1, CCL2 and HBB are considered to be prognostic biomarkers for SCD after machine learning. And immune infiltration plays an important role in the process of SCD. CONCLUSION: We discovered 5 prognostic biomarkers for SCD. And immune microenvironment changes was also found in SCD. Moreover, atherosclerosis might be an important risk factor for SCD.

OBJECTIVE: Patients with indeterminate pulmonary nodules (IPN) with an intermediate to a high probability of lung cancer generally undergo invasive diagnostic procedures. Chest computed tomography image and clinical data have been in estimating the pretest probability of lung cancer. In this study, we apply a deep learning network to integrate multi-modal data from CT images and clinical data (including blood-based biomarkers) to improve lung cancer diagnosis. Our goal is to reduce uncertainty and to avoid morbidity, mortality, over- and undertreatment of patients with IPNs. METHOD: We use a retrospective study design with cross-validation and external-validation from four different sites. We introduce a deep learning framework with a two-path structure to learn from CT images and clinical data. The proposed model can learn and predict with single modality if the multi-modal data is not complete. We use 1284 patients in the learning cohort for model development. Three external sites (with 155, 136 and 96 patients, respectively) provided patient data for external validation. We compare our model to widely applied clinical prediction models (Mayo and Brock models) and image-only methods (e.g., Liao et al. model). RESULTS: Our co-learning model improves upon the performance of clinical-factor-only (Mayo and Brock models) and image-only (Liao et al.) models in both cross-validation of learning cohort (e.g. , AUC: 0.787 (ours) vs. 0.707-0.719 (baselines), results reported in validation fold and external-validation using three datasets from University of Pittsburgh Medical Center (e.g., 0.918 (ours) vs. 0.828-0.886 (baselines)), Detection of Early Cancer Among Military Personnel (e.g., 0.712 (ours) vs. 0.576-0.709 (baselines)), and University of Colorado Denver (e.g., 0.847 (ours) vs. 0.679-0.746 (baselines)). In addition, our model achieves better re-classification performance (cNRI 0.04 to 0.20) in all cross- and external-validation sets compared to the Mayo model. CONCLUSIONS: Lung cancer risk estimation in patients with IPNs can benefit from the co-learning of CT image and clinical data. Learning from more subjects, even though those only have a single modality, can improve the prediction accuracy. An integrated deep learning model can achieve reasonable discrimination and re-classification performance.

Prostate cancer (PCa) is one of the deadliest cancers in men, and identifying cancerous tissue patterns at an early stage can assist clinicians in timely treating the PCa spread. Many researchers have developed deep learning systems for mass-screening PCa. These systems, however, are commonly trained with well-annotated datasets in order to produce accurate results. Obtaining such data for training is often time and resource-demanding in clinical settings and can result in compromised screening performance. To address these limitations, we present a novel knowledge distillation-based instance segmentation scheme that allows conventional semantic segmentation models to perform instance-aware segmentation to extract stroma, benign, and the cancerous prostate tissues from the whole slide images (WSI) with incremental few-shot training. The extracted tissues are then used to compute majority and minority Gleason scores, which, afterward, are used in grading the PCa as per the clinical standards. The proposed scheme has been thoroughly tested on two datasets, containing around 10,516 and 11,000 WSI scans, respectively. Across both datasets, the proposed scheme outperforms state-of-the-art methods by 2.01% and 4.45%, respectively, in terms of the mean IoU score for identifying prostate tissues, and 10.73% and 11.42% in terms of F1 score for grading PCa according to the clinical standards. Furthermore, the applicability of the proposed scheme is tested under a blind experiment with a panel of expert pathologists, where it achieved a statistically significant Pearson correlation of 0.9192 and 0.8984 with the clinicians' grading.

Dermoscopic images ideally depict pigmentation attributes on the skin surface which is highly regarded in the medical community for detection of skin abnormality, disease or even cancer. The identification of such abnormality, however, requires trained eyes and accurate detection necessitates the process being time-intensive. As such, computerized detection schemes have become quite an essential, especially schemes which adopt deep learning tactics. In this paper, a convolutional deep neural network, S2C-DeLeNet, is proposed, which (i) Performs segmentation procedure of lesion based regions with respect to the unaffected skin tissue from dermoscopic images using a segmentation sub-network, (ii) Classifies each image based on its medical condition type utilizing transferred parameters from the inherent segmentation sub-network. The architecture of the segmentation sub-network contains EfficientNet-B4 backbone in place of the encoder and the classification sub-network bears a 'Classification Feature Extraction' system which pulls trained segmentation feature maps towards lesion prediction. Inside the classification architecture, there have been designed, (i) A 'Feature Coalescing Module' in order to trail and mix each dimensional feature from both encoder and decoder, (ii) A '3D-Layer Residuals' block to create a parallel pathway of low-dimensional features with high variance for better classification. After fine-tuning on a publicly accessible dataset, a mean dice-score of 0.9494 during segmentation is procured which beats existing segmentation strategies and a mean accuracy of 0.9103 is obtained for classification which outperforms conventional and noted classifiers. Additionally, the already fine-tuned network demonstrates highly satisfactory results on other skin cancer segmentation datasets while cross-inference. Extensive experimentation is done to prove the efficacy of the network for not only dermoscopic images but also different medical modalities; which can show its potential in being a systematic diagnostic solution in the field of dermatology and possibly more.

Covid-19 disease has had a disastrous effect on the health of the global population, for the last two years. Automatic early detection of Covid-19 disease from Chest X-Ray (CXR) images is a very crucial step for human survival against Covid-19. In this paper, we propose a novel data-augmentation technique, called SVD-CLAHE Boosting and a novel loss function Balanced Weighted Categorical Cross Entropy (BWCCE), in order to detect Covid 19 disease efficiently from a highly class-imbalanced Chest X-Ray image dataset. Our proposed SVD-CLAHE Boosting method is comprised of both oversampling and under-sampling methods. First, a novel Singular Value Decomposition (SVD) based contrast enhancement and Contrast Limited Adaptive Histogram Equalization (CLAHE) methods are employed for oversampling the data in minor classes. Simultaneously, a Random Under Sampling (RUS) method is incorporated in major classes, so that the number of images per class will be more balanced. Thereafter, Balanced Weighted Categorical Cross Entropy (BWCCE) loss function is proposed in order to further reduce small class imbalance after SVD-CLAHE Boosting. Experimental results reveal that ResNet-50 model on the augmented dataset (by SVD-CLAHE Boosting), along with BWCCE loss function, achieved 95% F1 score, 94% accuracy, 95% recall, 96% precision and 96% AUC, which is far better than the results by other conventional Convolutional Neural Network (CNN) models like InceptionV3, DenseNet-121, Xception etc. as well as other existing models like Covid-Lite and Covid-Net. Hence, our proposed framework outperforms other existing methods for Covid-19 detection. Furthermore, the same experiment is conducted on VGG-19 model in order to check the validity of our proposed framework. Both ResNet-50 and VGG-19 model are pre-trained on the ImageNet dataset. We publicly shared our proposed augmented dataset on Kaggle website (https://www.kaggle.com/tr1gg3rtrash/balanced-augmented-covid-cxr-dataset), so that any research community can widely utilize this dataset. Our code is available on GitHub website online (https://github.com/MrinalTyagi/SVD-CLAHE-and-BWCCE).

BACKGROUND: The recent development of artificial intelligence (AI) technologies coupled with medical imaging data has gained considerable attention, and offers a non-invasive approach for cancer diagnosis and prognosis. In this context, improved breast cancer (BC) molecular characteristics assessment models are foreseen to enable personalized strategies with better clinical outcomes compared to existing screening strategies. And it is a promising approach to developing models for hormone receptors (HR) and subtypes of BC patients from dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) data. METHODS: In this institutional review board-approved study, 174 BC patients with both DCE-MRI and RNA-seq data in the local database were analyzed. Slice images from tumor lesions and multi-scale peri-tumor regions were used as model inputs, and five representative pre-trained transfer learning (TF) networks, such as Inception-v3 and Xception, were employed to establish prediction models. A comprehensive analysis was performed using five-fold cross-validation to avoid overfitting, and accuracy (ACC) and area under the receiver operating characteristic curve (AUROC) to evaluate model performance. RESULTS: Xception achieved the superior results when using solely tumor regions, with highest AUROCs of 0.844 (95% CI: [0.841, 0.847]) and 0.784 (95% CI: [0.781, 0.788]) for estrogen receptor (ER) and progesterone receptor (PR), respectively, and best ACC of 0.467 (95% CI: [0.462, 0.470]) for PAM50 subtypes. A significant improvement in the model performance was observed when images of the peri-tumor region were included, with optimal results achieved using images of the tumor and the 10 mm peri-tumor regions. Xception-based TF models performed most effectively in predicting ER and PR statuses, with the AUROCs were 0.942 (95% CI: [0.940, 0.944]) and 0.920 (95% CI: [0.917, 0.922]), respectively, whereas for PAM50 subtypes, the Inception-v3-based network yielded the highest ACC as 0.742 (95% CI: [0.738, 0.746]). CONCLUSIONS: Transfer learning analysis based on DCE-MRI data of tumor and peri-tumor regions was helpful to the non-invasive assessment of molecular characteristics of BC.

OBJECTIVES: Better tools are needed for risk assessment of Type B aortic dissection (TBAD) to determine optimal treatment for patients with uncomplicated disease. Magnetic resonance imaging (MRI) has the potential to inform computational fluid dynamics (CFD) simulations for TBAD by providing individualised quantification of haemodynamic parameters, for assessment of complication risks. This systematic review aims to present an overview of MRI applications for CFD studies of TBAD. METHODS: Following PRISMA guidelines, a search in Medline, Embase, and the Scopus Library identified 136 potentially relevant articles. Studies were included if they used MRI to inform CFD simulation in TBAD. RESULTS: There were 20 articles meeting the inclusion criteria. 19 studies used phase contrast MRI (PC-MRI) to provide data for CFD flow boundary conditions. In 12 studies, CFD haemodynamic parameter results were validated against PC-MRI. In eight studies, geometric models were developed from MR angiography. In three studies, aortic wall or intimal flap motion data were derived from PC/cine MRI. CONCLUSIONS: MRI provides complementary patient-specific information in CFD haemodynamic studies for TBAD that can be used for personalised care. MRI provides structural, dynamic and flow data to inform CFD for pre-treatment planning, potentially advancing its integration into clinical decision-making. The use of MRI to inform CFD in TBAD surgical planning is promising, however further validation and larger cohort studies are required.

BACKGROUND: Dermoscopic image segmentation using deep learning algorithms is a critical technology for skin cancer detection and therapy. Specifically, this technology is a spatially equivariant task and relies heavily on Convolutional Neural Networks (CNNs), which lost more effective features during cascading down-sampling or up-sampling. Recently, vision isotropic architecture has emerged to eliminate cascade procedures in CNNs as well as demonstrates superior performance. Nevertheless, it cannot be used for the segmentation task directly. Based on these discoveries, this research intends to explore an efficient architecture which not only preserves the advantages of the isotropic architecture but is also suitable for clinical dermoscopic diagnosis. METHODS: In this work, we introduce a novel Semi-Isotropic L-shaped network (SIL-Net) for dermoscopic image segmentation. First, we propose a Patch Embedding Weak Correlation (PEWC) module to address the issue of no interaction between adjacent patches during the standard Patch Embedding process. Second, a plug-and-play and zero-parameter Residual Spatial Mirror Information (RSMI) path is proposed to supplement effective features during up-sampling and optimize the lesion boundaries. Third, to further reconstruct deep features and get refined lesion regions, a Depth Separable Transpose Convolution (DSTC) based up-sampling module is designed. RESULTS: The proposed architecture obtains state-of-the-art performance on dermoscopy benchmark datasets ISIC-2017, ISIC-2018 and PH2. Respectively, the Dice coefficient (DICE) of above datasets achieves 89.63%, 93.47%, and 95.11%, where the Mean Intersection over Union (MIoU) are 82.02%, 88.21%, and 90.81%. Furthermore, the robustness and generalizability of our method has been demonstrated through additional experiments on standard intestinal polyp datasets (CVC-ClinicDB and Kvasir-SEG). CONCLUSION: Our findings demonstrate that SIL-Net not only has great potential for precise segmentation of the lesion region but also exhibits stronger generalizability and robustness, indicating that it meets the requirements for clinical diagnosis. Notably, our method shows state-of-the-art performance on all five datasets, which highlights the effectiveness of the semi-isotropic design mechanism.

BACKGROUND: Breast cancer is the most aggressive malignant tumor with high morbidity and mortality. Astragalin, a flavonoid widely found in a variety of edible and medicinal plants, is recorded to possess multiple biological and pharmacological activities. However, its effect of anti-breast cancer has been unknown. METHODS: Computational pharmacology was employed to explore the potential mechanism of anti-metastasis and anti-angiogenesis effects of Astragalin on breast cancer. The targets of Astragalin were obtained from TCMSP, Swiss Target Prediction, SEA, BATMAN-TCM, ChemMapper and STITCH databases, and targets of breast cancer were got from OMIM, GeneCards, and DisGeNET databases. Protein-protein interaction network (PPI), Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway enrichment analyses were performed to elucidate the interactions of these two groups of targets. Moreover, the anti-metastasis and anti-angiogenesis effects of Astragalin were validated by in vitro and in vivo experiments using wound healing assay, transwell migration and invasion assay, gelatin zymography assay, tube formation assay, and chick embryo chorioallantoic membrane model. RESULTS: Computational pharmacology analysis indicated that the effects of Astragalin against breast cancer were mainly related to the regulation of the cell movement, migration, and angiogenesis, and taking AKT, ZEB1, VEGF, and MMP9 as the promising targets. Further experimental pharmacology indicated that Astragalin exerted anti-metastasis and anti-angiogenesis activities on breast cancer, and verified AKT, ZEB1, VEGF, and MMP9 as the key targets. CONCLUSION: Astragalin suppresses the metastasis and angiogenesis of breast cancer, and AKT, ZEB1, VEGF, and MMP9 are the promising targets for Astragalin against breast cancer. Thus, Astragalin is a potential therapeutic agent for breast cancer.

Epstein-Barr virus (EBV) is widely known due to its role in the etiology of infectious mononucleosis. However, it is the first oncovirus that was identified and has been implicated in the etiology of several types of cancers. Globally, EBV infection is associated with more than 200, 000 new cancer cases and 150, 000 deaths yearly. A prophylactic or therapeutic vaccine targeting tumors associated with EBV infection is currently lacking. Therefore, this study aimed to develop a multiepitope-based polyvalent vaccine against EBV-associated tumors using immunoinformatics approach. The latency-associated proteins (LAP) of three strains of the virus were used in this study. Potential epitopes predicted from the proteins were analyzed and selected based on several predicted properties. Thirty viable B-cell and T-cell epitopes were selected and conjugated using various linkers alongside beta-defensin 3 as an adjuvant and pan HLA DR-binding epitope (PADRE) sequence to improve the immunogenicity of the vaccine construct. Molecular docking studies of the vaccine construct against toll-like receptors (TLRs) showed it is capable of inducing immune response via recognition by TLRs while immune simulation studies showed it could induce both cellular and humoral immune responses. Furthermore, molecular dynamics study of the complex formed by the vaccine candidate and TLR-4 showed that the complex was stable. Ultimately, the designed vaccine showed desirable properties based on in silico evaluation; however, experimental studies are needed to validate the efficacy of the vaccine against EBV-associated tumors.

Phantom limb pain after amputation is a debilitating condition that negatively affects activities of daily life and the quality of life of amputees. Most amputees are able to control the movement of the missing limb, which is called the phantom limb movement. Recognition of these movements is crucial for both technology-based amputee rehabilitation and prosthetic control. The aim of the current study is to classify and recognize the phantom movements in four different amputation levels of the upper and lower extremities. In the current study, we utilized ensemble learning algorithms for the recognition and classification of phantom movements of the different amputation levels of the upper and lower extremity. In this context, sEMG signals obtained from 38 amputees and 25 healthy individuals were collected and the dataset was created. Studies of processing sEMG signals in amputees are rather limited, and studies are generally on the classification of upper extremity and hand movements. Our study demonstrated that the ensemble learning-based models resulted in higher accuracy in the detection of phantom movements. The ensemble learning-based approaches outperformed the SVM, Decision tree, and kNN methods. The accuracy of the movement pattern recognition in healthy people was up to 96.33%, this was at most 79.16% in amputees.

BACKGROUND: Survival analysis is a primary problem before clinical treatments to cancer patients after their operations. In order to make this kind of analysis simple, many corresponding tools have been proposed. Though these tools are easy to use, there exist still two fatal flaws. One is that sample grouping is commonly empirical and wrongly based on original gene expressions or survival time. The other is that their feature selection methods mostly depend univariate semi-supervised regression or the multivariate one without considering the small sample size compared with the high dimension. OBJECTIVE: In order to solve the two problems, we design an automatic feature selection web tool which can also satisfy interactive sample grouping. METHODS: An automatic feature selection is performed on user-defined data or TCGA data. users can also perform manual feature selection. Then, hierarchical clustering is used and an automatic re-clustering strategy is proposed after interactive risk score split. Kaplan-Meier survival curve and log-rank test are utilized as the measurement. RESULTS: Experimental results on 53 datasets from TCGA demonstrate the effectiveness of our method. The tree view, heat map and scatter map can intuitively display the result of the selected genes to the doctors for further research. CONCLUSIONS: This method is suitable for survival analysis of high-dimensional small sample data sets. At the same time, it also provides a platform for researchers to analyze custom data. It solves the problems of the existing web tools and provides an effective feature selection method for survival analysis. AVAILABILITY: The full code package is freely available and can be downloaded at https://github.com/Yuan-23/IOFS-SA-ecp-data-main, and the online version at https://bioinfor.nefu.edu.cn/IOFS-SA/ is ready for use freely.

Our objective was to identify the molecule which can inhibit SARS-CoV-2 main protease and can be easily procured. Natural products may provide such molecules and can supplement the current custom chemical synthesis-based drug discovery for this objective. A combination of docking approaches, scoring functions, classical molecular dynamic simulation, binding pose metadynamics, and free energy perturbation calculations have been employed in this study. Theaflavin digallate has been observed in top-scoring compounds after the three independent virtual screening simulations of 598435 compounds (unique 27256 chemical entities). The main protease-theaflavin digallate complex interacts with critical active site residues of the main protease in molecular dynamics simulation independent of the explored computational framework, simulation time, initial structure, and force field used. Theaflavin digallate forms approximately three hydrogen bonds with Glutamate166 of main protease, primarily through hydroxyl groups in the benzene ring of benzo(7)annulen-6-one, along with other critical residues. Glu166 is the most critical amino acid for main protease dimerization, which is necessary for catalytic activity. The estimated binding free energy, calculated by Amber and Schrodinger MMGBSA module, reflects a high binding free energy between theaflavin digallate and main protease. Binding pose metadynamics simulation shows the highly persistent H-bond and a stable pose for the theaflavin digallate-main protease complex. Using method control, experimental controls, and test set, alchemical transformation studies confirm high relative binding free energy of theaflavin digallate with the main protease. Computational molecular interaction suggests that theaflavin digallate can inhibit the main protease of SARS-CoV-2.

BACKGROUND AND OBJECTIVE: Stroke is the second most deadly disease globally and seriously endangers people's lives and health. The automatic detection of stroke lesions from diffusion-weighted imaging (DWI) can improve the diagnosis. Recently, automatic detection methods based on YOLOv5 have been utilized in medical images. However, most of them barely capture the stroke lesions because of their small size and fuzzy boundaries. METHODS: To address this problem, a novel method for tracing the edge of the stroke lesion based on YOLOv5 (TE-YOLOv5) is proposed. Specifically, we constantly update the high-level features of the lesion using an aggregate pool (AP) module. Conversely, we feed the extracted feature into the reverse attention (RA) module to trace the edge relationship promptly. Overall, 1681 DWI images of 319 stroke patients have been collected, and experienced radiologists have marked the lesions. DWI images were randomly split into the training and test set at a ratio of 8:2. TE-YOLOv5 has been compared with the related models, and a detailed ablation analysis has been conducted to clarify the role of the RA and AP modules. RESULTS: TE-YOLOv5 outperforms its counterparts and achieves competitive performance with a precision of 81.5%, a recall of 75.8%, and a mAP@0.5 of 80.7% (mean average precision while the intersection over union is 0.5) under the same backbone. At the patient level, the positive finding rate can reach 98.51%, while the confidence is set at 80.0%. After ablating RA, the mAP@0.5 decreases to 79.6%; after ablating RA and AP, the mAP@0.5 decreases to 78.1%. CONCLUSIONS: The proposed TE-YOLOv5 can automatically and effectively detect stroke lesions from DWI images, especially for those with an extremely small size and blurred boundaries. AP and RA modules can aggregate multi-layer high-level features and concurrently track the edge relationship of stroke lesions. These detection methods might help radiologists improve stroke diagnosis and have great application potential in clinical practice.

There is an urgent need to detect depression using a non-intrusive approach that is reliable and accurate. In this paper, a simple and efficient unimodal depression detection approach based on speech is proposed, which is non-invasive, cost-effective and computationally inexpensive. A set of spectral, temporal and spectro-temporal features is derived from the speech signal of healthy and depressed subjects. To select a minimal subset of the relevant and non-redundant speech features to detect depression, a two-phase approach based on the nature-inspired wrapper-based feature selection Quantum-based Whale Optimization Algorithm (QWOA) is proposed. Experiments are performed on the publicly available Distress Analysis Interview Corpus Wizard-of-Oz (DAICWOZ) dataset and compared with three established univariate filtering techniques for feature selection and four well-known evolutionary algorithms. The proposed model outperforms all the univariate filter feature selection techniques and the evolutionary algorithms. It has low computational complexity in comparison to traditional wrapper-based evolutionary methods. The performance of the proposed approach is superior in comparison to existing unimodal and multimodal automated depression detection models. The combination of spectral, temporal and spectro-temporal speech features gave the best result with the LDA classifier. The performance achieved with the proposed approach, in terms of F1-score for the depressed class and the non-depressed class and error is 0.846, 0.932 and 0.094 respectively. Statistical tests demonstrate that the acoustic features selected using the proposed approach are non-redundant and discriminatory. Statistical tests also establish that the performance of the proposed approach is significantly better than that of the traditional wrapper-based evolutionary methods.

Through the revolutionization of artificial intelligence (AI) technologies in clinical research, significant improvement is observed in diagnosis of cancer. Utilization of these AI technologies, such as machine and deep learning, is imperative for the discovery of novel anticancer drugs and improves existing/ongoing cancer therapeutics. However, building a model for complicated cancers and their types remains a challenge due to lack of effective therapeutics that hinder the establishment of effective computational tools. In this review, we exploit recent approaches and state-of-the-art in implementing AI methods for anticancer drug discovery, and discussed how advances in these applications need to be considered in the current cancer therapeutics. Considering the immense potential of AI, we explore molecular docking and their interactions to recognize metabolic activities that support drug design. Finally, we highlight corresponding strategies in applying machine and deep learning methods to various types of cancer with their pros and cons.

Datasets are the key to deep learning in autism disease research. However, due to the small quantity and heterogeneity of samples in current public datasets, for example Autism Brain Imaging Data Exchange (ABIDE), the recognition research is not sufficiently effective. Previous studies primarily focused on optimizing feature selection methods and data augmentation to improve recognition accuracy. This research is based on the latter, which learns the edge distribution of a real brain network through the graph recurrent neural network (GraphRNN) and generates synthetic data that have an incentive effect on the discriminant model. Experimental results show that the synthetic data greatly improves the classification ability of the subsequent classifiers, for example, it can improve the classification accuracy of a 50-layer ResNet by up to 30% compared with the case without synthetic data.

In the past decade, deep learning methods have been implemented in the medical image fields and have achieved good performance. Recently, deep learning algorithms have been successful in the evaluation of diagnosis on lung images. Although chest radiography (CR) is the standard data modality for diagnosing pneumoconiosis, computed tomography (CT) typically provides more details of the lesions in the lung. Thus, a transformer-based factorized encoder (TBFE) was proposed and first applied for the classification of pneumoconiosis depicted on 3D CT images. Specifically, a factorized encoder consists of two transformer encoders. The first transformer encoder enables the interaction of intra-slice by encoding feature maps from the same slice of CT. The second transformer encoder explores the inter-slice interaction by encoding feature maps from different slices. In addition, the lack of grading standards on CT for labeling the pneumoconiosis lesions. Thus, an acknowledged CR-based grading system was applied to mark the corresponding pneumoconiosis CT stage. Then, we pre-trained the 3D convolutional autoencoder on the public LIDC-IDRI dataset and fixed the parameters of the last convolutional layer of the encoder to extract CT feature maps with underlying spatial structural information from our 3D CT dataset. Experimental results demonstrated the superiority of the TBFE over other 3D-CNN networks, achieving an accuracy of 97.06%, a recall of 89.33%, precision of 90%, and an F1-score of 93.33%, using 10-fold cross-validation.

Differential expression (DE) analysis has been routinely used to identify molecular features that are statistically significantly different between distinct biological groups. In recent years, differential network (DN) analysis has emerged as a powerful approach to uncover molecular network structure changes from one biological condition to the other where the molecular features with larger topological changes are selected as biomarkers. Although a large number of DE and a few DN-based methods are available, they have been usually implemented independently. DE analysis ignores the relationship among molecular features while DN analysis does not account for the expression changes at individual level. Therefore, an integrative analysis approach that accounts for both DE and DN is required to identify disease associated key features. Although, a handful of methods have been proposed, there is no method that optimizes the combination of DE and DN. We propose a novel integrative analysis method, DNrank, to identify disease-associated molecular features that leverages the strengths of both DE and DN by calculating a weight using resampling based cross validation scheme within the algorithm. First, differential expression analysis of individual molecular features is carried out. Second, a differential network structure is constructed using the differential partial correlation analysis. Third, the molecular features are ranked in the order of their significances by integrating their DE measures and DN structure using the modified Google's PageRank algorithm. In the algorithm, the optimum combination of DE and DN analyses is achieved by evaluating the prediction performance of top-ranked features utilizing support vector machine classifier with Monte Carlo cross validation. The proposed method is illustrated using both simulated data and three real data sets. The results show that the proposed method has a better performance in identifying important molecular features with respect to predictive discrimination. Also, as compared to existing feature selection methods, the top-ranked features selected by our method had a higher stability in selection. DNrank allows the researchers to identify the disease-associated features by utilizing both expression and network topology changes between two groups.

Computational drug repositioning is an effective way to find new indications for existing drugs, thus can accelerate drug development and reduce experimental costs. Recently, various deep learning-based repurposing methods have been established to identify the potential drug-disease associations (DDA). However, effective utilization of the relations of biological entities to capture the biological interactions to enhance the drug-disease association prediction is still challenging. To resolve the above problem, we proposed a heterogeneous graph neural network called REDDA (Relations-Enhanced Drug-Disease Association prediction). Assembled with three attention mechanisms, REDDA can sequentially learn drug/disease representations by a general heterogeneous graph convolutional network-based node embedding block, a topological subnet embedding block, a graph attention block, and a layer attention block. Performance comparisons on our proposed benchmark dataset show that REDDA outperforms 8 advanced drug-disease association prediction methods, achieving relative improvements of 0.76% on the area under the receiver operating characteristic curve (AUC) score and 13.92% on the precision-recall curve (AUPR) score compared to the suboptimal method. On the other benchmark dataset, REDDA also obtains relative improvements of 2.48% on the AUC score and 4.93% on the AUPR score. Specifically, case studies also indicate that REDDA can give valid predictions for the discovery of -new indications for drugs and new therapies for diseases. The overall results provide an inspiring potential for REDDA in the in silico drug development. The proposed benchmark dataset and source code are available in https://github.com/gu-yaowen/REDDA.

BACKGROUND: Neuropathic pain is a common chronic pain, characterized by spontaneous pain and mechanical allodynia. The incidence of neuropathic pain is on the rise due to infections, higher rates of diabetes and stroke, and increased use of chemotherapy drugs in cancer patients. At present, due to its pathophysiological process and molecular mechanism remaining unclear, there is a lack of effective treatment and prevention methods in clinical practice. Now, we use bioinformatics technology to integrate and filter hub genes that may be related to the pathogenesis of neuropathic pain, and explore their possible molecular mechanism by functional annotation and pathway enrichment analysis. METHODS: The expression profiles of GSE24982, GSE2884, GSE2636 and GSE30691 were downloaded from the Gene Expression Omnibus（GEO）database, and these datasets include 93 neuropathic pain Rattus norvegicus and 59 shame controls. After the four datasets were all standardized by quantiles, the differentially expressed genes (DEGs) between NPP Rattus norvegicus and the shame controls were finally identified by the robust rank aggregation (RRA) analysis method. In order to reveal the possible underlying biological function of DEGs, the Gene Ontology (GO) functional annotation and Kyoto Encyclopedia of Genes and Genomes (KEGG) Pathway enrichment analysis of DEGs were performed. In addition, a Protein-protein Interaction (PPI) network was also established. At the end of our study, a high throughput sequencing dataset GSE117526 was used to corroborate our calculation results. RESULTS: Through RRA analysis of the above four datasets GSE24982, GSE2884, GSE2636, and GSE30691, we finally obtained 231 DEGs, including 183 up-regulated genes and 47 down-regulated genes. Arranging 231 DEGs in descending order according to |log2 fold change (FC)|, we found that the top 20 key genes include 14 up-regulated genes and 6 down-regulated genes. The most down-regulated hub gene abnormal expressed in NPP was Egf17 (P-value = 0.008), Camk2n2 (P-value = 0.002), and Lep (P-value = 0.02), and the most up-regulated hub gene abnormal expressed in NPP was Nefm (P-value = 1.08E-06), Prx (P-value = 2.68E-07), and Stip1 (P-value = 4.40E-07). In GO functional annotation analysis results, regulation of ion transmembrane transport (GO:0034765; P-value = 1.45E-09) was the most remarkable enriched for biological process, synaptic membrane (GO:0097060; P-value = 2.95E-08) was the most significantly enriched for cellular component, channel activity (GO:0015267; P-value = 2.44E-06) was the most prominent enriched for molecular function. In KEGG pathway enrichment analysis results, the top three notable enrichment pathways were Neuroactive ligand-receptor interaction (rno04080; P-value = 3.46E-08), Calcium signaling pathway (rno04020; P-value = 5.37E-05), and Osteoclast differentiation (rno04380; P-value = 0.000459927). Cav1 and Lep appeared in the top 20 genes in both RRA analysis and PPI analysis, while Nefm appeared in RRA analysis and datasets GSE117526 validation analysis, so we finally identified these three genes as hub genes. CONCLUSIONS: Our research identified the hub genes and signal pathways of neuropathic pain, enriched the pathophysiological mechanism of neuropathic pain to some extent, and provided a possible basis for the targeted therapy of neuropathic pain.

BACKGROUND: The genome of SARS-CoV-2, is mutating rapidly and continuously challenging the management and preventive measures adopted and recommended by healthcare agencies. The spike protein is the main antigenic site that binds to the host receptor hACE-2 and is recognised by antibodies. Hence, the mutations in this site were analysed to assess their role in differential infectivity of lineages having these mutations, rendering the characterisation of these lineages as variants of concern (VOC) and variants of interest (VOI). METHODS: In this work, we examined the genome sequence of SARS-CoV-2 VOCs and their phylogenetic relationships with the other PANGOLIN lineages. The mutational landscape of WHO characterized variants was determined and mutational diversity was compared amongst the different severity groups. We then computationally studied the structural impact of the mutations in receptor binding domain of the VOCs. The binding affinity was quantitatively determined by molecular dynamics simulations and free energy calculations. RESULTS: The mutational frequency, as well as phylogenetic distance, was maximum in the case of omicron followed by the delta variant. The maximum binding affinity was for delta variant followed by the Omicron variant. The increased binding affinity of delta strain followed by omicron as compared to other variants and wild type advocates high transmissibility and quick spread of these two variants and high severity of delta variant. CONCLUSION: This study delivers a foundation for discovering the improved binding knacks and structural features of SARS-CoV-2 variants to plan novel therapeutics and vaccine candidates against the virus.

Radial sampling pattern is an important signal acquisition strategy in magnetic resonance imaging (MRI) owing to better immunity to motion-induced artifacts and less pronounced aliasing due to undersampling compared to the Cartesian sampling. These advantages of radial sampling can be exploited in acquisition of multidimensional signals such as High Angular Resolution Diffusion Imaging (HARDI), with tremendous scope of acceleration. Despite such benefits, gradient delays lead to samples being acquired from unknown miscentered radial trajectories, severely degrading the image reconstruction quality. In the present work, we propose Csr-Pert that is a joint framework, wherein these perturbed radial trajectories are estimated and utilized for image reconstruction from the compressively sensed measurements of (i) MRI data and (ii) HARDI data. The proposed Csr-Pert method is tested on one real MRI dataset with trajectory deviations and is observed to perform better than the existing state-of-the-art method at high acceleration factors up to 8. To the best of our knowledge, this is the first work to address the problem of estimating perturbed trajectories using the compressively sensed MRI and HARDI data. The method is also tested for varying combinations of trajectory deviations and sampling proportions. It is observed to yield very good quality HARDI reconstruction for a wide variety of scenarios. We have also demonstrated the robustness of the proposed method on real datasets in clinical settings assuming perturbed as well as noisy trajectories.

COVID-19 pandemic poses a severe threat to public health. However, so far, there are no effective drugs for COVID-19. Transcriptomic changes and key genes related to Th2 cells in COVID-19 have not been reported. These genes play an important role in host interactions with SARS-COV-2 and may be used as promising target. We analyzed five COVID-19-associated GEO datasets (GSE157103, GSE152641, GSE171110, GSE152418, and GSE179627) using the xCell algorithm and weighted gene co-expression network analysis (WGCNA). Results showed that 5 closely correlated modular genes to COVID-19 and Th2 cell enrichment levels, including purple, blue, pink, tan and turquoise, were intersected with differentially expressed genes (DEGs) and 648 shared genes were obtained. GO and KEGG pathway enrichment analyses revealed that they were enriched in cell proliferation, differentiation, and immune responses after virus infection. The most significantly enriched pathway involved the regulation of viral life cycle. Three key genes, namely CCNB1, BUB1, and UBE2C, may clarify the pathogenesis of COVID-19 associated with Th2 cells. 11 drug candidates were identified that could down-regulate three key genes using the cMAP database and demonstrated strong drugs binding energies aganist the three keygenes using molecular docking methods. BUB1, CCNB1 and UBE2C were identified key genes for COVID-19 and could be promising therapeutic targets.

Cardiovascular disease (CVD) is the most fatal disease in the world, so its accurate and automated detection in the early stages will certainly support the medical expert in timely diagnosis and treatment, which can save many lives. Many types of research have been carried out in this regard, but due to the problem of data imbalance in the medical and health care sector, it may not provide the desired results in all aspects. To overcome this problem, a sequential ensemble technique has been proposed that detects 6 types of cardiac arrhythmias on large ECG imbalanced datasets, and the data imbalanced issue of the ECG dataset has been addressed by using a hybrid data resampling technique called "Synthetically Minority Oversampling Technique and Tomek Link (SMOTE + Tomek)". The sequential ensemble technique employs two distinct deep learning models: Convolutional Neural Network (CNN) and a hybrid model, CNN with Long Short-Term Memory Network (CNN-LSTM). The two standard datasets "MIT-BIH arrhythmias database" (MITDB) and "PTB diagnostic database" (PTBDB) are combined and extracted 23, 998 ECG beats for the model validation. In this work, the three models CNN, CNN-LSTM, and ensemble approach were tested on four kinds of ECG datasets: the original data (imbalanced), the data sampled using a random oversampled technique, data sampled using SMOTE, and the dataset resampled using SMOTE + Tomek algorithm. The overall highest accuracy was obtained of 99.02% on the SMOTE + Tomek sampled dataset by ensemble technique and the minority class accuracy result (Recall) is improved by 20% as compared to the imbalanced data.

BACKGROUND: Appropriate anticoagulant therapy for patients with atrial fibrillation (AF) requires assessment of stroke and bleeding risks. However, risk stratification schemas such as CHA2DS2-VASc and HAS-BLED have modest predictive capacity for patients with AF. Multilabel machine learning (ML) techniques may improve predictive performance and support decision-making for anticoagulant therapy. We compared the performance of multilabel ML models with the currently used risk scores for predicting outcomes in AF patients. METHODS: This was a retrospective cohort study of 9670 patients, mean age 76.9 years, 46% women, who were hospitalized with non-valvular AF, and had 1-year follow-up. The outcomes were ischemic stroke (167), major bleeding (430) admissions, all-cause death (1912) and event-free survival (7387). Discrimination and calibration of ML models were compared with clinical risk scores by area under the curve (AUC). Risk stratification was assessed using net reclassification index (NRI). RESULTS: Multilabel gradient boosting classifier chain provided the best AUCs for stroke (0.685 95% CI 0.676, 0.694), major bleeding (0.709 95% CI 0.703, 0.716) and death (0.765 95% CI 0.763, 0.768) compared to multi-layer neural networks and classifier chain using support vector machine. It provided modest performance improvement for stroke compared to AUC of CHA2DS2-VASc (0.652, NRI = 3.2%, p-value = 0.1), but significantly improved major bleeding prediction compared to AUC of HAS-BLED (0.522, NRI = 22.8%, p-value < 0.05). It also achieved greater discriminant power for death compared with AUC of CHA2DS2-VASc (0.606, p-value < 0.05). ML models identified additional risk features such as hemoglobin level, renal function. CONCLUSIONS: Multilabel ML models can outperform clinical risk stratification scores for predicting the risk of major bleeding and death in non-valvular AF patients.

Early detection and treatment of Alzheimer's Disease (AD) are significant. Recently, multi-modality imaging data have promoted the development of the automatic diagnosis of AD. This paper proposes a method based on latent feature fusion to make full use of multi-modality image data information. Specifically, we learn a specific projection matrix for each modality by introducing a binary label matrix and local geometry constraints and then project the original features of each modality into a low-dimensional target space. In this space, we fuse latent feature representations of different modalities for AD classification. The experimental results on Alzheimer's Disease Neuroimaging Initiative database demonstrate the proposed methods effectiveness in classifying AD.

Atrial fibrillation (AF) is the most common sustained arrhythmia worldwide and imposes a substantial economic burden on the public healthcare system due to its high morbidity and mortality. Early detection of AF is crucial in providing timely treatment and preventing complications such as stroke and other thromboembolism. For AF diagnosis, the 12-lead electrocardiogram (ECG) has been established as the gold standard. However, it requires the clinical experiences of cardiologists and may be vulnerable to inter-observer variability. Although automated AF diagnostic techniques based on deep neural networks (DNN) have been proposed, most studies were conducted using small-scale datasets, resulting in the over-fitting problem. Furthermore, they have not fully exploited ECG components such as P-wave, QRS-complex, and T-wave contrary to the approach adopted by cardiologists who interpret ECG by considering its components. To overcome these limitations, this study presents the component-aware transformer (CAT), which segments the ECG waveform into each component, vectorizes them with length and types information into one vector, and used it as the input of the transformer. We conducted extensive experiments to evaluate the CAT using a large-scale dataset called Shaoxing Hospital Zhejiang University School of Medicine database (AF: 1,780 cases, non-AF: 8,866 cases). The quantitative evaluations demonstrate that the CAT outperforms the conventional deep learning techniques on both single- and 12-lead ECG signals. Moreover, the CAT trained on single-lead ECG is comparable to that of a 12-lead analysis, while conventional methods degraded significantly in performance. Consequently, the CAT is applicable to various single-channel signals such as airway pressure, photoplethysmogram, and blood pressure.

Computer tomography (CT) has played an essential role in the field of medical diagnosis, but the blurry edges and unclear textures in traditional CT images usually interfere the subsequent judgement from radiologists or clinicians. Deep learning based image super-resolution methods have been applied for CT image restoration recently. However, different levels of information of CT image details are mixed and difficult to be mapped from deep features by traditional convolution operations. Moreover, features representing regions of interest (ROIs) in CT images are treated equally as those for background, resulting in low concentration of meaningful features and high redundancy of computation. To tackle these issues, a CT image super-resolution network is proposed based on hybrid attention mechanism and global feature fusion, which consists of the following three parts: 1) stacked Swin Transformer blocks are used as the backbone to extract initial features from the degraded CT image; 2) a multi-branch hierarchical self-attention module (MHSM) is proposed to adaptively map multi-level features representing different levels of image information from the initial features and establish the relationship between these features through a self-attention mechanism, where three branches apply different strategies of integrating convolution, down-sampling and up-sampling operations according to three different scale factors; 3) a multidimensional local topological feature enhancement module (MLTEM) is proposed and plugged into the end of the backbone to refine features in the channel and spatial dimension simultaneously, so that the features representing ROIs could be enhanced while meaningless ones eliminated. Experimental results demonstrate that our method outperform the state-of-the-art super-resolution methods on restoring CT images with respect to peak signal-to-noise ratio (PSNR) and structural similarity (SSIM) indices.

The development of intelligent Robot-Assisted Minimally Invasive Surgery demands geometric reconstruction from endoscopic images. However, images of human tissue surfaces are commonly texture-less. Obtaining the dense depth map of a texture-less scene is very difficult because traditional feature-based 3D reconstruction methods cannot detect enough features to build dense correspondences for depth computation. Given this problem, this study proposes a novel reconstruction method based on our shape-based image augmentation method. The main contribution of this method is the provision of a novel means to resolve the texture-less problem mainly on the input data level. In our method, we first calculate two shape gradient maps using Shape-From-Shading (SFS) method and we build Fast Point Feature Histogram (FPFH) 3D descriptor map according to the shape. Second, a series of augmented images can be computed by combining shape gradient maps, FPFH map, and the original image with different weights. Finally, we detect features on the new augmented images. Based on feature calculated sparse depth information and SFS calculated dense shape information, we further integrate a rectified dense depth map. Experiments show that our method can reconstruct texture-less surfaces with good accuracy.

We analyse the haemodynamics of the left atrium, highlighting differences between healthy individuals and patients affected by atrial fibrillation. The computational study is based on patient-specific geometries of the left atria to simulate blood flow dynamics. We design a novel procedure to compute the boundary data for the 3D haemodynamic simulations, which are particularly useful in absence of data from clinical measurements. With this aim, we introduce a parametric definition of atrial displacement, and we use a closed-loop lumped parameter model of the whole cardiovascular circulation conveniently tuned on the basis of the patient's characteristics. We evaluate several fluid dynamics indicators for atrial haemodynamics, validating our numerical results in terms of clinical measurements; we investigate the impact of geometric and clinical characteristics on the risk of thrombosis. To highlight the correlation of thrombus formation with atrial fibrillation, according to medical evidence, we propose a novel indicator: age stasis. It arises from the combination of Eulerian and Lagrangian quantities. This indicator identifies regions where slow flow cannot properly rinse the chamber, accumulating stale blood particles, and creating optimal conditions for clots formation.

The long-term success of a dental implant is related to the material and design of the implant, and bone density. Conventional implants cause stress-shielding due to a mismatch between the implant and bone stiffness. Functionally graded porous materials and designs are a great choice for the design of implants to control the local stiffness at a certain location to meet the biomechanical requirements. The purpose of this study is to analyze five designs of axial and radial functionally graded materials (FGM) implants besides the conventional implant and conical and cylindrical shapes that were simulated with five different bone densities. The results showed that strain in bone increased with a decrease in cancellous bone density. The shape of the implant did not play an important role in strain/stress distribution. Conventional implants showed optimal strain (1000-2240 με) in low-density (0.7-0.8 g/cm3) bone, however, FGM implants produced optimal strain (990-1280 με) in the high-density bone (0.9-1 g/cm3) as compared to conventional implants. The proposed designs of FGM implants have the potential to address the complications of conventional implants in high-density bone.

As the number of people suffering from cardiovascular diseases increases every year, it becomes essential to have an accurate automatic electrocardiogram (ECG) diagnosis system. Researchers have adopted different methods, such as deep learning, to investigate arrhythmias classification. However, the importance of ECG waveform features is generally ignored when deep learning approaches are applied to classification tasks. P-wave, QRS-wave, and T-wave, containing plenty of physiological information, are three critical waves in the ECG heartbeat. The accurate localization of these critical ECG wave components is a prerequisite for ECG classification and diagnosis. In this study, a novel P-QRS-T wave localization method based on hybrid neural networks is proposed. The raw ECG signal is preprocessed sequentially by filtering, heartbeat extraction, and data standardization. The hybrid neural network is constructed by combining the residual neural network (ResNet) and the Long Short-Term Memory (LSTM). It predicts the relative positions of the P-peak, QRS-peak, and T-peak for each heartbeat. The proposed algorithm was validated on four ECG databases with input noise of different signal-to-noise ratio (SNR) levels. The results show that the proposed method can accurately predict the positions of the three key waves. The proposed P-QRS-T localization approach can improve the efficiency of ECG delineation. Integrated with cardiac disease classification methods, it can contribute to the development of advanced automatic ECG diagnosis systems.

Brain-computer interfaces (BCIs) can help people with disabilities to communicate with others, express themselves, and even create art. In this paper, a BCI painting system using a hybrid control approach based on steady-state visual evoked potential (SSVEP) and P300 was developed, which can enable simple painting through brain-controlled painting tools. The BCI painting system is composed of two parts: a hybrid stimulus interface and a hybrid electroencephalogram (EEG) signal processing module. The user selects the menus and tools through the SSVEP and P300 stimulus matrices, respectively, and the paintings are displayed in the canvas area of the hybrid stimulus interface in real time. Twenty subjects participated in this study. An offline training experiment was performed to construct the P300 and SSVEP recognition models for each subject; an online painting experiment, which included a copy-painting task and a free-painting task, was performed to evaluate the BCI painting system. The results of the online painting experiment showed that the average tool selection accuracy (88.92 ± 3.94%) of the BCI painting system using the hybrid stimulus interface was slightly higher than that of the traditional brain painting system based on the P300 stimulus interface; the average information transfer rate (ITR) (74.20 ± 5.28 bpm, 71.80 ± 5.15 bpm) in the copy-painting and free-painting tasks of the BCI painting system was significantly higher than that of the traditional brain painting system. Our BCI painting system can effectively help users express their artistic creativity and improve their painting efficiency, and can provide new methods and new ideas for developing BCI-controlled applications.

Automatic brain structure segmentation in Magnetic Resonance Image (MRI) plays an important role in the diagnosis of various neuropsychiatric diseases. However, most existing methods yield unsatisfactory results due to blurred boundaries and complex structures. Improving the segmentation ability requires the model to be explicit about the spatial localization and shape appearance of targets, which correspond to the low-frequency content features and the high-frequency edge features, respectively. Therefore, in this paper, to extract rich edge and content feature representations, we focus on the composition of the feature and utilize a frequency decoupling (FD) block to separate the low-frequency and high-frequency parts of the feature. Further, a novel edge-aware network (EA-Net) is proposed for jointly learning to segment brain structures and detect object edges. First, an encoder-decoder sub-network is utilized to obtain multi-level information from the input MRI, which is then sent to the FD block to complete the frequency separation. Further, we use different mechanisms to optimize both the low-frequency and high-frequency features. Finally, these two parts are fused to generate the final prediction. In particular, we extract the content mask and the edge mask from the optimization feature with different supervisions, which forces the network to learn the boundary features of the object. Extensive experiments are performed on two public brain MRI T1 scan datasets (the IBSR dataset and the MALC dataset) to evaluate the effectiveness of the proposed algorithm. The experiments show that the EA-Net achieves the best performance compared with the state-of-the-art methods, and improves the segmentation DSC score by 1.31% at most compared with the U-Net model and its variants. Moreover, we evaluate the EA-Net under different noise disturbances, and the results demonstrate the robustness and superiority of our method under low-quality noisy MRI. Code is available at https://github.com/huqian999/EA-Net.

In recent years, the global Internet of Medical Things (IoMT) industry has evolved at a tremendous speed. Security and privacy are key concerns on the IoMT, owing to the huge scale and deployment of IoMT networks. Machine learning (ML) and blockchain (BC) technologies have significantly enhanced the capabilities and facilities of healthcare 5.0, spawning a new area known as "Smart Healthcare." By identifying concerns early, a smart healthcare system can help avoid long-term damage. This will enhance the quality of life for patients while reducing their stress and healthcare costs. The IoMT enables a range of functionalities in the field of information technology, one of which is smart and interactive health care. However, combining medical data into a single storage location to train a powerful machine learning model raises concerns about privacy, ownership, and compliance with greater concentration. Federated learning (FL) overcomes the preceding difficulties by utilizing a centralized aggregate server to disseminate a global learning model. Simultaneously, the local participant keeps control of patient information, assuring data confidentiality and security. This article conducts a comprehensive analysis of the findings on blockchain technology entangled with federated learning in healthcare. 5.0. The purpose of this study is to construct a secure health monitoring system in healthcare 5.0 by utilizing a blockchain technology and Intrusion Detection System (IDS) to detect any malicious activity in a healthcare network and enables physicians to monitor patients through medical sensors and take necessary measures periodically by predicting diseases. The proposed system demonstrates that the approach is optimized effectively for healthcare monitoring. In contrast, the proposed healthcare 5.0 system entangled with FL Approach achieves 93.22% accuracy for disease prediction, and the proposed RTS-DELM-based secure healthcare 5.0 system achieves 96.18% accuracy for the estimation of intrusion detection.

A clinically comparable multi-tasking computerized deep U-Net-based model is demonstrated in this paper. It intends to offer clinical gland morphometric information and cancer grade classification to be provided as referential opinions for pathologists in order to abate human errors. It embraces enhanced feature learning capability that aids in extraction of potent multi-scale features; efficacious semantic gap recovery during feature concatenation; and successful interception of resolution-degradation and vanishing gradient problems while performing moderate computations. It is proposed by integrating three unique novel structural components namely Hybrid Convolutional Learning Units in the encoder and decoder, Attention Learning Units in skip connection, and Multi-Scalar Dilated Transitional Unit as the transitional layer in the traditional U-Net architecture. These units are composed of the amalgamated phenomenon of multi-level convolutional learning through conventional, atrous, residual, depth-wise, and point-wise convolutions which are further incorporated with target-specific attention learning and enlarged effectual receptive field size. Also, pre-processing techniques of patch-sampling, augmentation (color and morphological), stain-normalization, etc. are employed to burgeon its generalizability. To build network invariance towards digital variability, exhaustive experiments are conducted using three public datasets (Colorectal Adenocarcinoma Gland (CRAG), Gland Segmentation (GlaS) challenge, and Lung Colon-25000 (LC-25K) dataset)) and then its robustness is verified using an in-house private dataset of Hospital Colon (HosC). For the cancer classification, the proposed model achieved results of Accuracy (CRAG(95%), GlaS(97.5%), LC-25K(99.97%), HosC(99.45%)), Precision (CRAG(0.9678), GlaS(0.9768), LC-25K(1), HosC(1)), F1-score (CRAG(0.968), GlaS(0.977), LC 25K(0.9997), HosC(0.9965)), and Recall (CRAG(0.9677), GlaS(0.9767), LC-25K(0.9994), HosC(0.9931)). For the gland detection and segmentation, the proposed model achieved competitive results of F1-score (CRAG(0.924), GlaS(Test A(0.949), Test B(0.918)), LC-25K(0.916), HosC(0.959)); Object-Dice Index (CRAG(0.959), GlaS(Test A(0.956), Test B(0.909)), LC-25K(0.929), HosC(0.922)), and Object-Hausdorff Distance (CRAG(90.47), GlaS(Test A(23.17), Test B(71.53)), LC-25K(96.28), HosC(85.45)). In addition, the activation mappings for testing the interpretability of the classification decision-making process are reported by utilizing techniques of Local Interpretable Model-Agnostic Explanations, Occlusion Sensitivity, and Gradient-Weighted Class Activation Mappings. This is done to provide further evidence about the model's self-learning capability of the comparable patterns considered relevant by pathologists without any pre-requisite for annotations. These activation mapping visualization outcomes are evaluated by proficient pathologists, and they delivered these images with a class-path validation score of (CRAG(9.31), GlaS(9.25), LC-25K(9.05), and HosC(9.85)). Furthermore, the seg-path validation score of (GlaS (Test A(9.40), Test B(9.25)), CRAG(9.27), LC-25K(9.01), HosC(9.19)) given by multiple pathologists is included for the final segmented outcomes to substantiate the clinical relevance and suitability for facilitation at the clinical level. The proposed model will aid pathologists to formulate an accurate diagnosis by providing a referential opinion during the morphology assessment of histopathology images. It will reduce unintentional human error in cancer diagnosis and consequently will enhance patient survival rate.

Fatty liver disease is a common disease that causes extra fat storage in an individual's liver. Patients with fatty liver disease may progress to cirrhosis and liver failure, further leading to liver cancer. The prevalence of fatty liver disease ranges from 10% to 30% in many countries. In general, detecting fatty liver requires professional neuroimaging modalities or methods such as computed tomography, ultrasound, and medical experts' practical experiences. Considering this point, finding intelligent electronic noninvasive diagnostic approaches are desired at present. Currently, most existing works in the area of computerized noninvasive disease detection often apply one view (modality) or perform multi-view (several modalities) analysis, e.g., face, tongue, and/or sublingual for disease detection. The multi-view data of patients provides more complementary information for diagnosis. However, due to the conditions of data acquisition, interference by human factors, etc., many multi-view data are defective with some missing-view information, making these multi-view data difficult to evaluate. This factor largely affects the performance of classifying disease and the development of fully computerized noninvasive methods. Thus, the purpose of this study is to address the missing view issue among noninvasive disease detection. In this work, a multi-view dataset containing facial, sublingual vein, and tongue images are initially processed to produce corresponding feature for incomplete multi-view disease diagnostic evaluation. Hereby, we propose a novel method, i.e., multi-view completion, to process the incomplete multi-view data in order to complete the missing-view information for classifying fatty liver disease from healthy candidates. In particular, this method can explore the intra-view and inter-view information to produce the missing-view data effectively. Extensive experiments on a collected dataset with 220 fatty liver patients and 220 healthy samples show that our proposed approach achieves better diagnostic results with missing-view completion compared to the original incomplete multi-view data under various classifiers. Related results prove that our method can effectively process the missing-view issue and improve the noninvasive disease detection performance.

The Knee contact force (KCF) is a key factor in evaluating knee joint function of patients with knee osteoarthritis. In vivo measurement of KCF based on the instrumented implants is limited due to the ethical issues and technical complexities. Machine learning can be used to predict tibiofemoral compartment contact forces. However, anthropometric differences between individuals make the accurate predictions challenging. The purpose of this study was to develop transfer learning models to predict the medial KCF of patients with knee valgus in rehabilitation gaits. Four subjects with instrumented tibial prostheses were considered, including one with knee valgus and three with normal knee joint alignment. Two transfer learning models were proposed: a fine-tuning model and an adaptive model. In particular, a synchronization method for extracting experimental data in a complete gait cycle was developed, since different types of experimental data have different sampling frequencies. The transfer learning models were pre-trained by the experiment data of patients with normal knee joint alignment, and re-trained by the data of the patient with knee valgus. Predictions of the transfer learning models and traditional machine learning model were validated against the in vivo measurements. The proposed transfer learning models were tested within two levels: the single subject (Level 1) and multiple subjects (Level 2). The results show that the two transfer learning models could more accurately predict the medial KCF of patients with knee valgus than the traditional machine learning model. The performance of the fine-tuning model is better than that of the adaptive model. Compared with the traditional machine learning and inverse dynamics analysis, transfer learning represents a much easier and more accurate method. It can be introduced to help clinicians validate and adjust the rehabilitation gait for specific patients.

Automated sleep disorder detection is challenging because physiological symptoms can vary widely. These variations make it difficult to create effective sleep disorder detection models which support hu-man experts during diagnosis and treatment monitoring. From 2010 to 2021, authors of 95 scientific papers have taken up the challenge of automating sleep disorder detection. This paper provides an expert review of this work. We investigated whether digital technology and Artificial Intelligence (AI) can provide automated diagnosis support for sleep disorders. We followed the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines during the content discovery phase. We compared the performance of proposed sleep disorder detection methods, involving differ-ent datasets or signals. During the review, we found eight sleep disorders, of which sleep apnea and insomnia were the most studied. These disorders can be diagnosed using several kinds of biomedical signals, such as Electrocardiogram (ECG), Polysomnography (PSG), Electroencephalogram (EEG), Electromyogram (EMG), and snore sound. Subsequently, we established areas of commonality and distinctiveness. Common to all reviewed papers was that AI models were trained and tested with labelled physiological signals. Looking deeper, we discovered that 24 distinct algorithms were used for the detection task. The nature of these algorithms evolved, before 2017 only traditional Machine Learning (ML) was used. From 2018 onward, both ML and Deep Learning (DL) methods were used for sleep disorder detection. The strong emergence of DL algorithms has considerable implications for future detection systems because these algorithms demand significantly more data for training and testing when compared with ML. Based on our review results, we suggest that both type and amount of labelled data is crucial for the design of future sleep disorder detection systems because this will steer the choice of AI algorithm which establishes the desired decision support. As a guiding principle, more labelled data will help to represent the variations in symptoms. DL algorithms can extract information from these larger data quantities more effectively, therefore; we predict that the role of these algorithms will continue to expand.

Accurate segmentation of electrocardiogram (ECG) waves is crucial for cardiovascular diseases (CVDs). In this study, a bidirectional hidden semi-Markov model (BI-HSMM) based on the probability distributions of ECG waveform duration was proposed for ECG wave segmentation. Four feature-vectors of ECG signals were extracted as the observation sequence of the hidden Markov model (HMM), and the statistical probability distribution of each waveform duration was counted. Logistic regression (LR) was used to train model parameters. The starting and ending positions of the QRS wave were first detected, and thereafter, bidirectional prediction was employed for the other waves. Forwardly, ST segment, T wave, and TP segment were predicted. Backwardly, P wave and PQ segments were detected. The Viterbi algorithm was improved by integrating the recursive formula of the forward prediction and backward backtracking algorithms. In the QT database, the proposed method demonstrated excellent performance (Acc = 97.98%, F1 score of P wave = 98.37%, F1 score of QRS wave = 97.60%, F1 score of T wave = 97.79%). For the wearable dynamic electrocardiography (DCG) signals collected by the Shandong Provincial Hospital (SPH), the detection accuracy was 99.71% and the F1 of each waveform was above 99%. The experimental results and real DCG signal validation confirmed that the proposed new BI-HSMM method exhibits significant ability to segment the resting and DCG signals; this is conducive to the detection and monitoring of CVDs.

Early accurate mammography screening and diagnosis can reduce the mortality of breast cancer. Although CNN-based breast cancer computer-aided diagnosis (CAD) systems have achieved significant results in recent years, precise diagnosis of lesions in mammogram remains a challenge due to low signal-to-noise ratio (SNR) and physiological characteristics. Many researchers achieved excellent performance in detecting mammographic images by inputting region of interest (ROI) annotations while ROI annotations require a great quantity of manual labor, time and resources. We propose a two-stage method that combines images preprocessing and model optimization to address the aforementioned challenges. Firstly, we propose the breast database preprocess (BDP) method to preprocess INbreast then we get INbreast†. The only label we need is benign or malignant label of one mammogram, not manual labeling such as ROI annotations. Secondly, we apply focal loss to ECA-Net50 which is an improved model based on ResNet50 with efficient channel attention (ECA) module. Our method can adaptively extract the key features of mammograms, meanwhile solving the problem of hard-to-classify samples and unbalanced categories. The AUC value of our method on INbreast† is 0.960, accuracy is 0.929, Recall is 0.928. The precision of our method on INbreast† is 0.883 which improved by 0.254 compared to ResNet50. In addition, we use Grad-CAM to visualize the effect of our model. The visualized heatmaps extracted by our method can focus more on lesion regions. Both numerical and visualized experiments demonstrate that our method achieves satisfactory performance.

BACKGROUND: Sleep spindles are an indicator of the development and integrity of the central nervous system in infants. Identifying sleep spindles manually in EEG is time-consuming and typically requires experienced experts. Automated detection of sleep spindles would greatly facilitate this analysis. Deep learning methods have been widely used recently in EEG analysis. METHOD: We have developed a deep learning-based automated sleep spindle detection system, Deep-spindle, which employs a convolutional neural network (CNN) combined with a bidirectional Long Short-Term Memory (LSTM) network, which could assist in the analysis of infant sleep spindles. Deep-spindle was trained on the EEGs of ex-term infants to estimate the number and duration of sleep spindles. The ex-term EEG on channel F4-C4 was split into training (N=81) and validation (N=30) sets. An additional 30 ex-term EEG and 54 ex-preterm infant EEGs (channel F4-C4 and F3-C3) were used as an independent test set. RESULT: Deep-spindle detected the number of sleep spindles with 91.9% to 96.5% sensitivity and 95.3% to 96.7% specificity, and estimated sleep spindle duration with a percent error of 13.1% to 19.1% in the independent test set. For each detected spindle event, the user is presented with amplitude, power spectral density and the spectrogram of the corresponding spindle EEG, and the probability of the event being a sleep spindle event, providing the user with insight into why the event is predicted as a sleep spindle to provide confidence in the predictions. CONCLUSION: The Deep-spindle system can reduce physicians' workload, demonstrating the potential to assist physicians in the automated analysis of sleep spindles in infants.

Blood is made up of leukocytes (WBCs), erythrocytes (RBCs), and thrombocytes. The ratio of blood cancer diseases is increasing rapidly, among which leukemia is one of the famous cancer which may lead to death. Leukemia cancer is initiated by the unnecessary growth of immature WBCs present in the sponge tissues of bone marrow. It is generally analyzed by etiologists by perceiving slides of blood smear images under a microscope. The morphological features and blood cells count facilitated the etiologists to detect leukemia. Due to the late detection and expensive instruments used for leukemia analysis, the death rate has risen significantly. The fluorescence-based cell sorting technique and manual recounts using a hemocytometer are error-prone and imprecise. Leukemia detection methods consist of pre-processing, segmentation, features extraction, and classification. In this article, recent deep learning methodologies and challenges for leukemia detection are discussed. These methods are helpful to examine the microscopic blood smears images and for the detection of leukemia more accurately.

There have been several attempts to quantify the diagnostic distortion caused by algorithms that perform low-dimensional electrocardiogram (ECG) representation. However, there is no universally accepted quantitative measure that allows the diagnostic distortion arising from denoising, compression, and ECG beat representation algorithms to be determined. Hence, the main objective of this work was to develop a framework to enable biomedical engineers to efficiently and reliably assess diagnostic distortion resulting from ECG processing algorithms. We propose a semiautomatic framework for quantifying the diagnostic resemblance between original and denoised/reconstructed ECGs. Evaluation of the ECG must be done manually, but is kept simple and does not require medical training. In a case study, we quantified the agreement between raw and reconstructed (denoised) ECG recordings by means of kappa-based statistical tests. The proposed methodology takes into account that the observers may agree by chance alone. Consequently, for the case study, our statistical analysis reports the "true", beyond-chance agreement in contrast to other, less robust measures, such as simple percent agreement calculations. Our framework allows efficient assessment of clinically important diagnostic distortion, a potential side effect of ECG (pre-)processing algorithms. Accurate quantification of a possible diagnostic loss is critical to any subsequent ECG signal analysis, for instance, the detection of ischemic ST episodes in long-term ECG recordings.

The sixth cranial nerve, also known as the abducens nerve, is responsible for controlling the movements of the lateral rectus muscle. Palsies on the sixth nerve prevent some muscles that control eye movements from proper functioning, causing headaches, migraines, blurred vision, vertigo, and double vision. Hence, such palsy should be diagnosed in the early stages to treat it without leaving any sequela. The usual methods for diagnosing the sixth nerve palsy are invasive or depend on expensive equipment, and computer-based methods designed specifically to diagnose the aforementioned palsy were not found until the publication of this work. Therefore, a low-cost, non-invasive method can support or guide the ophthalmologist's diagnosis. In this context, this work presents a computational methodology to aid in diagnosing the sixth nerve palsy using videos to assist ophthalmologists in the diagnostic process, serving as a second opinion. The proposed method uses convolutional neural networks and image processing techniques to track both eyes' movement trajectory during the video. With this trajectory, it is possible to calculate the average velocity (AV) in which each eye moves. Since it is known that paretic eyes move slower than healthy eyes, comparing the AV of both eyes can determine if the eye is healthy or paretic. The results obtained with the proposed method showed that paretic eyes move at least 19.65% slower than healthy ones. This threshold, along with the AV of the movement of the eyes, can help ophthalmologists in their analysis. The proposed method reached 92.64% accuracy in diagnosing the sixth optic nerve palsy (SONP), with a Kappa index of 0.925, which highlights the reliability of the results and gives favorable perspectives for further clinical application.

Acute leukemia is a type of blood cancer with a high mortality rate. Current therapeutic methods include bone marrow transplantation, supportive therapy, and chemotherapy. Although a satisfactory remission of the disease can be achieved, the risk of recurrence is still high. Therefore, novel treatments are demanding. Chimeric antigen receptor-T (CAR-T) therapy has emerged as a promising approach to treating and curing acute leukemia. To harness the therapeutic potential of CAR-T cell therapy for blood diseases, reliable cell morphological identification is crucial. Nevertheless, the identification of CAR-T cells is a big challenge posed by their phenotypic similarity with other blood cells. To address this substantial clinical challenge, herein we first construct a CAR-T dataset with 500 original microscopy images after staining. Following that, we create a novel integrated model called RCMNet (ResNet18 with Convolutional Block Attention Module and Multi-Head Self-Attention) that combines the convolutional neural network (CNN) and Transformer. The model shows 99.63% top-1 accuracy on the public dataset. Compared with previous reports, our model obtains satisfactory results for image classification. Although testing on the CAR-T cell dataset, a decent performance is observed, which is attributed to the limited size of the dataset. Transfer learning is adapted for RCMNet and a maximum of 83.36% accuracy is achieved, which is higher than that of other state-of-the-art models. This study evaluates the effectiveness of RCMNet on a big public dataset and translates it to a clinical dataset for diagnostic applications.

Acute Pancreatitis (AP) is the inflammation of the pancreas that can be fatal or lead to further complications based on the severity of the attack. Early detection of AP disease can help save lives by providing utmost care, rigorous treatment, and better resources. In this era of data and technology, instead of relying on manual scoring systems, scientists are employing advanced machine learning and data mining models for the early detection of patients with high chances of mortality. The current work on AP mortality prediction is negligible, and the few studies that exist have many shortcomings and are impractical for clinical deployment. In this research work, we tried to overcome the existing issues. One main issue is the lack of high-quality public datasets for AP, which are crucial for effectively training ML models. The available datasets are small in size, have many missing values, and suffer from high class imbalance. We augmented three public datasets, MIMIC-III, MIMIC-IV, and eICU, to obtain a larger dataset, and experiments proved that augmented data trained classifiers better than original small datasets. Moreover, we employed emerging advanced techniques to handle underlying issues in data. The results showed that iterative imputer is best for filling missing values in AP data. It beats not only the basic techniques but also the Knn-based imputation. Class imbalance is first addressed using data downsampling; apparently, it gave decent results on small test sets. However, we conducted numerous experiments on large test sets to prove that downsampling in the case of AP produced misleading and poor results. Next, we applied various techniques to upsample data in two different class splits, a 50 to 50 and a 70 to 30 majority-minority class split. Four different tabular generative adversarial networks, CTGAN, TGAN, CopulaGAN, and CTAB, and a variational autoencoder, TVAE, were deployed for synthetic data generation. SMOTE was also utilized for data upsampling. The computational results showed that the Random Forest (RF) classifier outperformed all other classifiers on a 50 to 50 class split data generated by CTGAN, with 0.702 Fβ and 0.833 recall. Results produced by RF on the TVAE dataset were also comparable, with 0.698 Fβ. In the case of SMOTE-based upsampling, DNN performed best with a 0.671 Fβ score.

Resting-state Magnetic resonance imaging-based parcellation aims to group the voxels/vertices non-invasively based on their connectivity profiles, which has achieved great success in understanding the fundamental organizational principles of the human brain. Given the substantial inter-individual variability, the increasing number of studies focus on individual parcellation. However, current methods perform individual parcellations independently or are based on the group prior, requiring expensive computational costs, precise parcel alignment, and extra group information. In this work, an efficient and flexible parcellation framework of individual cerebral cortex was proposed based on a region growing algorithm by merging the unassigned and neighbor vertex with the highest-correlated parcel iteratively. It considered both consistency with prior atlases and individualized functional homogeneity of parcels, which can be applied to a single individual without parcel alignment and group information. The proposed framework was leveraged to 100 unrelated subjects for functional homogeneity comparison and individual identification, and 186 patients with Parkison's disease for symptom prediction. Results demonstrated our framework outperformed other methods in functional homogeneity, and the generated parcellations provided 100% individual identification accuracy. Moreover, the default mode network (DMN) exhibited higher functional homogeneity, intra-subject parcel reproducibility and fingerprinting accuracy, while the sensorimotor network did the opposite, reflecting that the DMN is the most representative, stable, and individual-identifiable network in the resting state. The correlation analysis showed that the severity of the disease symptoms was related negatively to the similarity of individual parcellation and the atlases of healthy populations. The disease severity can be correctly predicted using machine learning models based on individual topographic features such as parcel similarity and parcel size. In summary, the proposed framework not only significantly improves the functional homogeneity but also captures individualized and disease-related brain topography, serving as a potential tool to explore brain function and disease in the future.

BACKGROUND AND OBJECTIVE: Automatic segmentation and annotation of medical image plays a critical role in scientific research and the medical care community. Automatic segmentation and annotation not only increase the efficiency of clinical workflow, but also prevent overburdening of radiologists. The objective of this work is to improve the accuracy and give a probabilistic map for automatic annotation from small data set to reduce the use of tedious and prone to error manual annotations from chest X-rays. METHOD: In this paper, we have proposed an attention UW-Net, which introduces an intermediate layer acting as a bridge between the encoder and decoder pathways. The intermediate layer is a series of fully connected convolutional layers generated from the upsampling of the final encoder layer connected to the corresponding up sampled and down sampled blocks via skip-connections. The intermediate layer is further connected to the decoder pathway using a downsampling layer. RESULTS: The proposed attention UW-Net is giving a very good performance, achieving an average F1-score of 95.7%, 80.9%, 81.0% and 77.6% for lung (large), heart (medium), trachea (small), and collarbone (small) object segmentations, respectively. The attention UW-Net outperforms not only in comparison to U-Net and its variations but also with respect to other standard recent automatic and semi-automatic segmentation/annotation models. An ablation study was also performed to find the best suited high-performing architecture. CONCLUSION: The uniformity in prediction accuracy of segmentation masks for all kinds of segmentation masks (large, medium, and small lesions) makes this model best for automatic annotation of organs.

Despite global vaccination efforts, COVID-19 breakthrough infections caused by variant virus continue to occur frequently, long-term sequelae of COVID-19 infection like neuronal dysfunction emerge as a noteworthy issue. Neuroimmune disorder induced by Inflammatory factor storm was considered as a possible reason, however, little was known about the functional factors affecting neuroimmune response to this virus. Here, using medial prefrontal cortex single cell data of COVID-19 patients, expression pattern analysis indicated that some immune-related pathway genes expressed specifically, including genes associated with T cell receptor, TNF signaling in microglia and Cytokine-cytokine receptor interaction and HIF-1 signaling pathway genes in astrocytes. Besides the well-known immune-related cell type microglia, we also observed immune-related factors like IL17D, TNFRSF1A and TLR4 expressed in Astrocytes. Based on the ligand-receptor relationship of immune-related factors, crosstalk landscape among cell clusters were analyzed. The findings indicated that astrocytes collaborated with microglia and affect excitatory neurons, participating in the process of immune response and neuronal dysfunction. Moreover, subset of astrocytes specific immune factors (hinged neuroimmune genes) were proved to correlate with Covid-19 infection and ventilator-associated pneumonia using multi-tissue RNA-seq and scRNA-seq data. Function characterization clarified that hinged neuroimmune genes were involved in activation of inflammation and hypoxia signaling pathways, which could lead to hyper-responses related neurological sequelae. Finally, a risk model was constructed and testified in RNA-seq and scRNA data of peripheral blood.

OBJECTIVE: Cardiovascular disease (CVD) is a major healthcare challenge and therefore early risk assessment is vital. Previous assessment techniques use either "conventional CVD risk calculators (CCVRC)" or machine learning (ML) paradigms. These techniques are ad-hoc, unreliable, not fully automated, and have variabilities. We, therefore, introduce AtheroEdge-MCDLAI (AE3.0DL) windows-based platform using multiclass Deep Learning (DL) system. METHODS: Data was collected on 500 patients having both carotid ultrasound and corresponding coronary angiography scores (CAS), measured as stenosis in coronary arteries and considered as the gold standard. A total of 39 covariates were used, clubbed into three clusters, namely (i) Office-based: age, gender, body mass index, smoker, hypertension, systolic blood pressure, and diastolic blood pressure; (ii) Laboratory-based: Hyperlipidemia, hemoglobin A1c, and estimated glomerular filtration rate; and (iii) Carotid ultrasound image phenotypes: maximum plaque height, total plaque area, and intra-plaque neovascularization. Baseline characteristics for four classes (target labels) having significant (p < 0.0001) values were calculated using Chi-square and ANOVA. For handling the cohort's imbalance in the risk classes, AE3.0DL used the synthetic minority over-sampling technique (SMOTE). AE3.0DL used Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) DL models and the performance (accuracy and area-under-the-curve) was computed using 10-fold cross-validation (90% training, 10% testing) frameworks. AE3.0DL was validated and benchmarked. RESULTS: The AE3.0DL using RNN and LSTM showed an accuracy and AUC (p < 0.0001) pairs as (95.00% and 0.98), and (95.34% and 0.99), respectively, and showed an improvement of 32.93% and 9.94% against CCVRC and ML, respectively. AE3.0DL runs in <1 s. CONCLUSION: DL algorithms are a powerful paradigm for coronary artery disease (CAD) risk prediction and CVD risk stratification.

BACKGROUND: Organ dysfunction, especially liver injury, caused by dengue virus (DENV) infection has been associated with fatal cases in dengue patients around the world. However, the pathophysiological mechanisms of liver involvement in dengue remain unclear. There is accumulating evidence that miRNAs are playing an important role in regulating viral pathogenesis, and it can help in diagnostic and anti-viral therapies development. METHODS: We collected liver tissues of DENV-infected for small RNA sequencing to identify significantly different express miRNAs during dengue virus infection, and the identified target genes of these miRNAs were annotated by biological function and pathway enrichment. RESULTS: 31 significantly altered miRNAs were identified, including 16 up-regulated and 15 down-regulated miRNAs. By performing a series of miRNA prediction and signaling pathway enrichment analyses, the down-regulated miRNAs of mmu-miR-484, mmu-miR-1247-5p and mmu-miR-6538 were identified to be the crucial miRNAs. Further analysis revealed that the inflammation and immune responses involving Hippo, PI3K-Akt, MAPK, Wnt, mTOR, TGF-beta, Tight junction, and Platelet activation were modulated collectively by these three key miRNAs during DENV infection. These pathways are considered to be closely associated with the pathogenic mechanism and treatment strategy of dengue patients. CONCLUSION: The miRNAs identified by sequencing, especially miR-484 may be the potential therapeutic targets for liver involvement in dengue patients which involves the regulation of vascular permeability and expression of inflammatory cytokines.