Low-intensity transcranial ultrasound stimulation (TUS) is poised to become one of the most promising treatments for neurological disorders. However, while recent animal model experiments have successfully quantified the alterations of the functional activity coupling between a sonicated target cortical region and other cortical regions of interest (ROIs), the varying degree of alteration between these different connections remains unexplained. We hypothesise here that the incidental sonication of the tracts leaving the target region towards the different ROIs could participate in explaining these differences. To this end, we propose a tissue level phenomenological numerical model of the coupling between the ultrasound waves and the white matter electrical activity. The model is then used to reproduce in silico the sonication of the anterior cingulate cortex (ACC) of a macaque monkey and measure the neuromodulation power within the white matter tracts leaving the ACC for five cortical ROIs. The results show that the more induced power a white matter tract proximal to the ACC and connected to a secondary ROI receives, the more altered the connectivity fingerprint of the ACC to this region will be after sonication. These results point towards the need to isolate the sonication to the cortical region and minimise the spillage on the neighbouring tracts when aiming at modulating the target region without losing the functional connectivity with other ROIs. Those results further emphasise the potential role of the white matter in TUS and the need to account for white matter topology when designing TUS protocols.

Unfortunately, Covid-19 has infected millions of people very quickly, and it continues to infect people and spreads rapidly. Although there are some common symptoms of Covid-19, its effect varies from one individual to another. Estimating the severity of the infection has become a critical need as it can guide the decision makers to take an accurate and timely response. It will be valuable to provide early warning before infection takes place about susceptibility to the disease, especially since the lack of symptoms is a feature of the Covid-19 pandemic. Asymptomatic patients are considered as "silent diffusers" of the virus; hence, detecting people who will be asymptomatic before actual infection takes place will certainly safe the society from the uncontrolled and unseen spread of the virus. People can be classified based on their vulnerability to Covid-19 even before they are infected. Accordingly, precautionary measures can be taken individually based on the persons' Covid-19 susceptibility. This paper introduces a Covid-19's Integrated Herd Immunity (CIHI) strategy. The aim of CIHI is to keep the society safe with the minimal losses even with the existence of Covid-19. This can be accomplished by two basic factors; the first is an accurate prediction of the cases who will be asymptomatic if they were infected by the virus, while the second is to take suitable precautions for those who are predicted to be badly affected by the virus even before the actual infection takes place. CIHI is realized through a new classification strategy called Distance Based Classification Strategy (DBCS) which classifies people based on their vulnerability to Covid-19 infection. The proposed DBCS classifies individuals into six different types, then suitable precautionary measures can be taken for every type. DBCS can also identify future symptomatic and asymptomatic cases. In fact, DBCS consists of three sequential phases, which are; (i) Outlier Rejection Phase (ORP) using Hybrid Outlier Rejection (HOR) method, (ii) Feature Selection Phase (FSP) using Hybrid Feature Selection (HFS) method, and (iii) Classification Phase (CP) using Accumulative K-Nearest Neighbors (AKNN). DBCS has been compared with recent Covid-19 diagnosing techniques based on "NileDS" dataset. Experimental results have proven the efficiency and applicability of the proposed strategy as it provides the best classification accuracy.

BACKGROUND: A new coronavirus disease named COVID-19, caused by severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2), is rapidly spreading worldwide. However, there is currently no effective drug to fight COVID-19. METHODS: In this study, we developed a Virus-Drug Association (VDA) identification framework (VDA-RWLRLS) combining unbalanced bi-Random Walk, Laplacian Regularized Least Squares, molecular docking, and molecular dynamics simulation to find clues for the treatment of COVID-19. First, virus similarity and drug similarity are computed based on genomic sequences, chemical structures, and Gaussian association profiles. Second, an unbalanced bi-random walk is implemented on the virus network and the drug network, respectively. Third, the results of the random walks are taken as the input of Laplacian regularized least squares to compute the association score for each virus-drug pair. Fourth, the final associations are characterized by integrating the predictions from the virus network and the drug network. Finally, molecular docking and molecular dynamics simulation are implemented to measure the potential of screened anti-COVID-19 drugs and further validate the predicted results. RESULTS: In comparison with six state-of-the-art association prediction models (NGRHMDA, SMiR-NBI, LRLSHMDA, VDA-KATZ, VDA-RWR, and VDA-BiRW), VDA-RWLRLS demonstrates superior VDA prediction performance. It obtains the best AUCs of 0.885 8, 0.835 5, and 0.862 5 on the three VDA datasets. Molecular docking and dynamics simulations demonstrated that remdesivir and ribavirin may be potential anti-COVID-19 drugs. CONCLUSIONS: Integrating unbalanced bi-random walks, Laplacian regularized least squares, molecular docking, and molecular dynamics simulation, this work initially screened a few anti-SARS-CoV-2 drugs and may contribute to preventing COVID-19 transmission.

Severe Acute Respiratory Syndrome Corovirus2 (SARS-CoV-2) has been determined to be the cause of the current pandemic. Typical symptoms of patient having COVID-19 are fever, runny nose, cough (dry or not) and dyspnea. Several vaccines are available in markets that are tackling current pandemic. Many different strains of SAR-CoV-2 have been evolved with the passage of time. The emergence of VOCs particularly the B.1.351 ("South African") variant of SARS-CoV-2 has been reported to be more resistant than other SARS-CoV-2 strains to the current vaccines. Thus, the current research is focused to design multi-epitope subunit Vaccine (MEV) using structural vaccinology techniques. As a result, the designed MEV exhibit antigenic properties and possess therapeutic features that can trigger an immunological response against COVID-19. Furthermore, validation of the MEV using immune simulation and in silico cloning revealed that the proposed vaccine candidate effectively triggered the immune response. Conclusively, the developed MEV needs further wet lab exploration and could be a viable vaccine to manage and prevent COVID-19.

Obstructive sleep apnea (OSA), which has high morbidity and complications, is diagnosed via polysomnography (PSG). However, this method is expensive, time-consuming, and causes discomfort to the patient. Single-lead electrocardiogram (ECG) is a potential alternative to PSG for OSA diagnosis. Recent studies have successfully applied deep learning methods to OSA detection using ECG and obtained great success. However, most of these methods only focus on heart rate variability (HRV), ignoring the importance of ECG-derived respiration (EDR). In addition, they used relatively simple networks, and cannot extract more complex features. In this study, we proposed a one-dimensional squeeze-and-excitation (SE) residual group network to thoroughly extract the complementary information between HRV and EDR. We used the released and withheld sets in the Apnea-ECG dataset to develop and test the proposed method, respectively. In the withheld set, the method has an accuracy of 90.3%, a sensitivity of 87.6%, and a specificity of 91.9% for per-segment detection, indicating an improvement over existing methods for the same dataset. The proposed method can be integrated with wearable devices to realize inexpensive, convenient, and highly efficient OSA detectors.

The present brief survey is to alert developers in datamining, machine learning, inference methods, and other approaches in relation to diagnostic, predictive, and risk assessment medicine about a relatively new class of bioactive messaging peptides in which there is escalating interest. They provide patterns of communication and cross-chatter about states of health and disease within and, importantly, between cells (they also appear extracellularly in biological fluids). This chatter needs to be analyzed somewhat in the manner of the decryption of the Enigma code in the Second World War. It could lead not only to improved diagnosis but to predictive diagnosis, prediction of organ failure, and preventative medicine. This involves peptide products of short reading frames that have been previously somewhat neglected as unlikely gene products, with probably many examples in nuclear DNA, but certainly several known in the mitochondrial DNA. There is a great deal of knowledge now becoming available about the latter and itis believed thatthat the mRNA can be translated both by standard cytosolic and mitochondrial genetic codes, resulting in different peptides, adding a further level of complexity to the applications of bioinformatics and computational biology but a higher level of detail and sophistication to preventative diagnosis. The code to crack could be sophisticated and combinatorically complex to analyze by computers. Mitochondria may have combined with proto-eucaryotic cells some 2 billion years ago, only about a 7th of the age of the universe. Cells appeared some 2 billion years before that, also with possible signaling based on similar ideas. This makes life small in space but huge in time, refinement of which centrally involves these signaling processes.

Artificial Intelligence (AI) has emerged as a useful aid in numerous clinical applications for diagnosis and treatment decisions. Deep neural networks have shown the same or better performance than clinicians in many tasks owing to the rapid increase in the available data and computational power. In order to conform to the principles of trustworthy AI, it is essential that the AI system be transparent, robust, fair, and ensure accountability. Current deep neural solutions are referred to as black-boxes due to a lack of understanding of the specifics concerning the decision-making process. Therefore, there is a need to ensure the interpretability of deep neural networks before they can be incorporated into the routine clinical workflow. In this narrative review, we utilized systematic keyword searches and domain expertise to identify nine different types of interpretability methods that have been used for understanding deep learning models for medical image analysis applications based on the type of generated explanations and technical similarities. Furthermore, we report the progress made towards evaluating the explanations produced by various interpretability methods. Finally, we discuss limitations, provide guidelines for using interpretability methods and future directions concerning the interpretability of deep neural networks for medical imaging analysis.

In order to understand the organizational structures of healthy cerebral cortex and the abnormalities in neurological and psychiatric diseases, it is significant to parcellate the cortical surface. The cortical surface, however, is a highly folded complex geometric structure which challenges automatic cortical surface parcellation. Nowadays, the parcellation methods of cerebral cortex are mostly based on geometric simplification, i.e., iteratively inflating and mapping the cortical surface to a spherical surface for processing, which is time-consuming and cannot make full use of the intrinsic structural information of the original cortical surface. In this study, we proposed an anatomically constrained squeeze-and-excitation graph attention network (ASEGAT) for an end-to-end brain cortical surface parcellation on the original cortical surface manifold. The ASEGAT is formed by two graph attention modules and a squeeze-and-excitation module that incorporate self-attention and head attention for rendering features of each node. Furthermore, we designed an anatomic constraint loss to introduce the anatomical priori of regional adjacency relationships, which could improve the consistency of region labeling. We evaluated our model on a public dataset of 100 manually labeled brain surfaces. Compared with several advanced methods, the results showed that our proposed approach achieved state-of-the-art performance, obtaining an accuracy of 90.65% and a dice score of 89.00%.

BACKGROUND: The most prevalent neuropsychiatric disorder among children is attention deficit hyperactivity disorder (ADHD). ADHD presents with a high prevalence of comorbid disorders such as conduct disorder (CD). The lack of definitive confirmatory diagnostic tests for ADHD and CD make diagnosis challenging. The distinction between ADHD, ADHD + CD and CD is important as the course and treatment are different. Electrocardiography (ECG) signals may become altered in behavioral disorders due to brain-heart autonomic interactions. We have developed a software tool to categorize ADHD, ADHD + CD and CD automatically on ECG signals. METHOD: ECG signals from participants were decomposed using empirical wavelet transform into various modes, from which entropy features were extracted. Robust ten-fold cross-validation with adaptive synthetic sampling (ADASYN) and z-score normalization were performed at each fold. Analysis of variance (ANOVA) technique was employed to determine the variability within the three classes, and obtained the most discriminatory features. Highly significant entropy features were then fed to classifiers. RESULTS: Our model yielded the best classification results with the bagged tree classifier: 87.19%, 87.71% and 86.29% for accuracy, sensitivity and specificity, respectively. CONCLUSION: The proposed expert system can potentially assist mental health professionals in the stratification of the three classes, for appropriate intervention using accessible ECG signals.

BACKGROUND: Learning-based methods have achieved remarkable performances on depth estimation. However, the premise of most self-learning and unsupervised learning methods is built on rigorous, geometrically-aligned stereo rectification. The performances of these methods degrade when the rectification is not accurate. Therefore, we explore an approach for unsupervised depth estimation from stereo images that can handle imperfect camera parameters. METHODS: We propose an unsupervised deep convolutional network that takes rectified stereo image pairs as input and outputs corresponding dense disparity maps. First, a new vertical correction module is designed for predicting a correction map to compensate for the imperfect geometry alignment. Second, the left and right images, which are reconstructed based on the input image pair and corresponding disparities as well as the vertical correction maps, are regarded as the outputs of the generative term of the generative adversarial network (GAN). Then, the discriminator term of the GAN is used to distinguish the reconstructed images from the original inputs to force the generator to output increasingly realistic images. In addition, a residual mask is introduced to exclude pixels that conflict with the appearance of the original image in the loss calculation. RESULTS: The proposed model is validated on the publicly available Stereo Correspondence and Reconstruction of Endoscopic Data (SCARED) dataset and the average MAE is 3.054 mm. CONCLUSION: Our model can effectively handle imperfect rectified stereo images for depth estimation.

Medical imaging, and particularly retinal imaging, allows to accurately diagnose many eye pathologies as well as some systemic diseases such as hypertension or diabetes. Registering these images is crucial to correctly compare key structures, not only within patients, but also to contrast data with a model or among a population. Currently, this field is dominated by complex classical methods because the novel deep learning methods cannot compete yet in terms of results and commonly used methods are difficult to adapt to the retinal domain. In this work, we propose a novel method to register color fundus images based on previous works which employed classical approaches to detect domain-specific landmarks. Instead, we propose to use deep learning methods for the detection of these highly-specific domain-related landmarks. Our method uses a neural network to detect the bifurcations and crossovers of the retinal blood vessels, whose arrangement and location are unique to each eye and person. This proposal is the first deep learning feature-based registration method in fundus imaging. These keypoints are matched using a method based on RANSAC (Random Sample Consensus) without the requirement to calculate complex descriptors. Our method was tested using the public FIRE dataset, although the landmark detection network was trained using the DRIVE dataset. Our method provides accurate results, a registration score of 0.657 for the whole FIRE dataset (0.908 for category S, 0.293 for category P and 0.660 for category A). Therefore, our proposal can compete with complex classical methods and beat the deep learning methods in the state of the art.

Gastric cancer is one of the most severe malignant lesions. Neoadjuvant chemotherapy (NAC) has proven to be an effective method in gastric cancer treatment, and patients who achieved the pathologic complete response (pCR) after NAC can improve survival time further. To accurately predict pCR in an interpretable way, a new automated belief rule base (AutoBRB) model is developed with careful data analysis in this paper. In AutoBRB, to determine the referential values that are important for the rule building, both the information gain ratio and expert knowledge are used, while a table-based strategy is designed to initialize the belief degrees for each rule. Then, the differential evolution (DE) algorithm is employed and modified for model optimization to improve the model's performance. Finally, with the help of training data, an adaptive searching strategy is designed to set the confidence threshold for the final prediction. The experimental results demonstrate that AutoBRB shows a more reasonable performance on the prediction of pCR.

The Crimean-Congo hemorrhagic fever virus (CCHFV) is a lethal human pathogen belonging to the Nairoviridae family that causes Crimean-Congo hemorrhagic fever (CCHF), a tick-borne infection with an alarming mortality rate of up to 80%. CCHFV is the most widespread tick-borne virus with the potential to trigger a pandemic. To date, no vaccines or therapeutics for CCHF have been authorized. In this study, we implemented immunoinformatics approach for developing CCHF_GN728, a universal mRNA-based multi-epitope vaccine against CCHFV. Glycoprotein precursor (GPC) and nucleoprotein (NP) from the virus were selected and screened for potential immunogenic T- and B-cell epitopes. Our developed antigen exhibited the potential to generate 99.95% population coverage worldwide. Stable epitope-allele interaction was confirmed using molecular docking and dynamics simulation. In silico immune simulation corroborated immune cell response to antigen clearance rate. Optimized codons ensured efficient expression of the mRNA in the host cell. The vaccine exhibited stable and strong interactions with the Toll-like receptors. Our findings suggest that the CCHF_GN728 vaccine will trigger specific anti-CCHFV immune responses. Our model is ready for wet-lab experimentation to assess the efficacy of this putative vaccine candidate.

Computed Tomography (CT) imaging is used in Radiation Therapy planning, where the treatment is carefully tailored to each patient in order to maximize radiation dose to the target while decreasing adverse effects to nearby healthy tissues. A crucial step in this process is manual organ contouring, which if performed automatically could considerably decrease the time to starting treatment and improve outcomes. Computerized segmentation of male pelvic organs has been studied for decades and deep learning models have brought considerable advances to the field, but improvements are still demanded. A two-step framework for automatic segmentation of the prostate, bladder and rectum is presented: a convolutional neural network enhanced with attention gates performs an initial segmentation, followed by a region-based active contour model to fine-tune the segmentations to each patient's specific anatomy. The framework was evaluated on a large collection of planning CTs of patients who had Radiation Therapy for prostate cancer. The Surface Dice Coefficient improved from 79.41 to 81.00% on segmentation of the prostate, 94.03-95.36% on the bladder and 82.17-83.68% on the rectum, comparing the proposed framework with the baseline convolutional neural network. This study shows that traditional image segmentation algorithms can help improve the immense gains that deep learning models have brought to the medical imaging segmentation field.

Drug recall is a critical issue for manufacturing companies, as a manufacturer might face criticism and severe business downfall due to a defective drug. A defective drug is a highly detrimental issue, as it can cost several lives. Therefore, recalling the drug becomes one of the most sensitive issues in the pharmaceutical industry. This paper presents a blockchain-enabled network that allows manufacturers to effectively monitor a drug while in the supply chain with improved security and transparency throughout the process. The study also tries to minimize the cost and time sustained by the manufacturing company to transfer the drug to the end-user by proposing forward and backward supply chain mathematical models. Specifically, the forward chain model supports drug delivery from the manufacturer to the end-user in less time with a reliable transport mode. The backward supply chain model explicitly focuses on reducing the extra time and cost incurred to the manufacturer in pursuit of recalling the defective drug. Moreover, a real-time implementation of the proposed blockchain-enabled supply chain management system using the Hyperledger Composer is done to demonstrate the transparency of the process.

To facilitate the identification of arrhythmia, in this study, an S-shaped reconstruction method was proposed, and a two-dimensional (2-D) 19-layer deep squeeze-and-excitation residual network (SE-ResNet) was used to classify heartbeats. The proposed method has three steps. The first step involves data preprocessing, which includes denoising of the original electrocardiogram (ECG) data, removing of baseline drift, heartbeat extraction, and data balancing using a synthetic minority oversampling technique algorithm. Subsequently, the extracted one-dimensional heartbeat series is transformed into a 2-D matrix by employing the novel S-shaped reconstruction method for determining the relationship between distant points in an ECG series. Finally, the 2-D 19-layer SE-ResNet is used to divide the 2-D heartbeat matrix into five heartbeat categories, namely normal, supraventricular ectopic, ventricular ectopic, fusion, and unknown beats, in accordance with the American National Standards Institute/Advancement of Medical Instrumentation standard, and 10-fold cross-validation is employed to train the 2-D 19-layer SE-ResNet. The accuracy, positive prediction rate, sensitivity, and specificity of the proposed method reached 99.61%, 93.87%, 93.78%, and 99.27%, respectively. The results indicated that the S-shaped reconstruction method can be helpful for acquiring additional information from ECG heartbeat data.

In this article, we present a new benchmark for the segmentation of the retinal external limiting membrane (ELM) using an image dataset of spectral domain optical coherence tomography (OCT) scans in a patient population with idiopathic full-thickness macular holes. Specifically, the dataset used contains OCT images from one eye of 107 patients with an idiopathic full-thickness macular hole. In total, the dataset contains 5243 individual 2-dimensional (2-D) OCT image slices, with each patient contributing 49 individual spectral-domain OCT tagged image slices. We display precise image-wise binary annotations to segment the ELM line. The OCT images present high variations in image contrast, motion, brightness, and speckle noise which can affect the robustness of applied algorithms, so we performed an extensive OCT imaging and annotation data quality analysis. Imaging data quality control included noise, blurriness and contrast scores, motion estimation, darkness and average pixel scores, and anomaly detection. Annotation quality was measured using gradient mapping of ELM line annotation confidence, and idiopathic full-thickness macular hole detection. Finally, we compared qualitative and quantitative results with seven state-of-the-art machine learning-based segmentation methods to identify the ELM line with an automated system.

BACKGROUND: Liver segmentation is a fundamental step in the treatment planning and diagnosis of liver cancer. However, manual segmentation of liver is time-consuming because of the large slice quantity and subjectiveness associated with the specialist's experience, which can lead to segmentation errors. Thus, the segmentation process can be automated using computational methods for better time efficiency and accuracy. However, automatic liver segmentation is a challenging task, as the liver can vary in shape, ill-defined borders, and lesions, which affect its appearance. We aim to propose an automatic method for liver segmentation using computed tomography (CT) images. METHODS: The proposed method, based on deep convolutional neural network models and image processing techniques, comprise of four main steps: (1) image preprocessing, (2) initial segmentation, (3) reconstruction, and (4) final segmentation. RESULTS: We evaluated the proposed method using 131 CT images from the LiTS image base. An average sensitivity of 95.45%, an average specificity of 99.86%, an average Dice coefficient of 95.64%, an average volumetric overlap error (VOE) of 8.28%, an average relative volume difference (RVD) of -0.41%, and an average Hausdorff distance (HD) of 26.60 mm were achieved. CONCLUSIONS: This study demonstrates that liver segmentation, even when lesions are present in CT images, can be efficiently performed using a cascade approach and including a reconstruction step based on deep convolutional neural networks.

Alzheimer's disease (AD) is a gradually progressive neurodegenerative disease affecting cognition functions. Predicting the cognitive scores from neuroimage measures and identifying relevant imaging biomarkers are important research topics in the study of AD. Despite machine learning algorithms having many successful applications, the prediction model suffers from the so-called curse of dimensionality. Multi-task feature learning (MTFL) has helped tackle this problem incorporating the correlations among multiple clinical cognitive scores. However, MTFL neglects the inherent correlation among brain imaging measures. In order to better predict the cognitive scores and identify stable biomarkers, we first propose a generalized multi-task formulation framework that incorporates the task and feature correlation structures simultaneously. Second, we present a novel feature-aware sparsity-inducing norm (FAS-norm) penalty to incorporate a useful correlation between brain regions by exploiting correlations among features. Three multi-task learning models that incorporate the FAS-norm penalty are proposed following our framework. Finally, the algorithm based on the alternating direction method of multipliers (ADMM) is developed to optimize the non-smooth problems. We comprehensively evaluate the proposed models on the cross-sectional and longitudinal Alzheimer's disease neuroimaging initiative datasets. The inputs are the thickness measures and the volume measures of the cortical regions of interest. Compared with MTFL, our methods achieve an average decrease of 4.28% in overall error in the cross-sectional analysis and an average decrease of 7.97% in the Alzheimer's Disease Assessment Scale cognitive total score longitudinal analysis. Moreover, our methods identify sensitive and stable biomarkers to physicians, such as the hippocampus, lateral ventricle, and corpus callosum.

BACKGROUND: We investigated a 2-dimensional (2D) U-Net model to delineate lumbar bone marrow (BM) using a high resolution T1-weighted magnetic resonance imaging. METHOD: Healthy controls (n = 44, 836 images) and patients with hematologic diseases (n = 56, 1064 images) received MRI of the lumbar spines. Lumbar BM on each image was manually delineated by an experienced radiologist as a ground-truth. The 2D U-Net models were trained using a healthy lumbar BM only, diseased BM only, and using healthy and diseased BM combined, respectively. The models were validated using healthy and diseased subjects, separately. A repeated-measures analysis of variance was performed to compare segmentation accuracies with 2 validation cohorts among U-Net trained with healthy subjects (UNET_HC), U-Net trained with diseased subjects (UNET_HD), U-Net trained with all subjects including both healthy and diseased subjects (UNET_HCHD), and 3-dimensional Grow-Cut algorithm (3DGC). RESULTS: When validated with the healthy subjects, UNET_HC, UNET_HD, UNET_HCHD and 3DGC achieved the mean and standard deviation of the Dice Similarity Coefficient (DSC) of 0.9415 ± 0.07056, 0.9583 ± 0.05146, 0.9602 ± 0.0486 and 0.9139 ± 0.2039, respectively. When validated with the diseased subjects, DSCs of UNET_HC, UNET_HD, UNET_HCHD and 3DGC were 0.8303 ± 0.1073, 0.9502 ± 0.0217, 0.9502 ± 0.0217 and 0.8886 ± 0.2179, respectively. The U-Net models segmented BM better than the semi-automatic 3DGC (P < 0.0001), and UNET_HD produced better results than UNET_HC (P < 0.0001). CONCLUSIONS: We successfully constructed a fully automatic lumbar BM segmentation model for a high-resolution T1-weighted MRI using U-Net, which outperformed most of the previously reported approaches and the existing semi-automatic algorithm.

Deep learning methods achieved remarkable results in medical image analysis tasks but it has not yet been widely used by medical professionals. One of the main reasons for this restricted usage is the uncertainty of the reasons that influence the decision of the model. Explainable AI methods have been developed to improve the transparency, interpretability, and explainability of the black-box AI methods. The result of an explainable segmentation method will be more trusted by experts. In this study, we designed an explainable deep correction method by incorporating cascaded 1D and 2D models to refine the output of other models and provide reliable yet accurate results. We implemented a 2-step loop with a 1D local boundary validation model in the first step, and a 2D image patch segmentation model in the second step, to refine incorrect segmented regions slice-by-slice. The proposed method improved the result of the CNN segmentation models and achieved state-of-the-art results on 3D liver segmentation with the average dice coefficient of 98.27 on the Sliver07 dataset.