The archetypical folded shape of the human cortex has been a long-standing topic for neuroscientific research. Nevertheless, the accurate neuroanatomical segmentation of sulci remains a challenge. Part of the problem is the uncertainty of where a sulcus transitions into a gyrus and vice versa. This problem can be avoided by focusing on sulcal fundi and gyral crowns, which represent the topological opposites of cortical folding. We present Automated Brain Lines Extraction (ABLE), a method based on Laplacian surface collapse to reliably segment sulcal fundi and gyral crown lines. ABLE is built to work on standard FreeSurfer outputs and eludes the delineation of anastomotic sulci while maintaining sulcal fundi lines that traverse the regions with the highest depth and curvature. First, it segments the cortex into gyral and sulcal surfaces; then, each surface is spatially filtered. A Laplacian-collapse-based algorithm is applied to obtain a thinned representation of the surfaces. This surface is then used for careful detection of the endpoints of the lines. Finally, sulcal fundi and gyral crown lines are obtained by eroding the surfaces while preserving the connectivity between the endpoints. The method is validated by comparing ABLE with three other sulcal extraction methods using the Human Connectome Project (HCP) test-retest database to assess the reproducibility of the different tools. The results confirm ABLE as a reliable method for obtaining sulcal lines with an accurate representation of the sulcal topology while ignoring anastomotic branches and the overestimation of the sulcal fundi lines. ABLE is publicly available via https://github.com/HGGM-LIM/ABLE .

Functional magnetic resonance imaging (fMRI) has been shown successfully to assess and stratify patients with painful diabetic peripheral neuropathy (pDPN). This supports the idea of using neuroimaging as a mechanism-based technique to individualise therapy for patients with painful DPN. The aim of this study was to use deep learning to predict treatment response in patients with pDPN using resting state functional imaging (rs-fMRI). We divided 43 painful pDPN patients into responders and non-responders to lidocaine treatment (responders n = 29 and non-responders n = 14). We used rs-fMRI to extract functional connectivity features, using group independent component analysis (gICA), and performed automated treatment response deep learning classification with three-dimensional convolutional neural networks (3D-CNN). Using gICA we achieved an area under the receiver operating characteristic curve (AUC) of 96.60% and F1-Score of 95% in a ten-fold cross validation (CV) experiment using our described 3D-CNN algorithm. To our knowledge, this is the first study utilising deep learning methods to classify treatment response in pDPN.

Erratum in Neuroinformatics. 2023 Jan 17;:

We present here an online platform for sharing resources underlying publications in neuroscience. It enables authors to easily upload and distribute digital resources, such as data, code, and notebooks, in a structured and systematic way. Interactivity is a prominent feature of the Live Papers, with features to download, visualise or simulate data, models and results presented in the corresponding publications. The resources are hosted on reliable data storage servers to ensure long term availability and easy accessibility. All data are managed via the EBRAINS Knowledge Graph, thereby helping maintain data provenance, and enabling tight integration with tools and services offered under the EBRAINS ecosystem.

Brain aneurysm detection in Time-Of-Flight Magnetic Resonance Angiography (TOF-MRA) has undergone drastic improvements with the advent of Deep Learning (DL). However, performances of supervised DL models heavily rely on the quantity of labeled samples, which are extremely costly to obtain. Here, we present a DL model for aneurysm detection that overcomes the issue with "weak" labels: oversized annotations which are considerably faster to create. Our weak labels resulted to be four times faster to generate than their voxel-wise counterparts. In addition, our model leverages prior anatomical knowledge by focusing only on plausible locations for aneurysm occurrence. We first train and evaluate our model through cross-validation on an in-house TOF-MRA dataset comprising 284 subjects (170 females / 127 healthy controls / 157 patients with 198 aneurysms). On this dataset, our best model achieved a sensitivity of 83%, with False Positive (FP) rate of 0.8 per patient. To assess model generalizability, we then participated in a challenge for aneurysm detection with TOF-MRA data (93 patients, 20 controls, 125 aneurysms). On the public challenge, sensitivity was 68% (FP rate = 2.5), ranking 4th/18 on the open leaderboard. We found no significant difference in sensitivity between aneurysm risk-of-rupture groups (p = 0.75), locations (p = 0.72), or sizes (p = 0.15). Data, code and model weights are released under permissive licenses. We demonstrate that weak labels and anatomical knowledge can alleviate the necessity for prohibitively expensive voxel-wise annotations.

It is well known that brain development is very fast and complex in the early childhood with age-based neurological and physiological changes of brain structure and function. The brain maturity is an important indicator for evaluating the normal development of children. In this paper, we propose a multimodal regression framework to combine the features from structural magnetic resonance imaging (sMRI) and diffusion tensor imaging (DTI) data for age prediction of children. First, three types of features are extracted from sMRI and DTI data. Second, we propose to combine the sparse coding and Q-Learning for feature selection from each modality. Finally, the ensemble regression is performed by random forest based on proximity measures to fuse multimodal features for age prediction. The proposed method is evaluated on 212 participants, including 76 young children less than 2 years old and 136 children aged from 2-15 years old recruited from Shanghai Children's Hospital. The results show that integrating multimodal features has achieved the highest accuracies with the root mean squared error (RMSE) of 0.208 years and mean absolute error (MAE) of 0.150 years for age prediction of young children (0-2), and RMSE of 1.666 years and MAE of 1.087 years for older children (2-15). We have shown that the selected features by Q-Learning can consistently improve the prediction accuracy. The comparison of prediction results demonstrates that the proposed method performs better than other competing methods.