{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T07:44:58Z","timestamp":1785829498184,"version":"3.56.0"},"reference-count":38,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T00:00:00Z","timestamp":1785801600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Neurol."],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Acute ischemic stroke is a major cerebrovascular disease, and accurate lesion segmentation is important for quantitative image analysis and subsequent clinical assessment. Multimodal magnetic resonance imaging, including diffusion-weighted imaging, apparent diffusion coefficient maps, and fluid-attenuated inversion recovery, provides complementary information for lesion delineation. However, lesion appearance may vary across sequences, and blurred boundaries or small scattered lesions can make multimodal feature fusion unstable.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We developed MBGS-UNet, a multi-branch deep learning model for acute ischemic stroke lesion segmentation. Separate encoders were used to preserve sequence-specific information. A boundary-aware graph attention module was introduced at deeper feature levels to regulate cross-modal interaction in ambiguous regions, and an uncertainty-gated fusion module was used to balance graph-enhanced features with encoder features at the voxel level. Uncertainty-weighted boundary supervision and consistency learning were further incorporated to emphasize difficult regions during training. The model was evaluated on the ISLES-2022 dataset using an independent test set and label-free sliding-window inference.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>MBGS-UNet achieved a Dice score of 0.7208 on the independent test set, numerically higher than M2FNet (0.7068) and UMamba (0.7016) under the same evaluation protocol. However, case-wise paired statistical analysis did not provide sufficient evidence to support clear superiority over these strong baselines. Visual analysis showed that high-uncertainty responses were mainly concentrated around lesion boundaries and other error-prone regions, indicating a spatial relationship between predictive uncertainty and local segmentation difficulty.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>MBGS-UNet achieved competitive segmentation performance while providing interpretable uncertainty visualization. The uncertainty maps may offer useful cues for identifying ambiguous lesion boundaries and other regions that require closer review. Nevertheless, the observed numerical improvement should not be interpreted as conclusive evidence of superiority or clinical validation. Further evaluation on larger, more diverse, and external cohorts is required to establish broader robustness and clinical applicability.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fneur.2026.1872532","type":"journal-article","created":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T06:50:35Z","timestamp":1785826235000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Boundary-aware and uncertainty-guided deep learning for multimodal magnetic resonance imaging segmentation of stroke lesions"],"prefix":"10.3389","volume":"17","author":[{"given":"Zhongxiang","family":"Xing","sequence":"first","affiliation":[{"name":"College of Information Engineering, Sichuan Agricultural University","place":["Ya\u2019an, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuding","family":"Luo","sequence":"additional","affiliation":[{"name":"Department of Neurology, Ya\u2019an People\u2019s Hospital, Sichuan Province","place":["Ya\u2019an, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yupeng","family":"Niu","sequence":"additional","affiliation":[{"name":"Tianjin Key Laboratory of Radiation Medicine and Molecular Nuclear Medicine, Institute of Radiation Medicine, Chinese Academy of Medical Sciences and Peking Union Medical College","place":["Tianjin, China"]},{"name":"NewIdea Yunshu Technology Co., Ltd.","place":["Chengdu, China"]},{"name":"Tsinghua University","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yilin","family":"Yang","sequence":"additional","affiliation":[{"name":"College of Information Engineering, Sichuan Agricultural University","place":["Ya\u2019an, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhenzhen","family":"Lin","sequence":"additional","affiliation":[{"name":"College of Information Engineering, Sichuan Agricultural University","place":["Ya\u2019an, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Han","family":"Qin","sequence":"additional","affiliation":[{"name":"College of Information Engineering, Sichuan Agricultural University","place":["Ya\u2019an, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiyin","family":"Chen","sequence":"additional","affiliation":[{"name":"College of Information Engineering, Sichuan Agricultural University","place":["Ya\u2019an, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jian","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Neurology, Ya\u2019an People\u2019s Hospital, Sichuan Province","place":["Ya\u2019an, China"]},{"name":"Department of Neurology, The Affiliated Hospital, Southwest Medical University","place":["Luzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiong","family":"Mu","sequence":"additional","affiliation":[{"name":"College of Information Engineering, Sichuan Agricultural University","place":["Ya\u2019an, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,8,4]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"259","DOI":"10.1002\/jmri.23595","article-title":"Clinical Mri of acute ischemic stroke","volume":"36","author":"Gonz\u00e1lez","year":"2012","journal-title":"J Magn Reson Imaging"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"100004","DOI":"10.1016\/j.array.2019.100004","article-title":"A review: deep learning for medical image segmentation using multi-modality fusion","volume":"3","author":"Zhou","year":"2019","journal-title":"Array"},{"key":"ref3","volume-title":"What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision? Advances in Neural Information Processing Systems","author":"Kendall","year":"2017"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"762","DOI":"10.1038\/s41597-022-01875-5","article-title":"Isles 2022: a multi-center magnetic resonance imaging stroke lesion segmentation dataset","volume":"9","author":"Hernandez Petzsche","year":"2022","journal-title":"Sci Data"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"307","DOI":"10.1159\/000330462","article-title":"The ischemic penumbra: correlates in imaging and implications for treatment of ischemic strokethe Johann Jacob Wepfer award 2011","volume":"32","author":"Heiss","year":"2011","journal-title":"Cerebrovasc Dis"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1016\/j.media.2016.10.004","article-title":"Efficient multi-scale 3d CNN with fully connected CRF for accurate brain lesion segmentation","volume":"36","author":"Kamnitsas","year":"2017","journal-title":"Med Image Anal"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1016\/j.media.2016.05.004","article-title":"Brain tumor segmentation with deep neural networks","volume":"35","author":"Havaei","year":"2017","journal-title":"Med Image Anal"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1016\/j.aiopen.2021.01.001","article-title":"Graph neural networks: a review of methods and applications","volume":"1","author":"Zhou","year":"2020","journal-title":"AI open"},{"key":"ref9","article-title":"Graph attention networks","author":"Veli\u010dkovi\u0107","year":"2017","journal-title":"arXiv preprint arXiv:171010903"},{"key":"ref10","article-title":"Revisiting graph neural networks: all we have is low-pass filters","author":"Nt","year":"2019","journal-title":"arXiv preprint arXiv:190509550"},{"key":"ref11","article-title":"Graph neural networks exponentially lose expressive power for node classification","author":"Oono","year":"2019","journal-title":"arXiv preprint arXiv:190510947"},{"key":"ref12","volume-title":"Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning International Conference on Machine Learning","author":"Gal","year":"2016"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"379","DOI":"10.1002\/j.1538-7305.1948.tb01338.x","article-title":"A mathematical theory of communication","volume":"27","author":"Shannon","year":"1948","journal-title":"Bell Syst Tech J"},{"key":"ref14","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-32226-7_90","volume-title":"Semi-Supervised Medical Image Segmentation Via Learning Consistency Under Transformations","author":"Bortsova","year":"2019"},{"key":"ref15","volume-title":"3d U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation","author":"\u00c7i\u00e7ek","year":"2016"},{"key":"ref16","volume-title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","author":"Ronneberger","year":"2015"},{"key":"ref17","volume-title":"Delving Deep Into Rectifiers: Surpassing Human-Level Performance on Imagenet Classification","author":"He","year":"2015"},{"key":"ref18","article-title":"Instance normalization: the missing ingredient for fast stylization","author":"Ulyanov","year":"2016","journal-title":"arXiv preprint arXiv:160708022"},{"key":"ref19","volume-title":"Boundary Loss for Highly Unbalanced Segmentation International Conference on Medical Imaging with Deep Learning","author":"Kervadec","year":"2019"},{"key":"ref20","volume-title":"Mean Teachers Are Better Role Models: Weight-Averaged Consistency Targets Improve Semi-Supervised Deep Learning Results Advances in Neural Information Processing Systems","author":"Tarvainen","year":"2017"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"1310","DOI":"10.1109\/TMI.2010.2046908","article-title":"N4itk: improved N3 bias correction","volume":"29","author":"Tustison","year":"2010","journal-title":"IEEE Trans Med Imaging"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"4952","DOI":"10.1002\/hbm.24750","article-title":"Automated brain extraction of multisequence Mri using artificial neural networks","volume":"40","author":"Isensee","year":"2019","journal-title":"Hum Brain Mapp"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1016\/j.media.2007.06.004","article-title":"Symmetric diffeomorphic image registration with cross-correlation: evaluating automated labeling of elderly and neurodegenerative brain","volume":"12","author":"Avants","year":"2008","journal-title":"Med Image Anal"},{"key":"ref24","volume-title":"Simple and Scalable Predictive Uncertainty Estimation Using Deep Ensembles. Advances in Neural Information Processing Systems","author":"Lakshminarayanan","year":"2017"},{"key":"ref25","article-title":"Monai: an open-source framework for deep learning in healthcare","author":"Cardoso","year":"2022","journal-title":"arXiv preprint arXiv:221102701"},{"key":"ref26","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv preprint arXiv:171105101"},{"key":"ref27","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1186\/s12880-015-0068-x","article-title":"Metrics for evaluating 3d medical image segmentation: analysis, selection, and tool","volume":"15","author":"Taha","year":"2015","journal-title":"BMC Med Imaging"},{"key":"ref28","doi-asserted-by":"publisher","first-page":"499","DOI":"10.1109\/TMI.2019.2930068","article-title":"Reducing the Hausdorff distance in medical image segmentation with convolutional neural networks","volume":"39","author":"Karimi","year":"2019","journal-title":"IEEE Trans Med Imaging"},{"key":"ref29","doi-asserted-by":"publisher","first-page":"263","DOI":"10.1007\/s40747-025-01861-5","article-title":"M2fnet: multi-modality multi-level fusion network for segmentation of acute and sub-acute ischemic stroke","volume":"11","author":"Chen","year":"2025","journal-title":"Complex Intell Syst"},{"key":"ref30","volume-title":"Swin Unetr: Swin Transformers for Semantic Segmentation of Brain Tumors in Mri Images International MICCAI Brainlesion Workshop","author":"Hatamizadeh","year":"2021"},{"key":"ref31","article-title":"3d Ux-net: a large kernel volumetric convnet modernizing hierarchical transformer for medical image segmentation","author":"Lee","year":"2022","journal-title":"arXiv preprint arXiv:220915076"},{"key":"ref32","article-title":"U-mamba: enhancing long-range dependency for biomedical image segmentation","author":"Ma","year":"2024","journal-title":"arXiv preprint arXiv:240104722"},{"key":"ref33","volume-title":"Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries","author":"Myronenko","year":"2019"},{"key":"ref34","article-title":"Attention U-net: learning where to look for the pancreas","author":"Oktay","year":"2018","journal-title":"arXiv preprint arXiv:180403999"},{"key":"ref35","volume-title":"Mednext: Transformer-Driven Scaling of Convnets for Medical Image Segmentation International Conference on Medical Image Computing and Computer-Assisted Intervention","author":"Roy","year":"2023"},{"key":"ref36","volume-title":"Segmamba: Long-Range Sequential Modeling Mamba for 3d Medical Image Segmentation","author":"Xing","year":"2024"},{"key":"ref37","volume-title":"On Calibration of Modern Neural Networks International Conference on Machine Learning","author":"Guo","year":"2017"},{"key":"ref38","volume-title":"Selective Classification for Deep Neural Networks Advances in Neural Information Processing Systems","author":"Geifman","year":"2017"}],"container-title":["Frontiers in Neurology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fneur.2026.1872532\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T06:50:41Z","timestamp":1785826241000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fneur.2026.1872532\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,4]]},"references-count":38,"alternative-id":["10.3389\/fneur.2026.1872532"],"URL":"https:\/\/doi.org\/10.3389\/fneur.2026.1872532","relation":{},"ISSN":["1664-2295"],"issn-type":[{"value":"1664-2295","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,4]]},"article-number":"1872532"}}