{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T07:41:38Z","timestamp":1772005298852,"version":"3.50.1"},"reference-count":49,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T00:00:00Z","timestamp":1768176000000},"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. Neurosci."],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>White matter tract segmentation is critical for mapping brain connectivity in both clinical and research settings. Recent deep learning methods have enabled direct voxel-wise segmentation from diffusion MRI (dMRI), bypassing tractography. However, most approaches rely on a limited number of peaks extracted from the fiber orientation distribution function (fODF) at each voxel, which discards important orientation information, particularly in problematic regions with complex fiber configurations such as crossing fibers and bottlenecks.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>In this work, we introduce FODSeg, a voxel-based segmentation method that utilizes the complete fODF representation for each voxel, capturing the full angular structure of white matter orientation. Additionally, we reformulate tract segmentation as a singleclass problem, training one model per tract to reduce label conflicts inherent in multi-class approaches. This combination allows FODSeg to better distinguish tracts with similar local orientations and improves robustness in regions with structural ambiguity. We evaluate FODSeg on the Human Connectome Project dataset across all 72 white matter tracts using six segmentation accuracy metrics.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>FODSeg achieves higher Dice scores and lower volumetric overreach values in 70% of the tracts while maintaining high specificity. Our results demonstrate the superior performance of FODSeg over existing segmentation approaches. Notably, our method shows significant improvements in anatomically challenging bottleneck regions, reducing false positives and improving tract-specific precision.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>Overall, FODSeg advances white matter tract segmentation by leveraging the full richness of the fODF signal while improving accuracy, specificity, and anatomical consistency.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fnins.2025.1734498","type":"journal-article","created":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T08:14:03Z","timestamp":1768205643000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["FODSeg: a deep learning framework for tract-specific white matter segmentation from full angular distributions"],"prefix":"10.3389","volume":"19","author":[{"given":"Ankita","family":"Joshi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hailong","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nehal A.","family":"Parikh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lili","family":"He","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2026,1,12]]},"reference":[{"key":"ref1","doi-asserted-by":"crossref","first-page":"451","DOI":"10.1093\/med\/9780195369779.003.0027","article-title":"Mathematics of crossing fibers","volume-title":"Diffusion MRI: theory, methods, and application","author":"Alexander","year":"2010"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"1525","DOI":"10.1109\/TMI.2007.907301","article-title":"A fuzzy, nonparametric segmentation framework for DTI and MRI analysis: with applications to DTI-tract extraction","volume":"26","author":"Awate","year":"2007","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"625","DOI":"10.1002\/1522-2594(200010)44:4<625::aid-mrm17>3.0.co;2-o","article-title":"In vivo fiber tractography using DT-MRI data","volume":"44","author":"Basser","year":"2000","journal-title":"Magn. Reson. Med."},{"key":"ref4","article-title":"Tractometry\u2013comprehensive multi-modal quantitative assessment of white matter along specific tracts","volume":"678","author":"Bells","year":"2011","journal-title":"Proc. ISMRM"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"117402","DOI":"10.1016\/j.neuroimage.2020.117402","article-title":"Classifyber, a robust streamline-based linear classifier for white matter bundle segmentation","volume":"224","author":"Berto","year":"2021","journal-title":"NeuroImage"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"e70132","DOI":"10.1101\/2024.07.20.603804","article-title":"White matter tract crossing and bottleneck regions in the fetal brain","volume":"46","author":"Calixto","year":"2025","journal-title":"Hum. Brain. Mapp"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"17149","DOI":"10.1038\/s41598-020-74054-4","article-title":"Bundle analytics, a computational framework for investigating the shapes and profiles of brain pathways across populations","volume":"10","author":"Chandio","year":"2020","journal-title":"Sci. Rep."},{"key":"ref8","first-page":"424","article-title":"3D U-net: learning dense volumetric segmentation from sparse annotation","author":"\u00c7i\u00e7ek","year":"2016"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"989","DOI":"10.1002\/hbm.23082","article-title":"Profilometry: a new statistical framework for the characterization of white matter pathways, with application to multiple sclerosis","volume":"37","author":"Dayan","year":"2016","journal-title":"Hum. Brain Mapp."},{"key":"ref10","first-page":"1","article-title":"Multimodality white matter tract segmentation using CNN","volume-title":"Proceedings of the ACM Turing Celebration Conference-China, 2019 May 17\u201319, Chengdu, China","author":"Dong","year":"2019"},{"key":"ref11","article-title":"An image is worth 16x16 words: transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv preprint arXiv:2010.11929."},{"key":"ref12","doi-asserted-by":"publisher","first-page":"659","DOI":"10.1016\/j.nicl.2017.06.011","article-title":"White matter tractography for neurosurgical planning: a topography-based review of the current state of the art","volume":"15","author":"Essayed","year":"2017","journal-title":"Neuroimage Clin"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"93","DOI":"10.1007\/s11263-006-6854-8","article-title":"Curvature-driven PDE methods for matrix-valued images","volume":"69","author":"Feddern","year":"2006","journal-title":"Int. J. Comput. Vis."},{"key":"ref14","doi-asserted-by":"publisher","first-page":"124","DOI":"10.1016\/j.neuroimage.2015.05.016","article-title":"Robust and efficient linear registration of white-matter fascicles in the space of streamlines","volume":"117","author":"Garyfallidis","year":"2015","journal-title":"NeuroImage"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"105","DOI":"10.1016\/j.neuroimage.2013.04.127","article-title":"The minimal preprocessing pipelines for the human connectome project","volume":"80","author":"Glasser","year":"2013","journal-title":"NeuroImage"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"103738","DOI":"10.1016\/j.nicl.2025.103738","article-title":"Deep learning based tractography with TractSeg in patients with hemispherotomy: evaluation and refinement","volume":"45","author":"Gruen","year":"2025","journal-title":"NeuroImage: Clinical"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"665","DOI":"10.1016\/j.neuroimage.2006.02.043","article-title":"Fibertract segmentation in position orientation space from high angular resolution diffusion MRI","volume":"32","author":"Hagmann","year":"2006","journal-title":"NeuroImage"},{"key":"ref18","article-title":"Automated design of deep learning methods for biomedical image segmentation","author":"Isensee","year":"2019","journal-title":"arXiv preprint arXiv:1904.08128."},{"key":"ref19","doi-asserted-by":"publisher","first-page":"2747","DOI":"10.1002\/hbm.22099","article-title":"Investigating the prevalence of complex fiber configurations in white matter tissue with diffusion magnetic resonance imaging","volume":"34","author":"Jeurissen","year":"2013","journal-title":"Hum. Brain Mapp."},{"key":"ref20","doi-asserted-by":"publisher","first-page":"1376570","DOI":"10.3389\/fnins.2024.1376570","article-title":"A systematic review of automated methods to perform white matter tract segmentation","volume":"18","author":"Joshi","year":"2024","journal-title":"Front. Neurosci."},{"key":"ref21","doi-asserted-by":"publisher","first-page":"102129","DOI":"10.1016\/j.media.2021.102129","article-title":"A machine learning-based method for estimating the number and orientations of major fascicles in diffusion-weighted magnetic resonance imaging","volume":"72","author":"Karimi","year":"2021","journal-title":"Med. Image Anal."},{"key":"ref22","first-page":"arXiv-2307","article-title":"Direct segmentation of brain white matter tracts in diffusion MRI","author":"Kebiri","year":"2023","journal-title":"ArXiv"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"200101","DOI":"10.1016\/j.jpedcp.2024.200101","article-title":"Corpus callosum abnormalities at term-equivalent age are associated with language development at 2 years\u2019 corrected age in infants born very preterm","volume":"11","author":"Kojima","year":"2024","journal-title":"J. Pediatr. Clin. Pract."},{"key":"ref24","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-73018-5_22","article-title":"Two parallel stages deep learning network for anterior visual pathway segmentation","author":"Li","year":"2021"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"116993","DOI":"10.1016\/j.neuroimage.2020.116993","article-title":"Neuro4Neuro: a neural network approach for neural tract segmentation using large-scale population-based diffusion imaging","volume":"218","author":"Li","year":"2020","journal-title":"NeuroImage"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"866974","DOI":"10.3389\/fradi.2022.866974","article-title":"Informative and reliable tract segmentation for preoperative planning","volume":"2","author":"Lucena","year":"2022","journal-title":"Front Radiol"},{"key":"ref27","doi-asserted-by":"publisher","first-page":"1349","DOI":"10.1038\/s41467-017-01285-x","article-title":"The challenge of mapping the human connectome based on diffusion tractography","volume":"8","author":"Maier-Hein","year":"2017","journal-title":"Nat. Commun."},{"key":"ref28","doi-asserted-by":"crossref","DOI":"10.1109\/ISBI45749.2020.9098454","article-title":"Automatic segmentation of white matter tracts using multiple brain MRI sequences","volume-title":"2020 IEEE 17th international symposium on biomedical imaging (ISBI), 2020 Apr 3\u20137, Iowa City, IA, USA","author":"Nelkenbaum","year":"2020"},{"key":"ref29","first-page":"32","article-title":"Pytorch: An imperative style, high-performance deep learning library","author":"Paszke","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref30","doi-asserted-by":"crossref","DOI":"10.1109\/ISBI.2019.8759575","article-title":"3D convolutional neural network segmentation of white matter tract masks from MR diffusion anisotropy maps","volume-title":"2019 IEEE 16th international symposium on biomedical imaging (ISBI 2019), 2019 April 8\u201311, Venice, Italy","author":"Pomiecko","year":"2019"},{"key":"ref31","doi-asserted-by":"publisher","first-page":"3976","DOI":"10.1016\/j.neuroimage.2011.10.045","article-title":"Apparent fibre density: a novel measure for the analysis of diffusion-weighted magnetic resonance images","volume":"59","author":"Raffelt","year":"2012","journal-title":"NeuroImage"},{"key":"ref32","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.neuroimage.2018.10.029","article-title":"Limits to anatomical accuracy of diffusion tractography using modern approaches","volume":"185","author":"Schilling","year":"2019","journal-title":"NeuroImage"},{"key":"ref33","doi-asserted-by":"publisher","first-page":"1196","DOI":"10.1002\/hbm.25697","article-title":"Prevalence of white matter pathways coming into a single white matter voxel orientation: the bottleneck issue in tractography","volume":"43","author":"Schilling","year":"2022","journal-title":"Hum. Brain Mapp."},{"key":"ref34","doi-asserted-by":"crossref","first-page":"105","DOI":"10.1016\/B978-0-12-396460-1.00006-8","article-title":"Multiple fibers: beyond the diffusion tensor","volume-title":"Diffusion Mri","author":"Seunarine","year":"2014"},{"key":"ref35","doi-asserted-by":"publisher","first-page":"125","DOI":"10.1016\/j.neuroimage.2013.05.057","article-title":"Advances in diffusion MRI acquisition and processing in the human connectome project","volume":"80","author":"Sotiropoulos","year":"2013","journal-title":"NeuroImage"},{"key":"ref36","first-page":"2106.10270","article-title":"How to train your ViT. Data, augmentation, and regularization in vision transformers","volume-title":"arXiv preprint","author":"Steiner","year":"2021"},{"key":"ref37","doi-asserted-by":"crossref","first-page":"465","DOI":"10.1093\/med\/9780195369779.003.0028","article-title":"The biophysics of crossing fibers","volume-title":"Diffusion MRI: theory, methods, and application","author":"Tournier","year":"2010"},{"key":"ref38","doi-asserted-by":"publisher","first-page":"1459","DOI":"10.1016\/j.neuroimage.2007.02.016","article-title":"Robust determination of the fibre orientation distribution in diffusion MRI: non-negativity constrained super-resolved spherical deconvolution","volume":"35","author":"Tournier","year":"2007","journal-title":"NeuroImage"},{"key":"ref39","article-title":"Improved probabilistic streamlines tractography by 2nd order integration over fibre orientation distributions","volume-title":"Proc. Intl. Soc. Mag. Reson. Med.","author":"Tournier","year":"2010"},{"key":"ref40","doi-asserted-by":"publisher","first-page":"1176","DOI":"10.1016\/j.neuroimage.2004.07.037","article-title":"Direct estimation of the fiber orientation density function from diffusion-weighted MRI data using spherical deconvolution","volume":"23","author":"Tournier","year":"2004","journal-title":"NeuroImage"},{"key":"ref41","doi-asserted-by":"publisher","first-page":"116137","DOI":"10.1016\/j.neuroimage.2019.116137","article-title":"MRtrix3: a fast, flexible and open software framework for medical image processing and visualisation","volume":"202","author":"Tournier","year":"2019","journal-title":"NeuroImage"},{"key":"ref42","doi-asserted-by":"publisher","first-page":"62","DOI":"10.1016\/j.neuroimage.2013.05.041","article-title":"The WU-Minn human connectome project: an overview","volume":"80","author":"Van Essen","year":"2013","journal-title":"NeuroImage"},{"key":"ref43","doi-asserted-by":"publisher","first-page":"1267","DOI":"10.1109\/TMI.2005.854516","article-title":"DTI segmentation using an information theoretic tensor dissimilarity measure","volume":"24","author":"Wang","year":"2005","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref44","doi-asserted-by":"publisher","first-page":"1750","DOI":"10.1038\/s41386-020-0691-2","article-title":"Multiparametric mapping of white matter microstructure in catatonia","volume":"45","author":"Wasserthal","year":"2020","journal-title":"Neuropsychopharmacology"},{"key":"ref45","doi-asserted-by":"publisher","first-page":"101559","DOI":"10.1016\/j.media.2019.101559","article-title":"Combined tract segmentation and orientation mapping for bundle-specific tractography","volume":"58","author":"Wasserthal","year":"2019","journal-title":"Med. Image Anal."},{"key":"ref46","doi-asserted-by":"publisher","first-page":"239","DOI":"10.1016\/j.neuroimage.2018.07.070","article-title":"TractSeg-fast and accurate white matter tract segmentation","volume":"183","author":"Wasserthal","year":"2018","journal-title":"NeuroImage"},{"key":"ref47","doi-asserted-by":"publisher","first-page":"1255","DOI":"10.1002\/mrm.21965","article-title":"About \u201caxial\u201d and \u201cradial\u201d diffusivities","volume":"61","author":"Wheeler-Kingshott","year":"2009","journal-title":"Magn. Reson. Med."},{"key":"ref001","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1007\/978-3-031-21206-2_10","article-title":"DC 2 U-net: tract segmentation in brain white matter using dense Criss-cross U-net","author":"Yin","year":"2022","journal-title":"International Workshop on Computational Diffusion MRI"},{"key":"ref48","doi-asserted-by":"publisher","first-page":"118870","DOI":"10.1016\/j.neuroimage.2021.118870","article-title":"Quantitative mapping of the brain's structural connectivity using diffusion MRI tractography: a review","volume":"249","author":"Zhang","year":"2022","journal-title":"NeuroImage"}],"container-title":["Frontiers in Neuroscience"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnins.2025.1734498\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T08:14:06Z","timestamp":1768205646000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnins.2025.1734498\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,12]]},"references-count":49,"alternative-id":["10.3389\/fnins.2025.1734498"],"URL":"https:\/\/doi.org\/10.3389\/fnins.2025.1734498","relation":{},"ISSN":["1662-453X"],"issn-type":[{"value":"1662-453X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,12]]},"article-number":"1734498"}}