{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T02:03:28Z","timestamp":1780711408068,"version":"3.54.1"},"reference-count":39,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,4,28]],"date-time":"2025-04-28T00:00:00Z","timestamp":1745798400000},"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. Med."],"abstract":"<jats:sec><jats:title>Objective<\/jats:title><jats:p>Accurate anterior visual pathway (AVP) segmentation is vital for clinical applications, but manual delineation is time-consuming and resource-intensive. We aim to explore the feasibility of automatic AVP segmentation and volume measurement in brain T1-weighted imaging (T1WI) using the 3D UX-Net deep-learning model.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>Clinical data and brain 3D T1WI from 119 adults were retrospectively collected. Two radiologists annotated the AVP course in each participant\u2019s images. The dataset was randomly divided into training (<jats:italic>n<\/jats:italic> = 89), validation (<jats:italic>n<\/jats:italic> = 15), and test sets (<jats:italic>n<\/jats:italic> = 15). A 3D UX-Net segmentation model was trained on the training data, with hyperparameters optimized using the validation set. Model accuracy was evaluated on the test set using Dice similarity coefficient (DSC), 95% Hausdorff distance (HD95), and average symmetric surface distance (ASSD). The 3D UX-Net\u2019s performance was compared against 3D U-Net, Swin UNEt TRansformers (UNETR), UNETR++, and Swin Soft Mixture Transformer (Swin SMT). The AVP volume in the test set was calculated using the model\u2019s effective voxel volume, with volume difference (VD) assessing measurement accuracy. The average AVP volume across all subjects was derived from 3D UX-Net\u2019s automatic segmentation.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>The 3D UX-Net achieved the highest DSC (0.893 \u00b1 0.017), followed by Swin SMT (0.888 \u00b1 0.018), 3D U-Net (0.875 \u00b1 0.019), Swin UNETR (0.870 \u00b1 0.017), and UNETR++ (0.861 \u00b1 0.020). For surface distance metrics, 3D UX-Net demonstrated the lowest median ASSD (0.234 mm [0.188\u20130.273]). The VD of Swin SMT was significantly lower than that of 3D U-Net (<jats:italic>p<\/jats:italic> = 0.008), while no statistically significant differences were observed among other groups. All models exhibited identical HD95 (1 mm [1-1]). Automatic segmentation across all subjects yielded a mean AVP volume of 1446.78 \u00b1 245.62 mm<jats:sup>3<\/jats:sup>, closely matching manual segmentations (VD = 0.068 \u00b1 0.064). Significant sex-based volume differences were identified (<jats:italic>p<\/jats:italic> &amp;lt; 0.001), but no age correlation was observed.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>We provide normative values for the automatic MRI measurement of the AVP in adults. The 3D UX-Net model based on brain T1WI achieves high accuracy in segmenting and measuring the volume of the AVP.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fmed.2025.1530361","type":"journal-article","created":{"date-parts":[[2025,4,28]],"date-time":"2025-04-28T05:32:52Z","timestamp":1745818372000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Automatic segmentation and volume measurement of anterior visual pathway in brain 3D-T1WI using deep learning"],"prefix":"10.3389","volume":"12","author":[{"given":"Yongliang","family":"Han","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haixiang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qi","family":"Luo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingjie","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chun","family":"Zeng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiao","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Linquan","family":"Dai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yiqiu","family":"Wei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiyuan","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenlong","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shaoguo","family":"Cui","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongmei","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,4,28]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1186\/s13244-019-0719-5","article-title":"Imaging of cranial nerves: A pictorial overview.","volume":"10","author":"Romano","year":"2019","journal-title":"Insights Imaging."},{"key":"B2","doi-asserted-by":"publisher","first-page":"243","DOI":"10.1016\/j.nic.2007.10.001","article-title":"Pathology of the optic nerve.","volume":"18","author":"J\u00e4ger","year":"2008","journal-title":"Neuroimaging Clin N Am."},{"key":"B3","doi-asserted-by":"publisher","first-page":"1342","DOI":"10.1038\/s41591-018-0107-6","article-title":"Clinically applicable deep learning for diagnosis and referral in retinal disease.","volume":"24","author":"De Fauw","year":"2018","journal-title":"Nat Med."},{"key":"B4","article-title":"A fast and fully automated approach to segment optic nerves on MRI and its application to radiosurgery.","author":"Dolz","year":"2015","journal-title":"Proceedings of the IEEE 12th International Symposium on Biomedical Imaging (ISBI)."},{"key":"B5","doi-asserted-by":"publisher","first-page":"103494","DOI":"10.1016\/j.nicl.2023.103494","article-title":"Methods of diffusion MRI tractography for localization of the anterior optic pathway: A systematic review of validated methods.","volume":"39","author":"Carrozzi","year":"2023","journal-title":"Neuroimage Clin."},{"key":"B6","doi-asserted-by":"publisher","first-page":"1856","DOI":"10.1109\/TMI.2016.2535222","article-title":"Deep learning guided par-titioned shape model for anterior visual pathway segmentation.","volume":"35","author":"Mansoor","year":"2016","journal-title":"IEEE Trans Med Imaging."},{"key":"B7","doi-asserted-by":"publisher","first-page":"34006","DOI":"10.1117\/1.JMI.1.3.034006","article-title":"Robust optic nerve segmentation on clinically acquired computed tomography.","volume":"1","author":"Harrigan","year":"2014","journal-title":"J Med Imaging."},{"key":"B8","doi-asserted-by":"publisher","first-page":"651216","DOI":"10.1117\/12.711182","article-title":"Automatic delineation of the optic nerves and chiasm on CT images.","volume":"41","author":"Gensheimer","year":"2007","journal-title":"SPIE Med Imaging."},{"key":"B9","doi-asserted-by":"publisher","first-page":"509","DOI":"10.1007\/978-3-030-34110-7_42","article-title":"Spatial probabilistic distribution map based 3D FCN for visual pathway segmentation.","author":"Zhao","year":"2019","journal-title":"ICIG"},{"key":"B10","doi-asserted-by":"publisher","first-page":"102766","DOI":"10.1016\/j.media.2023.102766","article-title":"CNTSeg: A multimodal deep-learning-based network for cranial nerves tract segmentation.","volume":"86","author":"Xie","year":"2023","journal-title":"Med Image Anal."},{"key":"B11","doi-asserted-by":"publisher","first-page":"453","DOI":"10.1038\/s41598-023-50980-x","article-title":"Biometry extraction and probabilistic anatomical atlas of the anterior Visual Pathway using dedicated high-resolution 3-D MRI.","volume":"14","author":"Pravat\u00e0","year":"2024","journal-title":"Sci Rep."},{"key":"B12","author":"Lee","year":"2023","journal-title":"3D UX-Net: A Large Kernel Volumetric ConvNet Modernizing Hierarchical Transformer for Medical Image Segmentation."},{"key":"B13","doi-asserted-by":"publisher","first-page":"105750","DOI":"10.1016\/j.msard.2024.105750","article-title":"Enhanced choroid plexus segmentation with 3D UX-Net and its association with disease progression in multiple sclerosis.","volume":"88","author":"Wang","year":"2024","journal-title":"Mult Scler Relat Disord."},{"key":"B14","author":"Ronneberger","year":"2015","journal-title":"U-Net: Convolutional Networks for Biomedical Image Segmentation."},{"key":"B15","author":"Hatamizadeh","year":"2022","journal-title":"Swin UNETR: Swin Transformers for Semantic Segmentation of Brain Tumors in MRI Images."},{"key":"B16","author":"Shaker","year":"2024","journal-title":"UNETR++: Delving into Efficient and Accurate 3D Medical Image Segmentation."},{"key":"B17","author":"P\u0142otka","year":"2024","journal-title":"Swin SMT: Global Sequential Modeling in 3D Medical Image Segmentation."},{"key":"B18","doi-asserted-by":"publisher","first-page":"M20","DOI":"10.1167\/iovs.18-25957","article-title":"IMI-defining and classifying myopia: A proposed set of standards for clinical and epidemiologic studies.","volume":"60","author":"Flitcroft","year":"2019","journal-title":"Invest Ophthalmol Vis Sci."},{"key":"B19","doi-asserted-by":"publisher","first-page":"39","DOI":"10.5603\/FM.a2018.0065","article-title":"Morphometric characteristics of the optic canal and the optic nerve.","volume":"78","author":"Radunovic","year":"2019","journal-title":"Folia Morphol."},{"key":"B20","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1055\/s-0028-1124020","article-title":"The optic nerve.","volume":"29","author":"Selhorst","year":"2009","journal-title":"Semin Neurol."},{"key":"B21","author":"Zhang","year":"2018","journal-title":"Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels."},{"key":"B22","doi-asserted-by":"publisher","first-page":"1451","DOI":"10.1109\/TMI.2006.880587","article-title":"Generalized overlap measures for evaluation and validation in medical image analysis.","volume":"25","author":"Crum","year":"2006","journal-title":"IEEE Trans Med Imaging."},{"key":"B23","doi-asserted-by":"publisher","first-page":"19","DOI":"10.48550\/arXiv.1812.06740","article-title":"Computing the hausdorff distance of two sets from their signed distance functions.","volume":"30","author":"Kraft","year":"2020","journal-title":"Int J Comput Geometry Appl."},{"key":"B24","doi-asserted-by":"publisher","first-page":"15006","DOI":"10.1117\/1.JMI.5.1.015006","article-title":"Family of boundary overlap metrics for the evaluation of medical image segmentation.","volume":"5","author":"Yeghiazaryan","year":"2018","journal-title":"J Med Imaging."},{"key":"B25","author":"Yeghiazaryan","year":"2015","journal-title":"An Overview of Current Evaluation Methods used in Medical Image Segmentation."},{"key":"B26","doi-asserted-by":"publisher","first-page":"601","DOI":"10.1016\/j.patrec.2020.09.003","article-title":"Spatial probabilistic distribution map-based two-channel 3D U-net for visual pathway segmentation.","volume":"138","author":"Ai","year":"2020","journal-title":"Pattern Recogn Lett"},{"key":"B27","doi-asserted-by":"publisher","first-page":"279","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","journal-title":"Computational Diffusion MRI. Mathematics and Visualization."},{"key":"B28","doi-asserted-by":"publisher","first-page":"034501","DOI":"10.1117\/1.JMI.10.3.034501","article-title":"Automatic segmentation and quantification of the optic nerve on MRI using a 3D U-Net.","volume":"10","author":"van Elst","year":"2023","journal-title":"J Med Imaging."},{"key":"B29","doi-asserted-by":"publisher","first-page":"551","DOI":"10.1016\/j.ajo.2009.05.007","article-title":"Bilateral abnormalities of optic nerve size and eye shape in unilateral amblyopia.","volume":"148","author":"Pineles","year":"2009","journal-title":"Am J Ophthalmol."},{"key":"B30","doi-asserted-by":"publisher","first-page":"2264","DOI":"10.1212\/WNL.0000000000002771","article-title":"Quantitative MRI criteria for optic pathway enlargement in neurofibromatosis type 1.","volume":"86","author":"Avery","year":"2016","journal-title":"Neurology."},{"key":"B31","doi-asserted-by":"publisher","first-page":"4235","DOI":"10.1167\/iovs.13-12357","article-title":"MRI acquisition and analysis protocol for in vivo intraorbital optic nerve segmentation at 3T.","volume":"54","author":"Yiannakas","year":"2013","journal-title":"Invest Ophthalmol Vis Sci."},{"key":"B32","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1016\/j.clinimag.2022.02.021","article-title":"Evaluation of optic nerve diameters in individuals with neurofibromatosis and comparison of normative values in different pediatric age groups.","volume":"85","author":"Tosun","year":"2022","journal-title":"Clin Imaging."},{"key":"B33","doi-asserted-by":"publisher","first-page":"941303","DOI":"10.1117\/12.2081887","article-title":"Constructing a statistical atlas of the radii of the optic nerve and cerebrospinal fluid sheath in young healthy adults.","volume":"9413","author":"Harrigan","year":"2015","journal-title":"Proc SPIE Int Soc Opt Eng."},{"key":"B34","doi-asserted-by":"publisher","first-page":"34501","DOI":"10.1117\/1.JMI.4.3.034501","article-title":"Efficient orbital structures segmentation with prior anatomical knowledge.","volume":"4","author":"Aghdasi","year":"2017","journal-title":"J Med Imaging"},{"key":"B35","doi-asserted-by":"publisher","first-page":"595","DOI":"10.1097\/IJG.0b013e3181996f05","article-title":"Optic disk size variability between African, Asian, white, Hispanic, and Filipino Americans using Heidelberg retinal tomography.","volume":"18","author":"Seider","year":"2009","journal-title":"J Glaucoma."},{"key":"B36","doi-asserted-by":"publisher","first-page":"2403","DOI":"10.1016\/j.ophtha.2011.06.013","article-title":"Variation in optic nerve and macular structure with age and race with spectral-domain optical coherence tomography.","volume":"118","author":"Girkin","year":"2011","journal-title":"Ophthalmology."},{"key":"B37","doi-asserted-by":"publisher","first-page":"444","DOI":"10.1136\/jnnp.70.4.444","article-title":"Magnetic resonance imaging, magnetisation transfer imaging, and diffusion weighted imaging correlates of optic nerve, brain, and cervical cord damage in Leber\u2019s hereditary optic neuropathy.","volume":"70","author":"Inglese","year":"2001","journal-title":"J Neurol Neurosurg Psychiatry."},{"key":"B38","doi-asserted-by":"publisher","first-page":"1772","DOI":"10.4102\/sajr.v23i1.1772","article-title":"Normal measurements of the optic nerve, optic nerve sheath and optic chiasm in the adult population.","volume":"23","author":"Mncube","year":"2019","journal-title":"SA J Radiol."},{"key":"B39","doi-asserted-by":"publisher","first-page":"5048","DOI":"10.1007\/s00330-020-06859-w","article-title":"Optic chiasm measurements may be useful markers of anterior optic pathway degeneration in neuromyelitis optica spectrum disorders.","volume":"30","author":"Juenger","year":"2020","journal-title":"Eur Radiol."}],"container-title":["Frontiers in Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2025.1530361\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,28]],"date-time":"2025-04-28T05:32:54Z","timestamp":1745818374000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2025.1530361\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,28]]},"references-count":39,"alternative-id":["10.3389\/fmed.2025.1530361"],"URL":"https:\/\/doi.org\/10.3389\/fmed.2025.1530361","relation":{},"ISSN":["2296-858X"],"issn-type":[{"value":"2296-858X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4,28]]},"article-number":"1530361"}}