{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T13:12:12Z","timestamp":1780665132782,"version":"3.54.1"},"reference-count":23,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T00:00:00Z","timestamp":1780617600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T00:00:00Z","timestamp":1780617600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100007214","name":"Velux Stiftung","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100007214","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100023947","name":"Ente Ospedaliero Cantonale","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100023947","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100008486","name":"Schweizerische Multiple Sklerose Gesellschaft","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100008486","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Eur Radiol Exp"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>Manual segmentation of the whole anterior visual pathway (aVP) from high-resolution magnetic resonance imaging (MRI) is time-consuming and prone to inter-rater variability. We developed and validated a fully automated deep learning framework, \u201caVP-seg,\u201d to perform rapid, multiclass segmentation of the optic nerves, chiasm, and optic tracts in healthy volunteers and multiple sclerosis (MS) patients.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Materials and methods<\/jats:title>\n                    <jats:p>We developed and validated a cascaded two-stage three-dimensional convolutional neural network (principal segmentation + refinement) for automated multiclass segmentation of the aVP from 0.6-mm isotropic three-dimensional constructive interference in steady state (CISS) MRI. The model was trained and evaluated in 34 healthy controls and 46 MS patients. Ground truth was derived from manual segmentations by two expert radiologists. Spatial agreement metrics included Dice similarity coefficient (DSC), 95th percentile Hausdorff distance (HD95), and volumetric similarity.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Agreement with the ground truth for the whole aVP was high (DSC 0.86\u2009\u00b1\u20090.03, mean\u2009\u00b1\u2009standard deviation; 95% confidence interval (CI) 0.85\u20130.86). Boundary alignment was strong (HD95 1.18\u2009mm \u00b1 0.54; 95% CI 1.06\u20131.30) and volumetric similarity was high (0.96\u2009\u00b1\u20090.04; 95% CI 0.95\u20130.97). Accuracy was consistent for the left and right optic nerves (DSC 0.85\u20130.86\u2009\u00b1\u20090.05\u20130.04) and chiasm (DSC 0.83\u2009\u00b1\u20090.09), but lower for the left and right optic tracts (DSC 0.74\u20130.75\u2009\u00b1\u20090.07\u20130.07).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>The aVP-seg provided accurate, automated multiclass segmentation of the whole aVP from high-resolution CISS MRI. This tool may standardize and accelerate the extraction of quantitative biomarkers of aVP integrity in neuro-ophthalmic conditions.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Relevance statement<\/jats:title>\n                    <jats:p>Automated multiclass segmentation of the entire anterior visual pathway enables standardized and reproducible preparation of MRI data for quantitative analysis. This approach facilitates future assessment of optic pathway involvement in MS and other neuro-ophthalmic disorders.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Key Points<\/jats:title>\n                    <jats:p>\n                      <jats:list list-type=\"bullet\">\n                        <jats:list-item>\n                          <jats:p>aVP-seg enabled fully automated segmentation of the entire anterior visual pathway from high-resolution CISS MRI data.<\/jats:p>\n                        <\/jats:list-item>\n                        <jats:list-item>\n                          <jats:p>Automated segmentation reduces processing time and operator-dependent variability.<\/jats:p>\n                        <\/jats:list-item>\n                        <jats:list-item>\n                          <jats:p>aVP-seg shows robust performance across both healthy subjects and MS patients.<\/jats:p>\n                        <\/jats:list-item>\n                      <\/jats:list>\n                    <\/jats:p>\n                  <\/jats:sec>","DOI":"10.1186\/s41747-026-00741-y","type":"journal-article","created":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T12:51:32Z","timestamp":1780663892000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Whole anterior visual pathway segmentation from high-resolution MRI using artificial intelligence"],"prefix":"10.1186","volume":"10","author":[{"given":"Andrea","family":"Diociasi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5225-2993","authenticated-orcid":false,"given":"Emanuele","family":"Pravat\u00e0","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Luca","family":"Carmisciano","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Oliver C.","family":"Kiersnowski","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Iester","family":"Michele","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kevin Klein","family":"Gunnewiek","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Luigi","family":"Lorenzini","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lorenzo","family":"Gualco","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Matteo","family":"Pardini","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Luca","family":"Roccatagliata","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chiara","family":"Zecca","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Claudio","family":"Gobbi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Roberto","family":"Guidotti","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrea","family":"Chincarini","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,5]]},"reference":[{"key":"741_CR1","doi-asserted-by":"publisher","first-page":"4308","DOI":"10.1093\/brain\/awac030","volume":"145","author":"M Pisa","year":"2022","unstructured":"Pisa M, Pansieri J, Yee S et al (2022) Anterior optic pathway pathology in CNS demyelinating diseases. Brain 145:4308\u20134319. https:\/\/doi.org\/10.1093\/brain\/awac030","journal-title":"Brain"},{"key":"741_CR2","doi-asserted-by":"publisher","first-page":"1355","DOI":"10.1016\/S1474-4422(16)30237-X","volume":"15","author":"V Biousse","year":"2016","unstructured":"Biousse V, Newman NJ (2016) Diagnosis and clinical features of common optic neuropathies. Lancet Neurol 15:1355\u20131367. https:\/\/doi.org\/10.1016\/S1474-4422(16)30237-X","journal-title":"Lancet Neurol"},{"key":"741_CR3","doi-asserted-by":"publisher","first-page":"169","DOI":"10.1148\/rg.2018170141","volume":"38","author":"BG Dutra","year":"2018","unstructured":"Dutra BG, da Rocha AJ, Nunes RH, Maia ACM Jr (2018) Neuromyelitis optica spectrum disorders: spectrum of MR imaging findings and their differential diagnosis. Radiographics 38:169\u2013193. https:\/\/doi.org\/10.1148\/rg.2018170141","journal-title":"Radiographics"},{"key":"741_CR4","doi-asserted-by":"publisher","first-page":"292","DOI":"10.1016\/S1474-4422(15)00393-2","volume":"15","author":"M Filippi","year":"2016","unstructured":"Filippi M, Rocca MA, Ciccarelli O et al (2016) MRI criteria for the diagnosis of multiple sclerosis: MAGNIMS consensus guidelines. Lancet Neurol 15:292\u2013303. https:\/\/doi.org\/10.1016\/S1474-4422(15)00393-2","journal-title":"Lancet Neurol"},{"key":"741_CR5","doi-asserted-by":"publisher","first-page":"571","DOI":"10.1002\/ana.27145","volume":"97","author":"WJ Brownlee","year":"2025","unstructured":"Brownlee WJ, Vidal-Jordana A, Shatila M et al (2025) Towards a unified set of diagnostic criteria for multiple sclerosis. Ann Neurol 97:571\u2013582. https:\/\/doi.org\/10.1002\/ana.27145","journal-title":"Ann Neurol"},{"key":"741_CR6","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1038\/s41433-020-01288-x","volume":"35","author":"N Minakaran","year":"2021","unstructured":"Minakaran N, de Carvalho ER, Petzold A, Wong SH (2021) Optical coherence tomography (OCT) in neuro-ophthalmology. Eye 35:17\u201332. https:\/\/doi.org\/10.1038\/s41433-020-01288-x","journal-title":"Eye"},{"key":"741_CR7","doi-asserted-by":"publisher","first-page":"453","DOI":"10.1038\/s41598-023-50980-x","volume":"14","author":"E Pravat\u00e0","year":"2024","unstructured":"Pravat\u00e0 E, Diociasi A, Navarra R et al (2024) Biometry extraction and probabilistic anatomical atlas of the anterior visual pathway using dedicated high-resolution 3-D MRI. Sci Rep 14:453. https:\/\/doi.org\/10.1038\/s41598-023-50980-x","journal-title":"Sci Rep"},{"key":"741_CR8","doi-asserted-by":"publisher","first-page":"1637","DOI":"10.1007\/s00234-020-02481-1","volume":"62","author":"K Gau","year":"2020","unstructured":"Gau K, Schmidt CSM, Urbach H et al (2020) Accuracy and practical aspects of semi- and fully automatic segmentation methods for resected brain areas. Neuroradiology 62:1637\u20131648","journal-title":"Neuroradiology"},{"key":"741_CR9","doi-asserted-by":"publisher","first-page":"1061","DOI":"10.3174\/ajnr.A7082","volume":"42","author":"E Pravat\u00e0","year":"2021","unstructured":"Pravat\u00e0 E, Roccatagliata L, Sormani MP et al (2021) Dedicated 3D-T2-STIR-ZOOMit imaging improves demyelinating lesion detection in the anterior visual pathways of patients with multiple sclerosis. AJNR Am J Neuroradiol 42:1061\u20131068. https:\/\/doi.org\/10.3174\/ajnr.A7082","journal-title":"AJNR Am J Neuroradiol"},{"key":"741_CR10","doi-asserted-by":"publisher","first-page":"1061","DOI":"10.1007\/s003300000452","volume":"10","author":"I Yousry","year":"2000","unstructured":"Yousry I, Camelio S, Schmid UD et al (2000) Visualization of cranial nerves I\u2013XII: value of 3D CISS and T2-weighted FSE sequences. Eur Radiol 10:1061\u20131067. https:\/\/doi.org\/10.1007\/s003300000452","journal-title":"Eur Radiol"},{"key":"741_CR11","doi-asserted-by":"publisher","first-page":"118482","DOI":"10.1016\/j.neuroimage.2021.118482","volume":"243","author":"D Karimi","year":"2021","unstructured":"Karimi D, Jaimes C, Machado-Rivas F et al (2021) Deep learning-based parameter estimation in fetal diffusion-weighted MRI. Neuroimage 243:118482. https:\/\/doi.org\/10.1016\/j.neuroimage.2021.118482","journal-title":"Neuroimage"},{"key":"741_CR12","doi-asserted-by":"publisher","first-page":"034501","DOI":"10.1117\/1.JMI.10.3.034501","volume":"10","author":"S van Elst","year":"2023","unstructured":"van Elst S, de Bloeme CM, Noteboom S et al (2023) Automatic segmentation and quantification of the optic nerve on MRI using a 3D U-Net. J Med Imaging 10:034501. https:\/\/doi.org\/10.1117\/1.JMI.10.3.034501","journal-title":"J Med Imaging"},{"key":"741_CR13","doi-asserted-by":"publisher","first-page":"601","DOI":"10.1016\/j.patrec.2020.09.003","volume":"138","author":"D Ai","year":"2020","unstructured":"Ai D, Zhao Z, Fan J et al (2020) Spatial probabilistic distribution map-based two-channel 3D U-net for visual pathway segmentation. Pattern Recognit Lett 138:601\u2013607. https:\/\/doi.org\/10.1016\/j.patrec.2020.09.003","journal-title":"Pattern Recognit Lett"},{"key":"741_CR14","doi-asserted-by":"publisher","first-page":"1530361","DOI":"10.3389\/fmed.2025.1530361","volume":"12","author":"Y Han","year":"2025","unstructured":"Han Y, Wang H, Luo Q et al (2025) Automatic segmentation and volume measurement of anterior visual pathway in brain 3D-T1WI using deep learning. Front Med 12:1530361. https:\/\/doi.org\/10.3389\/fmed.2025.1530361","journal-title":"Front Med"},{"key":"741_CR15","doi-asserted-by":"publisher","first-page":"e70071","DOI":"10.1002\/hbm.70071","volume":"45","author":"S Li","year":"2024","unstructured":"Li S, Zhang W, Yao S et al (2024) Tractography-based automated identification of retinogeniculate visual pathway with novel microstructure-informed supervised contrastive learning. Hum Brain Mapp 45:e70071. https:\/\/doi.org\/10.1002\/hbm.70071","journal-title":"Hum Brain Mapp"},{"key":"741_CR16","doi-asserted-by":"publisher","first-page":"102766","DOI":"10.1016\/j.media.2023.102766","volume":"86","author":"L Xie","year":"2023","unstructured":"Xie L, Huang J, Yu J et al (2023) CNTSeg: a multimodal deep-learning-based network for cranial nerves tract segmentation. Med Image Anal 86:102766. https:\/\/doi.org\/10.1016\/j.media.2023.102766","journal-title":"Med Image Anal"},{"key":"741_CR17","doi-asserted-by":"publisher","first-page":"1102","DOI":"10.1109\/ISBI.2015.7164064","volume":"2015","author":"J Dolz","year":"2015","unstructured":"Dolz J, Leroy HA, Reyns N, Massoptier L, Vermandel M (2015) A fast and fully automated approach to segment optic nerves on MRI and its application to radiosurgery. Proc IEEE Int Symp Biomed Imaging 2015:1102\u20131105. https:\/\/doi.org\/10.1109\/ISBI.2015.7164064","journal-title":"Proc IEEE Int Symp Biomed Imaging"},{"key":"741_CR18","doi-asserted-by":"publisher","first-page":"1856","DOI":"10.1109\/TMI.2016.2535222","volume":"35","author":"A Mansoor","year":"2016","unstructured":"Mansoor A, Cerrolaza JJ, Idrees R et al (2016) Deep learning guided partitioned shape model for anterior visual pathway segmentation. IEEE Trans Med Imaging 35:1856\u20131865. https:\/\/doi.org\/10.1109\/TMI.2016.2535222","journal-title":"IEEE Trans Med Imaging"},{"key":"741_CR19","doi-asserted-by":"publisher","first-page":"205521731773009","DOI":"10.1177\/2055217317730097","volume":"3","author":"RL Harrigan","year":"2017","unstructured":"Harrigan RL, Smith AK, Lyttle B et al (2017) Quantitative characterization of optic nerve atrophy in patients with multiple sclerosis. Mult Scler J Exp Transl Clin 3:2055217317730097. https:\/\/doi.org\/10.1177\/2055217317730097","journal-title":"Mult Scler J Exp Transl Clin"},{"key":"741_CR20","doi-asserted-by":"publisher","first-page":"877","DOI":"10.1016\/j.media.2011.05.001","volume":"15","author":"JH Noble","year":"2011","unstructured":"Noble JH, Dawant BM (2011) An atlas-navigated optimal medial axis and deformable model algorithm (NOMAD) for the segmentation of the optic nerves and chiasm in MR and CT images. Med Image Anal 15:877\u2013884. https:\/\/doi.org\/10.1016\/j.media.2011.05.001","journal-title":"Med Image Anal"},{"key":"741_CR21","doi-asserted-by":"publisher","unstructured":"Mansoor A, Cerrolaza JJ, Avery RA et al (2016) Partitioned shape modeling with on-the-fly sparse appearance learning for anterior visual pathway segmentation. In: Oyarzun Laura C et al (eds) Clinical image-based procedures. Translational research in medical imaging. Lecture notes in computer science. Springer, Heidelberg, pp 104\u2013112. https:\/\/doi.org\/10.1007\/978-3-319-31808-0_13","DOI":"10.1007\/978-3-319-31808-0_13"},{"key":"741_CR22","doi-asserted-by":"publisher","first-page":"850","DOI":"10.1016\/S1474-4422(25)00270-4","volume":"24","author":"X Montalban","year":"2025","unstructured":"Montalban X, Lebrun-Fr\u00e9nay C, Oh J et al (2025) Diagnosis of multiple sclerosis: 2024 revisions of the McDonald criteria. Lancet Neurol 24:850\u2013865. https:\/\/doi.org\/10.1016\/S1474-4422(25)00270-4","journal-title":"Lancet Neurol"},{"key":"741_CR23","doi-asserted-by":"publisher","first-page":"103187","DOI":"10.1016\/j.nicl.2022.103187","volume":"36","author":"G Mart\u00ed-Juan","year":"2022","unstructured":"Mart\u00ed-Juan G, Fr\u00edas M, Garcia-Vidal A et al (2022) Detection of lesions in the optic nerve with magnetic resonance imaging using a 3D convolutional neural network. Neuroimage Clin 36:103187. https:\/\/doi.org\/10.1016\/j.nicl.2022.103187","journal-title":"Neuroimage Clin"}],"container-title":["European Radiology Experimental"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s41747-026-00741-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s41747-026-00741-y","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s41747-026-00741-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T12:51:34Z","timestamp":1780663894000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1186\/s41747-026-00741-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,5]]},"references-count":23,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["741"],"URL":"https:\/\/doi.org\/10.1186\/s41747-026-00741-y","relation":{},"ISSN":["2509-9280"],"issn-type":[{"value":"2509-9280","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,5]]},"assertion":[{"value":"19 January 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 April 2026","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 April 2026","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 June 2026","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"This study was approved by the local Ethics Committee of Canton Ticino, Switzerland (Ref. 2017-00814; CE3224; date of approval: 24.02.2017).","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Written informed consent was obtained from all participants.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"EP received compensation for speaking activity and consulting fees unrelated to the present work from Bayer and Sanofi. CZ and CG have the following disclosure: Ente Ospedaliero Cantonale (employer) received compensation for speaking activities, consulting fees, or grants from AbbVie, Alexion, Almirall, Biogen, Bristol Myers Squibb, Eisai, Lilly, Lundbeck, Merck, Merz, Neuraxpharm, Novartis, Organon, Pfizer, Pharmaticino, Roche, Sandoz, Sanofi, Spirig, Takeda, and Teva Pharma. LG and LR are members of the Scientific Editorial Board of\n                      European Radiology Experimental\n                      and, as such, have not participated in the selection or review processes for this article.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"82"}}