{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T21:56:12Z","timestamp":1790286972891,"version":"4.1.0"},"reference-count":27,"publisher":"S. Karger AG","issue":"1","license":[{"start":{"date-parts":[[2025,12,22]],"date-time":"2025-12-22T00:00:00Z","timestamp":1766361600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"},{"start":{"date-parts":[[2025,12,22]],"date-time":"2025-12-22T00:00:00Z","timestamp":1766361600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Digit Biomark"],"abstract":"<jats:p>Introduction: Eye movements are key biomarkers for diagnosing and monitoring neuro-otological, neuro-ophthalmological and neurodegenerative disorders. Video-oculography (VOG) systems enable detection of small, rapid eye movements and subtle oculomotor pathologies that may be missed during clinical exams. However, they rely on high-quality input, struggle with torsional movements, and are often limited by high costs in clinical and research settings. Methods: To overcome these limitations, we developed 3DeepVOG, a deep learning-based framework for three-dimensional monocular gaze tracking (horizontal, vertical, and torsional rotation) that operates robustly across varied imaging conditions, including low-light and noisy environments. The method combines automated pupil and iris segmentation with geometrically interpretable estimation using a two-sphere anatomical eyeball model with corneal refraction correction. Torsion is tracked in real time using a novel mini-patch template matching approach. The system was trained on over 24,000 annotated samples obtained across multiple devices and clinical scenarios. Application was tested against a gold-standard VOG system in healthy controls. Results: 3DeepVOG operates in real time (&gt;300 fps) and achieves gaze errors of \u223c0.1\u00b0 in all three dimensions. Oculomotor measures \u2013 saccadic peak velocity, smooth pursuit gain, and optokinetic nystagmus slow-phase velocity \u2013 show good-to-excellent agreement with a clinical gold-standard system. As proof of concept, we present a case of acute unilateral vestibular failure where 3DeepVOG reliably captures 3D nystagmus. Conclusions: 3DeepVOG enables accurate, quantitative eye movement tracking across three dimensions under diverse conditions. As an open-source framework, it provides an accessible and scalable tool for advancing research and clinical assessment in neurological oculomotor disorders.<\/jats:p>","DOI":"10.1159\/000549948","type":"journal-article","created":{"date-parts":[[2025,12,22]],"date-time":"2025-12-22T17:00:51Z","timestamp":1766422851000},"page":"21-31","source":"Crossref","is-referenced-by-count":2,"title":["3DeepVOG: An Open-Source Framework for Real-Time, Accurate 3D Gaze Tracking with Deep Learning"],"prefix":"10.1159","volume":"10","author":[{"given":"Jingkang","family":"Zhao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Seyed-Ahmad","family":"Ahmadi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Julian","family":"Decker","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ken","family":"M\u00f6hwald","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peter","family":"zu Eulenburg","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andreas","family":"Zwergal","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Virginia L.","family":"Flanagin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5115-3777","authenticated-orcid":false,"given":"Max","family":"Wuehr","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"127","published-online":{"date-parts":[[2025,12,22]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1002\/mdc3.13413"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.2147\/EB.S384769"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/nrneurol.2012.273"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-444-63437-5.00008-X"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1167\/15.14.11"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.3988\/jcn.2022.0413"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3109\/00016489109131342"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1080\/00016489.2016.1269364"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.3389\/fneur.2022.917413"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.jneumeth.2019.05.016"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.3233\/VES-160587"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1167\/iovs.05-0234"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.116894"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1155\/2007\/23570"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ismar52148.2021.00053"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2021.3067765"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.3390\/info11090408"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.jneumeth.2010.08.004"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.14253\/acn.2023.25.2.55"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1093\/brain\/awg163"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.jneumeth.2017.11.012"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcm.2016.02.012"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.anl.2004.11.009"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s12311-022-01374-8"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1159\/000511287"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s00415-022-11493-1"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1159\/000538992"}],"container-title":["Digital Biomarkers"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/karger.com\/article-pdf\/doi\/10.1159\/000549948","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T17:00:40Z","timestamp":1770397240000},"score":1,"resource":{"primary":{"URL":"https:\/\/karger.com\/article\/doi\/10.1159\/000549948"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,22]]},"references-count":27,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,1,1]]}},"URL":"https:\/\/doi.org\/10.1159\/000549948","archive":["Portico"],"relation":{"is-supplemented-by":[{"id-type":"doi","id":"10.6084\/m9.figshare.30931016","asserted-by":"subject"}]},"ISSN":["2504-110X"],"issn-type":[{"value":"2504-110X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,22]]}}}