{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T19:36:24Z","timestamp":1792784184510,"version":"4.5.0"},"reference-count":26,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2026,5,10]],"date-time":"2026-05-10T00:00:00Z","timestamp":1778371200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,5,10]],"date-time":"2026-05-10T00:00:00Z","timestamp":1778371200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Optical and Acoustic Imaging for Surgical and Interventional Sciences hubes programme","award":["UKRI145"],"award-info":[{"award-number":["UKRI145"]}]},{"name":"Royal Academy of Engineering under the Chair in Emerging Technologies programme","id":[{"id":"https:\/\/ror.org\/0008ahc55","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J CARS"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Purpose:<\/jats:title>\n                    <jats:p>Monocular depth and pose estimation play an essential role in developing colonoscopy-assisted navigation systems. Accurate geometric understanding can reduce blind spots, lower the risk of missed or recurrent lesions, and prevent incomplete examinations. However, this task remains challenging due to texture-less surfaces, complex illumination, tissue deformation, and the scarcity of in-vivo datasets with reliable ground truth.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods:<\/jats:title>\n                    <jats:p>We propose a self-supervised learning framework that leverages anatomical and illumination priors to guide geometric learning. The framework integrates two complementary cues: (1) edge maps, obtained from a learning-based detector trained to capture thin and high-frequency mucosal boundaries, and (2) luminance decomposition, produced through intrinsic image separation that isolates shading from reflectance. These modalities provide structural and photometric guidance to the pose and depth networks, with an edge-guided loss applied in a stage-wise refinement that enhances motion alignment while preserving depth consistency.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results:<\/jats:title>\n                    <jats:p>Experiments on phantom (C3VD) and real (EndoMapper) datasets demonstrate state-of-the-art performance in depth estimation and competitive accuracy in pose estimation. Ablation analyses further evaluate the influence of training domain, temporal sampling, and supervision type. Two practical findings emerge: Self-supervised training on real data outperforms supervised training on phantom data, highlighting the importance of domain realism; and dataset-specific frame-rate sampling is critical for generating effective training sequences.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion:<\/jats:title>\n                    <jats:p>\n                      The proposed framework enhances geometric learning in endoscopic videos by incorporating structure- and illumination-aware cues, providing a robust foundation for reliable, marker-free colonoscopy navigation. The code and pretrained models are publicly available at:\n                      <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" xlink:href=\"https:\/\/github.com\/XinweiJu\/PRISM\" ext-link-type=\"uri\">https:\/\/github.com\/XinweiJu\/PRISM<\/jats:ext-link>\n                      .\n                    <\/jats:p>\n                  <\/jats:sec>","DOI":"10.1007\/s11548-026-03669-1","type":"journal-article","created":{"date-parts":[[2026,5,10]],"date-time":"2026-05-10T05:20:56Z","timestamp":1778390456000},"page":"1207-1215","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Multi-modal monocular endoscopic depth and pose estimation with edge-guided self-supervision"],"prefix":"10.1007","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1137-9357","authenticated-orcid":false,"given":"Xinwei","family":"Ju","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rema","family":"Daher","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Danail","family":"Stoyanov","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sophia","family":"Bano","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Francisco","family":"Vasconcelos","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,5,10]]},"reference":[{"issue":"4","key":"3669_CR1","doi-asserted-by":"publisher","first-page":"322","DOI":"10.1136\/flgastro-2018-101089","volume":"12","author":"W Waddingham","year":"2021","unstructured":"Waddingham W, Nieuwenburg SA, Carlson S et al (2021) Recent advances in the detection and management of early gastric cancer and its precursors. Frontline Gastroenterol 12(4):322\u2013331","journal-title":"Frontline Gastroenterol"},{"key":"3669_CR2","doi-asserted-by":"publisher","unstructured":"Zhou T, Brown M et al (2017) Unsupervised learning of depth and ego-motion from video. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1851\u20131858. https:\/\/doi.org\/10.1109\/CVPR.2017.700","DOI":"10.1109\/CVPR.2017.700"},{"key":"3669_CR3","doi-asserted-by":"publisher","unstructured":"Godard C, Mac\u00a0Aodha O, Firman M et al (2019) Digging into self-supervised monocular depth estimation. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 3828\u20133838. https:\/\/doi.org\/10.1109\/ICCV.2019.00393","DOI":"10.1109\/ICCV.2019.00393"},{"key":"3669_CR4","doi-asserted-by":"publisher","unstructured":"Zhao C, Zhang Y et al (2022) Monovit: self-supervised monocular depth estimation with a vision transformer. In: 2022 international conference on 3D vision (3DV). IEEE, pp 668\u2013678. https:\/\/doi.org\/10.1109\/3DV57658.2022.00077","DOI":"10.1109\/3DV57658.2022.00077"},{"key":"3669_CR5","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2023.107619","volume":"238","author":"Y Liu","year":"2023","unstructured":"Liu Y, Zuo S (2023) Self-supervised monocular depth estimation for gastrointestinal endoscopy. Comput Methods Programs Biomed 238:107619. https:\/\/doi.org\/10.1016\/j.cmpb.2023.107619","journal-title":"Comput Methods Programs Biomed"},{"key":"3669_CR6","doi-asserted-by":"publisher","unstructured":"Huang Z, Wang Y (2025) Occlusion-aware self-supervised monocular depth estimation for weak-texture endoscopic images. In: International conference on intelligent computing. Springer, pp 323\u2013334. https:\/\/doi.org\/10.1007\/978-981-96-9946-9_28","DOI":"10.1007\/978-981-96-9946-9_28"},{"key":"3669_CR7","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2021.102338","volume":"77","author":"S Shao","year":"2022","unstructured":"Shao S, Pei Z, Chen W et al (2022) Self-supervised monocular depth and ego-motion estimation in endoscopy: appearance flow to the rescue. Med Image Anal 77:102338. https:\/\/doi.org\/10.1016\/j.media.2021.102338","journal-title":"Med Image Anal"},{"key":"3669_CR8","doi-asserted-by":"publisher","unstructured":"Zhou L, Luo J et al (2023) Tackling challenges of low-texture and illumination variations for endoscopy self-supervised monocular depth estimation. In: 2023 IEEE international conference on bioinformatics and biomedicine (BIBM). IEEE, pp 2427\u20132432. https:\/\/doi.org\/10.1109\/BIBM58861.2023.10385682","DOI":"10.1109\/BIBM58861.2023.10385682"},{"key":"3669_CR9","doi-asserted-by":"publisher","unstructured":"Rodr\u00edguez-Puigvert J, Batlle VM, Montiel J et al (2023) Lightdepth: single-view depth self-supervision from illumination decline. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 21273\u201321283. https:\/\/doi.org\/10.1109\/ICCV51070.2023.01945","DOI":"10.1109\/ICCV51070.2023.01945"},{"issue":"6","key":"3669_CR10","doi-asserted-by":"publisher","first-page":"1255","DOI":"10.1007\/s11548-025-03371-8","volume":"20","author":"R Daher","year":"2025","unstructured":"Daher R, Vasconcelos F, Stoyanov D (2025) Shades: self-supervised monocular depth estimation through non-lambertian image decomposition. Int J Comput Assist Radiol Surg 20(6):1255\u20131263. https:\/\/doi.org\/10.1007\/s11548-025-03371-8","journal-title":"Int J Comput Assist Radiol Surg"},{"key":"3669_CR11","doi-asserted-by":"publisher","unstructured":"Li B, Liu B, Zhu M et al (2024) Image intrinsic-based unsupervised monocular depth estimation in endoscopy. IEEE J Biomed Health Inform. https:\/\/doi.org\/10.1109\/JBHI.2024.3400804","DOI":"10.1109\/JBHI.2024.3400804"},{"key":"3669_CR12","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109461","volume":"139","author":"X Soria","year":"2023","unstructured":"Soria X, Sappa A, Humanante P et al (2023) Dense extreme inception network for edge detection. Pattern Recogn 139:109461. https:\/\/doi.org\/10.1016\/j.patcog.2023.109461","journal-title":"Pattern Recogn"},{"key":"3669_CR13","doi-asserted-by":"publisher","unstructured":"Jin W, Daher R, Stoyanov D et al (2023) A self-supervised approach for detecting the edges of haustral folds in colonoscopy video. In: MICCAI workshop on data engineering in medical imaging. Springer, pp 56\u201366. https:\/\/doi.org\/10.1007\/978-3-031-44992-5_6","DOI":"10.1007\/978-3-031-44992-5_6"},{"key":"3669_CR14","doi-asserted-by":"publisher","unstructured":"Ju X, Daher R, Caramalau R et al (2024) Segcol challenge: semantic segmentation for tools and fold edges in colonoscopy data. arXiv preprint arXiv:2412.16078. https:\/\/doi.org\/10.48550\/arXiv.2412.16078","DOI":"10.48550\/arXiv.2412.16078"},{"key":"3669_CR15","doi-asserted-by":"publisher","unstructured":"Bui N-T, Hoang D-H, Nguyen Q-T et al (2024) Meganet: multi-scale edge-guided attention network for weak boundary polyp segmentation. In: Proceedings of the IEEE\/CVF winter conference on applications of computer vision, pp 7985\u20137994. https:\/\/doi.org\/10.1109\/WACV57701.2024.00780","DOI":"10.1109\/WACV57701.2024.00780"},{"key":"3669_CR16","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.102956","volume":"90","author":"TL Bobrow","year":"2023","unstructured":"Bobrow TL, Golhar M, Vijayan R et al (2023) Colonoscopy 3D video dataset with paired depth from 2D\u20133D registration. Med Image Anal 90:102956. https:\/\/doi.org\/10.1016\/j.media.2023.102956","journal-title":"Med Image Anal"},{"key":"3669_CR17","doi-asserted-by":"publisher","unstructured":"Rau, A, Bano S, Jin Y et al (2024) Simcol3d \u2014 3d reconstruction during colonoscopy challenge. Med. Image Anal. 96, 103195.https:\/\/doi.org\/10.1016\/j.media.2024.103195","DOI":"10.1016\/j.media.2024.103195"},{"key":"3669_CR18","doi-asserted-by":"publisher","unstructured":"Ozyoruk KB, Gokceler GI, Bobrow TL et al (2021) Endoslam dataset and an unsupervised monocular visual odometry and depth estimation approach for endoscopic videos. Med. Image Anal. 71, 102058. https:\/\/doi.org\/10.1016\/j.media.2021.102058","DOI":"10.1016\/j.media.2021.102058"},{"key":"3669_CR19","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2024.109038","volume":"181","author":"BH Jeong","year":"2024","unstructured":"Jeong BH, Kim HK et al (2024) Depth estimation from monocular endoscopy using simulation and image transfer approach. Comput Biol Med 181:109038. https:\/\/doi.org\/10.1016\/j.compbiomed.2024.109038","journal-title":"Comput Biol Med"},{"key":"3669_CR20","doi-asserted-by":"publisher","unstructured":"Rau A, Bhattarai B, Agapito L et al (2023) Task-guided domain gap reduction for monocular depth prediction in endoscopy. In: MICCAI workshop on data engineering in medical imaging. Springer, pp 111\u2013122. https:\/\/doi.org\/10.1007\/978-3-031-44992-5_11","DOI":"10.1007\/978-3-031-44992-5_11"},{"issue":"1","key":"3669_CR21","doi-asserted-by":"publisher","first-page":"283","DOI":"10.1038\/s41597-020-00622-y","volume":"7","author":"H Borgli","year":"2020","unstructured":"Borgli H, Thambawita V, Smedsrud PH et al (2020) HyperKvasir, a comprehensive multi-class image and video dataset for gastrointestinal endoscopy. Sci Data 7(1):283. https:\/\/doi.org\/10.1038\/s41597-020-00622-y","journal-title":"Sci Data"},{"key":"3669_CR22","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2024.3423791","author":"Q He","year":"2024","unstructured":"He Q, Feng G et al (2024) Monolot: self-supervised monocular depth estimation in low-texture scenes for automatic robotic endoscopy. IEEE J Biomed Health Inform. https:\/\/doi.org\/10.1109\/JBHI.2024.3423791","journal-title":"IEEE J Biomed Health Inform"},{"issue":"1","key":"3669_CR23","doi-asserted-by":"publisher","first-page":"671","DOI":"10.1038\/s41597-023-02564-7","volume":"10","author":"P Azagra","year":"2023","unstructured":"Azagra P, Sostres C, Ferr\u00e1ndez \u00c1 et al (2023) Endomapper dataset of complete calibrated endoscopy procedures. Sci Data 10(1):671. https:\/\/doi.org\/10.1038\/s41597-023-02564-7","journal-title":"Sci Data"},{"key":"3669_CR24","unstructured":"Eigen D, Puhrsch C, Fergus R (2014) Depth map prediction from a single image using a multi-scale deep network. In: Advances in neural information processing systems, vol 27"},{"key":"3669_CR25","unstructured":"Grupp M (2017) evo: Python package for the evaluation of odometry and SLAM. https:\/\/github.com\/MichaelGrupp\/evo"},{"key":"3669_CR26","doi-asserted-by":"publisher","unstructured":"Allan M, Mcleod J, Wang C et al (2021) Stereo correspondence and reconstruction of endoscopic data challenge. arXiv preprint arXiv:2101.01133. https:\/\/doi.org\/10.48550\/arXiv.2101.01133","DOI":"10.48550\/arXiv.2101.01133"}],"container-title":["International Journal of Computer Assisted Radiology and Surgery"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11548-026-03669-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11548-026-03669-1","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11548-026-03669-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T13:20:09Z","timestamp":1786108809000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11548-026-03669-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,10]]},"references-count":26,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2026,6]]}},"alternative-id":["3669"],"URL":"https:\/\/doi.org\/10.1007\/s11548-026-03669-1","relation":{},"ISSN":["1861-6429"],"issn-type":[{"value":"1861-6429","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,10]]},"assertion":[{"value":"15 January 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 April 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 May 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare that they have no conflict of interest.","order":1,"name":"Ethics","label":"Conflict of interest","group":{"name":"EthicsHeading","label":"Declarations"}}]}}