{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T09:06:17Z","timestamp":1784279177125,"version":"3.55.0"},"reference-count":44,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013804","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100013804","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Pattern Recognition"],"published-print":{"date-parts":[[2026,11]]},"DOI":"10.1016\/j.patcog.2026.113646","type":"journal-article","created":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T07:30:09Z","timestamp":1775633409000},"page":"113646","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PC","title":["PolyS-Net: A joint learning framework for depth-aware and scale-aware polyp size estimation"],"prefix":"10.1016","volume":"179","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5664-6992","authenticated-orcid":false,"given":"Sijia","family":"Du","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Ding","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yaqi","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chen","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruilan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huiyu","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qingwei","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaobo","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9715-6674","authenticated-orcid":false,"given":"Dahong","family":"Qian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"1","key":"10.1016\/j.patcog.2026.113646_bib0001","article-title":"Cancer statistics, 2023","volume":"73","author":"Siegel","year":"2023","journal-title":"CA Cancer J. Clin."},{"issue":"03","key":"10.1016\/j.patcog.2026.113646_bib0002","doi-asserted-by":"crossref","first-page":"270","DOI":"10.1055\/s-0043-102569","article-title":"Colorectal polypectomy and endoscopic mucosal resection (EMR): european society of gastrointestinal endoscopy (ESGE) clinical guideline","volume":"49","author":"Ferlitsch","year":"2017","journal-title":"Endoscopy"},{"issue":"5","key":"10.1016\/j.patcog.2026.113646_bib0003","doi-asserted-by":"crossref","first-page":"485","DOI":"10.5946\/ce.2017.183","article-title":"Mis-sizing of adenomatous polyps is common among endoscopists and impacts colorectal cancer screening recommendations","volume":"51","author":"Pham","year":"2018","journal-title":"Clin. Endosc."},{"key":"10.1016\/j.patcog.2026.113646_bib0004","article-title":"Endoscopic size measurement of colorectal polyps: a systematic review of techniques","author":"Taghiakbari","year":"2025","journal-title":"Endoscopy"},{"issue":"05","key":"10.1016\/j.patcog.2026.113646_bib0005","doi-asserted-by":"crossref","first-page":"E602","DOI":"10.1055\/a-0577-2798","article-title":"A structured light laser probe for gastrointestinal polyp size measurement: a preliminary comparative study","volume":"6","author":"Visentini-Scarzanella","year":"2018","journal-title":"Endosc Int Open"},{"issue":"4","key":"10.1016\/j.patcog.2026.113646_bib0006","doi-asserted-by":"crossref","first-page":"652","DOI":"10.1016\/j.gie.2014.01.053","article-title":"Variation in polyp size estimation among endoscopists and impact on surveillance intervals","volume":"80","author":"Chaptini","year":"2014","journal-title":"Gastrointest. Endosc."},{"issue":"3","key":"10.1016\/j.patcog.2026.113646_bib0007","first-page":"289","article-title":"Uncertainty meets 3D-spatial feature in colonoscopic polyp-size determination","volume":"10","author":"Itoh","year":"2022","journal-title":"Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization"},{"issue":"10","key":"10.1016\/j.patcog.2026.113646_bib0008","doi-asserted-by":"crossref","first-page":"1817","DOI":"10.1007\/s11548-021-02477-z","article-title":"Binary polyp-size classification based on deep-learned spatial information","volume":"16","author":"Itoh","year":"2021","journal-title":"Int. J. Comput. Assist. Radiol. Surg."},{"key":"10.1016\/j.patcog.2026.113646_bib0009","doi-asserted-by":"crossref","DOI":"10.1109\/ACCESS.2025.3527720","article-title":"Real-time multi-task deep learning model for polyp detection, characterization, and size estimation","author":"Sunthornwetchapong","year":"2025","journal-title":"IEEE Access"},{"issue":"04","key":"10.1016\/j.patcog.2026.113646_bib0010","doi-asserted-by":"crossref","first-page":"260","DOI":"10.1055\/a-2189-7036","article-title":"A real-time deep learning-based system for colorectal polyp size estimation by white-light endoscopy: development and multicenter prospective validation","volume":"56","author":"Wang","year":"2024","journal-title":"Endoscopy"},{"key":"10.1016\/j.patcog.2026.113646_bib0011","series-title":"2024 IEEE International Symposium on Biomedical Imaging (ISBI)","first-page":"1","article-title":"Estimating polyp size from a single colonoscopy image using a shape-from-shading model","author":"Ruano","year":"2024"},{"key":"10.1016\/j.patcog.2026.113646_bib0012","series-title":"2025 IEEE\/ACM Conference on Connected Health: Applications, Systems and Engineering Technologies (CHASE)","first-page":"159","article-title":"Beyond the diameter: 3D surface area estimation for more accurate polyp sizing","author":"Nabijiang","year":"2025"},{"key":"10.1016\/j.patcog.2026.113646_bib0013","doi-asserted-by":"crossref","first-page":"80575","DOI":"10.1109\/ACCESS.2022.3195241","article-title":"Colonformer: an efficient transformer based method for colon polyp segmentation","volume":"10","author":"Duc","year":"2022","journal-title":"IEEE Access"},{"key":"10.1016\/j.patcog.2026.113646_bib0014","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"263","article-title":"Pranet: parallel reverse attention network for polyp segmentation","author":"Fan","year":"2020"},{"key":"10.1016\/j.patcog.2026.113646_bib0015","doi-asserted-by":"crossref","DOI":"10.1016\/j.compmedimag.2024.102390","article-title":"Leveraging a realistic synthetic database to learn shape-from-shading for estimating the colon depth in colonoscopy images","volume":"115","author":"Ruano","year":"2024","journal-title":"Computer. Med. Imaging Graph."},{"key":"10.1016\/j.patcog.2026.113646_bib0016","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2023.102956","article-title":"Colonoscopy 3D video dataset with paired depth from 2D-3D registration","volume":"90","author":"Bobrow","year":"2023","journal-title":"Med. Image Anal."},{"issue":"4","key":"10.1016\/j.patcog.2026.113646_bib0017","doi-asserted-by":"crossref","first-page":"978","DOI":"10.1109\/TMRB.2023.3320267","article-title":"Bimodal camera pose prediction for endoscopy","volume":"5","author":"Rau","year":"2023","journal-title":"IEEE Trans. Med. Rob. Bionics"},{"key":"10.1016\/j.patcog.2026.113646_bib0018","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"611","article-title":"Towards automated colonoscopy diagnosis: binary polyp size estimation via unsupervised depth learning","author":"Itoh","year":"2018"},{"key":"10.1016\/j.patcog.2026.113646_bib0019","doi-asserted-by":"crossref","DOI":"10.1055\/a-2556-1836","article-title":"Use of artificial intelligence to measure colorectal polyp size without a reference object","volume":"13","author":"Yii","year":"2025","journal-title":"Endosc. Int. Open"},{"issue":"3","key":"10.1016\/j.patcog.2026.113646_bib0020","doi-asserted-by":"crossref","first-page":"266","DOI":"10.1080\/21681163.2021.2012835","article-title":"Depth estimation from single-shot monocular endoscope image using image domain adaptation and edge-aware depth estimation","volume":"10","author":"Oda","year":"2022","journal-title":"Comput. Methods Biomech. Biomed. Eng. Imaging Visual."},{"key":"10.1016\/j.patcog.2026.113646_bib0021","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2023.105989","article-title":"A geometry-aware deep network for depth estimation in monocular endoscopy","volume":"122","author":"Yang","year":"2023","journal-title":"Eng. Appl. Artif. Intell."},{"issue":"3","key":"10.1016\/j.patcog.2026.113646_bib0022","doi-asserted-by":"crossref","first-page":"1623","DOI":"10.1109\/TPAMI.2020.3019967","article-title":"Towards robust monocular depth estimation: mixing datasets for zero-shot cross-dataset transfer","volume":"44","author":"Ranftl","year":"2020","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.113646_bib0023","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"10371","article-title":"Depth anything: unleashing the power of large-scale unlabeled data","author":"Yang","year":"2024"},{"key":"10.1016\/j.patcog.2026.113646_bib0024","unstructured":"S.F. Bhat, R. Birkl, D. Wofk, P. Wonka, M. M\u00fcller, ZoeDepth: Zero-shot transfer by combining relative and metric depth, 2023, arXiv: 2302.12288."},{"key":"10.1016\/j.patcog.2026.113646_bib0025","unstructured":"J.J. Han, A. Acar, C. Henry, J.Y. Wu, Depth anything in medical images: A comparative study, 2024, arXiv: 2401.16600."},{"key":"10.1016\/j.patcog.2026.113646_bib0026","unstructured":"Q. Tian, Z. Chen, H. Liao, X. Huang, L. Li, S. Ourselin, H. Liu, EndoOmni: Zero-shot cross-dataset depth estimation in endoscopy by robust self-learning from noisy labels, 2024, arXiv: 2409.05442."},{"key":"10.1016\/j.patcog.2026.113646_bib0027","unstructured":"A. Bochkovskii, A. Delaunoy, H. Germain, M. Santos, Y. Zhou, S.R. Richter, V. Koltun, Depth pro: Sharp monocular metric depth in less than a second, 2024, arXiv: 2410.02073."},{"key":"10.1016\/j.patcog.2026.113646_bib0028","series-title":"Proceedings of the Asian Conference on Computer Vision","first-page":"922","article-title":"Primedepth: efficient monocular depth estimation with a stable diffusion preimage","author":"Zavadski","year":"2024"},{"key":"10.1016\/j.patcog.2026.113646_bib0029","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"10684","article-title":"High-resolution image synthesis with latent diffusion models","author":"Rombach","year":"2022"},{"issue":"2","key":"10.1016\/j.patcog.2026.113646_bib0030","doi-asserted-by":"crossref","first-page":"1228","DOI":"10.1109\/TCSVT.2023.3292995","article-title":"Multi-task learning with multi-query transformer for dense prediction","volume":"34","author":"Xu","year":"2023","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.patcog.2026.113646_bib0031","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"779","article-title":"You only look once: unified, real-time object detection","author":"Redmon","year":"2016"},{"key":"10.1016\/j.patcog.2026.113646_bib0032","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"4015","article-title":"Segment anything","author":"Kirillov","year":"2023"},{"issue":"1","key":"10.1016\/j.patcog.2026.113646_bib0033","doi-asserted-by":"crossref","first-page":"918","DOI":"10.1038\/s41597-025-05251-x","article-title":"Polyp-Size: a precise endoscopic dataset for AI-driven polyp sizing","volume":"12","author":"Song","year":"2025","journal-title":"Sci. Data"},{"issue":"1","key":"10.1016\/j.patcog.2026.113646_bib0034","doi-asserted-by":"crossref","first-page":"539","DOI":"10.1038\/s41597-024-03359-0","article-title":"REAL-Colon: A dataset for developing real-world AI applications in colonoscopy","volume":"11","author":"Biffi","year":"2024","journal-title":"Sci. Data"},{"key":"10.1016\/j.patcog.2026.113646_bib0035","series-title":"Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision","first-page":"2149","article-title":"Resolution-robust large mask inpainting with fourier convolutions","author":"Suvorov","year":"2022"},{"key":"10.1016\/j.patcog.2026.113646_bib0036","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"9492","article-title":"Repurposing diffusion-based image generators for monocular depth estimation","author":"Ke","year":"2024"},{"key":"10.1016\/j.patcog.2026.113646_bib0037","doi-asserted-by":"crossref","first-page":"21875","DOI":"10.52202\/079017-0688","article-title":"Depth anything v2","volume":"37","author":"Yang","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2026.113646_bib0038","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2022.109297","article-title":"Learning depth via leveraging semantics: self-supervised monocular depth estimation with both implicit and explicit semantic guidance","volume":"137","author":"Li","year":"2023","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113646_bib0039","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.110770","article-title":"Graph semantic information for self-supervised monocular depth estimation","volume":"156","author":"Zhang","year":"2024","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113646_bib0040","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"4696","article-title":"Augmenting colonoscopy using extended and directional cyclegan for lossy image translation","author":"Mathew","year":"2020"},{"key":"10.1016\/j.patcog.2026.113646_bib0041","series-title":"2025 IEEE International Conference on Robotics and Automation (ICRA)","first-page":"15776","article-title":"Polyp-gen: realistic and diverse polyp image generation for endoscopic dataset expansion","author":"Liu","year":"2025"},{"key":"10.1016\/j.patcog.2026.113646_bib0042","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.111416","article-title":"Generative feature style augmentation for domain generalization in medical image segmentation","volume":"162","author":"Huang","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113646_bib0043","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"20697","article-title":"Dust3r: geometric 3d vision made easy","author":"Wang","year":"2024"},{"key":"10.1016\/j.patcog.2026.113646_bib0044","series-title":"Proceedings of the Computer Vision and Pattern Recognition Conference","first-page":"10394","article-title":"Boost the inference with co-training: a depth-guided mutual learning framework for semi-supervised medical polyp segmentation","author":"Li","year":"2025"}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326006114?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326006114?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T08:27:37Z","timestamp":1784276857000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320326006114"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":44,"alternative-id":["S0031320326006114"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113646","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"PolyS-Net: A joint learning framework for depth-aware and scale-aware polyp size estimation","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113646","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"113646"}}