{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T23:28:23Z","timestamp":1786490903181,"version":"build-2736575974"},"reference-count":60,"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"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Medical Image Analysis"],"published-print":{"date-parts":[[2026,11]]},"DOI":"10.1016\/j.media.2026.104231","type":"journal-article","created":{"date-parts":[[2026,7,26]],"date-time":"2026-07-26T13:31:38Z","timestamp":1785072698000},"page":"104231","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Causality-inspired representation learning with spatiotemporal memory for polyp detection in endoscopic videos"],"prefix":"10.1016","volume":"114","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-9602-0535","authenticated-orcid":false,"given":"Zhuo","family":"Hu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Changjin","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qi","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaopu","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cheng","family":"Xue","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guangquan","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yudong","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"1","key":"10.1016\/j.media.2026.104231_b1","doi-asserted-by":"crossref","first-page":"75","DOI":"10.1038\/s41597-023-01981-y","article-title":"A multi-centre polyp detection and segmentation dataset for generalisability assessment","volume":"10","author":"Ali","year":"2023","journal-title":"Sci. Data"},{"key":"10.1016\/j.media.2026.104231_b2","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1016\/j.compmedimag.2015.02.007","article-title":"WM-DOVA maps for accurate polyp highlighting in colonoscopy: Validation vs. saliency maps from physicians","volume":"43","author":"Bernal","year":"2015","journal-title":"Comput. Med. Imaging Graph."},{"issue":"5","key":"10.1016\/j.media.2026.104231_b3","doi-asserted-by":"crossref","first-page":"378","DOI":"10.1159\/000525345","article-title":"Frame-by-frame analysis of a commercially available artificial intelligence polyp detection system in full-length colonoscopies","volume":"103","author":"Brand","year":"2022","journal-title":"Digestion"},{"issue":"5","key":"10.1016\/j.media.2026.104231_b4","doi-asserted-by":"crossref","first-page":"477","DOI":"10.1002\/ueg2.12235","article-title":"Development and evaluation of a deep learning model to improve the usability of polyp detection systems during interventions","volume":"10","author":"Brand","year":"2022","journal-title":"United Eur. Gastroenterol. J."},{"issue":"3","key":"10.1016\/j.media.2026.104231_b5","first-page":"229","article-title":"Global cancer statistics 2022: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries","volume":"74","author":"Bray","year":"2024","journal-title":"CA: Cancer J. Clin."},{"key":"10.1016\/j.media.2026.104231_b6","series-title":"European Conference on Computer Vision","first-page":"213","article-title":"End-to-end object detection with transformers","author":"Carion","year":"2020"},{"key":"10.1016\/j.media.2026.104231_b7","doi-asserted-by":"crossref","unstructured":"Chen, Y., Cao, Y., Hu, H., Wang, L., 2020. Memory enhanced global-local aggregation for video object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 10337\u201310346.","DOI":"10.1109\/CVPR42600.2020.01035"},{"key":"10.1016\/j.media.2026.104231_b8","doi-asserted-by":"crossref","unstructured":"Deng, J., Pan, Y., Yao, T., Zhou, W., Li, H., Mei, T., 2019. Relation distillation networks for video object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 7023\u20137032.","DOI":"10.1109\/ICCV.2019.00712"},{"issue":"2","key":"10.1016\/j.media.2026.104231_b9","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3762179","article-title":"Deep causal learning: Representation, discovery and inference","volume":"58","author":"Deng","year":"2025","journal-title":"ACM Comput. Surv."},{"key":"10.1016\/j.media.2026.104231_b10","doi-asserted-by":"crossref","unstructured":"Duan, K., Bai, S., Xie, L., Qi, H., Huang, Q., Tian, Q., 2019. Centernet: Keypoint triplets for object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 6569\u20136578.","DOI":"10.1109\/ICCV.2019.00667"},{"key":"10.1016\/j.media.2026.104231_b11","series-title":"Biomedical image analysis competitions: The state of current participation practice","author":"Eisenmann","year":"2022"},{"issue":"11","key":"10.1016\/j.media.2026.104231_b12","doi-asserted-by":"crossref","first-page":"1397","DOI":"10.1080\/00365521.2022.2085059","article-title":"A video based benchmark data set (ENDOTEST) to evaluate computer-aided polyp detection systems","volume":"57","author":"Fitting","year":"2022","journal-title":"Scand. J. Gastroenterol."},{"key":"10.1016\/j.media.2026.104231_b13","series-title":"EndoCV@ ISBI","first-page":"101","article-title":"Detection of polyps during colonoscopy ProcedureUsing YOLOv5 network","author":"Gan","year":"2021"},{"key":"10.1016\/j.media.2026.104231_b14","series-title":"A causality-inspired model for intima-media thickening assessment in ultrasound videos","author":"Gao","year":"2025"},{"key":"10.1016\/j.media.2026.104231_b15","series-title":"Yolox:exceeding yolo series in 2021","author":"Ge","year":"2021"},{"key":"10.1016\/j.media.2026.104231_b16","doi-asserted-by":"crossref","unstructured":"Girshick, R., 2015. Fast r-cnn. In: Proceedings of the IEEE International Conference on Computer Vision. pp. 1440\u20131448.","DOI":"10.1109\/ICCV.2015.169"},{"issue":"1","key":"10.1016\/j.media.2026.104231_b17","first-page":"47","article-title":"Cancer incidence and mortality in China, 2022","volume":"4","author":"Han","year":"2024","journal-title":"J. Natl. Cancer Cent."},{"key":"10.1016\/j.media.2026.104231_b18","series-title":"Causal Inference in Statistics, Social, and Biomedical Sciences","author":"Imbens","year":"2015"},{"key":"10.1016\/j.media.2026.104231_b19","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2024.103307","article-title":"Validating polyp and instrument segmentation methods in colonoscopy through medico 2020 and medai 2021 challenges","volume":"99","author":"Jha","year":"2025","journal-title":"Med. Image Anal."},{"key":"10.1016\/j.media.2026.104231_b20","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"44","article-title":"Yona: You only need one adjacent reference-frame for accurate and fast video polyp detection","author":"Jiang","year":"2023"},{"key":"10.1016\/j.media.2026.104231_b21","series-title":"Ultralytics YOLO26","author":"Jocher","year":"2026"},{"key":"10.1016\/j.media.2026.104231_b22","doi-asserted-by":"crossref","DOI":"10.1016\/j.compbiomed.2024.109601","article-title":"MEFA-net: A mask enhanced feature aggregation network for polyp segmentation","volume":"186","author":"Ke","year":"2025","journal-title":"Comput. Biol. Med."},{"issue":"10","key":"10.1016\/j.media.2026.104231_b23","doi-asserted-by":"crossref","first-page":"985","DOI":"10.5152\/tjg.2023.22491","article-title":"A systematic review and meta-analysis of convolutional neural network in the diagnosis of colorectal polyps and cancer","volume":"34","author":"Keshtkar","year":"2023","journal-title":"Turk. J. Gastroenterol."},{"issue":"2","key":"10.1016\/j.media.2026.104231_b24","doi-asserted-by":"crossref","first-page":"26","DOI":"10.3390\/jimaging9020026","article-title":"A real-time polyp-detection system with clinical application in colonoscopy using deep convolutional neural networks","volume":"9","author":"Krenzer","year":"2023","journal-title":"J. Imaging"},{"key":"10.1016\/j.media.2026.104231_b25","series-title":"Annual Conference on Medical Image Understanding and Analysis","first-page":"276","article-title":"Classification of gastroscopy images under extreme class imbalance: A deep learning pipeline","author":"Krenzer","year":"2025"},{"issue":"1","key":"10.1016\/j.media.2026.104231_b26","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1186\/s12880-023-01007-4","article-title":"Automated classification of polyps using deep learning architectures and few-shot learning","volume":"23","author":"Krenzer","year":"2023","journal-title":"BMC Med. Imaging"},{"key":"10.1016\/j.media.2026.104231_b27","article-title":"Enhancing transformer-based architectures with geometric deep learning for colonoscopic polyp size classification using transfer learning","author":"Krenzer","year":"2025","journal-title":"Artif. Intell. Med."},{"key":"10.1016\/j.media.2026.104231_b28","series-title":"EndoCV@ ISBI","first-page":"58","article-title":"Endoscopic detection and segmentation of gastroenterological diseases with deep convolutional neural networks","author":"Krenzer","year":"2020"},{"issue":"1","key":"10.1016\/j.media.2026.104231_b29","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1186\/s12938-022-01001-x","article-title":"Fast machine learning annotation in the medical domain: A semi-automated video annotation tool for gastroenterologists","volume":"21","author":"Krenzer","year":"2022","journal-title":"BioMed. Eng. OnLine"},{"key":"10.1016\/j.media.2026.104231_b30","doi-asserted-by":"crossref","first-page":"2497","DOI":"10.1109\/TMM.2026.3651028","article-title":"Causality-inspired graph neural networks for cross-modal retrieval","volume":"28","author":"Li","year":"2026","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.media.2026.104231_b31","doi-asserted-by":"crossref","DOI":"10.1016\/j.bspc.2025.108860","article-title":"An efficient object detection network for early polyp detection","volume":"113","author":"Liao","year":"2026","journal-title":"Biomed. Signal Process. Control."},{"key":"10.1016\/j.media.2026.104231_b32","series-title":"European Conference on Computer Vision","first-page":"740","article-title":"Microsoft coco: Common objects in context","author":"Lin","year":"2014"},{"key":"10.1016\/j.media.2026.104231_b33","series-title":"CCF Conference on Computer Supported Cooperative Work and Social Computing","first-page":"390","article-title":"TEmory: A temporal-memory approach to weakly supervised colonic polyp frame detection","author":"Liu","year":"2024"},{"key":"10.1016\/j.media.2026.104231_b34","doi-asserted-by":"crossref","first-page":"2351","DOI":"10.1109\/TIP.2025.3558089","article-title":"CRCL: Causal representation consistency learning for anomaly detection in surveillance videos","volume":"34","author":"Liu","year":"2025","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.media.2026.104231_b35","doi-asserted-by":"crossref","unstructured":"Lv, F., Liang, J., Li, S., Zang, B., Liu, C.H., Wang, Z., Liu, D., 2022. Causality inspired representation learning for domain generalization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 8046\u20138056.","DOI":"10.1109\/CVPR52688.2022.00788"},{"key":"10.1016\/j.media.2026.104231_b36","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"387","article-title":"LDPolypVideo benchmark: A large-scale colonoscopy video dataset of diverse polyps","author":"Ma","year":"2021"},{"issue":"8","key":"10.1016\/j.media.2026.104231_b37","doi-asserted-by":"crossref","first-page":"2027","DOI":"10.1053\/j.gastro.2018.04.003","article-title":"Artificial intelligence-assisted polyp detection for colonoscopy: initial experience","volume":"154","author":"Misawa","year":"2018","journal-title":"Gastroenterology"},{"issue":"4","key":"10.1016\/j.media.2026.104231_b38","doi-asserted-by":"crossref","first-page":"960","DOI":"10.1016\/j.gie.2020.07.060","article-title":"Development of a computer-aided detection system for colonoscopy and a publicly accessible large colonoscopy video database (with video)","volume":"93","author":"Misawa","year":"2021","journal-title":"Gastrointest Endosc."},{"key":"10.1016\/j.media.2026.104231_b39","series-title":"Y-net: A deep convolutional neural network for polyp detection","author":"Mohammed","year":"2018"},{"issue":"1","key":"10.1016\/j.media.2026.104231_b40","doi-asserted-by":"crossref","first-page":"336","DOI":"10.1038\/s41420-025-02593-8","article-title":"Epithelial-mesenchymal transition in colorectal cancer metastasis and progression: Molecular mechanisms and therapeutic strategies","volume":"11","author":"Nie","year":"2025","journal-title":"Cell Death Discov."},{"key":"10.1016\/j.media.2026.104231_b41","unstructured":"Peng, Y., Li, H., Wu, P., Zhang, Y., Sun, X., Wu, F., 2025. D-FINE: Redefine regression task of DETRs as fine-grained distribution refinement. In: International Conference on Learning Representations. vol. 2025, pp. 44015\u201344031."},{"issue":"5","key":"10.1016\/j.media.2026.104231_b42","doi-asserted-by":"crossref","first-page":"400","DOI":"10.1001\/jama.2024.22975","article-title":"Adenoma detection rates by physicians and subsequent colorectal cancer risk","volume":"333","author":"Pilonis","year":"2025","journal-title":"Jama"},{"key":"10.1016\/j.media.2026.104231_b43","series-title":"Polyp detection in colonoscopy images using deep learning and bootstrap aggregation","author":"Polat","year":"2021"},{"issue":"5","key":"10.1016\/j.media.2026.104231_b44","doi-asserted-by":"crossref","first-page":"612","DOI":"10.1109\/JPROC.2021.3058954","article-title":"Toward causal representation learning","volume":"109","author":"Sch\u00f6lkopf","year":"2021","journal-title":"Proc. IEEE"},{"key":"10.1016\/j.media.2026.104231_b45","doi-asserted-by":"crossref","first-page":"1050","DOI":"10.1109\/TIFS.2026.3652013","article-title":"Casper: A causality-inspired defense with confounder against label inference attacks in vertical split federated learning","volume":"21","author":"Shen","year":"2026","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"issue":"3","key":"10.1016\/j.media.2026.104231_b46","first-page":"233","article-title":"Colorectal cancer statistics, 2023","volume":"73","author":"Siegel","year":"2023","journal-title":"CA: Cancer J. Clin."},{"key":"10.1016\/j.media.2026.104231_b47","doi-asserted-by":"crossref","unstructured":"Tan, M., Pang, R., Le, Q.V., 2020. Efficientdet: Scalable and efficient object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 10781\u201310790.","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"10.1016\/j.media.2026.104231_b48","doi-asserted-by":"crossref","unstructured":"Tian, Z., Shen, C., Chen, H., He, T., 2019. Fcos: Fully convolutional one-stage object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 9627\u20139636.","DOI":"10.1109\/ICCV.2019.00972"},{"issue":"01","key":"10.1016\/j.media.2026.104231_b49","doi-asserted-by":"crossref","first-page":"63","DOI":"10.1055\/a-2147-0571","article-title":"Direct comparison of multiple computer-aided polyp detection systems","volume":"56","author":"Troya","year":"2024","journal-title":"Endoscopy"},{"key":"10.1016\/j.media.2026.104231_b50","doi-asserted-by":"crossref","DOI":"10.3389\/fonc.2024.1417862","article-title":"A complete benchmark for polyp detection, segmentation and classification in colonoscopy images","volume":"14","author":"Tudela","year":"2024","journal-title":"Front. Oncol."},{"issue":"4","key":"10.1016\/j.media.2026.104231_b51","doi-asserted-by":"crossref","first-page":"1252","DOI":"10.1053\/j.gastro.2020.06.023","article-title":"Lower adenoma miss rate of computer-aided detection-assisted colonoscopy vs routine white-light colonoscopy in a prospective tandem study","volume":"159","author":"Wang","year":"2020","journal-title":"Gastroenterology"},{"key":"10.1016\/j.media.2026.104231_b52","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2024.103384","article-title":"Tsdetector: Temporal\u2013spatial self-correction collaborative learning for colonoscopy video detection","volume":"100","author":"Wang","year":"2025","journal-title":"Med. Image Anal."},{"issue":"4","key":"10.1016\/j.media.2026.104231_b53","doi-asserted-by":"crossref","first-page":"609","DOI":"10.1007\/s10389-023-01831-6","article-title":"The global, regional, and national burden of colorectal cancer in 204 countries and territories from 1990 to 2019","volume":"32","author":"Wu","year":"2024","journal-title":"J. Public Health"},{"key":"10.1016\/j.media.2026.104231_b54","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"302","article-title":"Multi-frame collaboration for effective endoscopic video polyp detection via spatial-temporal feature transformation","author":"Wu","year":"2021"},{"key":"10.1016\/j.media.2026.104231_b55","doi-asserted-by":"crossref","DOI":"10.1016\/j.bspc.2024.107326","article-title":"Yolo-ob: an improved anchor-free real-time multiscale colon polyp detector in colonoscopy","volume":"103","author":"Yang","year":"2025","journal-title":"Biomed. Signal Process. Control."},{"issue":"11","key":"10.1016\/j.media.2026.104231_b56","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pmed.1002683","article-title":"Variable generalization performance of a deep learning model to detect pneumonia in chest radiographs: A cross-sectional study","volume":"15","author":"Zech","year":"2018","journal-title":"PLoS Med."},{"issue":"3","key":"10.1016\/j.media.2026.104231_b57","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0214133","article-title":"Real-time gastric polyp detection using convolutional neural networks","volume":"14","author":"Zhang","year":"2019","journal-title":"PloS One"},{"key":"10.1016\/j.media.2026.104231_b58","first-page":"655","article-title":"Causal intervention for weakly-supervised semantic segmentation","volume":"33","author":"Zhang","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"6","key":"10.1016\/j.media.2026.104231_b59","doi-asserted-by":"crossref","first-page":"7853","DOI":"10.1109\/TPAMI.2022.3223955","article-title":"TransVOD: End-to-end video object detection with spatial-temporal transformers","volume":"45","author":"Zhou","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.media.2026.104231_b60","doi-asserted-by":"crossref","unstructured":"Zhu, X., Wang, Y., Dai, J., Yuan, L., Wei, Y., 2017. Flow-guided feature aggregation for video object detection. In: Proceedings of the IEEE International Conference on Computer Vision. pp. 408\u2013417.","DOI":"10.1109\/ICCV.2017.52"}],"container-title":["Medical Image Analysis"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1361841526003002?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1361841526003002?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T22:38:38Z","timestamp":1786487918000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1361841526003002"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":60,"alternative-id":["S1361841526003002"],"URL":"https:\/\/doi.org\/10.1016\/j.media.2026.104231","relation":{},"ISSN":["1361-8415"],"issn-type":[{"value":"1361-8415","type":"print"}],"subject":[],"published":{"date-parts":[[2026,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Causality-inspired representation learning with spatiotemporal memory for polyp detection in endoscopic videos","name":"articletitle","label":"Article Title"},{"value":"Medical Image Analysis","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.media.2026.104231","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"104231"}}