{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/angiodysplasia-detection-and-localization","title":"Angiodysplasia Detection and Localization Using Deep Convolutional Neural Networks","arxiv_id":"1804.08024","date":"2018-04-21","proceeding":null,"authors":["Alexey Shvets","Vladimir Iglovikov","Alexander Rakhlin","Alexandr A. Kalinin"],"abstract":"Accurate detection and localization for angiodysplasia lesions is an\nimportant problem in early stage diagnostics of gastrointestinal bleeding and\nanemia. Gold-standard for angiodysplasia detection and localization is\nperformed using wireless capsule endoscopy. This pill-like device is able to\nproduce thousand of high enough resolution images during one passage through\ngastrointestinal tract. In this paper we present our winning solution for\nMICCAI 2017 Endoscopic Vision SubChallenge: Angiodysplasia Detection and\nLocalization its further improvements over the state-of-the-art results using\nseveral novel deep neural network architectures. It address the binary\nsegmentation problem, where every pixel in an image is labeled as an\nangiodysplasia lesions or background. Then, we analyze connected component of\neach predicted mask. Based on the analysis we developed a classifier that\npredict angiodysplasia lesions (binary variable) and a detector for their\nlocalization (center of a component). In this setting, our approach outperforms\nother methods in every task subcategory for angiodysplasia detection and\nlocalization thereby providing state-of-the-art results for these problems. The\nsource code for our solution is made publicly available at\nhttps://github.com/ternaus/angiodysplasia-segmentatio","url_abs":"http://arxiv.org/abs/1804.08024v1","url_pdf":"http://arxiv.org/pdf/1804.08024v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"angiodysplasia-detection-and-localization","repo_url":"https://github.com/ternaus/angiodysplasia-segmentation","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}