{"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/rotation-equivariant-cnns-for-digital","title":"Rotation Equivariant CNNs for Digital Pathology","arxiv_id":"1806.03962","date":"2018-06-08","proceeding":null,"authors":["Bastiaan S. Veeling","Jasper Linmans","Jim Winkens","Taco Cohen","Max Welling"],"abstract":"We propose a new model for digital pathology segmentation, based on the\nobservation that histopathology images are inherently symmetric under rotation\nand reflection. Utilizing recent findings on rotation equivariant CNNs, the\nproposed model leverages these symmetries in a principled manner. We present a\nvisual analysis showing improved stability on predictions, and demonstrate that\nexploiting rotation equivariance significantly improves tumor detection\nperformance on a challenging lymph node metastases dataset. We further present\na novel derived dataset to enable principled comparison of machine learning\nmodels, in combination with an initial benchmark. Through this dataset, the\ntask of histopathology diagnosis becomes accessible as a challenging benchmark\nfor fundamental machine learning research.","url_abs":"http://arxiv.org/abs/1806.03962v1","url_pdf":"http://arxiv.org/pdf/1806.03962v1.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":"rotation-equivariant-cnns-for-digital","repo_url":"https://github.com/basveeling/keras_gcnn","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"rotation-equivariant-cnns-for-digital","repo_url":"https://github.com/basveeling/pcam","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"rotation-equivariant-cnns-for-digital","repo_url":"https://github.com/basveeling/keras-gcnn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"rotation-equivariant-cnns-for-digital","repo_url":"https://github.com/eb00/pcam_analysis","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"machine-learning","task_name":"BIG-bench Machine Learning"},{"task_slug":"breast-tumour-classification","task_name":"Breast Tumour Classification"}],"methods":[],"datasets_introduced":[{"slug":"pcam","name":"PCam","full_name":"PatchCamelyon"}],"methods_introduced":[],"results":[{"leaderboard":"/sota/breast-tumour-classification-on-pcam","task":"Breast Tumour Classification","dataset":"PCam","model":"p4m-DenseNet (D4)","rank_in_archive_order":8,"of":16,"metrics":{"AUC":"0.963"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1806.03962","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}