{"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/detecting-cancer-metastases-on-gigapixel","title":"Detecting Cancer Metastases on Gigapixel Pathology Images","arxiv_id":"1703.02442","date":"2017-03-03","proceeding":null,"authors":["Yun Liu","Krishna Gadepalli","Mohammad Norouzi","George E. Dahl","Timo Kohlberger","Aleksey Boyko","Subhashini Venugopalan","Aleksei Timofeev","Philip Q. Nelson","Greg S. Corrado","Jason D. Hipp","Lily Peng","Martin C. Stumpe"],"abstract":"Each year, the treatment decisions for more than 230,000 breast cancer\npatients in the U.S. hinge on whether the cancer has metastasized away from the\nbreast. Metastasis detection is currently performed by pathologists reviewing\nlarge expanses of biological tissues. This process is labor intensive and\nerror-prone. We present a framework to automatically detect and localize tumors\nas small as 100 x 100 pixels in gigapixel microscopy images sized 100,000 x\n100,000 pixels. Our method leverages a convolutional neural network (CNN)\narchitecture and obtains state-of-the-art results on the Camelyon16 dataset in\nthe challenging lesion-level tumor detection task. At 8 false positives per\nimage, we detect 92.4% of the tumors, relative to 82.7% by the previous best\nautomated approach. For comparison, a human pathologist attempting exhaustive\nsearch achieved 73.2% sensitivity. We achieve image-level AUC scores above 97%\non both the Camelyon16 test set and an independent set of 110 slides. In\naddition, we discover that two slides in the Camelyon16 training set were\nerroneously labeled normal. Our approach could considerably reduce false\nnegative rates in metastasis detection.","url_abs":"http://arxiv.org/abs/1703.02442v2","url_pdf":"http://arxiv.org/pdf/1703.02442v2.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":"detecting-cancer-metastases-on-gigapixel","repo_url":"https://github.com/Reemr/Cancer-detection","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"detecting-cancer-metastases-on-gigapixel","repo_url":"https://github.com/Srinidhi-kv/Cancer_metastasis_detection","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"detecting-cancer-metastases-on-gigapixel","repo_url":"https://github.com/chenxd2/Detecting-Cancer-Metastases-on-Gigapixel-Pathology-Images","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"detecting-cancer-metastases-on-gigapixel","repo_url":"https://github.com/kira-95/adl_cancer_detection","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"detecting-cancer-metastases-on-gigapixel","repo_url":"https://github.com/olahosa/adl_cancer_detection","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"detecting-cancer-metastases-on-gigapixel","repo_url":"https://github.com/virabehnam/CAMELYON16-Breast-Cancer-Detection","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"medical-object-detection","task_name":"Medical Object Detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/medical-object-detection-on-barretts","task":"Medical Object Detection","dataset":"Barrett’s Esophagus","model":"Sliding Window","rank_in_archive_order":2,"of":2,"metrics":{"Mean Accuracy":"74%"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1703.02442","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}