{"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/learning-to-segment-breast-biopsy-whole-slide","title":"Learning to Segment Breast Biopsy Whole Slide Images","arxiv_id":"1709.02554","date":"2017-09-08","proceeding":null,"authors":["Sachin Mehta","Ezgi Mercan","Jamen Bartlett","Donald Weaver","Joann Elmore","Linda Shapiro"],"abstract":"We trained and applied an encoder-decoder model to semantically segment\nbreast biopsy images into biologically meaningful tissue labels. Since\nconventional encoder-decoder networks cannot be applied directly on large\nbiopsy images and the different sized structures in biopsies present novel\nchallenges, we propose four modifications: (1) an input-aware encoding block to\ncompensate for information loss, (2) a new dense connection pattern between\nencoder and decoder, (3) dense and sparse decoders to combine multi-level\nfeatures, (4) a multi-resolution network that fuses the results of\nencoder-decoders run on different resolutions. Our model outperforms a\nfeature-based approach and conventional encoder-decoders from the literature.\nWe use semantic segmentations produced with our model in an automated diagnosis\ntask and obtain higher accuracies than a baseline approach that employs an SVM\nfor feature-based segmentation, both using the same segmentation-based\ndiagnostic features.","url_abs":"http://arxiv.org/abs/1709.02554v2","url_pdf":"http://arxiv.org/pdf/1709.02554v2.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":"learning-to-segment-breast-biopsy-whole-slide","repo_url":"https://github.com/sacmehta/WSISegmentation","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"diagnostic","task_name":"Diagnostic"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"whole-slide-images","task_name":"whole slide images"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}