BACH: grand challenge on breast cancer histology imagesDownload PDF

11 Apr 2019 (modified: 29 Sept 2024)MIDL Abstract 2019Readers: Everyone
Keywords: Breast cancer, Histology, Digital pathology, Challenge, Deep learning
TL;DR: Summary of the Grand Challenge on BreAst Cancer Histology images (BACH), focused on classification and localization of clinically relevant histopathological classes in microscopy and whole-slide images.
Abstract: The Grand Challenge on BreAst Cancer Histology images (BACH) aimed at the classification and localization of clinically relevant histopathological classes in microscopy and whole-slide images from a large annotated dataset, specifically compiled and made publicly available for the challenge. A total of 64 submissions, out of 677 registrations, effectively entered the competition. The submitted algorithms improved the state-of-the-art in automatic classification of breast cancer with microscopy images to an accuracy of 87%, with convolutional neural networks being the most successful methodology. Detailed analysis of the results allowed the identification of remaining challenges in the field and recommendations for future developments. The BACH dataset remains publicly available to promote further improvements to the field of automatic classification in digital pathology.
Code Of Conduct: I have read and accept the code of conduct.
Remove If Rejected: Remove submission from public view if paper is rejected.
Link: (currently under review for Medical Image Analysis)
Community Implementations: [![CatalyzeX](/images/catalyzex_icon.svg) 1 code implementation](https://www.catalyzex.com/paper/bach-grand-challenge-on-breast-cancer/code)
3 Replies

Loading