A completely annotated whole slide image dataset of canine breast cancer to aid human breast cancer research

TL;DR

This paper introduces a fully annotated dataset of canine mammary carcinoma whole slide images, including mitotic figures, to support research in human breast cancer and improve automated detection methods.

Contribution

The authors created a comprehensive, fully annotated dataset of 21 canine breast cancer whole slide images with mitotic figure labels, incorporating expert consensus and machine learning enhancements.

Findings

Achieved a mean F1-score of 0.791 on the dataset

Detected 13,907 mitotic figures and 36,379 negatives

Demonstrated cross-species applicability with up to 0.696 F1-score on human data

Abstract

Canine mammary carcinoma (CMC) has been used as a model to investigate the pathogenesis of human breast cancer and the same grading scheme is commonly used to assess tumor malignancy in both. One key component of this grading scheme is the density of mitotic figures (MF). Current publicly available datasets on human breast cancer only provide annotations for small subsets of whole slide images (WSIs). We present a novel dataset of 21 WSIs of CMC completely annotated for MF. For this, a pathologist screened all WSIs for potential MF and structures with a similar appearance. A second expert blindly assigned labels, and for non-matching labels, a third expert assigned the final labels. Additionally, we used machine learning to identify previously undetected MF. Finally, we performed representation learning and two-dimensional projection to further increase the consistency of the annotations. Our dataset consists of 13,907 MF and 36,379 hard negatives. We achieved a mean F1-score of 0.791 on the test set and of up to 0.696 on a human breast cancer dataset.