Mitosis Detection, Fast and Slow: Robust and Efficient Detection of Mitotic Figures

TL;DR

This paper introduces a robust, two-stage deep learning framework for mitosis detection in histology images, achieving state-of-the-art accuracy and generalizability across multiple datasets and domain shifts.

Contribution

The authors propose a novel two-stage mitosis detection method combining EUNet for candidate segmentation and EfficientNet-B7 for refinement, with domain generalization techniques to handle domain shifts.

Findings

Achieved state-of-the-art performance on large public datasets.

Won domain generalization challenges MIDOG21 and MIDOG22.

Processed 1,125 whole-slide images to create a mitotic figure repository.

Abstract

Counting of mitotic figures is a fundamental step in grading and prognostication of several cancers. However, manual mitosis counting is tedious and time-consuming. In addition, variation in the appearance of mitotic figures causes a high degree of discordance among pathologists. With advances in deep learning models, several automatic mitosis detection algorithms have been proposed but they are sensitive to {\em domain shift} often seen in histology images. We propose a robust and efficient two-stage mitosis detection framework, which comprises mitosis candidate segmentation ({\em Detecting Fast}) and candidate refinement ({\em Detecting Slow}) stages. The proposed candidate segmentation model, termed \textit{EUNet}, is fast and accurate due to its architectural design. EUNet can precisely segment candidates at a lower resolution to considerably speed up candidate detection. Candidates are then refined using a deeper classifier network, EfficientNet-B7, in the second stage. We make sure both stages are robust against domain shift by incorporating domain generalization methods. We demonstrate state-of-the-art performance and generalizability of the proposed model on the three largest publicly available mitosis datasets, winning the two mitosis domain generalization challenge contests (MIDOG21 and MIDOG22). Finally, we showcase the utility of the proposed algorithm by processing the TCGA breast cancer cohort (1,125 whole-slide images) to generate and release a repository of more than 620K mitotic figures.