MitoDet: Simple and robust mitosis detection

TL;DR

MitoDet is a robust mitosis detection method that uses RetinaNet with extensive data augmentation to address domain shift caused by different microscopes, achieving competitive results in a challenging clinical setting.

Contribution

The paper introduces a simple yet effective mitosis detection algorithm that generalizes well across different domains using strong data augmentation techniques.

Findings

Achieved an F1 score of 0.7138 on the test set.

Addresses domain shift caused by different microscopes.

Employs RetinaNet with extensive data augmentation.

Abstract

Mitotic figure detection is a challenging task in digital pathology that has a direct impact on therapeutic decisions. While automated methods often achieve acceptable results under laboratory conditions, they frequently fail in the clinical deployment phase. This problem can be mainly attributed to a phenomenon called domain shift. An important source of a domain shift is introduced by different microscopes and their camera systems, which noticeably change the color representation of digitized images. In this method description we present our submitted algorithm for the Mitosis Domain Generalization Challenge, which employs a RetinaNet trained with strong data augmentation and achieves an F1 score of 0.7138 on the preliminary test set.