A bag of tricks for real-time Mitotic Figure detection

TL;DR

This paper introduces a set of training techniques for real-time mitotic figure detection in histopathology images, achieving high accuracy and speed across diverse datasets and domains, suitable for clinical use.

Contribution

It presents a robust, efficient detection method based on RTMDet with novel training tricks to handle variability and artifacts in histopathology images.

Findings

F1 score between 0.78 and 0.84 across multiple datasets

Achieves 0.81 F1 on MIDOG 2025 challenge

Outperforms larger models in speed and accuracy

Abstract

Mitotic figure (MF) detection in histopathology images is challenging due to large variations in slide scanners, staining protocols, tissue types, and the presence of artifacts. This paper presents a collection of training techniques - a bag of tricks - that enable robust, real-time MF detection across diverse domains. We build on the efficient RTMDet single stage object detector to achieve high inference speed suitable for clinical deployment. Our method addresses scanner variability and tumor heterogeneity via extensive multi-domain training data, balanced sampling, and careful augmentation. Additionally, we employ targeted, hard negative mining on necrotic and debris tissue to reduce false positives. In a grouped 5-fold cross-validation across multiple MF datasets, our model achieves an F1 score between 0.78 and 0.84. On the preliminary test set of the MItosis DOmain Generalization (MIDOG) 2025 challenge, our single-stage RTMDet-S based approach reaches an F1 of 0.81, outperforming larger models and demonstrating adaptability to new, unfamiliar domains. The proposed solution offers a practical trade-off between accuracy and speed, making it attractive for real-world clinical adoption.