Robust Pan-Cancer Mitotic Figure Detection with YOLOv12

TL;DR

This paper presents a mitotic figure detection approach based on the state-of-the-art YOLOv12 object detection architecture that achieved an F1-score of 0.801 on the preliminary test set (hotspots only) and ranked second on the final test leaderboard.

Abstract

Mitotic figures represent a key histoprognostic feature in tumor pathology, providing crucial insights into tumor aggressiveness and proliferation. However, their identification remains challenging, subject to significant inter-observer variability, even among experienced pathologists. To address this issue, the MItosis DOmain Generalization (MIDOG) 2025 challenge marks the third edition of an international competition aiming to develop robust mitosis detection algorithms. In this paper, we present a mitotic figure detection approach based on the state-of-the-art YOLOv12 object detection architecture. Our method achieved an F1-score of 0.801 on the preliminary test set (hotspots only) and ranked second on the final test leaderboard with an F1-score of 0.7216 across complex and heterogeneous whole-slide regions, without relying on external data.

Figures (1)

• Figure 1: Illustration of the augmentation workflow. (A) Example of a raw $640 \times 640$ H&E tile extracted from an ROI. (B–F) Stain-normalized variants generated using a multi-target Macenko normalizer, mimicking natural staining variability across domains.