Automated Classification of Normal and Atypical Mitotic Figures Using ConvNeXt V2: MIDOG 2025 Track 2

TL;DR

This paper introduces a ConvNeXt V2-based method for classifying normal and atypical mitotic figures in histopathology images, addressing challenges like class imbalance and variability, and demonstrating robust performance on the MIDOG 2025 dataset.

Contribution

The paper presents a novel application of ConvNeXt V2 with specific preprocessing and ensemble strategies for mitotic figure classification in diverse histopathological images.

Findings

Achieved robust classification performance on MIDOG 2025 dataset.

Effectively handled class imbalance and morphological variability.

Demonstrated the efficiency of modern convolutional architectures for this task.

Abstract

This paper presents our solution for the MIDOG 2025 Challenge Track 2, which focuses on binary classification of normal mitotic figures (NMFs) versus atypical mitotic figures (AMFs) in histopathological images. Our approach leverages a ConvNeXt V2 base model with center cropping preprocessing and 5-fold cross-validation ensemble strategy. The method addresses key challenges including severe class imbalance, high morphological variability, and domain heterogeneity across different tumor types, species, and scanners. Through strategic preprocessing with 60% center cropping and mixed precision training, our model achieved robust performance on the diverse MIDOG 2025 dataset. The solution demonstrates the effectiveness of modern convolutional architectures for mitotic figure subtyping while maintaining computational efficiency through careful architectural choices and training optimizations.