Adaptive Learning Strategies for Mitotic Figure Classification in MIDOG2025 Challenge

Biwen Meng, Xi Long, Jingxin Liu
9/1/2025
eess.IVcs.AIcs.CV

No confident code implementation found for this paper.

Abstract

Atypical mitotic figures (AMFs) are clinically relevant indicators of abnormal cell division, yet their reliable detection remains challenging due to morphological ambiguity and scanner variability. In this work, we investigated three variants of adapting the pathology foundation model UNI2 for the MIDOG2025 Track 2 challenge: (1) LoRA + UNI2, (2) VPT + UNI2 + Vahadane Normalizer, and (3) VPT + UNI2 + GRL + Stain TTA. We observed that the integration of Visual Prompt Tuning (VPT) with stain normalization techniques contributed to improved generalization. The best robustness was achieved by further incorporating test-time augmentation (TTA) with Vahadane and Macenko stain normalization. Our final submission achieved a balanced accuracy of 0.8837 and an ROC-AUC of 0.9513 on the preliminary leaderboard, ranking within the top 10 teams. These results suggest that prompt-based adaptation combined with stain-normalization TTA offers a promising strategy for atypical mitosis classification under diverse imaging conditions.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Robust Atypical Mitosis Classification with DenseNet121: Stain-Aware Augmentation and Hybrid Loss for Domain Generalization

90% match2025

Parameter-efficient fine-tuning (PEFT) of Vision Foundation Models for Atypical Mitotic Figure Classification

89% match2025

Is Synthetic Image Augmentation Useful for Imbalanced Classification Problems? Case-Study on the MIDOG2025 Atypical Cell Detection Competition

88% match2025

Teacher-Student Model for Detecting and Classifying Mitosis in the MIDOG 2025 Challenge

86% match2025

Characterizing the Features of Mitotic Figures Using a Conditional Diffusion Probabilistic Model

86% match2023

Ensemble YOLO Framework for Multi-Domain Mitotic Figure Detection in Histopathology Images

86% match2025

Cite this paper

@article{meng2025adaptive,
  title  = {Adaptive Learning Strategies for Mitotic Figure Classification in MIDOG2025 Challenge},
  author = {Biwen Meng and Xi Long and Jingxin Liu},
  year   = {2025},
  eprint = {2509.02640},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2509.02640v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2509.02640.svg)](https://codeofpaper.com/paper/2509.02640)

Discussion