# Benchmarking Deep Learning and Vision Foundation Models for Atypical vs. Normal Mitosis Classification with Cross-Dataset Evaluation

arXiv: https://arxiv.org/abs/2506.21444 · HTML: https://mlsanity.com/paper/2506.21444/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 40 references that are in the map.
- First posted on arXiv 26 Jun 2025.

## Builds on (most cited first, 16 of 16)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [EfficientNetV2: Smaller Models and Faster Training](https://mlsanity.com/paper/2104.00298/) (2021)
- [Virchow2: Scaling Self-Supervised Mixed Magnification Models in Pathology](https://mlsanity.com/paper/2408.00738/) (2024)
- [Mitosis domain generalization in histopathology images -- The MIDOG challenge](https://mlsanity.com/paper/2204.03742/) (2022)
- [A Clinical Benchmark of Public Self-Supervised Pathology Foundation Models](https://mlsanity.com/paper/2407.06508/) (2024)
- [Predicting breast tumor proliferation from whole-slide images: the TUPAC16 challenge](https://mlsanity.com/paper/1807.08284/) (2018)
- [Distilling foundation models for robust and efficient models in digital pathology](https://mlsanity.com/paper/2501.16239/) (2025)
- [Domain generalization across tumor types, laboratories, and species -- insights from the 2022 edition of the Mitosis Domain Generalization Challenge](https://mlsanity.com/paper/2309.15589/) (2023)
- [Histologic Dataset of Normal and Atypical Mitotic Figures on Human Breast Cancer (AMi-Br)](https://mlsanity.com/paper/2501.04467/) (2025)
- [Quantifying the Scanner-Induced Domain Gap in Mitosis Detection](https://mlsanity.com/paper/2103.16515/) (2021)
- [A Comprehensive Evaluation of Histopathology Foundation Models for Ovarian Cancer Subtype Classification](https://mlsanity.com/paper/2405.09990/) (2024)
- [Are pathologist-defined labels reproducible? Comparison of the TUPAC16 mitotic figure dataset with an alternative set of labels](https://mlsanity.com/paper/2007.05351/) (2020)
- [Deep learning-based Subtyping of Atypical and Normal Mitoses using a Hierarchical Anchor-Free Object Detector](https://mlsanity.com/paper/2212.05900/) (2022)

## Built on by (most cited first, 7 of 7)

- [Efficient Fine-Tuning of DINOv3 Pretrained on Natural Images for Atypical Mitotic Figure Classification](https://mlsanity.com/paper/2508.21041/) (2025)
- [Ensemble of Pathology Foundation Models for MIDOG 2025 Track 2: Atypical Mitosis Classification](https://mlsanity.com/paper/2509.02591/) (2025)
- [Foundation Model-Driven Classification of Atypical Mitotic Figures with Domain-Aware Training Strategies](https://mlsanity.com/paper/2509.02601/) (2025)
- [Adaptive Learning Strategies for Mitotic Figure Classification in MIDOG2025 Challenge](https://mlsanity.com/paper/2509.02640/) (2025)
- [Parameter-efficient fine-tuning (PEFT) of Vision Foundation Models for Atypical Mitotic Figure Classification](https://mlsanity.com/paper/2509.16935/) (2025)
- [Robust Atypical Mitosis Classification with DenseNet121: Stain-Aware Augmentation and Hybrid Loss for Domain Generalization](https://mlsanity.com/paper/2510.22630/) (2025)
- [Beyond Classification: Pathology Foundation Models as Detection Encoders for Mitotic Figures](https://mlsanity.com/paper/2607.28007/) (2026)

## Abstract (arXiv)

Atypical mitosis marks a deviation in the cell division process that has been shown be an independent prognostic marker for tumor malignancy. However, atypical mitosis classification remains challenging due to low prevalence, at times subtle morphological differences from normal mitotic figures, low inter-rater agreement among pathologists, and class imbalance in datasets. Building on the Atypical Mitosis dataset for Breast Cancer (AMi-Br), this study presents a comprehensive benchmark comparing deep learning approaches for automated atypical mitotic figure (AMF) classification, including end-to-end trained deep learning models, foundation models with linear probing, and foundation models fine-tuned with low-rank adaptation (LoRA). For rigorous evaluation, we further introduce two new held-out AMF datasets - AtNorM-Br, a dataset of mitotic figures from the TCGA breast cancer cohort, and AtNorM-MD, a multi-domain dataset of mitotic figures from a subset of the MIDOG++ training set. We found average balanced accuracy values of up to 0.8135, 0.7788, and 0.7723 on the in-domain AMi-Br and the out-of-domain AtNorm-Br and AtNorM-MD datasets, respectively. Our work shows that atypical mitotic figure classification, while being a challenging problem, can be effectively addressed through the use of recent advances in transfer learning and model fine-tuning techniques. We make all code and data used in this paper available in this github repository: https://github.com/DeepMicroscopy/AMi-Br_Benchmark.