# Stain-Robust Mitotic Figure Detection for the Mitosis Domain Generalization Challenge

arXiv: https://arxiv.org/abs/2109.00853 · HTML: https://mlsanity.com/paper/2109.00853/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 10 references that are in the map.
- First posted on arXiv 2 Sep 2021.

## Builds on (most cited first, 6 of 6)

- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [NuClick: A Deep Learning Framework for Interactive Segmentation of Microscopy Images](https://mlsanity.com/paper/2005.14511/) (2020)
- [Assessment of algorithms for mitosis detection in breast cancer histopathology images](https://mlsanity.com/paper/1411.5825/) (2014)
- [Robust Interactive Semantic Segmentation of Pathology Images with Minimal User Input](https://mlsanity.com/paper/2108.13368/) (2021)
- [Segmentation of Skin Lesions and their Attributes Using Multi-Scale Convolutional Neural Networks and Domain Specific Augmentations](https://mlsanity.com/paper/1809.10243/) (2018)
- [NuClick: From Clicks in the Nuclei to Nuclear Boundaries](https://mlsanity.com/paper/1909.03253/) (2019)

## Built on by (most cited first, 14 of 14)

- [Mitosis domain generalization in histopathology images -- The MIDOG challenge](https://mlsanity.com/paper/2204.03742/) (2022)
- [Domain Generalization in Computational Pathology: Survey and Guidelines](https://mlsanity.com/paper/2310.19656/) (2023)
- [IMPaSh: A Novel Domain-shift Resistant Representation for Colorectal Cancer Tissue Classification](https://mlsanity.com/paper/2208.11052/) (2022)
- [TIAger: Tumor-Infiltrating Lymphocyte Scoring in Breast Cancer for the TiGER Challenge](https://mlsanity.com/paper/2206.11943/) (2022)
- [Consistency Regularisation in Varying Contexts and Feature Perturbations for Semi-Supervised Semantic Segmentation of Histology Images](https://mlsanity.com/paper/2301.13141/) (2023)
- [MoMA: Momentum Contrastive Learning with Multi-head Attention-based Knowledge Distillation for Histopathology Image Analysis](https://mlsanity.com/paper/2308.16561/) (2023)
- [Detecting Mitoses with a Convolutional Neural Network for MIDOG 2022 Challenge](https://mlsanity.com/paper/2208.12437/) (2022)
- [SoftCTM: Cell detection by soft instance segmentation and consideration of cell-tissue interaction](https://mlsanity.com/paper/2312.12151/) (2023)
- [A Fully Automated and Explainable Algorithm for the Prediction of Malignant Transformation in Oral Epithelial Dysplasia](https://mlsanity.com/paper/2307.03757/) (2023)
- [Benchmarking Domain Generalization Algorithms in Computational Pathology](https://mlsanity.com/paper/2409.17063/) (2024)
- [An Automated Pipeline for Tumour-Infiltrating Lymphocyte Scoring in Breast Cancer](https://mlsanity.com/paper/2311.06185/) (2023)
- [Improving Mitosis Detection Via UNet-based Adversarial Domain Homogenizer](https://mlsanity.com/paper/2209.09193/) (2022)
- [Transformer-based Model for Oral Epithelial Dysplasia Segmentation](https://mlsanity.com/paper/2311.05452/) (2023)
- [Value bounds and Convergence Analysis for Averages of LRP attributions](https://mlsanity.com/paper/2509.08963/) (2025)

## Abstract (arXiv)

The detection of mitotic figures from different scanners/sites remains an important topic of research, owing to its potential in assisting clinicians with tumour grading. The MItosis DOmain Generalization (MIDOG) challenge aims to test the robustness of detection models on unseen data from multiple scanners for this task. We present a short summary of the approach employed by the TIA Centre team to address this challenge. Our approach is based on a hybrid detection model, where mitotic candidates are segmented on stain normalised images, before being refined by a deep learning classifier. Cross-validation on the training images achieved the F1-score of 0.786 and 0.765 on the preliminary test set, demonstrating the generalizability of our model to unseen data from new scanners.