# Rethinking Mitosis Detection: Towards Diverse Data and Feature Representation

arXiv: https://arxiv.org/abs/2307.05889 · HTML: https://mlsanity.com/paper/2307.05889/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 38 references that are in the map.
- First posted on arXiv 12 Jul 2023.

## Builds on (most cited first, 19 of 19)

- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [Exploring Simple Siamese Representation Learning](https://mlsanity.com/paper/2011.10566/) (2020)
- [Domain Generalization: A Survey](https://mlsanity.com/paper/2103.02503/) (2021)
- [FDA: Fourier Domain Adaptation for Semantic Segmentation](https://mlsanity.com/paper/2004.05498/) (2020)
- [HoVer-Net: Simultaneous Segmentation and Classification of Nuclei in Multi-Tissue Histology Images](https://mlsanity.com/paper/1812.06499/) (2018)
- [Wider or Deeper: Revisiting the ResNet Model for Visual Recognition](https://mlsanity.com/paper/1611.10080/) (2016)
- [Domain Generalization for Medical Imaging Classification with Linear-Dependency Regularization](https://mlsanity.com/paper/2009.12829/) (2020)
- [Exact Feature Distribution Matching for Arbitrary Style Transfer and Domain Generalization](https://mlsanity.com/paper/2203.07740/) (2022)
- [Mitosis domain generalization in histopathology images -- The MIDOG challenge](https://mlsanity.com/paper/2204.03742/) (2022)
- [Whole-Slide Mitosis Detection in H&E Breast Histology Using PHH3 as a Reference to Train Distilled Stain-Invariant Convolutional Networks](https://mlsanity.com/paper/1808.05896/) (2018)
- [Domain Generalization on Medical Imaging Classification using Episodic Training with Task Augmentation](https://mlsanity.com/paper/2106.06908/) (2021)
- [Assessment of algorithms for mitosis detection in breast cancer histopathology images](https://mlsanity.com/paper/1411.5825/) (2014)
- [Quantifying the Scanner-Induced Domain Gap in Mitosis Detection](https://mlsanity.com/paper/2103.16515/) (2021)
- [Robust White Matter Hyperintensity Segmentation on Unseen Domain](https://mlsanity.com/paper/2102.06650/) (2021)
- [RestainNet: a self-supervised digital re-stainer for stain normalization](https://mlsanity.com/paper/2202.13804/) (2022)
- [Leveraging Unlabeled Whole-Slide-Images for Mitosis Detection](https://mlsanity.com/paper/1807.11677/) (2018)
- [A Novel Dataset and a Deep Learning Method for Mitosis Nuclei Segmentation and Classification](https://mlsanity.com/paper/2212.13401/) (2022)

## Abstract (arXiv)

Mitosis detection is one of the fundamental tasks in computational pathology, which is extremely challenging due to the heterogeneity of mitotic cell. Most of the current studies solve the heterogeneity in the technical aspect by increasing the model complexity. However, lacking consideration of the biological knowledge and the complex model design may lead to the overfitting problem while limited the generalizability of the detection model. In this paper, we systematically study the morphological appearances in different mitotic phases as well as the ambiguous non-mitotic cells and identify that balancing the data and feature diversity can achieve better generalizability. Based on this observation, we propose a novel generalizable framework (MitDet) for mitosis detection. The data diversity is considered by the proposed diversity-guided sample balancing (DGSB). And the feature diversity is preserved by inter- and intra- class feature diversity-preserved module (InCDP). Stain enhancement (SE) module is introduced to enhance the domain-relevant diversity of both data and features simultaneously. Extensive experiments have demonstrated that our proposed model outperforms all the SOTA approaches in several popular mitosis detection datasets in both internal and external test sets using minimal annotation efforts with point annotations only. Comprehensive ablation studies have also proven the effectiveness of the rethinking of data and feature diversity balancing. By analyzing the results quantitatively and qualitatively, we believe that our proposed model not only achieves SOTA performance but also might inspire the future studies in new perspectives. Source code is at https://github.com/Onehour0108/MitDet.