# Challenging mitosis detection algorithms: Global labels allow centroid localization

arXiv: https://arxiv.org/abs/2211.16852 · HTML: https://mlsanity.com/paper/2211.16852/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 19 references that are in the map.
- First posted on arXiv 30 Nov 2022.

## Builds on (most cited first, 7 of 7)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Attention-based Deep Multiple Instance Learning](https://mlsanity.com/paper/1802.04712/) (2018)
- [Predicting breast tumor proliferation from whole-slide images: the TUPAC16 challenge](https://mlsanity.com/paper/1807.08284/) (2018)
- [Deep Interpretable Classification and Weakly-Supervised Segmentation of Histology Images via Max-Min Uncertainty](https://mlsanity.com/paper/2011.07221/) (2020)
- [WeGleNet: A Weakly-Supervised Convolutional Neural Network for the Semantic Segmentation of Gleason Grades in Prostate Histology Images](https://mlsanity.com/paper/2105.10445/) (2021)
- [Leveraging Unlabeled Whole-Slide-Images for Mitosis Detection](https://mlsanity.com/paper/1807.11677/) (2018)
- [A Unified Framework for Tumor Proliferation Score Prediction in Breast Histopathology](https://mlsanity.com/paper/1612.07180/) (2016)

## Built on by (most cited first, 1 of 1)

- [Teacher-Student Model for Detecting and Classifying Mitosis in the MIDOG 2025 Challenge](https://mlsanity.com/paper/2509.03614/) (2025)

## Abstract (arXiv)

Mitotic activity is a crucial proliferation biomarker for the diagnosis and prognosis of different types of cancers. Nevertheless, mitosis counting is a cumbersome process for pathologists, prone to low reproducibility, due to the large size of augmented biopsy slides, the low density of mitotic cells, and pattern heterogeneity. To improve reproducibility, deep learning methods have been proposed in the last years using convolutional neural networks. However, these methods have been hindered by the process of data labelling, which usually solely consist of the mitosis centroids. Therefore, current literature proposes complex algorithms with multiple stages to refine the labels at pixel level, and to reduce the number of false positives. In this work, we propose to avoid complex scenarios, and we perform the localization task in a weakly supervised manner, using only image-level labels on patches. The results obtained on the publicly available TUPAC16 dataset are competitive with state-of-the-art methods, using only one training phase. Our method achieves an F1-score of 0.729 and challenges the efficiency of previous methods, which required multiple stages and strong mitosis location information.