# On the Value of PHH3 for Mitotic Figure Detection on H&E-stained Images

arXiv: https://arxiv.org/abs/2406.19899 · HTML: https://mlsanity.com/paper/2406.19899/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 57 references that are in the map.
- First posted on arXiv 28 Jun 2024.

## Builds on (most cited first, 13 of 13)

- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [FCOS: Fully Convolutional One-Stage Object Detection](https://mlsanity.com/paper/1904.01355/) (2019)
- [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)
- [Cross-Modality Attentive Feature Fusion for Object Detection in Multispectral Remote Sensing Imagery](https://mlsanity.com/paper/2112.02991/) (2021)
- [Epithelium segmentation using deep learning in H&E-stained prostate specimens with immunohistochemistry as reference standard](https://mlsanity.com/paper/1808.05883/) (2018)
- [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)
- [EXACT: A collaboration toolset for algorithm-aided annotation of images with annotation version control](https://mlsanity.com/paper/2004.14595/) (2020)
- [Virtual staining for mitosis detection in Breast Histopathology](https://mlsanity.com/paper/2003.07801/) (2020)
- [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)
- [Learning Melanocytic Cell Masks from Adjacent Stained Tissue](https://mlsanity.com/paper/2211.00646/) (2022)
- [Deep Learning-Based Automatic Assessment of AgNOR-scores in Histopathology Images](https://mlsanity.com/paper/2212.07721/) (2022)

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

- [Is Self-Supervision Enough? Benchmarking Foundation Models Against End-to-End Training for Mitotic Figure Classification](https://mlsanity.com/paper/2412.06365/) (2024)

## Abstract (arXiv)

The count of mitotic figures (MFs) observed in hematoxylin and eosin (H&E)-stained slides is an important prognostic marker as it is a measure for tumor cell proliferation. However, the identification of MFs has a known low inter-rater agreement. Deep learning algorithms can standardize this task, but they require large amounts of annotated data for training and validation. Furthermore, label noise introduced during the annotation process may impede the algorithm's performance. Unlike H&E, the mitosis-specific antibody phospho-histone H3 (PHH3) specifically highlights MFs. Counting MFs on slides stained against PHH3 leads to higher agreement among raters and has therefore recently been used as a ground truth for the annotation of MFs in H&E. However, as PHH3 facilitates the recognition of cells indistinguishable from H&E stain alone, the use of this ground truth could potentially introduce noise into the H&E-related dataset, impacting model performance. This study analyzes the impact of PHH3-assisted MF annotation on inter-rater reliability and object level agreement through an extensive multi-rater experiment. We found that the annotators' object-level agreement increased when using PHH3-assisted labeling. Subsequently, MF detectors were evaluated on the resulting datasets to investigate the influence of PHH3-assisted labeling on the models' performance. Additionally, a novel dual-stain MF detector was developed to investigate the interpretation-shift of PHH3-assisted labels used in H&E, which clearly outperformed single-stain detectors. However, the PHH3-assisted labels did not have a positive effect on solely H&E-based models. The high performance of our dual-input detector reveals an information mismatch between the H&E and PHH3-stained images as the cause of this effect.