DFG / FWF ·520330054 ·09/2024-09/2027

(mu)RoMI: Robust and Accurate Multi-Tumor, Multi-Species, Multi-Laboratory and Multi-Scanner Mitosis Detection

Generating the biggest and highest quality dataset for mitotic figures, including up to 14 scanners and PHH3-IHC-grounding.

Neoplasia, a common cause of death in both animals and humans, requires treatment decisions based on pathological examination of tumor specimens. Histological analysis, particularly mitotic count (MC), plays a crucial role in prognostication. However, our research highlights significant challenges, including heterogeneity in MC distribution throughout histological slides, observer-dependent variability, morphological complexities, and technical limitations in mitotic figure detection. These factors contribute to poor agreement among trained pathologists, with published κ values between 0.08 and 0.77, posing a risk of incorrect prognostication and therapeutic decisions (Bertram et al., 2018; Donovan et al., 2020).

Canine mast cell tumor stained with phospho-histone H3 (PHH3) antibody, clearly highlighting mitotic figures in brown from the surrounding cell nuclei in blue.


Our research shows that computer-aided image analysis using machine/deep learning techniques excels in histopathologic classification tasks on H&E-stained slides, surpassing human observers with ample data (Bertram et al., 2022; Bertram 2019a). We’ve developed large-scale, high-quality labeled datasets, and our algorithm has proven to enhance pathologists’ performance significantly (Bertram et al., 2022). This advancement suggests a more reliable tumor prognostication using the cost-effective H&E-stained slides (Villani et al., 2016; Tracht, Zhang, and Peker, 2017).

The need for a multi-domain reference whole slide image data set as open data.

Successful implementation of deep learning-based, data-driven methods hinges on access to representative large-scale datasets. Image domains in histopathology, encompassing staining variations, species, tissue types, and digitization devices, contribute to dataset variability. Different regions within histological sections may contain diverse tissue components and artifacts, potentially rendering selected regions of interest (ROI) non-representative (Aubreville et al., 2020b; Bertram et al., 2019a). This variation leads to a domain shift in data distribution, impacting algorithm performance significantly (Aubreville et al., 2021b; Stacke et al., 2021). Addressing this challenge through domain adaptation approaches is crucial in computational histopathology, and while progress has been made, a persistent domain gap impedes the development of robust software solutions applicable to the full spectrum of biological and imaging variations in digitized histological tumor sections across different tissue types, image locations, laboratories, species, and scanners (Aubreville et al., 2020a; Stacke et al., 2021).

Co-registered H&E and PHH3 stains. The left image shows mitotic figures in an early phase (PHHE-positive) and the right panels show a mitotic figure in a late phase (PHHE-negative).

Dataset Dashboard

We transparently report on our dataset creation progress. Have a look at our dashboard. The full version is available at this link.

Project team

Marc Aubreville, Sweta Banerjee, Christof A. Bertram (PI, VetMedUni Vienna), Viktoria Weiss (VetMedUni Vienna), Christoph Stroblberger (MedUni Vienna), Robert Klopfleisch (PI, FU Berlin), Thomas Conrad (FU Berlin)

Journals

  • A Subphase-Labeled Mitotic Dataset for AI-powered Cell Division Analysis

    Zsanett Zsofia Ivan, Dominik Hirling, Istvan Grexa, Jonas Ammeling, Csaba Molnar, Tamas Micsik, Katalin Dobra, Levente Kuthi, Farkas Sukosd, Janos Fillinger, Judit Moldvay, Erika Toth, Marc Aubreville, Vivien Miczan and Peter Horvath

    2026 · Scientific Data doi link

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

    Sweta Banerjee, Viktoria Weiss, Taryn A. Donovan, Rutger H. J. Fick, Thomas Conrad, Jonas Ammeling, Nils Porsche, Robert Klopfleisch, Christopher Kaltenecker, Katharina Breininger, Marc Aubreville and Christof A Bertram

    2026 · Machine Learning for Biomedical Imaging doi

  • Benchmarking Foundation Models for Mitotic Figure Classification

    Jonas Ammeling, Jonathan Ganz, Emely Rosbach, Ludwig Lausser, Christof A. Bertram, Katharina Breininger and Marc Aubreville

    2026 · Machine Learning for Biomedical Imaging doi link

  • Reporting Transparency in Veterinary Pathology Deep Learning: A Systematic Review of Reproducibility-Critical Details

    Sweta Banerjee, Christof A. Bertram, Viktoria Weiss, Jonas Ammeling, Thomas Conrad, Nils Porsche, Robert Klopfleisch, Christoph Stoblberger, Christopher Kaltenecker, Katharina Breininger and Marc Aubreville

    2026 · Veterinary Pathology doi

  • Domain generalization across tumor types, laboratories, and species — Insights from the 2022 edition of the Mitosis Domain Generalization Challenge

    Marc Aubreville, Nikolas Stathonikos, Taryn A. Donovan, Robert Klopfleisch, Jonas Ammeling, Jonathan Ganz, Frauke Wilm, Mitko Veta, Samir Jabari, Markus Eckstein, Jonas Annuscheit, Christian Krumnow, Engin Bozaba, Sercan Çayır, Hongyan Gu, Xiang ‘Anthony’ Chen, Mostafa Jahanifar, Adam Shephard, Satoshi Kondo, Satoshi Kasai, Sujatha Kotte, V.G. Saipradeep, Maxime W. Lafarge, Viktor H. Koelzer, Ziyue Wang, Yongbing Zhang, Sen Yang, Xiyue Wang, Katharina Breininger and Christof A. Bertram

    2024 · Medical Image Analysis doi link

Conference proceedings

Resources

← All grants