output
20142025
most citedMitosis domain generalization in histopathology images -- The MIDOG challenge

162 citations

Showing cs.CVShow all

5 papers · 1 filter

cs.CV2025

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

Sweta Banerjee, Viktoria Weiss, Taryn A. Donovan +9

Atypical mitosis marks a deviation in the cell division process that has been shown be an independent prognostic marker for tumor malignancy. However, atypical mitosis classificati…

cs.CV2024★ 8 cited

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

Jonathan Ganz, Christian Marzahl, Jonas Ammeling +20

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…

cs.CV2023★ 12 cited

Nuclear Pleomorphism in Canine Cutaneous Mast Cell Tumors: Comparison of Reproducibility and Prognostic Relevance between Estimates, Manual Morphometry and Algorithmic Morphometry

Andreas Haghofer, Eda Parlak, Alexander Bartel +18

Variation in nuclear size and shape is an important criterion of malignancy for many tumor types; however, categorical estimates by pathologists have poor reproducibility. Measurem…

cs.CV2021★ 12 cited

How Many Annotators Do We Need? -- A Study on the Influence of Inter-Observer Variability on the Reliability of Automatic Mitotic Figure Assessment

Frauke Wilm, Christof A. Bertram, Christian Marzahl +23

Density of mitotic figures in histologic sections is a prognostically relevant characteristic for many tumours. Due to high inter-pathologist variability, deep learning-based algor…

cs.CV2020★ 75 cited

A completely annotated whole slide image dataset of canine breast cancer to aid human breast cancer research

Marc Aubreville, Christof A. Bertram, Taryn A. Donovan +3

Canine mammary carcinoma (CMC) has been used as a model to investigate the pathogenesis of human breast cancer and the same grading scheme is commonly used to assess tumor malignan…