Mitosis domain generalization in histopathology images - MIDOG 2021

Written by Tribun on

Mitosis domain generalization in histopathology images - MIDOG 2021

Share this article

subscribe to our blog

[NOVEMBER 25TH, 2022]

In 2021, Tribun Health participated to the MIDOG21 challenge "Mitosis domain generalization in histopathology images" and won the 3rd place. The MIDOG21 journal article summarizing the challenge was just officially published on Science Direct.

In order to support the research, and renew our interest in generalizable models, we are very pleased to announce that Tribun Health is donating the prize money for one of the MIDOG 2022 tracks.

Please find the article preview of the 2021 challenge below. Enjoy your reading.

Abstract. "The density of mitotic figures (MF) within tumor tissue is known to be highly correlated with tumor proliferation and thus is an important marker in tumor grading. Recognition of MF by pathologists is subject to a strong inter-rater bias, limiting its prognostic value. State-of-the-art deep learning methods can support experts but have been observed to strongly deteriorate when applied in a different clinical environment. [...] ".

Download the full article.