HRD-related morphology discovery in breast cancer by controlling for confounding factors

Yoni Schirris; Hugo Mark Horlings

doi:10.1016/j.xcrm.2022.100873

HRD-related morphology discovery in breast cancer by controlling for confounding factors

Cell Rep Med. 2022 Dec 20;3(12):100873. doi: 10.1016/j.xcrm.2022.100873.

Authors

Yoni Schirris¹, Hugo Mark Horlings²

Affiliations

¹ Netherlands Cancer Institute, Plesmanlaan 121, Amsterdam, CX 1066, the Netherlands; University of Amsterdam, Science Park 402, Amsterdam, XH 1098, the Netherlands.
² Netherlands Cancer Institute, Plesmanlaan 121, Amsterdam, CX 1066, the Netherlands. Electronic address: h.horlings@nki.nl.

Abstract

Lazard et al.¹ predict homologous recombination deficiency from hematoxylin and eosin-stained slides of breast cancer tissue using deep learning. By controlling for technical artifacts on a curated dataset, the model puts forward novel HRD-related morphologies in luminal breast cancers.

Publication types

Comment

MeSH terms

BRCA1 Protein
Breast Neoplasms*
Female
Humans

Substances

BRCA1 Protein