System Maintenance Notice

Please note that maintenance work is scheduled between 4 AM and 5 AM - CET. During this time, you may experience reduced performance. Thanks for your patience.

Publications

Journal Article Ahead of print

PubMed: 42298170 DOI: 10.1038/s41746-026-02895-w

Deep learning analysis of breast cancer histology predicts ATM pathogenic variant carrier status.

NPJ Digit Med

Authors: Nicolas M Viart, Lucie Thibault, Tristan Lazard, Séverine Eon-Marchais, Yue Jiao, Laetitia Fuhrmann, Dorothée Le Gal, Eve Cavaciuti, Marie-Gabrielle Dondon, Juana Beauvallet, Marina De Brot, Joanne Ngeow, Soo-Hwang Teo, Maria Isabel Achatz, Elizabeth Santana Dos Santos, Fergus J Couch, Dominique Stoppa-Lyonnet, Melissa C Southey, Anne Vincent-Salomon, Thomas Walter, Nadine Andrieu, Fabienne Lesueur

Affiliations

  • Inserm, U1331, Institut Curie, Paris, France, PSL University, Paris, France, Mines Paris, Paris, France.
  • Department of Pathology, Institut Curie, Paris, France.
  • Center for Computational Biology (CBIO), Mines Paris, Paris, France, PSL University, Paris, France.
  • Department of Anatomic Pathology, A.C. Camargo Cancer Center, São Paulo, Brazil.
  • Cancer Genetics Service, National Cancer Centre Singapore, Singapore, Singapore.
  • Lee Kong Chian School of Medicine, Nanyang Technological University, Singapore, Singapore.
  • Malaysia Cancer Research Program, Department of Surgery, Faculty of Medicine, University of Malaysia, Kuala Lumpur, Malaysia, Jalan Universiti, Kuala Lumpur, Malaysia.
  • Centro de Oncologia, Hospital Sírio-Libanês, São Paulo, Brazil.
  • Mayo Clinic, Rochester, NY, USA.
  • Service de Génétique, Institut Curie, Paris, France, Université Paris Cité, Paris, France, Inserm, Paris, France.
  • Monash University, Clayton, Australia, University of Melbourne, Parkville, VIC, Australia.
  • Cancer Epidemiology Division, Cancer Council Victoria, Melbourne, VIC, Australia.
  • Inserm, U1331, Institut Curie, Paris, France, PSL University, Paris, France, Mines Paris, Paris, France.

Abstract

We performed deep learning analysis of histopathological whole-slide (full-face) images (WSI) to predict ATM pathogenic or likely pathogenic variant (PV/LPV) status of women with breast cancer and identify specific histological patterns of their tumor.In the discovery set composed of tumors from PV/LPV carriers (58 WSI) and noncarriers (129 WSI), our deep learning model predicted ATM status of patients with an area under the curve of 0.90 [95%CI: 0.85-0.95] and a balanced accuracy of 0.80 [95%CI: 0.72-0.88]. In the replication set (29 WSI from carriers and 22 WSI from noncarriers), corresponding results were 0.85 [95%CI: 0.70-1.00] and 0.67 [95%CI: 0.51-0.83]. We found that tumors developed by ATM PV/LPV carriers often displayed discohesive neoplastic cells as observed in invasive lobular carcinomas, and dense lymphocytic infiltrate reflecting an immune-enriched microenvironment.Recognizing these tumors at the time of diagnosis is a critical first step toward precision medicine in affected women and precision prevention in family members.

MeSH

Breast Neoplasms, Neoplasms, Deep Learning, Breast, Histology, Learning