Article Dans Une Revue Nature Communications Année : 2025

Deep learning assessment of metastatic relapse risk from digitized breast cancer histological slides

Valentin Gaury
Charlie Saillard
Kevin Elgui
  • Fonction : Auteur
Benoit Schmauch
Loïc Herpin
Aurélie Kamoun
Alexandre Filiot
  • Fonction : Auteur
Oussama Tchita
Rémy Dubois
  • Fonction : Auteur
Lionel Guillou
Jerome Lemonnier
Meriem Sefta
  • Fonction : Auteur
Sibille Everhard
  • Fonction : Auteur
Jean François Reboud
  • Fonction : Auteur
Fabien Brulport
  • Fonction : Auteur
Jocelyn Dachary
  • Fonction : Auteur
Pierre Courtiol
  • Fonction : Auteur

Résumé

Accurate risk stratification is critical for guiding treatment decisions in early breast cancer. We present an artificial intelligence (AI)-based tool that analyzes digitized tumor slides to predict 5-year metastasis-free survival (MFS) in patients with estrogen receptor-positive, HER2-negative (ER + /HER2 - ) early breast cancer (EBC). Our deep learning model, RlapsRisk BC, independently predicts MFS and provides significant prognostic value beyond traditional clinico-pathological variables (C-index 0.81 vs 0.76, p < 0.05). Applying a 5% MFS event probability threshold stratifies patients into low- and high-risk groups. After dichotomization, combining RlapsRisk BC with clinico-pathological factors increases cumulative sensitivity (0.69 vs 0.63) and dynamic specificity (0.80 vs 0.76) compared to clinical factors alone. Expert analysis of high-impact regions identified by the model highlights well-established morphological features, supporting its interpretability and biological relevance.

Fichier principal
Vignette du fichier
2025_Drubay_NatCommun.pdf (3.27 Mo) Télécharger le fichier
Origine Publication financée par une institution
Licence

Dates et versions

inserm-05219747 , version 1 (22-08-2025)

Licence

Identifiants

Citer

Ingrid Garberis, Valentin Gaury, Charlie Saillard, Damien Drubay, Kevin Elgui, et al.. Deep learning assessment of metastatic relapse risk from digitized breast cancer histological slides. Nature Communications, 2025, 16 (1), pp.5876. ⟨10.1038/s41467-025-60824-z⟩. ⟨inserm-05219747⟩
1086 Consultations
281 Téléchargements

Altmetric

Partager

  • More