Accéder directement au contenu Accéder directement à la navigation
Nouvelle interface
Pré-publication, Document de travail

Neural network for the prediction of treatment response in Triple Negative Breast Cancer *

Abstract : A bstract The automatic analysis of stained histological sections is becoming increasingly popular. Deep Learning is today the method of choice for the computational analysis of such data, and has shown spectacular results for large datasets for a large variety of cancer types and prediction tasks. On the other hand, many scientific questions relate to small, highly specific cohorts. Such cohorts pose serious challenges for Deep Learning, typically trained on large datasets. In this article, we propose a modification of the standard nested cross-validation procedure for hyper-parameter tuning and model selection, dedicated to the analysis of small cohorts. We also propose a new architecture for the particularly challenging question of treatment prediction, and apply this workflow to the prediction of response to neoadjuvant chemotherapy for Triple Negative Breast Cancer.
Liste complète des métadonnées

https://hal-mines-paristech.archives-ouvertes.fr/hal-03633354
Contributeur : Thomas Walter Connectez-vous pour contacter le contributeur
Soumis le : jeudi 7 avril 2022 - 00:42:46
Dernière modification le : mercredi 26 octobre 2022 - 10:54:51

Lien texte intégral

Identifiants

Citation

Peter Naylor, Tristan Lazard, Guillaume Bataillon, Marick Lae, Anne Vincent-Salomon, et al.. Neural network for the prediction of treatment response in Triple Negative Breast Cancer *. 2022. ⟨hal-03633354⟩

Partager

Métriques

Consultations de la notice

45