DI-UMONS : Dépôt institutionnel de l’université de Mons

Recherche transversale
Rechercher
(titres de publication, de périodique et noms de colloque inclus)
2019-02-20 - Colloque/Article dans les actes avec comité de lecture - Anglais - page(s)

El Adoui Mohammed , LARHMAM Mohamed Amine, Drisis Stylianos, Benjelloun Mohammed , "Deep Learning approach predicting breast tumor response to neoadjuvant treatment using DCE-MRI volumes acquired before and after chemotherapy" in SPIE MEDICAL IMAGING Computer-Aided Diagnosis, San diego, Californie, 2019

  • Codes CREF : Techniques d'imagerie et traitement d'images (DI2770), Théorie de l'information (DI1161), Informatique mathématique (DI1160), Imagerie médicale, radiologie, tomographie (DI3243)
  • Unités de recherche UMONS : Informatique (F114)
  • Instituts UMONS : Institut de Recherche en Technologies de l’Information et Sciences de l’Informatique (InforTech)
Texte intégral :

Abstract(s) :

(Anglais) This work aims to provide a performing deep learning model to predict the breast cancer response to chemotherapy using Magnetic Resonance Images (MRI) acquired before and after the first chemotherapy. To provide an early prediction of breast cancer response to chemotherapy, we used a Convolution Neural Network (CNN) architecture, taking as inputs two pre-aligned and segmented breast tumor MRI slices acquired before and after the chemotherapy for 42 patients with local breast cancer. Within 80 epochs of training, we obtained 92.72% of accuracy on validation data. We obtained an Area Under the Curve (AUC) of 0.96.