Skip to Main content Skip to Navigation
Conference papers

Pondération dynamique en apprentissage multi-vues pour des applications radiomics

Hongliu Cao 1 Simon Bernard 1 Robert Sabourin 2 Laurent Heutte 1
1 DocApp - LITIS - Equipe Apprentissage
LITIS - Laboratoire d'Informatique, de Traitement de l'Information et des Systèmes
Abstract : Cancer diagnosis and treatment often require a personalized analysis for each patient nowadays, due to the heterogeneity among the different types of tumor and among patients. Radiomics is a recent medical imaging field that has shown during the past few years to be promising for achieving this personalization. However, we have shown in a recent study that most of the state-of-the-art works in Radiomics fail to identify this problem as a multi-view learning task and that multi-view learning techniques are generally more efficient. In this work, we propose to further investigate the potential of one family of multi-view learning methods based on Multiple Classifiers Systems where one classifier is learnt on each view and all classifiers are combined afterwards. In particular, we propose a random forest based dynamic weighted voting scheme, which personalizes the combination of views for each new patient for classification tasks. The proposed method is validated on several real-world Radiomics problems, with a comparison to the state-of-the-art Radiomics approach and to static voting schemes for Multiple Classifiers Systems.
Document type :
Conference papers
Complete list of metadatas
Contributor : Simon Bernard <>
Submitted on : Tuesday, April 30, 2019 - 9:15:50 AM
Last modification on : Thursday, May 2, 2019 - 10:54:06 AM


  • HAL Id : hal-02114995, version 1


Hongliu Cao, Simon Bernard, Robert Sabourin, Laurent Heutte. Pondération dynamique en apprentissage multi-vues pour des applications radiomics. Conférence sur l’apprentissage automatique (CAp), Jun 2018, Rouen, France. ⟨hal-02114995⟩



Record views