Pondération dynamique en apprentissage multi-vues pour des applications radiomics - Normandie Université Accéder directement au contenu
Communication Dans Un Congrès Année : 2018

Pondération dynamique en apprentissage multi-vues pour des applications radiomics

Hongliu Cao
  • Fonction : Auteur
Simon Bernard
Laurent Heutte

Résumé

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.
Fichier non déposé

Dates et versions

hal-02114995 , version 1 (30-04-2019)

Identifiants

  • HAL Id : hal-02114995 , version 1

Citer

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⟩
35 Consultations
0 Téléchargements

Partager

Gmail Facebook X LinkedIn More