GraphX$^{NET}-$ Chest X-Ray Classification Under Extreme Minimal Supervision - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2019

GraphX$^{NET}-$ Chest X-Ray Classification Under Extreme Minimal Supervision

Ruoteng Li
  • Fonction : Auteur
  • PersonId : 1051165
Philip Sellars
  • Fonction : Auteur
Qingnan Fan
  • Fonction : Auteur
Robby T Tan
  • Fonction : Auteur

Résumé

The task of classifying X-ray data is a problem of both theoretical and clinical interest. Whilst supervised deep learning methods rely upon huge amounts of labelled data, the critical problem of achieving a good classification accuracy when an extremely small amount of labelled data is available has yet to be tackled. In this work, we introduce a novel semi-supervised framework for X-ray classification which is based on a graph-based optimisation model. To the best of our knowledge, this is the first method that exploits graph-based semi-supervised learning for X-ray data classification. Furthermore, we introduce a new multi-class classification functional with carefully selected class priors which allows for a smooth solution that strengthens the synergy between the limited number of labels and the huge amount of unlabelled data. We demonstrate, through a set of numerical and visual experiments, that our method produces highly competitive results on the ChestX-ray14 data set whilst drastically reducing the need for annotated data.
Fichier principal
Vignette du fichier
samplepaper.pdf (2.03 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02193970 , version 1 (25-07-2019)

Identifiants

Citer

Angelica I. Aviles-Rivero, Nicolas Papadakis, Ruoteng Li, Philip Sellars, Qingnan Fan, et al.. GraphX$^{NET}-$ Chest X-Ray Classification Under Extreme Minimal Supervision. International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI'19), Oct 2019, Shenzen, China. pp.504-512. ⟨hal-02193970⟩

Collections

CNRS
52 Consultations
36 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More