Adaptive image-feature learning for disease classification using inductive graph networks

  title={Adaptive image-feature learning for disease classification using inductive graph networks},
  author={Hendrik Burwinkel and Anees Kazi and G. Vivar and Shadi Albarqouni and G. Zahnd and Nassir Navab and Seyed-Ahmad Ahmadi},
  • Hendrik Burwinkel, Anees Kazi, +4 authors Seyed-Ahmad Ahmadi
  • Published 2019
  • Computer Science, Engineering, Mathematics
  • ArXiv
  • Recently, Geometric Deep Learning (GDL) has been introduced as a novel and versatile framework for computer-aided disease classification. GDL uses patient meta-information such as age and gender to model patient cohort relations in a graph structure. Concepts from graph signal processing are leveraged to learn the optimal mapping of multi-modal features, e.g. from images to disease classes. Related studies so far have considered image features that are extracted in a pre-processing step. We… CONTINUE READING
    6 Citations

    Figures, Tables, and Topics from this paper

    Latent Patient Network Learning for Automatic Diagnosis
    • PDF
    Fusion High-Resolution Network for Diagnosing ChestX-ray Images
    • 5
    • PDF
    Decision Support for Intoxication Prediction Using Graph Convolutional Networks
    • PDF
    A Survey towards Federated Semi-supervised Learning
    • 6


    Spectral Graph Convolutions for Population-based Disease Prediction
    • 78
    • Highly Influential
    • PDF
    Geometric Deep Learning on Graphs and Manifolds Using Mixture Model CNNs
    • 771
    • PDF
    Self-Attention Equipped Graph Convolutions for Disease Prediction
    • 8
    • PDF
    Graph Attention Networks
    • 2,349
    • Highly Influential
    • PDF
    Inductive Representation Learning on Large Graphs
    • 2,528
    • Highly Influential
    • PDF
    Semi-Supervised Classification with Graph Convolutional Networks
    • 5,694
    • PDF
    Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering
    • 2,520
    • PDF
    Learning Deep Features for Discriminative Localization
    • 2,950
    • PDF
    Geometric Deep Learning: Going beyond Euclidean data
    • 1,228
    • PDF