Graph neural networks in multi-stained pathological imaging: extended comparative analysis of Radiomic features.

Journal: International journal of computer assisted radiology and surgery
Published Date:

Abstract

PURPOSE: This study investigates the application of Radiomic features within graph neural networks (GNNs) for the classification of multiple-epitope-ligand cartography (MELC) pathology samples. It aims to enhance the diagnosis of often misdiagnosed skin diseases such as eczema, lymphoma, and melanoma. The novel contribution lies in integrating Radiomic features with GNNs and comparing their efficacy against traditional multi-stain profiles.

Authors

  • Luis Carlos Rivera Monroy
    Pattern Recognition Lab, Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, Germany. luis.rivera@fau.de.
  • Leonhard Rist
    Pattern Recognition Lab, Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, Germany.
  • Christian Ostalecki
    Department of Dermatology, Universitätsklinikum Erlangen, Erlangen, Germany.
  • Andreas Bauer
    Department of Dermatology, Universitätsklinikum Erlangen, Erlangen, Germany.
  • Julio Vera
    Laboratory of Systems Tumor Immunology, Department of Dermatology, Erlangen University Hospital and Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, Germany.
  • Katharina Breininger
  • Andreas Maier
    Pattern Recognition Lab, University Erlangen-Nürnberg, Erlangen, Germany.