A graph neural network framework for mapping histological topology in oral mucosal tissue.

Journal: BMC bioinformatics
PMID:

Abstract

BACKGROUND: Histological feature representation is advantageous for computer aided diagnosis (CAD) and disease classification when using predictive techniques based on machine learning. Explicit feature representations in computer tissue models can assist explainability of machine learning predictions. Different approaches to feature representation within digital tissue images have been proposed. Cell-graphs have been demonstrated to provide precise and general constructs that can model both low- and high-level features. The basement membrane is high-level tissue architecture, and interactions across the basement membrane are involved in multiple disease processes. Thus, the basement membrane is an important histological feature to study from a cell-graph and machine learning perspective.

Authors

  • Aravind Nair
    Division of Theoretical Computer Science, Department of Computer Science, KTH Royal Institute of Technology, Stockholm, Sweden.
  • Helena Arvidsson
    Division of Oral Diagnostics and Rehabilitation, Department of Dental Medicine, Karolinska Institutet, Stockholm, Sweden.
  • Jorge E Gatica V
    Division of Theoretical Computer Science, Department of Computer Science, KTH Royal Institute of Technology, Stockholm, Sweden.
  • Nikolce Tudzarovski
    Division of Oral Diagnostics and Rehabilitation, Department of Dental Medicine, Karolinska Institutet, Stockholm, Sweden.
  • Karl Meinke
    Division of Theoretical Computer Science, Department of Computer Science, KTH Royal Institute of Technology, Stockholm, Sweden.
  • Rachael V Sugars
    Division of Oral Diagnostics and Rehabilitation, Department of Dental Medicine, Karolinska Institutet, Stockholm, Sweden. rachael.sugars@ki.se.