Using Hierarchically Connected Nodes and Multiple GNN Message Passing Steps to Increase the Contextual Information in Cell-Graph Classification

J. Sims*, H.I. Grabsch, D. Magee

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingAcademicpeer-review

Abstract

Graphs are useful in analysing histopathological images as they are able to represent neighbourhood interactions and spatial relationships. Typically graph nodes represent cells and the vertices are constructed by applying a nearest neighbor algorithm to cell's locations. When passing these graphs through one graph neural network (GNN) message passing step, each node can only utilise features from nodes within its immediate neighbourhood to make a classification. To overcome this, we introduce two levels of hierarchically connected nodes that we term "supernodes". These supernodes, used in conjunction with at least four GNN message passing steps, allow for cell node classifications to be influenced by a wider area, enabling the entire graph to learn tissue-level structures. The method is evaluated on a supervised task to classify individual cells as belonging to a specific tissue class. Results demonstrate that the inclusion of supernodes with multiple GNN message passing steps increases model accuracy.
Original languageEnglish
Title of host publicationIMAGING SYSTEMS FOR GI ENDOSCOPY, AND GRAPHS IN BIOMEDICAL IMAGE ANALYSIS, ISGIE 2022
EditorsL Manfredi, S Ahmadi, M Bronstein, A Kazi, D Lomanto, A Mathew, L Magerand, K Mullakaeva, B Papiez, RH Taylor, E Trucco
PublisherSpringer International Publishing AG
Pages99-107
Number of pages9
Volume13754
ISBN (Electronic)978-3-031-21083-9
ISBN (Print)9783031210822
DOIs
Publication statusPublished - 2022
EventMICCAI 2022 Imaging Systems for GI Endoscopy (ISGIE) - Singapore, Singapore
Duration: 18 Sept 2022 → …
https://miccai2022-isgie.github.io/

Publication series

SeriesLecture Notes in Computer Science
Volume13754
ISSN0302-9743

Workshop

WorkshopMICCAI 2022 Imaging Systems for GI Endoscopy (ISGIE)
Abbreviated titleMICCAI 2022
Country/TerritorySingapore
CitySingapore
Period18/09/22 → …
Internet address

Keywords

  • Graph neural network
  • Node classification
  • Digital pathology
  • HETEROGENEITY

Fingerprint

Dive into the research topics of 'Using Hierarchically Connected Nodes and Multiple GNN Message Passing Steps to Increase the Contextual Information in Cell-Graph Classification'. Together they form a unique fingerprint.

Cite this