Abstract: Multi-level Cancer Profiling through Joint Cell-graph Representations

Rivera Monroy LC, Rist L, Wilm F, Ostalecki C, Baur A, Vera González J, Breininger K, Maier A (2025)

Publication Type: Conference contribution

Publication year: 2025

Journal

Informatik aktuell Gesellschaft für Informatik (GI)

Publisher: Springer Link

Edited Volumes: Bildverarbeitung für die Medizin 2025

Series: Informatik aktuell

Pages Range: 156-156

Conference Proceedings Title: Bildverarbeitung für die Medizin 2025

Event location: Regensburg DE

ISBN: 9783658474218

DOI: 10.1007/978-3-658-47422-5_34

Abstract

Digital pathology has enabled advanced cancer analysis, yet traditional patch-based methods struggle to capture complex, topological structures in whole-slide images (WSIs). This study introduces a graph-based framework using graph neural networks (GNNs) to model histopathology samples as multi-level cell graphs, integrating both cell- and disease-level information for improved classification. Our approach encompasses five cancer types and two staining protocols, modeling each sample as a graph to capture spatial and phenotypic relationships between cells and diseases. We implemented this framework using graph random neural networks (GRAND) [1], achieving a cell-level classification accuracy of 88% and a disease-level accuracy of 83%, significantly outperforming CNN and XGBoost baselines [2, 3]. These results emphasize the potential of GNNs to generalize across multiple cancers and staining methods, providing a valuable diagnostic tool for pathologists. Future research will extend this model to additional cancer types and explore its applicability and robustness in diverse clinical settings, with the goal of achieving interpretable and scalable computational pathology solutions [4].

Authors with CRIS profile

Luis Carlos Rivera Monroy Lehrstuhl für Informatik 5 (Mustererkennung) Leonhard Rist Lehrstuhl für Informatik 5 (Mustererkennung) Frauke Wilm Lehrstuhl für Informatik 5 (Mustererkennung) Christian Ostalecki Department of Dermatology Andreas Baur Department of Dermatology Julio Vera González Professur für Tumorimmunologie (Schwerpunkt Systembiologie) Katharina Breininger Department Artificial Intelligence in Biomedical Engineering (AIBE) Andreas Maier Lehrstuhl für Informatik 5 (Mustererkennung)

How to cite

APA:

Rivera Monroy, L.C., Rist, L., Wilm, F., Ostalecki, C., Baur, A., Vera González, J.,... Maier, A. (2025). Abstract: Multi-level Cancer Profiling through Joint Cell-graph Representations. In Bildverarbeitung für die Medizin 2025 (pp. 156-156). Regensburg, DE: Springer Link.

MLA:

Rivera Monroy, Luis Carlos, et al. "Abstract: Multi-level Cancer Profiling through Joint Cell-graph Representations." Proceedings of the German Conference on Medical Image Computing, Regensburg Springer Link, 2025. 156-156.

BibTeX: Download