HIEGNet: A Heterogenous Graph Neural Network Including the Immune Environment in Glomeruli Classification

Niklas Kormann, Masoud Ramuz, Zeeshan Nisar, Nadine S. Schaadt, Hendrik Annuth, Benjamin Doerr, Friedrich Feuerhake, Thomas Lampert, Johannes F. Lutzeyer
Proceedings of The 8th International Conference on Medical Imaging with Deep Learning, PMLR 301:763-786, 2026.

Abstract

Graph Neural Networks (GNNs) have recently been found to excel in histopathology. However, an important histopathological task, where GNNs have not been extensively explored, is the classification of glomeruli health as an important indicator in nephropathology. This task presents unique difficulties, particularly for the graph construction, i.e., the identification of nodes, edges, and informative features. In this work, we propose a pipeline composed of different traditional and machine learning-based computer vision techniques to identify nodes, edges, and their corresponding features to form a heterogeneous graph. We then proceed to propose a novel heterogeneous GNN architecture for glomeruli classification, called HIEGNet, that integrates both glomeruli and their surrounding immune cells. Hence, HIEGNet is able to consider the immune environment of each glomerulus in its classification. Our HIEGNet was trained and tested on a dataset of Whole Slide Images from kidney transplant patients. Experimental results demonstrate that HIEGNet outperforms several baseline models and generalises best between patients among all baseline models. Our implementation is publicly available at https://github.com/nklsKrmnn/HIEGNet.git.

Cite this Paper

BibTeX
@InProceedings{pmlr-v301-kormann26a, title = {HIEGNet: A Heterogenous Graph Neural Network Including the Immune Environment in Glomeruli Classification}, author = {Kormann, Niklas and Ramuz, Masoud and Nisar, Zeeshan and Schaadt, Nadine S. and Annuth, Hendrik and Doerr, Benjamin and Feuerhake, Friedrich and Lampert, Thomas and Lutzeyer, Johannes F.}, booktitle = {Proceedings of The 8th International Conference on Medical Imaging with Deep Learning}, pages = {763--786}, year = {2026}, editor = {Tasdizen, Tolga and Elhabian, Shireen and Summers, Ronald and Chen, Chen and Koch, Lisa and Zhuang, Yan}, volume = {301}, series = {Proceedings of Machine Learning Research}, month = {09--11 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v301/main/assets/kormann26a/kormann26a.pdf}, url = {https://proceedings.mlr.press/v301/kormann26a.html}, abstract = {Graph Neural Networks (GNNs) have recently been found to excel in histopathology. However, an important histopathological task, where GNNs have not been extensively explored, is the classification of glomeruli health as an important indicator in nephropathology. This task presents unique difficulties, particularly for the graph construction, i.e., the identification of nodes, edges, and informative features. In this work, we propose a pipeline composed of different traditional and machine learning-based computer vision techniques to identify nodes, edges, and their corresponding features to form a heterogeneous graph. We then proceed to propose a novel heterogeneous GNN architecture for glomeruli classification, called HIEGNet, that integrates both glomeruli and their surrounding immune cells. Hence, HIEGNet is able to consider the immune environment of each glomerulus in its classification. Our HIEGNet was trained and tested on a dataset of Whole Slide Images from kidney transplant patients. Experimental results demonstrate that HIEGNet outperforms several baseline models and generalises best between patients among all baseline models. Our implementation is publicly available at https://github.com/nklsKrmnn/HIEGNet.git.} }
Endnote
%0 Conference Paper %T HIEGNet: A Heterogenous Graph Neural Network Including the Immune Environment in Glomeruli Classification %A Niklas Kormann %A Masoud Ramuz %A Zeeshan Nisar %A Nadine S. Schaadt %A Hendrik Annuth %A Benjamin Doerr %A Friedrich Feuerhake %A Thomas Lampert %A Johannes F. Lutzeyer %B Proceedings of The 8th International Conference on Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2026 %E Tolga Tasdizen %E Shireen Elhabian %E Ronald Summers %E Chen Chen %E Lisa Koch %E Yan Zhuang %F pmlr-v301-kormann26a %I PMLR %P 763--786 %U https://proceedings.mlr.press/v301/kormann26a.html %V 301 %X Graph Neural Networks (GNNs) have recently been found to excel in histopathology. However, an important histopathological task, where GNNs have not been extensively explored, is the classification of glomeruli health as an important indicator in nephropathology. This task presents unique difficulties, particularly for the graph construction, i.e., the identification of nodes, edges, and informative features. In this work, we propose a pipeline composed of different traditional and machine learning-based computer vision techniques to identify nodes, edges, and their corresponding features to form a heterogeneous graph. We then proceed to propose a novel heterogeneous GNN architecture for glomeruli classification, called HIEGNet, that integrates both glomeruli and their surrounding immune cells. Hence, HIEGNet is able to consider the immune environment of each glomerulus in its classification. Our HIEGNet was trained and tested on a dataset of Whole Slide Images from kidney transplant patients. Experimental results demonstrate that HIEGNet outperforms several baseline models and generalises best between patients among all baseline models. Our implementation is publicly available at https://github.com/nklsKrmnn/HIEGNet.git.
APA
Kormann, N., Ramuz, M., Nisar, Z., Schaadt, N.S., Annuth, H., Doerr, B., Feuerhake, F., Lampert, T. & Lutzeyer, J.F.. (2026). HIEGNet: A Heterogenous Graph Neural Network Including the Immune Environment in Glomeruli Classification. Proceedings of The 8th International Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 301:763-786 Available from https://proceedings.mlr.press/v301/kormann26a.html.

Related Material