Hyper-AdaC: Adaptive clustering-based hypergraph representation of whole slide images for survival analysis

Hakim Benkirane, Maria Vakalopoulou, Stergios Christodoulidis, Ingrid-Judith Garberis, Stefan Michiels, Paul-Henry Cournède
Proceedings of the 2nd Machine Learning for Health symposium, PMLR 193:405-418, 2022.

Abstract

The emergence of deep learning in the medical field has popularized the development of models to predict survival outcomes from histopathology images in precision oncology. Graph-based formalism has opened interesting perspectives for generating informative representations, as they can be context-aware and model local and global topological structures in the tumor’s microenvironment. However, the critical issue in using graph representations lies in their generalizability. They can suffer from overfitting due to their large sizes or high discrepancies between nodes due to random sampling from WSI. In addition, standard graph formulations are limited to pairwise interactions, which can sometimes fail to represent the reality observed in histopathology and hinder the interpretability of those interactions. In this work, we present Hyper-AdaC, an adaptive clustering-based hypergraph representation to model high-order correlations among different regions of the WSIs while being compact enough to help graph neural networks generalize in the case of survival prediction. We evaluate our approach on $5$ different public available cancer datasets. Our method outperforms most state-of-the-art graph-based methods for survival prediction with WSIs, creating a more efficient and robust alternative to other graph representations. Moreover, due to our formulation, attention maps are depicted at different resolutions depending on the tissue characteristics of each WSI. The code is available at: https://github.com/HakimBenkirane/Hyper-adaC.

Cite this Paper

BibTeX
@InProceedings{pmlr-v193-benkirane22a, title = {Hyper-AdaC: Adaptive clustering-based hypergraph representation of whole slide images for survival analysis}, author = {Benkirane, Hakim and Vakalopoulou, Maria and Christodoulidis, Stergios and Garberis, Ingrid-Judith and Michiels, Stefan and Courn{\`e}de, Paul-Henry}, booktitle = {Proceedings of the 2nd Machine Learning for Health symposium}, pages = {405--418}, year = {2022}, editor = {Parziale, Antonio and Agrawal, Monica and Joshi, Shalmali and Chen, Irene Y. and Tang, Shengpu and Oala, Luis and Subbaswamy, Adarsh}, volume = {193}, series = {Proceedings of Machine Learning Research}, month = {28 Nov}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v193/benkirane22a/benkirane22a.pdf}, url = {https://proceedings.mlr.press/v193/benkirane22a.html}, abstract = {The emergence of deep learning in the medical field has popularized the development of models to predict survival outcomes from histopathology images in precision oncology. Graph-based formalism has opened interesting perspectives for generating informative representations, as they can be context-aware and model local and global topological structures in the tumor’s microenvironment. However, the critical issue in using graph representations lies in their generalizability. They can suffer from overfitting due to their large sizes or high discrepancies between nodes due to random sampling from WSI. In addition, standard graph formulations are limited to pairwise interactions, which can sometimes fail to represent the reality observed in histopathology and hinder the interpretability of those interactions. In this work, we present Hyper-AdaC, an adaptive clustering-based hypergraph representation to model high-order correlations among different regions of the WSIs while being compact enough to help graph neural networks generalize in the case of survival prediction. We evaluate our approach on $5$ different public available cancer datasets. Our method outperforms most state-of-the-art graph-based methods for survival prediction with WSIs, creating a more efficient and robust alternative to other graph representations. Moreover, due to our formulation, attention maps are depicted at different resolutions depending on the tissue characteristics of each WSI. The code is available at: https://github.com/HakimBenkirane/Hyper-adaC.} }
Endnote
%0 Conference Paper %T Hyper-AdaC: Adaptive clustering-based hypergraph representation of whole slide images for survival analysis %A Hakim Benkirane %A Maria Vakalopoulou %A Stergios Christodoulidis %A Ingrid-Judith Garberis %A Stefan Michiels %A Paul-Henry Cournède %B Proceedings of the 2nd Machine Learning for Health symposium %C Proceedings of Machine Learning Research %D 2022 %E Antonio Parziale %E Monica Agrawal %E Shalmali Joshi %E Irene Y. Chen %E Shengpu Tang %E Luis Oala %E Adarsh Subbaswamy %F pmlr-v193-benkirane22a %I PMLR %P 405--418 %U https://proceedings.mlr.press/v193/benkirane22a.html %V 193 %X The emergence of deep learning in the medical field has popularized the development of models to predict survival outcomes from histopathology images in precision oncology. Graph-based formalism has opened interesting perspectives for generating informative representations, as they can be context-aware and model local and global topological structures in the tumor’s microenvironment. However, the critical issue in using graph representations lies in their generalizability. They can suffer from overfitting due to their large sizes or high discrepancies between nodes due to random sampling from WSI. In addition, standard graph formulations are limited to pairwise interactions, which can sometimes fail to represent the reality observed in histopathology and hinder the interpretability of those interactions. In this work, we present Hyper-AdaC, an adaptive clustering-based hypergraph representation to model high-order correlations among different regions of the WSIs while being compact enough to help graph neural networks generalize in the case of survival prediction. We evaluate our approach on $5$ different public available cancer datasets. Our method outperforms most state-of-the-art graph-based methods for survival prediction with WSIs, creating a more efficient and robust alternative to other graph representations. Moreover, due to our formulation, attention maps are depicted at different resolutions depending on the tissue characteristics of each WSI. The code is available at: https://github.com/HakimBenkirane/Hyper-adaC.
APA
Benkirane, H., Vakalopoulou, M., Christodoulidis, S., Garberis, I., Michiels, S. & Cournède, P.. (2022). Hyper-AdaC: Adaptive clustering-based hypergraph representation of whole slide images for survival analysis. Proceedings of the 2nd Machine Learning for Health symposium, in Proceedings of Machine Learning Research 193:405-418 Available from https://proceedings.mlr.press/v193/benkirane22a.html.

Related Material