Self-supervised graph representations of WSIs

Oscar Pina, Verónica Vilaplana
Proceedings of the First International Workshop on Geometric Deep Learning in Medical Image Analysis, PMLR 194:107-117, 2022.

Abstract

In this manuscript we propose a framework for the analysis of whole slide images (WSI) on the cell entity space with self-supervised deep learning on graphs and explore its representation quality at different levels of application. It consists of a two step process in which the cell level analysis is performed locally, by clusters of nearby cells that can be seen as small regions of the image, in order to learn representations that capture the cell environment and distribution. In a second stage, a WSI graph is generated with these regions as nodes and the representations learned as initial node embeddings. The graph is leveraged for a downstream task, region of interest (ROI) detection addressed as a graph clustering. The representations outperform the evaluation baselines at both levels of application, which has been carried out predicting whether a cell, or region, is tumor or not based on its learned representations with a logistic regressor.

Cite this Paper

BibTeX
@InProceedings{pmlr-v194-pina22a, title = {Self-supervised graph representations of WSIs}, author = {Pina, Oscar and Vilaplana, Ver\'onica}, booktitle = {Proceedings of the First International Workshop on Geometric Deep Learning in Medical Image Analysis}, pages = {107--117}, year = {2022}, editor = {Bekkers, Erik and Wolterink, Jelmer M. and Aviles-Rivero, Angelica}, volume = {194}, series = {Proceedings of Machine Learning Research}, month = {18 Nov}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v194/pina22a/pina22a.pdf}, url = {https://proceedings.mlr.press/v194/pina22a.html}, abstract = {In this manuscript we propose a framework for the analysis of whole slide images (WSI) on the cell entity space with self-supervised deep learning on graphs and explore its representation quality at different levels of application. It consists of a two step process in which the cell level analysis is performed locally, by clusters of nearby cells that can be seen as small regions of the image, in order to learn representations that capture the cell environment and distribution. In a second stage, a WSI graph is generated with these regions as nodes and the representations learned as initial node embeddings. The graph is leveraged for a downstream task, region of interest (ROI) detection addressed as a graph clustering. The representations outperform the evaluation baselines at both levels of application, which has been carried out predicting whether a cell, or region, is tumor or not based on its learned representations with a logistic regressor.} }
Endnote
%0 Conference Paper %T Self-supervised graph representations of WSIs %A Oscar Pina %A Verónica Vilaplana %B Proceedings of the First International Workshop on Geometric Deep Learning in Medical Image Analysis %C Proceedings of Machine Learning Research %D 2022 %E Erik Bekkers %E Jelmer M. Wolterink %E Angelica Aviles-Rivero %F pmlr-v194-pina22a %I PMLR %P 107--117 %U https://proceedings.mlr.press/v194/pina22a.html %V 194 %X In this manuscript we propose a framework for the analysis of whole slide images (WSI) on the cell entity space with self-supervised deep learning on graphs and explore its representation quality at different levels of application. It consists of a two step process in which the cell level analysis is performed locally, by clusters of nearby cells that can be seen as small regions of the image, in order to learn representations that capture the cell environment and distribution. In a second stage, a WSI graph is generated with these regions as nodes and the representations learned as initial node embeddings. The graph is leveraged for a downstream task, region of interest (ROI) detection addressed as a graph clustering. The representations outperform the evaluation baselines at both levels of application, which has been carried out predicting whether a cell, or region, is tumor or not based on its learned representations with a logistic regressor.
APA
Pina, O. & Vilaplana, V.. (2022). Self-supervised graph representations of WSIs. Proceedings of the First International Workshop on Geometric Deep Learning in Medical Image Analysis, in Proceedings of Machine Learning Research 194:107-117 Available from https://proceedings.mlr.press/v194/pina22a.html.

Related Material