Uncertainty-based Graph Convolutional Networks for Organ Segmentation Refinement

Roger D. Soberanis-Mukul, Nassir Navab, Shadi Albarqouni
Proceedings of the Third Conference on Medical Imaging with Deep Learning, PMLR 121:755-769, 2020.

Abstract

Organ segmentation in CT volumes is an important pre-processing step in many computer assisted intervention and diagnosis methods. In recent years, convolutional neural networks have dominated the state of the art in this task. However, since this problem presents a challenging environment due to high variability in the organ’s shape and similarity between tissues, the generation of false negative and false positive regions in the output segmentation is a common issue. Recent works have shown that the uncertainty analysis of the model can provide us with useful information about potential errors in the segmentation. In this context, we proposed a segmentation refinement method based on uncertainty analysis and graph convolutional networks. We employ the uncertainty levels of the convolutional network in a particular input volume to formulate a semi-supervised graph learning problem that is solved by training a graph convolutional network. To test our method we refine the initial output of a 2D U-Net. We validate our framework with the NIH pancreas dataset and the spleen dataset of the medical segmentation decathlon. We show that our method outperfroms the state-of-the art CRF refinement method by improving the dice score by $1%$ for the pancreas and $2%$ for spleen, with respect to the original U-Net’s prediction. Finally, we discuss the results and current limitations of the model for future work in this research direction. For reproducibility purposes, we make our code publicly available: {https://github.com/rodsom22/gcn_refinement}.

Cite this Paper

BibTeX
@InProceedings{pmlr-v121-soberanis-mukul20a, title = {Uncertainty-based Graph Convolutional Networks for Organ Segmentation Refinement}, author = {Soberanis-Mukul, Roger D. and Navab, Nassir and Albarqouni, Shadi}, booktitle = {Proceedings of the Third Conference on Medical Imaging with Deep Learning}, pages = {755--769}, year = {2020}, editor = {Arbel, Tal and Ben Ayed, Ismail and de Bruijne, Marleen and Descoteaux, Maxime and Lombaert, Herve and Pal, Christopher}, volume = {121}, series = {Proceedings of Machine Learning Research}, month = {06--08 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v121/soberanis-mukul20a/soberanis-mukul20a.pdf}, url = {https://proceedings.mlr.press/v121/soberanis-mukul20a.html}, abstract = {Organ segmentation in CT volumes is an important pre-processing step in many computer assisted intervention and diagnosis methods. In recent years, convolutional neural networks have dominated the state of the art in this task. However, since this problem presents a challenging environment due to high variability in the organ’s shape and similarity between tissues, the generation of false negative and false positive regions in the output segmentation is a common issue. Recent works have shown that the uncertainty analysis of the model can provide us with useful information about potential errors in the segmentation. In this context, we proposed a segmentation refinement method based on uncertainty analysis and graph convolutional networks. We employ the uncertainty levels of the convolutional network in a particular input volume to formulate a semi-supervised graph learning problem that is solved by training a graph convolutional network. To test our method we refine the initial output of a 2D U-Net. We validate our framework with the NIH pancreas dataset and the spleen dataset of the medical segmentation decathlon. We show that our method outperfroms the state-of-the art CRF refinement method by improving the dice score by $1%$ for the pancreas and $2%$ for spleen, with respect to the original U-Net’s prediction. Finally, we discuss the results and current limitations of the model for future work in this research direction. For reproducibility purposes, we make our code publicly available: {https://github.com/rodsom22/gcn_refinement}.} }
Endnote
%0 Conference Paper %T Uncertainty-based Graph Convolutional Networks for Organ Segmentation Refinement %A Roger D. Soberanis-Mukul %A Nassir Navab %A Shadi Albarqouni %B Proceedings of the Third Conference on Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2020 %E Tal Arbel %E Ismail Ben Ayed %E Marleen de Bruijne %E Maxime Descoteaux %E Herve Lombaert %E Christopher Pal %F pmlr-v121-soberanis-mukul20a %I PMLR %P 755--769 %U https://proceedings.mlr.press/v121/soberanis-mukul20a.html %V 121 %X Organ segmentation in CT volumes is an important pre-processing step in many computer assisted intervention and diagnosis methods. In recent years, convolutional neural networks have dominated the state of the art in this task. However, since this problem presents a challenging environment due to high variability in the organ’s shape and similarity between tissues, the generation of false negative and false positive regions in the output segmentation is a common issue. Recent works have shown that the uncertainty analysis of the model can provide us with useful information about potential errors in the segmentation. In this context, we proposed a segmentation refinement method based on uncertainty analysis and graph convolutional networks. We employ the uncertainty levels of the convolutional network in a particular input volume to formulate a semi-supervised graph learning problem that is solved by training a graph convolutional network. To test our method we refine the initial output of a 2D U-Net. We validate our framework with the NIH pancreas dataset and the spleen dataset of the medical segmentation decathlon. We show that our method outperfroms the state-of-the art CRF refinement method by improving the dice score by $1%$ for the pancreas and $2%$ for spleen, with respect to the original U-Net’s prediction. Finally, we discuss the results and current limitations of the model for future work in this research direction. For reproducibility purposes, we make our code publicly available: {https://github.com/rodsom22/gcn_refinement}.
APA
Soberanis-Mukul, R.D., Navab, N. & Albarqouni, S.. (2020). Uncertainty-based Graph Convolutional Networks for Organ Segmentation Refinement. Proceedings of the Third Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 121:755-769 Available from https://proceedings.mlr.press/v121/soberanis-mukul20a.html.

Related Material