Unsupervisedly Training GANs for Segmenting Digital Pathology with Automatically Generated Annotations

Michael Gadermayr, Laxmi Gupta, Barbara M. Klinkhammer, Peter Boor, Dorit Merhof
Proceedings of The 2nd International Conference on Medical Imaging with Deep Learning, PMLR 102:175-184, 2019.

Abstract

Recently, generative adversarial networks exhibited excellent performances in semi-supervised image analysis scenarios. In this paper, we go even further by proposing a fully unsupervised approach for segmentation applications with prior knowledge of the objects’ shapes. We propose and investigate different strategies to generate simulated label data and perform image-to-image translation between the image and the label domain using an adversarial model. For experimental evaluation, we consider the segmentation of the glomeruli, an application scenario from renal pathology. Experiments provide proof of concept and also confirm that the strategy for creating the simulated label data is of particular relevance considering the stability of GAN trainings.

Cite this Paper

BibTeX
@InProceedings{pmlr-v102-gadermayr19a, title = {Unsupervisedly Training GANs for Segmenting Digital Pathology with Automatically Generated Annotations}, author = {Gadermayr, Michael and Gupta, Laxmi and Klinkhammer, Barbara M. and Boor, Peter and Merhof, Dorit}, booktitle = {Proceedings of The 2nd International Conference on Medical Imaging with Deep Learning}, pages = {175--184}, year = {2019}, editor = {Cardoso, M. Jorge and Feragen, Aasa and Glocker, Ben and Konukoglu, Ender and Oguz, Ipek and Unal, Gozde and Vercauteren, Tom}, volume = {102}, series = {Proceedings of Machine Learning Research}, month = {08--10 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v102/gadermayr19a/gadermayr19a.pdf}, url = {https://proceedings.mlr.press/v102/gadermayr19a.html}, abstract = {Recently, generative adversarial networks exhibited excellent performances in semi-supervised image analysis scenarios. In this paper, we go even further by proposing a fully unsupervised approach for segmentation applications with prior knowledge of the objects’ shapes. We propose and investigate different strategies to generate simulated label data and perform image-to-image translation between the image and the label domain using an adversarial model. For experimental evaluation, we consider the segmentation of the glomeruli, an application scenario from renal pathology. Experiments provide proof of concept and also confirm that the strategy for creating the simulated label data is of particular relevance considering the stability of GAN trainings.} }
Endnote
%0 Conference Paper %T Unsupervisedly Training GANs for Segmenting Digital Pathology with Automatically Generated Annotations %A Michael Gadermayr %A Laxmi Gupta %A Barbara M. Klinkhammer %A Peter Boor %A Dorit Merhof %B Proceedings of The 2nd International Conference on Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2019 %E M. Jorge Cardoso %E Aasa Feragen %E Ben Glocker %E Ender Konukoglu %E Ipek Oguz %E Gozde Unal %E Tom Vercauteren %F pmlr-v102-gadermayr19a %I PMLR %P 175--184 %U https://proceedings.mlr.press/v102/gadermayr19a.html %V 102 %X Recently, generative adversarial networks exhibited excellent performances in semi-supervised image analysis scenarios. In this paper, we go even further by proposing a fully unsupervised approach for segmentation applications with prior knowledge of the objects’ shapes. We propose and investigate different strategies to generate simulated label data and perform image-to-image translation between the image and the label domain using an adversarial model. For experimental evaluation, we consider the segmentation of the glomeruli, an application scenario from renal pathology. Experiments provide proof of concept and also confirm that the strategy for creating the simulated label data is of particular relevance considering the stability of GAN trainings.
APA
Gadermayr, M., Gupta, L., Klinkhammer, B.M., Boor, P. & Merhof, D.. (2019). Unsupervisedly Training GANs for Segmenting Digital Pathology with Automatically Generated Annotations. Proceedings of The 2nd International Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 102:175-184 Available from https://proceedings.mlr.press/v102/gadermayr19a.html.

Related Material