Unsupervisedly Training GANs for Segmenting Digital Pathology with Automatically Generated Annotations

Michael Gadermayr, Laxmi Gupta, Barbara M. Klinkhammer, Peter Boor, Dorit Merhof

Code Of Conduct: I have read and accept the code of conduct.

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.

Remove If Rejected: (optional) Remove submission if paper is rejected.

Keywords: Adversarial Networks, Histology, Kidney, Segmentation, Unsupervised