Automated Segmentation of Epithelial Tissue Using Cycle-Consistent Generative Adversarial Networks

Stephan Eule, Matthias Haering, Joerg Grosshans, Fred Wolf

Abstract: A central problem in biomedical imaging is the preparation of images for further quantitative analysis via automated image segmentation. Recently, fully convolutional neural networks, such as the U-Net were applied successfully in a variety segmentation tasks. A downside of this approach is the requirement for a large amount of well-prepared training samples, consisting of image - ground truth mask pairs. Since these have to be prepared for each experiment by hand this task can be very costly and time-consuming. Here, we present a segmentation method based on cycle consistent generative adversarial networks, which can be trained even in absence of prepared image - mask pairs. We show that it successfully performs image segmentation tasks on samples with substantial defects and even generalises well to different tissue types.

Keywords: Segmentation, GANs, Epithelial Tissue

Author Affiliation: MPIDS, Goettingen, Germany and Universitaetsmedizin Goettingen, Germany