Learning Generative Models of Tissue Organization with Supervised GANs
This work addresses the need for generative models of tissue organization in biomedical imaging, offering an incremental improvement by unifying stages into an end-to-end framework.
The paper tackles the problem of generating realistic electron microscope images with cell membrane and mitochondria annotations by proposing a two-stage supervised GAN approach, resulting in accurate synthetic images validated through shape features, segmentation accuracies, and user studies.
A key step in understanding the spatial organization of cells and tissues is the ability to construct generative models that accurately reflect that organization. In this paper, we focus on building generative models of electron microscope (EM) images in which the positions of cell membranes and mitochondria have been densely annotated, and propose a two-stage procedure that produces realistic images using Generative Adversarial Networks (or GANs) in a supervised way. In the first stage, we synthesize a label "image" given a noise "image" as input, which then provides supervision for EM image synthesis in the second stage. The full model naturally generates label-image pairs. We show that accurate synthetic EM images are produced using assessment via (1) shape features and global statistics, (2) segmentation accuracies, and (3) user studies. We also demonstrate further improvements by enforcing a reconstruction loss on intermediate synthetic labels and thus unifying the two stages into one single end-to-end framework.