GANs for Biological Image Synthesis
This work addresses the challenge of generating biologically relevant synthetic images for microscopy, which could aid in data augmentation and prediction tasks in cell biology, though it is incremental as it adapts existing GAN methods to a new domain.
The paper tackles the problem of synthesizing realistic multi-channel biological cell images using Generative Adversarial Networks (GANs), achieving the ability to generate images that capture spatial correlations between fluorescent proteins and mimic temporal changes in protein localization during the cell cycle.
In this paper, we propose a novel application of Generative Adversarial Networks (GAN) to the synthesis of cells imaged by fluorescence microscopy. Compared to natural images, cells tend to have a simpler and more geometric global structure that facilitates image generation. However, the correlation between the spatial pattern of different fluorescent proteins reflects important biological functions, and synthesized images have to capture these relationships to be relevant for biological applications. We adapt GANs to the task at hand and propose new models with casual dependencies between image channels that can generate multi-channel images, which would be impossible to obtain experimentally. We evaluate our approach using two independent techniques and compare it against sensible baselines. Finally, we demonstrate that by interpolating across the latent space we can mimic the known changes in protein localization that occur through time during the cell cycle, allowing us to predict temporal evolution from static images.