Generative Modeling with Conditional Autoencoders: Building an Integrated Cell

TL;DR

This paper introduces a conditional generative model that captures cell and nuclear morphology variations and subcellular structure localization from microscopy images, enabling realistic image synthesis and structure prediction.

Contribution

It presents a novel conditional autoencoder framework that models cell morphology and structure localization probabilistically, generalizing across diverse subcellular localizations.

Findings

Produces photo-realistic cell images

Predicts unobserved structure localization

Demonstrates effective generalization

Abstract

We present a conditional generative model to learn variation in cell and nuclear morphology and the location of subcellular structures from microscopy images. Our model generalizes to a wide range of subcellular localization and allows for a probabilistic interpretation of cell and nuclear morphology and structure localization from fluorescence images. We demonstrate the effectiveness of our approach by producing photo-realistic cell images using our generative model. The conditional nature of the model provides the ability to predict the localization of unobserved structures given cell and nuclear morphology.