Batch Equalization with a Generative Adversarial Network

Abstract

Advances in automation and imaging have made it possible to capture large image datasets for experiments that span multiple weeks with multiple experimental batches of data. However, accurate biological comparisons across the batches is challenged by the batch-to-batch variation due to uncontrollable experimental noise (e.g., different stain intensity or illumination conditions). To mediate the batch variation (i.e. the batch effect), we developed a batch equalization method that can transfer images from one batch to another while preserving the biological phenotype. The equalization method is trained as a generative adversarial network (GAN), using the StarGAN architecture that has shown considerable ability in doing style transfer for consumer images. After incorporating an additional objective that disentangles batch effect from biological features using an existing GAN framework, we show that the equalized images have less batch information as determined by a batch-prediction task and perform better in a biologically relevant task (e.g., Mechanism of Action prediction).

Evaluating batch correction methods for image-based cell profiling

“…Representation learning methods process the raw pixels from the fluorescent channel images, usually using neural-network-based approaches [26][27]28 . Qian et al 29 trained a generative adversarial network (GAN) to capture the batch effects from one batch using the style transfer framework. The GAN is then used to align the data by transferring the learned style to every image in the other batches.…”