Pix2pix Conditional Generative Adversarial Networks for Scheimpflug Camera Color-Coded Corneal Tomography Image Generation

Purpose: To assess the ability of pix2pix conditional generative adversarial network (pix2pix cGAN) to create plausible synthesized Scheimpflug camera color-coded corneal tomography images based upon a modest-sized original dataset to be used for image augmentation during training a deep convolutional neural network (DCNN) for classification of keratoconus and normal corneal images. Methods: Original images of 1778 eyes of 923 nonconsecutive patients with or without keratoconus were retrospectively analyzed. Images were labeled and preprocessed for use in training the proposed pix2pix cGAN. The best quality synthesized images were selected based on the Frechet inception distance score, and their quality was studied by calculating the mean square error, structural similarity index, and the peak signal-to-noise ratio. We used original, traditionally augmented original and synthesized images to train a DCNN for image classification and compared classification performance metrics. Results: The pix2pix cGAN synthesized images showed plausible subjectively and objectively assessed quality. Training the DCNN with a combination of real and synthesized images allowed better classification performance compared with training using original images only or with traditional augmentation. Conclusions: Using the pix2pix cGAN to synthesize corneal tomography images can overcome issues related to small datasets and class imbalance when training computer-aided diagnostic models. Translational Relevance: Pix2pix cGAN can provide an unlimited supply of plausible synthetic Scheimpflug camera color-coded corneal tomography images at levels useful for experimental and clinical applications.

Automated summary

The study evaluated the ability of pix2pix cGAN to synthesize realistic Scheimpflug camera color-coded corneal tomography images, and used them for training deep convolutional neural networks for keratoconus and normal corneal image classification. The results showed that the synthesized images had good quality and improved classification performance.