Creating realistic anterior segment optical coherence tomography images using generative adversarial networks.

Aims: To develop a generative adversarial network (GAN) capable of generating realistic high-resolution anterior segment optical coherence tomography (AS-OCT) images.

Methods: This study included 142 628 AS-OCT B-scans from the American University of Beirut Medical Center. The Style and WAvelet based GAN architecture was trained to generate realistic AS-OCT images and was evaluated through the Fréchet Inception Distance (FID) Score and a blinded assessment by three refractive surgeons who were asked to distinguish between real and generated images.

Polygenic and Network-based studies in risk identification and demystification of cancer.

Introduction: Diseases were initially thought to be the consequence of a single gene mutation. Advances in DNA sequencing tools and our understanding of gene behavior have revealed that complex diseases, such as cancer, are the product of genes cooperating with each other and with their environment in orchestrated communication networks. Seeing that the function of individual genes is still used to analyze cancer, the shift to using functionally interacting groups of genes as a new unit of study holds promise for demystifying cancer.