Generalizability of Deep Neural Networks for Vertical Cup-to-Disc Ratio Estimation in Ultra-Widefield and Smartphone-Based Fundus Images.

Purpose: To develop and validate a deep learning system (DLS) for estimation of vertical cup-to-disc ratio (vCDR) in ultra-widefield (UWF) and smartphone-based fundus images.

Methods: A DLS consisting of two sequential convolutional neural networks (CNNs) to delineate optic disc (OD) and optic cup (OC) boundaries was developed using 800 standard fundus images from the public REFUGE data set. The CNNs were tested on 400 test images from the REFUGE data set and 296 UWF and 300 smartphone-based images from a teleophthalmology clinic.

Comparison of Efficacy and Safety of XEN45 Implant Versus Trabeculectomy in Asian Eyes.

Prcis: Combined phacoemulsification and trabeculectomy is able to achieve greater reduction in intraocular pressure (IOP), higher rates of complete surgical success and fewer postoperative manipulations and visits compared with combined phacoemulsification and Xen implantation in glaucomatous eyes.

Purpose: Our study aims to compare and understand the differences between the efficacy and safety of XEN45 implantation and trabeculectomy in Asian eyes with glaucoma.

Materials And Methods: This was a retrospective, single-center, comparative study of consecutive patients who underwent combined phacoemulsification and trabeculectomy (Phaco-Trab) from January 2013 to June 2014 and combined phacoemulsification and XEN45 implantation (Phaco-Xen) from May 2017 to September 2018 in a tertiary Ophthalmology center in Singapore.