Adnan Tufail

The paper uses an autoencoder to derive retinal phenotypes from OCT images, identifies 118 genetic loci, and shows their relevance to retinal morphology and disease prediction.

The paper introduces MR-Fish, a method using proteomics and Mendelian randomisation to identify causal relationships between proteins and diseases, finding causal links for several proteins associated with conditions like T2DM and CHD.

This study identifies early microvascular damage in diabetic retinas before clinical DR diagnosis and finds no spatial correlation between capillary dropout and neural cell loss in the inner nuclear layer.

This paper uses deep learning to generate perfusion maps from structural OCT images without expert labels, outperforming clinicians in fidelity.