Deep Learning for Cornea Microscopy Blind Deblurring

TL;DR

This paper proposes a deep learning approach to deblur and upscale cornea microscopy images, addressing the challenge of spherical eye shape distortion in medical imaging.

Contribution

It introduces a novel deep learning model combining deblurring and super-resolution specifically for cornea microscopy images.

Findings

Effective deblurring of cornea images demonstrated

Improved image resolution achieved with the proposed model

Potential for enhanced medical diagnosis accuracy

Abstract

The goal of this project is to build a deep-learning solution that deblurs cornea scans, used for medical examination. The spherical shape of the eye prevents ophtamologist from having completely sharp image. Provided with a stack of corneas from confocal images, our approach is to build a model that performs an upscaling of the images using an SR (Super Resolution) Network.