Journal article

Classifying Retinal Degeneration in Histological Sections Using Deep Learning

Daniel Al Mouiee, Erik Meijering, Michael Kalloniatis, Lisa Nivison-Smith, Richard A Williams, David AX Nayagam, Thomas C Spencer, Chi D Luu, Ceara McGowan, Stephanie B Epp, Mohit N Shivdasani

TRANSLATIONAL VISION SCIENCE & TECHNOLOGY | ASSOC RESEARCH VISION OPHTHALMOLOGY INC | Published : 2021

Abstract

Purpose: Artificial intelligence (AI) techniques are increasingly being used to classify retinal diseases. In this study we investigated the ability of a convolutional neural network (CNN) in categorizing histological images into different classes of retinal degeneration. Methods: Images were obtained from a chemically induced feline model of monocular retinal dystrophy and split into training and testing sets. The training set was graded for the level of retinal degeneration and used to train various CNN architectures. The testing set was evaluated through the best architecture and graded by six observers. Comparisons between model and observer classifications, and interobserver variability..

View full abstract

Grants

Awarded by National Health and Medical Research Council (NHMRC)


Funding Acknowledgements

The authors thank the staff of the Biological Resource Centre, University of Melbourne at theRoyal Victorian Eye and Ear Hospital for assistance with animal husbandry. Funding for conducting the animal experiments was provided by the National Health and Medical Research Council (NHMRC) Project Grant (GNT1063093). The Bionics Institute acknowledges the support it receives from the Victorian Government through its Operational Infrastructure Support Program.