Methods for Exploiting High Resolution Imagery for Deep Learning Based Diabetic Retinopathy Detection and Grading

Methods for Exploiting High Resolution Imagery for Deep Learning Based Diabetic Retinopathy Detection and Grading

Presenter(s)

Adam Saunders

Comments

Presentation: 11:00 a.m.-12:00 p.m., Kennedy Union Boll Theatre

Description

Diabetic retinopathy is a disease that affects the eyes of people with diabetes, and it can cause blindness. To diagnose diabetic retinopathy, ophthalmologists image the back surface of the inside of the eye, a process referred to as fundus photography. Ophthalmologists must then diagnose and grade the severity of diabetic retinopathy by analyzing details in the image, which can be difficult and time-consuming. Alternatively, due to the availability of labeled datasets containing fundus images with diabetic retinopathy, AI methods like deep learning can provide automated detection and grading algorithms. These deep learning algorithms sometimes use images at a much lower resolution than is available from fundus photography. However, we show that the resolution of a image has a large effect on the accuracy of the algorithm. Here, we study several techniques to increase the accuracy of the algorithm by taking advantage of higher-resolution data, including increasing the network input size, introducing a region-of-interest channel, and using a non-uniform downsampling approach.

Publication Date

4-19-2023

Project Designation

Honors Thesis

Primary Advisor

Russell Hardie

Primary Advisor's Department

Electrical and Computer Engineering

Keywords

Stander Symposium, School of Engineering

Institutional Learning Goals

Scholarship; Practical Wisdom

Methods for Exploiting High Resolution Imagery for Deep Learning Based Diabetic Retinopathy Detection and Grading

Share

COinS