Deep Learning on Retina Images as Screening Tool for Diagnostic Decision Support

TL;DR

This paper presents a deep learning system that analyzes retina images to assist in diagnosing diabetic retinopathy, achieving over 76% agreement with expert labels.

Contribution

The study develops a CNN-based model inspired by Kaggle contest solutions for automatic diabetic retinopathy detection from retina images.

Findings

Achieved 76.73% agreement with medical experts.

Successfully distinguished healthy and diabetic retinopathy cases.

Implemented effective preprocessing and CNN architecture.

Abstract

In this project, we developed a deep learning system applied to human retina images for medical diagnostic decision support. The retina images were provided by EyePACS. These images were used in the framework of a Kaggle contest, whose purpose to identify diabetic retinopathy signs through an automatic detection system. Using as inspiration one of the solutions proposed in the contest, we implemented a model that successfully detects diabetic retinopathy from retina images. After a carefully designed preprocessing, the images were used as input to a deep convolutional neural network (CNN). The CNN performed a feature extraction process followed by a classification stage, which allowed the system to differentiate between healthy and ill patients using five categories. Our model was able to identify diabetic retinopathy in the patients with an agreement rate of 76.73% with respect to the medical expert's labels for the test data.