Diabetic Retinopathy Classification using Downscaling Algorithms and Deep Learning

TL;DR

This paper introduces a novel deep learning approach utilizing downscaling algorithms and a multi-channel Inception V3 architecture to improve diabetic retinopathy classification accuracy by combining datasets and optimizing preprocessing.

Contribution

It proposes a new multi-channel Inception V3 model with a unique preprocessing phase and demonstrates improved accuracy, specificity, and sensitivity over previous methods.

Findings

Outperforms previous state-of-the-art methods in DR classification

Combines Kaggle and Indian datasets for better training

Uses downscaling algorithms to handle large, variable image sizes

Abstract

Diabetic Retinopathy (DR) is an art and science of recording and classifying the retinal images of a diabetic patient. DR classification deals with classifying retinal fundus image into five stages on the basis of severity of diabetes. One of the major issue faced while dealing with DR classification problem is the large and varying size of images. In this paper we propose and explore the use of several downscaling algorithms before feeding the image data to a Deep Learning Network for classification. For improving training and testing; we amalgamate two datasets: Kaggle and Indian Diabetic Retinopathy Image Dataset. Our experiments have been performed on a novel Multi Channel Inception V3 architecture with a unique self crafted preprocessing phase. We report results of proposed approach using accuracy, specificity and sensitivity, which outperform the previous state of the art methods. Index Terms: Diabetic Retinopathy, Downscaling Algorithms, Multichannel CNN Architecture, Deep Learning