Classification of Large-Scale Fundus Image Data Sets: A Cloud-Computing Framework

TL;DR

This paper introduces a cloud-based framework for efficient classification of large fundus image datasets, optimizing feature selection to improve accuracy and reduce processing time in diabetic retinopathy detection.

Contribution

It proposes a generalized feature selection method combined with cloud computing to enhance classification accuracy and efficiency in large-scale fundus image analysis.

Findings

Achieved 90.1% accuracy in DR lesion classification with 792 seconds processing time.

Classified microaneurysms with 72% accuracy.

Classified minor blood vessels with 83.5% accuracy in 326 seconds.

Abstract

Large medical image data sets with high dimensionality require substantial amount of computation time for data creation and data processing. This paper presents a novel generalized method that finds optimal image-based feature sets that reduce computational time complexity while maximizing overall classification accuracy for detection of diabetic retinopathy (DR). First, region-based and pixel-based features are extracted from fundus images for classification of DR lesions and vessel-like structures. Next, feature ranking strategies are used to distinguish the optimal classification feature sets. DR lesion and vessel classification accuracies are computed using the boosted decision tree and decision forest classifiers in the Microsoft Azure Machine Learning Studio platform, respectively. For images from the DIARETDB1 data set, 40 of its highest-ranked features are used to classify four DR lesion types with an average classification accuracy of 90.1% in 792 seconds. Also, for classification of red lesion regions and hemorrhages from microaneurysms, accuracies of 85% and 72% are observed, respectively. For images from STARE data set, 40 high-ranked features can classify minor blood vessels with an accuracy of 83.5% in 326 seconds. Such cloud-based fundus image analysis systems can significantly enhance the borderline classification performances in automated screening systems.