Automatic Discrimination of Color Retinal Images using the Bag of Words Approach

TL;DR

This paper presents a Bag of Words approach for automatic diagnosis of diabetic retinopathy from color retinal images, achieving high accuracy in distinguishing normal and abnormal images with bright lesions.

Contribution

It introduces a novel use of Bag of Words with single and multiple dictionary methods for retinopathy diagnosis from fundus images.

Findings

Achieved 97.2% accuracy with single dictionary

Achieved 99.77% accuracy with multiple dictionaries

Validated on 430 images from six datasets

Abstract

Diabetic retinopathy (DR) and age related macular degeneration (ARMD) are among the major causes of visual impairment worldwide. DR is mainly characterized by red spots, namely microaneurysms and bright lesions, specifically exudates whereas ARMD is mainly identified by tiny yellow or white deposits called drusen. Since exudates might be the only manifestation of the early diabetic retinopathy, there is an increase demand for automatic retinopathy diagnosis. Exudates and drusen may share similar appearances, thus discriminating between them is of interest to enhance screening performance. In this research, we investigative the role of bag of words approach in the automatic diagnosis of retinopathy diabetes. We proposed to use a single based and multiple based methods for the construction of the visual dictionary by combining the histogram of word occurrences from each dictionary and building a single histogram. The introduced approach is evaluated for automatic diagnosis of normal and abnormal color fundus images with bright lesions. This approach has been implemented on 430 fundus images, including six publicly available datasets, in addition to one local dataset. The mean accuracies reported are 97.2% and 99.77% for single based and multiple based dictionaries respectively.