Automated classification of diabetic retinopathy through reliable feature selection

• Published in: Australasian physical & engineering sciences in medicine Vol. 43; no. 3; pp. 927 - 945
• Main Authors: Gayathri, S., Gopi, Varun P., Palanisamy, P.
• Format: Journal Article
• Language: English
• Published: Cham Springer International Publishing 01.09.2020; Springer Nature B.V
• Subjects: Biological and Medical Physics; Biomedical and Life Sciences; Biomedical Engineering and Bioengineering; Biomedicine; Biophysics; Blood vessels; Classification; Classifiers; Datasets; Diabetes; Diabetes mellitus; Diabetic retinopathy; Feature extraction; Feature selection; Machine learning; Medical and Radiation Physics; Multilayers; Redundancy; Robustness; Scientific Paper; Support vector machines; SURF; DR detection; 10-Fold cross validation; BRISK; Feature selection and ranking; Retinal fundus images; MR-MR method
• ISSN: 2662-4729; 0158-9938; 2662-4737; 2662-4737; 1879-5447
• DOI: 10.1007/s13246-020-00890-3

Diabetic retinopathy (DR) is a complication of diabetes mellitus that damages the blood vessels in the retina. DR is considered a serious vision-threatening impediment that most diabetic subjects are at risk of developing. Effective automatic detection of DR is challenging. Feature extraction plays an important role in the effective classification of disease. Here we focus on a feature extraction technique that combines two feature extractors, speeded up robust features and binary robust invariant scalable keypoints, to extract the relevant features from retinal fundus images. The selection of top-ranked features using the MR-MR (maximum relevance-minimum redundancy) feature selection and ranking method enhances the efficiency of classification. The system is evaluated across various classifiers, such as support vector machine, Adaboost, Naive Bayes, Random Forest, and multi-layer perception (MLP) when giving input image features extracted from standard datasets (IDRiD, MESSIDOR, and DIARETDB0). The performances of the classifiers were analyzed by comparing their specificity, precision, recall, false positive rate, and accuracy values. We found that when the proposed feature extraction and selection technique is used together with MLP outperforms all the other classifiers for all datasets in binary and multiclass classification.