A novel automated system of discriminating Microaneurysms in fundus images. (April 2020)

• Record Type: Journal Article
• Authors: Jeba Derwin, D.; Tamil Selvi, S.; Jeba Singh, O.; Priestly Shan, B.
• Is Part Of: Biomedical signal processing and control. Volume 58(2020)
• Publication Date: 2020-04
• Subjects: Diabetic retinopathy -- Microaneurysms -- Local neighborhood differential coherence pattern -- Feed forward neural network; Signal processing -- Periodicals; Biomedical engineering -- Periodicals; Signal Processing, Computer-Assisted -- Periodicals; Image Processing, Computer-Assisted -- Periodicals; Biomedical Engineering -- Periodicals; 610.28
• DOI: 10.1016/j.bspc.2019.101839
• Languages: English
• ISSNs: 1746-8094

Abstract

Highlights: Our proposed system will assist the ophthalmologist while diagnosing the early stage of DR. The introduced Local Neighbourhood Differential Coherence Pattern successfully captures the textual characteristics between lesion and non-lesion area. Candidate extraction reduces the occurrence of false positives and reduces the computation time considerably. Our pre-processing technique is superior in improving the contrast, color and luminance that provides an efficient screening. Computation time is found to be only 70 sec. Abstract: Diabetic retinopathy, a chronic disease in diabetic patients leads to Vision loss, by disabling microvascular complications, if not recognized and cured at the earlier stage. This article explores a novel and reliable method for automatic early detection of Microaneurysms (MA) in fundus images. Microaneurysms characterized by small red spots on the retina, the red lesions are symptoms of early stage of DR. Development of an automated screening system would assist an ophthalmologist in diagnosing DR at an early stage. Hence, in this paper, a novel feature extraction technique using a Local Neighborhood Differential Coherence Pattern (LNDCP) is proposed. In this method, texture characteristics needed for classification by Feed Forward Neural Network (FFNN) is captured efficiently. The performance of the algorithm is validated using experiments on Retinopathy Online Challenge (ROC) public dataset and a single real-time dataset, AGAR300. Efficiency of the algorithm is benchmarked with state-of-art approaches and a Free-response Receiver Operating Characteristic (FROC) score of 0.481 and 0.442 have been achieved for ROC and AGAR300 respectively.