Auto-Metric Graph Neural Network optimized with Capuchin search optimization algorithm for coinciding diabetic retinopathy and diabetic Macular edema grading. (February 2023)

• Record Type: Journal Article
• Authors: Jasper Gnana Chandran, J.; Jabez, J.; Srinivasulu, Senduru
• Is Part Of: Biomedical signal processing and control. Volume 80:Part 2(2023)
• Publication Date: 2023-02
• Subjects: Auto-Metric Graph Neural Network -- Capuchin search optimization -- Diabetic Retinopathy -- Diabetic Macular Edema Grading -- Messidor dataset; 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.2022.104386
• Languages: English
• ISSNs: 1746-8094

Abstract

Highlights: In this manuscript, AGNN-CSO is proposed for coinciding DR, DME grading. Initially, input image is taken from two public benchmark datasets. Input fund us image is pre-processed by APPDRC filtering method. Then GLCM window adaptive algorithm is used for feature extraction phase. Extracted features of DR and DME are fed to AGNN for classification. Abstract: Diabetic retinopathy (DR) and diabetic macular edema (DME) are the major eternal blindness in aged people. In this manuscript, Auto-Metric Graph Neural Network (AGNN) optimized with Capuchin search optimization algorithm is proposed for coinciding DR and DME grading (AGNN-CSO-DR-DME). The novelty of this work is to identify the Diabetic retinopathy and diabetic macular edema grading at initial stage with higher accuracy by decreasing the error rate and computation time. Initially, input image is taken from two public benchmark datasets that is ISBI 2018 imbalanced diabetic retinopathy grading dataset and Messidor dataset. Then, the input fundus image is pre-processed by APPDRC filtering method removes noise in input images. Also, the pre-processed images are given to the Gray level co-occurrence matrix (GLCM) window adaptive algorithm based feature extraction method. The extracted features of the DR and DME are fed to AGNN for classifying the grading of both DR and DME diseases. Generally, AGNN not reveal any adoption of optimization methods compute optimum parameters for assuring correct grading of both DR and DME diseases. Thus, CSOA is used for optimizing the AGNN weight parameters. The proposed method is carried out in python, its efficiency is assessed under performances metrics, such as f-measure, execution time and accuracy. The proposed method attains higher accuracy in ISBI 2018 IDRiD dataset 99.57 %, 97.28 %, and 96.34 %, compared with existing methods, like CANet-DR-DME, HDLCNN-MGMO-DR-DME, ANN-DR-DME and 91.17 %, 96.52 % and 97.36 %higher accuracy in Messidor dataset compared with existing methods, like CANet-DR-DME, TCNN-DR-DME, and 2-d -FBSE-FAWT-DR-DME.