Article: Dual feature set enabled with optimised deep belief network for diagnosing diabetic retinopathy Journal: International Journal of Biomedical Engineering and Technology (IJBET) 2022 Vol.39 No.4 pp.369 - 395 Abstract: In DR detection, there are a lot of challenges to be faced in order to provide better performance and accuracy. The problem that still remains in DR detection is selection of image features, and classifiers for appropriate datasets. In order to develop a better detection method, this paper intends to propose an advanced model for detecting DR using fundus images. This detection model accomplishes in four phases include pre-processing, blood vessel segmentation, feature extraction and classification. Initially, contrast limited AHE (CLAHE) and median filtering methods are used for pre-processing. For blood vessel segmentation, fuzzy C-mean (FCM) thresholding works well for making rough clustering of pixels. Further, the local features and morphological transformation-based features are extracted from the segmented blood vessels. Moreover, the deep learning classifier called deep belief network (DBN) classifies the extracted features, which detects whether the image is healthy or affected. As a novelty, the number of hidden neurons in DBN is optimised using modified monarch butterfly optimisation (MBO) termed as distance-based MBO (D-MBO). To the next of the simulation, the performance of the proposed D-MBO-DBN-based DR detection model is compared over the existing models by analysing the most relevant positive, and negative performance measures, and substantiates the overall performance. Inderscience Publishers - linking academia, business and industry through research

Title: Dual feature set enabled with optimised deep belief network for diagnosing diabetic retinopathy

Authors: S. Shafiulla Basha; K. Venkata Ramanaiah

Addresses: Y.S.R. Engineering College, Yogi Vemana University, Proddatur-516360, Andhra Pradesh, India ' Y.S.R. Engineering College, Yogi Vemana University, Proddatur-516360, Andhra Pradesh, India

Abstract: In DR detection, there are a lot of challenges to be faced in order to provide better performance and accuracy. The problem that still remains in DR detection is selection of image features, and classifiers for appropriate datasets. In order to develop a better detection method, this paper intends to propose an advanced model for detecting DR using fundus images. This detection model accomplishes in four phases include pre-processing, blood vessel segmentation, feature extraction and classification. Initially, contrast limited AHE (CLAHE) and median filtering methods are used for pre-processing. For blood vessel segmentation, fuzzy C-mean (FCM) thresholding works well for making rough clustering of pixels. Further, the local features and morphological transformation-based features are extracted from the segmented blood vessels. Moreover, the deep learning classifier called deep belief network (DBN) classifies the extracted features, which detects whether the image is healthy or affected. As a novelty, the number of hidden neurons in DBN is optimised using modified monarch butterfly optimisation (MBO) termed as distance-based MBO (D-MBO). To the next of the simulation, the performance of the proposed D-MBO-DBN-based DR detection model is compared over the existing models by analysing the most relevant positive, and negative performance measures, and substantiates the overall performance.

Keywords: diabetic retinopathy detection; fuzzy C-mean; FCM; deep belief network; DBN; monarch butterfly optimisation; MBO; hidden neuron optimisation.

DOI: 10.1504/IJBET.2022.124664

International Journal of Biomedical Engineering and Technology, 2022 Vol.39 No.4, pp.369 - 395

Received: 12 Mar 2019
Accepted: 05 Jul 2019
Published online: 05 Aug 2022 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article

Title: Dual feature set enabled with optimised deep belief network for diagnosing diabetic retinopathy

Keep up-to-date