Accelerating Retinal Fundus Image Classification Using Artificial Neural Networks (ANNs) and Reconfigurable Hardware (FPGA)

Ghani, Arfan; See, Chan Hwang; Sudhakaran, Vaisakh; Ahmad, Jahanzeb; Abd-Alhammed, Raed

Abstract

Diabetic Retinopathy (DR) and Glaucoma are common eye diseases that affect a blood vessel in the retina and are one of the leading causes of vision loss around the world. Glaucoma is a common eye condition where the optic nerve that connects the eye to the brain becomes damaged. Whereas, DR is a complication of diabetes caused by high blood sugar levels damaging the back of the eye In order to produce an accurate and early diagnosis, an extremely high number of retinal images needs to be processed. Given the required computational complexity of image processing algorithms and the need for high-performance architectures, this paper proposes and demonstrates the use of fully parallel Field Programmable Gate Arrays (FPGAs) to overcome the burden of real-time computing in conventional software architectures. The experimental results achieved through software implementation were validated on an FPGA device. The results show a remarkable improvement in terms of computational speed and power consumption. This paper presents various pre-processing methods to analyse fundus images which can serve as a diagnostic tool for detection of glaucoma and diabetic retinopathy. In the proposed adaptive thresholding based pre-processing method, features were selected by calculating the area of the segmented optic disk which were further classified by using feedforward Neural Network (NN). The analysis is carried out using feature extraction through existing methodologies such as adaptive thresholding, histogram, and wavelet transform. Results obtained through these methods were quantified to obtain optimum performance in terms of classification accuracy. The proposed hardware implementation outperforms existing methods and offers a significant improvement in terms of computational speed and power consumption.

• Journal Article Type: Article
• Acceptance Date: Dec 9, 2019
• Online Publication Date: Dec 11, 2019
• Publication Date: Dec 11, 2019
• Deposit Date: Dec 9, 2019
• Publicly Available Date: Dec 9, 2019
• Journal: Electronics
• Publisher: MDPI
• Peer Reviewed: Peer Reviewed
• Volume: 8
• Issue: 12
• DOI: https://doi.org/10.3390/electronics8121522
• Keywords: Neural Network; Machine learning; Glaucoma; Diabetic retinopathy; Adaptive thresholding; FPGA
• Public URL: http://researchrepository.napier.ac.uk/Output/2383837