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

Abstract

Diabetic retinopathy (DR) and glaucoma are common eye diseases that affect a blood vessel in the retina and are two 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 showed a remarkable improvement in terms of computational speed and power consumption. This paper presents various preprocessing 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 preprocessing method, features were selected by calculating the area of the segmented optic disk, which was further classified using a feedforward neural network (NN). The analysis was 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.

HARP: Hierarchical Attention Oriented Region-Based Processing for High-Performance Computation in Vision Sensor

“…After pruning these regions, we did not concede any accuracy drop. Adding to it, Ghani et al also demonstrated a region-of-interest-based image classification where they passed only the ROI data of an entire image for training a neural network and achieved 100% accuracy [ 32 ]. Therefore, it is an effective solution to prune redundant spatiotemporal information from images first and then apply the learning method to expedite the overall processing with optimal computation cost.…”

FAU-Net: Fixup Initialization Channel Attention Neural Network for Complex Blood Vessel Segmentation

“…Yet, there is a common problem with the above networks, i.e., to obtain accurate segmentation results, it often requires a lot of training time, and the segmentation efficiency of the network is very low. Arfan et al [26] proposed a method based on artificial neural networks and fully parallel field-programmable gate arrays (FPGAs). The hardware implementation proposed by this method can effectively improve the segmentation efficiency.…”

Modeling of Fundus Laser Exposure for Estimating Safe Laser Coagulation Parameters in the Treatment of Diabetic Retinopathy

“…Today, special attention in research is directed to the development of algorithms for processing fundus images [13][14][15][16][17]. Most importantly, the analysis of patient images using computer vision techniques in the treatment of diabetic retinopathy makes the process personalized and therefore more efficient and safer.…”