Retinal blood vessel segmentation for macula detachment surgery monitoring instruments

Abstract

In recent years image processing has improved detection and diagnosis in medical application. Image processing applications are now embedded in medical instruments such as MRI and CT. In the case of retinopathy, fast extraction of blood vessels can allow the physician to view injury regions during surgery. Macula detachment surgeries, or computer-aided intraocular surgeries, require precise and real-time knowledge of the vasculature during the operation. Use of artificial neural network has produced good results in image processing applications, but its implementation may not be suitable for real-time applications in small, embedded hardware. Because of error resiliency of the neural network, its structure can be pruned and simplified. In this paper an efficient hardware implementation of neural network for retinal vessel segmentation is proposed. We simplify the neural network structure in such a way that the accuracy of the results is not altered significantly. Simulation results and FPGA implementation show that our proposed network has low complexity and can be applied for segmentation of retinal vessels with acceptable accuracy. This makes the proposed method a good candidate to be implemented in any device such as a binocular indirect ophthalmoscope. KEYWORDS artificial neural networks (ANN), error compensation, hardware implementation, retinal vessel segmentation, retinopathy

Classification of diabetic retinopathy using unlabeled data and knowledge distillation

“…Diabetes is a common disease that could harm the micro-vessels in the human eye retina [11][12][13][14][15]. The advanced stage of this disease can lead to diabetic retinopathy (DR), which is considered a prevalent cause of vision loss.…”

Accelerated Blood Vessel Enhancement in Retinal Fundus Image based on Reconfigurable Hardware

“…Though the VHDL code was generated automatically using their developed tool, which could bring efficiency in the designing stage, it inherits the drawback from the convolution operation of having an interruption or gap between two rows of data. Hajabdollahi, M. et al [26] proposed an artificial neural network-based system. To provide real time processing and ease of implementation on FPGA, the network has been simplified, which requires a compensation method for deteriorated accuracy.…”

Low Complexity Convolutional Neural Network for Vessel Segmentation in Portable Retinal Diagnostic Devices

“…In [14,15] methods for retinal vessel analysis are presented and implemented on GPU. In [12] and [13] hardware architectures are presented for retinal vessel segmentation system.…”

“…Vessel segmentation in intraocular surgery requires real time vessel analysis and for portable and onsite devices needs real time and low power segmentation system [3,12,13]. In this regard some recent studies focused on the problem of real time retinal vessel segmentation on dedicated hardware such as GPU and FPGA.…”