Deep Learning in Retinal Image Segmentation and Feature Extraction: A Review

Abstract

Image recognition and understanding is considered as a remarkable subfield of Artificial Intelligence (AI). In practice, retinal image data have high dimensionality leading to enormous size data. As the morphological retinal image datasets can be analyzed in an expansive and non-invasive way, AI more precisely Deep Learning (DL) methods are facilitating in developing intelligent retinal image analysis tools. The most recently developed DL technique, Convolutional Neural Network (CNN) showed remarkable efficiency in identifying, localizing, and quantifying the complex and hierarchical image features that are responsible for severe cardiovascular diseases. Different deep layered CNN architectures such as LeeNet, AlexNet, and ResNet have been developed exploiting CNN morphology. This wide variety of CNN structures can iteratively learn complex data structures of different datasets through supervised or unsupervised learning and perform exquisite analysis for feature recognition independently to diagnose threatening cardiovascular diseases. In modern ophthalmic practice, DL based automated methods are being used in retinopathy screening, grading, identifying, and quantifying the pathological features to employ further therapeutic approaches and offering a wide potentiality to get rid of ophthalmic system complexity. In this review, the recent advances of DL technologies in retinal image segmentation and feature extraction are extensively discussed. To accomplish this study the pertinent materials were extracted from different publicly available databases and online sources deploying the relevant keywords that includes retinal imaging, artificial intelligence, deep learning and retinal database. For the associated publications the reference lists of selected articles were further investigated.

An Artificial Intelligence-Based Bio-Medical Stroke Prediction and Analytical System Using a Machine Learning Approach

“…Because of them, adults are at risk of severe disability and possibly death. If an impending stroke can be recognised or predicted in its early stages, it may be feasible to significantly mitigate its effects [8][9][10]. Several risk factors for stroke have been established through the course of a great number of investigations and clinical trials.…”

Diabetic Retinopathy Grading with Deep Visual Attention Network

“…One major limitation of the methods reviewed thus far is that they relied on the fact that the fundus images used in training process are labeled by an expert in advance [13,19,20]. To overcome this limitation, Yuego et al [15] proposed a Self-supervised Fuzzy Clustering Network (SFCN) method that take as input unlabeled retinal images and classify them as having DR or not. Although the models trained are effective in detecting presence of the DR in the fundus images, however, they still do not solve the fundamental problem of specifying the severity of the disease.…”

Multimodal Biometric-Based Secured Access Mechanism for Wireless Sensor Networks

“…The method associates dynamic identity for users and removes constant parameters from user's request confirming that any two request messages are indistinguishable and independent. A study on current progresses in deep learning methodologies for feature extraction and retinal image segmentation was done by Kuryati et al [25]. Image compression methods built on neural network was analyzed in [26].…”