Feature Extraction Methods for Electroretinogram Signal Analysis: A Review

Soroor Behbahani,Hamid Ahmadieh,Sreeraman Rajan

doi:10.1109/access.2021.3103848

Abstract

Feature extraction is an essential aspect of electroretinogram (ERG) signal analysis. The extracted features are beneficial to analyze the signal further and compress the signal for storage or transmission purposes. Various methods have been widely employed to extract the characteristics of ERG signals. Methods based on the time-domain, frequency-domain, time-frequency domain and nonlinear and chaotic feature extraction techniques have been used to extract features that characterize ERG signals. This paper reviews several feature extraction methods applied to ERG and compares their performance under different conditions to provide guidance to select the most appropriate feature extraction method based on the performance.

Highlights

Electroretinogram (ERG) is the electrical response of different retinal cells to light and darkness
The b-wave is a positive wave that directly follows the a-wave and usually has a significant positive amplitude [21,22]. In addition to these two main components of ERG, there are three more components: the iwave, which may originate from the OFF-pathway distal to retinal ganglion cells (RGCs) [23]; the photopic negative response (PhNR) that appears as a negative-going wave after the i-wave, which may be useful as a tool to monitor longitudinal change in RGCs function [24]; and the oscillatory potentials (OPs) which seem to be generated by the amacrine cells in the inner retina
The results indicated an improvement in Multifocal ERG (mfERG) glaucoma diagnosis based on Wavelet Analysis (WA), especially when combined with ganglion cell–inner plexiform layer

Summary

Introduction

Electroretinogram (ERG) is the electrical response of different retinal cells to light and darkness. Multifocal ERG (mfERG) is the best electro-functional method used to study the retina's focal function in a quick and reproducible way [6,7]. This is mainly used to diagnose and monitor macular disorders [8]. PERG has shown a correlation with optic nerve integrity and can provide information from RGCs, which cannot be supplied by ffERG [9] Besides these different types of ERG recordings, visual evoked potentials (VEP)

Methods

Discussion

Conclusion