Advanced Analysis of Electroretinograms Based on Wavelet Scalogram Processing

Abstract

The electroretinography (ERG) is a diagnostic test that measures the electrical activity of the retina in response to a light stimulus. The current ERG signal analysis uses four components, namely amplitude, and the latency of a-wave and b-wave. Nowadays, the international electrophysiology community established the standard for electroretinography in 2008. However, in terms of signal analysis, there were no major changes. ERG analysis is still based on a four-component evaluation. The article describes the ERG database, including the classification of signals via the advanced analysis of electroretinograms based on wavelet scalogram processing. To implement an extended analysis of the ERG, the parameters extracted from the wavelet scalogram of the signal were obtained using digital image processing and machine learning methods. Specifically, the study focused on the preprocessing of wavelet scalogram as images, and the extraction of connected components and thier evaluation. As a machine learning method, a decision tree was selected as one that incorporated feature selection. The study results show that the proposed algorithm more accurately implements the classification of adult electroretinogram signals by 19%, and pediatric signals by 20%, in comparison with the classical features of ERG. The promising use of ERG is presented using differential diagnostics, which may also be used in preclinical toxicology and experimental modeling. The problem of developing methods for electrophysiological signals analysis in ophthalmology is associated with the complex morphological structures of electrophysiological signal components.

OculusGraphy: Signal Analysis of the Electroretinogram in a Rabbit Model of Endophthalmitis Using Discrete and Continuous Wavelet Transforms

“…The Gaussian eight-degree wavelet figure also displays the segment numbering for the corresponding scalogram. To describe the CWT wavelet scalograms uniformly, the scalogram areas were divided into even and odd segments as previously described [ 47 ]. The spatial arrangement and energy of central segments Nos.…”

“…Furthermore, Morlet wavelet transforms, along with, potentially, continuous wavelet transform (CWT), have been used to classify glaucomatous and healthy sectors based on frequency content differences in adult ERGs, aiding in the accurate diagnosis and treatment of optic nerve diseases [ 42 ]. In the context of pediatric and adult ERG semi-automatic parameter extraction, the Gaussian wavelet has been preferred due to its convenience and better time-domain properties [ 47 ]. However, challenges remain in achieving simultaneous localization in both the frequency and time domains, necessitating further advancements in wavelet analysis techniques.…”

Review of various feature extraction approaches for ERG signal analysis: Advantages and drawbacks

“…Researchers and clinicians should consider the advantages and limitations of time-frequency analysis when selecting appropriate feature extraction methods for their specific research or clinical applications [39,40].…”

“…Quantifying these features provides valuable insights into retinal health, facilitating early diagnosis, treatment monitoring, and prognosis evaluation. This paper aims to comprehensively review feature extraction approaches for ERG signal analysis, focusing on their advantages and drawbacks [5][6][7][8]. The review aims to assist researchers and clinicians in selecting appropriate methods for their specific needs.…”

Optimal Combination of Mother Wavelet and AI Model for Precise Classification of Pediatric Electroretinogram Signals

“…Finally, in [20], the Gaussian wavelet was chosen for its convenience in pediatric and adult ERG semi-automatic parameter extraction and better time domain properties. However, challenges remain in achieving simultaneous localization in both the frequency and time domains, indicating a need for further improvement in wavelet analysis techniques.…”