Abstract
Electroretinography (ERG) is a non-invasive method of assessing retinal function by recording the retina’s response to a brief flash of light. This study focused on optimizing the ERG waveform signal classification by utilizing Short-Time Fourier Transform (STFT) spectrogram preprocessing with a machine learning (ML) decision system. Several window functions of different sizes and window overlaps were compared to enhance feature extraction concerning specific ML algorithms. The obtained spectrograms were employed to train deep learning models alongside manual feature extraction for more classical ML models. Our findings demonstrated the superiority of utilizing the Visual Transformer architecture with a Hamming window function, showcasing its advantage in ERG signal classification. Also, as a result, we recommend the RF algorithm for scenarios necessitating manual feature extraction, particularly with the Boxcar (rectangular) or Bartlett window functions. By elucidating the optimal methodologies for feature extraction and classification, this study contributes to advancing the diagnostic capabilities of ERG analysis in clinical settings.
Original language | English |
---|---|
Article number | 866 |
Number of pages | 21 |
Journal | Bioengineering |
Volume | 11 |
Issue number | 9 |
DOIs | |
Publication status | Published - Sept 2024 |
Keywords
- electroretinography
- biomedical signal processing algorithms
- short-time Fourier transform
- spectrogram
- feature extraction
- classification
- machine learning
- deep learning
- neural network
- retinal study