An Integrated Spatial-Spectral Denoising Framework for Robust Electrically Evoked Compound Action Potential...

The electrically evoked compound action potential (ECAP) is a crucial physiological signal used by clinicians to evaluate auditory nerve functionality. Clean ECAP recordings help to accurately estimate auditory neural activity patterns and ECAP magnitudes, particularly through the panoramic ECAP (PECAP) framework. However, noise-especially in low-signal-to-noise ratio (SNR) conditions-can lead to significant errors in parameter estimation. This study proposes a two-stage preprocessing denoising (TSPD) algorithm to address this issue and enhance ECAP signals. First, an ECAP matrix is constructed using the forward-masking technique, representing the signal as a two-dimensional image. This matrix undergoes spatial noise reduction via an improved spatial median (I-Median) filter. In the second stage, the denoised matrix is vectorized and further processed using a log-spectral amplitude (LSA) Wiener filter for spectral domain denoising. The enhanced vector is then reconstructed into the ECAP matrix for parameter estimation using PECAP. The above integrated spatial-spectral denoising framework is denoted as PECAP-TSPD in this work. Evaluations are conducted using a simulation-based ECAP model mixed with simulated and experimental noise, designed to emulate the spatial characteristics of real ECAPs. Three objective quality measures-namely, normalized root mean square error (RMSE), two-dimensional correlation coefficient (TDCC), and structural similarity index (SSIM)-are used. Simulated and experimental results show that the proposed PECAP-TSPD method has the lowest average RMSE of PECAP magnitudes (1.952%) and auditory neural patterns (1.407%), highest average TDCC (0.9988), and average SSIM (0.9931) compared to PECAP (6.446%, 5.703%, 0.9859, 0.8997), PECAP with convolutional neural network (CNN)-based denoising mask (PECAP-CNN) (9.700%, 7.111%, 0.9766, 0.8832), and PECAP with improved median filtering (PECAP-I-Median) (4.515%, 3.321%, 0.9949, 0.9470) under impulse noise conditions.