Sparse-Denoising Methods for Extracting Desaturation Transients in Cerebral Oxygenation Signals of Preterm Infants

TL;DR

This study compares denoising techniques for extracting transient cerebral oxygen desaturations in preterm infants' NIRS signals, finding that dual low-pass filter and total variation denoising outperform SSA_DCT in synthetic data.

Contribution

The paper introduces and evaluates optimized LPF_TVD methods for isolating transient signals in cerebral NIRS data, demonstrating superior accuracy and efficiency over SSA_DCT.

Findings

LPF_TVD outperforms SSA_DCT in synthetic data accuracy.

LPF_TVD is 3-4 orders of magnitude more computationally efficient.

Further research needed on real NIRS signals.

Abstract

Preterm infants are at high risk of developing brain injury in the first days of life as a consequence of poor cerebral oxygen delivery. Near-infrared spectroscopy (NIRS) is an established technology developed to monitor regional tissue oxygenation. Detailed waveform analysis of the cerebral NIRS signal could improve the clinical utility of this method in accurately predicting brain injury. Frequent transient cerebral oxygen desaturations are commonly observed in extremely preterm infants, yet their clinical significance remains unclear. The aim of this study was to examine and compare the performance of two distinct approaches in isolating and extracting transient deflections within NIRS signals. We optimized three different simultaneous low-pass filtering and total variation denoising (LPF_TVD) methods and compared their performance with a recently proposed method that uses singular-spectrum analysis and the discrete cosine transform (SSA_DCT). Parameters for the LPF_TVD methods were optimized over a grid search using synthetic NIRS-like signals. The SSA_DCT method was modified with a post-processing procedure to increase sparsity in the extracted components. Our analysis, using a synthetic NIRS-like dataset, showed that a LPF_TVD method outperformed the modified SSA_DCT method: median mean-squared error of 0.97 (95% CI: 0.86 to 1.07) was lower for the LPF_TVD method compared to the modified SSA_DCT method of 1.48 (95% CI: 1.33 to 1.63), P<0.001. The dual low-pass filter and total variation denoising methods are considerably more computational efficient, by 3 to 4 orders of magnitude, than the SSA_DCT method. More research is needed to examine the efficacy of these methods in extracting oxygen desaturation in real NIRS signals.