Merkofer Julian P, van de Sande Dennis M J, Amirrajab Sina, Min Nam Kyung, van Sloun Ruud J G, Bhogal Alex A
Department of Electrical Engineering, Eindhoven University of Technology, Eindhoven, the Netherlands.
Department of Biomedical Engineering, Eindhoven University of Technology, Eindhoven, the Netherlands.
NMR Biomed. 2025 Jun;38(6):e70038. doi: 10.1002/nbm.70038.
Accurate quantification of metabolites in magnetic resonance spectroscopy (MRS) is challenged by low signal-to-noise ratio (SNR), overlapping metabolites, and various artifacts. Particularly, unknown and unparameterized baseline effects obscure the quantification of low-concentration metabolites, limiting MRS reliability. This paper introduces wavelet analysis-based neural decomposition (WAND), a novel data-driven method designed to decompose MRS signals into their constituent components: metabolite-specific signals, baseline, and artifacts. WAND takes advantage of the enhanced separability of these components within the wavelet domain. The method employs a neural network, specifically a U-Net architecture, trained to predict masks for wavelet coefficients obtained through the continuous wavelet transform. These masks effectively isolate desired signal components in the wavelet domain, which are then inverse-transformed to obtain separated signals. Notably, an artifact mask is created by inverting the sum of all known signal masks, enabling WAND to capture and remove even unpredictable artifacts. The effectiveness of WAND in achieving accurate decomposition is demonstrated through numerical evaluations using simulated spectra. Furthermore, WAND's artifact removal capabilities significantly enhance the quantification accuracy of linear combination model fitting. The method's robustness is further validated using data from the 2016 MRS Fitting Challenge and in vivo experiments.
磁共振波谱法（MRS）中代谢物的准确定量受到低信噪比（SNR）、代谢物重叠以及各种伪影的挑战。特别是，未知和未参数化的基线效应会模糊低浓度代谢物的定量，限制了MRS的可靠性。本文介绍了基于小波分析的神经分解（WAND），这是一种新颖的数据驱动方法，旨在将MRS信号分解为其组成成分：代谢物特异性信号、基线和伪影。WAND利用了小波域内这些成分增强的可分离性。该方法采用神经网络，特别是U-Net架构，经过训练以预测通过连续小波变换获得的小波系数的掩码。这些掩码在小波域中有效地分离出所需的信号成分，然后进行逆变换以获得分离后的信号。值得注意的是，通过反转所有已知信号掩码的总和来创建伪影掩码，使WAND能够捕获并去除甚至不可预测的伪影。通过使用模拟光谱的数值评估证明了WAND在实现准确分解方面的有效性。此外，WAND的伪影去除能力显著提高了线性组合模型拟合的定量准确性。使用来自2016年MRS拟合挑战赛的数据和体内实验进一步验证了该方法的稳健性。
