Magnetic Resonance Spectroscopy Deep Learning Denoising Using Few in Vivo Data

作者：Dicheng Chen, Wanqi Hu, Huiting Liu, Yirong Zhou, Tianyu Qiu, Yihui Huang, Zi Wang, Meijin Lin, Liangjie Lin, Zhigang Wu, Jiazheng Wang, Hao Chen, Xi Chen, Gen Yan, Di Guo, Jianzhong Lin, Xiaobo Qu · 发表于：IEEE Transactions on Computational Imaging · 年份：2023 · DOI：10.1109/tci.2023.3267623 · 被引用次数：27 · 研究领域：Advanced MRI Techniques and Applications、Electron Spin Resonance Studies、NMR spectroscopy and applications

Magnetic Resonance Spectroscopy (MRS) is a noninvasive tool to reveal metabolic information. One challenge of1H-MRS is the low Signal-Noise Ratio (SNR). To improve the SNR, a typical approach is to perform a large number of Signal Averaging (SA). The data acquisition time, however, is proportional to the number of SA accordingly. A complete clinical MRS scan takes approximately 10 minutes in a common setting with the number of SA of 128. Recently, deep learning has been introduced to improve the SNR, but mostly the simulated data were used as the training set. This may hinder the MRS applications since some potential differences, such as acquisition system imperfections, physiological and psychologic conditions may exist between the simulated andin vivodata. In this paper, a new scheme that purely used repeated samples of realistic data was proposed. A deep learning model, Refusion Long Short-Term Memory (ReLSTM), was designed to learn the mapping from the time domain data with low SNR (24 SA) to the one with high SNR (128 SA). Experiments on thein vivobrain spectra of 7 healthy, 2 tumor and 1 cerebral infarction region shows that using SA of 24, only 20% of a common setting, the spectra denoised by ReLSTM can provide the estimated concentrations of metabolites with the reliability comparable to those of the high-SNR spectra obtained commonly with 128 SA. Furthermore, compared with the state-of-the-art Low-Rank (LR) denoising method, the ReLSTM achieves lower relative errors ...