Denoising magnetic resonance spectroscopy (MRS) data using stacked autoencoder for improving signal‐to‐noise ratio and speed of MRS

• Published in: Medical physics (Lancaster) Vol. 50; no. 12; pp. 7955 - 7966
• Main Authors: Wang, Jing, Ji, Bing, Lei, Yang, Liu, Tian, Mao, Hui, Yang, Xiaofeng
• Format: Journal Article
• Language: English
• Published: United States 01.12.2023
• Subjects: Brain - diagnostic imaging; Brain - metabolism; denoising; Humans; Image Processing, Computer-Assisted - methods; Magnetic Resonance Imaging - methods; Magnetic resonance spectroscopy (MRS); Magnetic Resonance Spectroscopy - methods; metabolite quantification; signal to noise ratio (SNR); Signal-To-Noise Ratio; sparse representation; stack auto‐encoder (SAE); denoising; signal to noise ratio (SNR); metabolite quantification; Magnetic resonance spectroscopy (MRS); sparse representation; stack auto-encoder (SAE)

Background While magnetic resonance imaging (MRI) provides high resolution anatomical images with sharp soft tissue contrast, magnetic resonance spectroscopy (MRS) enables non‐invasive detection and measurement of biochemicals and metabolites. However, MRS has low signal‐to‐noise ratio (SNR) when co...