English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Background: Magnetic resonance spectroscopy (MRS) enables non-invasivedetection and measurement of biochemicals and metabolites. However, MRS has lowsignal-to-noise ratio (SNR) when concentrations of metabolites are in the rangeof the million molars. Standard approach of using a high number of signalaveraging (NSA) to achieve sufficient NSR comes at the cost of a longacquisition time. Purpose: We propose to use deep-learning approaches todenoise MRS data without increasing the NSA. Methods: The study was conductedusing data collected from the brain spectroscopy phantom and human subjects. Weutilized a stack auto-encoder (SAE) network to train deep learning models fordenoising low NSA data (NSA = 1, 2, 4, 8, and 16) randomly truncated from highSNR data collected with high NSA (NSA=192) which were also used to obtain theground truth. We applied both self-supervised and fully-supervised trainingapproaches and compared their performance of denoising low NSA data based onimproved SNRs. Results: With the SAE model, the SNR of low NSA data (NSA = 1)obtained from the phantom increased by 22.8% and the MSE decreased by 47.3%.For low NSA images of the human parietal and temporal lobes, the SNR increasedby 43.8% and the MSE decreased by 68.8%. In all cases, the chemical shift ofNAA in the denoised spectra closely matched with the high SNR spectra,suggesting no distortion to the spectra from denoising. Furthermore, thedenoising performance of the SAE model was more effective in denoising spectrawith higher noise levels. Conclusions: The reported SAE denoising method is amodel-free approach to enhance the SNR of low NSA MRS data. With the denoisingcapability, it is possible to acquire MRS data with a few NSA, resulting inshorter scan times while maintaining adequate spectroscopic information fordetecting and quantifying the metabolites of interest.

Denoising Magnetic Resonance Spectroscopy (MRS) Data Using Stacked Autoencoder for Improving Signal-to-Noise Ratio and Speed of MRS