NNFit: A Self-Supervised Deep Learning Method for Accelerated Quantification of High-Resolution Short-Echo-Time MR Spectroscopy Datasets

2025/01/15 by Alexander S. Giuffrida, Sulaiman Sheriff, Vicki Huang +7 · 1 voice
Physics and Astronomy · Medicine · #NMR spectroscopy and applications #Advanced MRI Techniques and Applications #Atomic and Subatomic Physics Research

paper · doi:10.1148/ryai.230579

Abstract

NNFit, a deep learning method for accelerated quantification of echo-planar spectroscopic imaging datasets, achieved competitive quantitative performance compared with a standard parametric modeling spectral analysis method (FITT), with greater computational efficiency.

Citations

• Three‐dimensional magnetization‐prepared rapid gradient‐echo imaging (3D MP RAGE)

Discussions

• NNFit: A Self-Supervised Deep Learning Method for Accelerated Quantification of High-Resolution Short Echo Time MR Spectroscopy Datasets https://doi.org/10.1148/ryai.230579 @EmoryRadiology @EmoryBIOS [bsky, 6 points, 0 comments]

Related

• Accelerated Nuclear Magnetic Resonance Spectroscopy with Deep Learning
• TVCondNet: A Conditional Denoising Neural Network for NMR Spectroscopy
• Q-MRS: A Deep Learning Framework for Quantitative Magnetic Resonance Spectra Analysis
• DeepCEST: 9.4 T Chemical Exchange Saturation Transfer MRI contrast predicted from 3 T data - a proof of concept study
• Towards Ultimate NMR Resolution with Deep Learning