Denoising single MR spectra by deep learning: Miracle or mirage?

Dziadosz, Martyna; Rizzo, Rudy; Kyathanahally, Sreenath P; Kreis, Roland (2023). Denoising single MR spectra by deep learning: Miracle or mirage? Magnetic resonance in medicine, 90(5), pp. 1749-1761. Wiley 10.1002/mrm.29762

Magnetic_Resonance_in_Med_-_2023_-_Dziadosz_-_Denoising_single_MR_spectra_by_deep_learning_Miracle_or_mirage.pdf - Published Version
Available under License Creative Commons: Attribution-Noncommercial (CC-BY-NC).

Download (3MB) | Preview


The inherently poor SNR of MRS measurements presents a significant hurdle to its clinical application. Denoising by machine or deep learning (DL) was proposed as a remedy. It is investigated whether such denoising leads to lower estimate uncertainties or whether it essentially reduces noise in signal-free areas only.


Noise removal based on supervised DL with U-nets was implemented using simulated 1 H MR spectra of human brain in two approaches: (1) via time-frequency domain spectrograms and (2) using 1D spectra as input. Quality of denoising was evaluated in three ways: (1) by an adapted fit quality score, (2) by traditional model fitting, and (3) by quantification via neural networks.


Visually appealing spectra were obtained; hinting that denoising is well-suited for MRS. However, an adapted denoising score showed that noise removal is inhomogeneous and more efficient for signal-free areas. This was confirmed by quantitative analysis of traditional fit results as well as DL quantitation following DL denoising. DL denoising, although apparently successful as judged by mean squared errors, led to substantially biased estimates in both implementations.


The implemented DL-based denoising techniques may be useful for display purposes, but do not help quantitative evaluations, confirming expectations based on estimation theory: Cramér Rao lower bounds defined by the original data and the appropriate fitting model cannot be circumvented in an unbiased way for single data sets, unless additional prior knowledge can be incurred in the form of parameter restrictions/relations or applicable substates.

Item Type:

Journal Article (Original Article)


04 Faculty of Medicine > Faculty Institutions > sitem Center for Translational Medicine and Biomedical Entrepreneurship
04 Faculty of Medicine > Department of Radiology, Neuroradiology and Nuclear Medicine (DRNN) > Institute of Diagnostic, Interventional and Paediatric Radiology > DCR Magnetic Resonance Spectroscopy and Methodology (AMSM)
04 Faculty of Medicine > Department of Radiology, Neuroradiology and Nuclear Medicine (DRNN) > Institute of Diagnostic and Interventional Neuroradiology

Graduate School:

Graduate School for Cellular and Biomedical Sciences (GCB)

UniBE Contributor:

Dziadosz, Martyna, Rizzo, Rudy, Kreis, Roland


600 Technology > 610 Medicine & health








Pubmed Import

Date Deposited:

20 Jun 2023 10:00

Last Modified:

31 Aug 2023 00:15

Publisher DOI:


PubMed ID:


Uncontrolled Keywords:

MR spectroscopy deep learning denoising machine learning parameter estimation quantification




Actions (login required)

Edit item Edit item
Provide Feedback