University of Oulu

Nykänen, O., Nevalainen, M., Casula, V., Isosalo, A., Inkinen, S.I., Nikki, M., Lattanzi, R., Cloos, M.A., Nissi, M.J. and Nieminen, M.T. (2023), Deep-Learning-Based Contrast Synthesis From MRF Parameter Maps in the Knee Joint. J Magn Reson Imaging, 58: 559-568.

Deep-learning-based contrast synthesis from MRF parameter maps in the knee joint

Saved in:
Author: Nykänen, Olli1,2; Nevalainen, Mika2,3,4; Casula, Victor2,3;
Organizations: 1Department of Applied Physics, Faculty of Science and Forestry, University of Eastern Finland, Kuopio, Finland
2Research Unit of Medical Imaging, Physics and Technology, Faculty of Medicine, University of Oulu, Oulu, Finland
3Medical Research Center, University of Oulu and Oulu University Hospital, Oulu, Finland
4Department of Diagnostic Radiology, Oulu University Hospital, Oulu, Finland
5Helsinki University Hospital, Helsinki, Finland
6Center for Advanced Imaging Innovation and Research (CAI2R) and Bernard and Irene Schwartz Center for Biomedical Imaging, Department of Radiology, New York University Grossman School of Medicine, New York, New York, USA
7Centre for Advanced Imaging, University of Queensland, Brisbane, Australia
Format: article
Version: published version
Access: open
Online Access: PDF Full Text (PDF, 2.9 MB)
Persistent link:
Language: English
Published: John Wiley & Sons, 2022
Publish Date: 2023-06-30


Background: Magnetic resonance fingerprinting (MRF) is a method to speed up acquisition of quantitative MRI data. However, MRF does not usually produce contrast-weighted images that are required by radiologists, limiting reachable total scan time improvement. Contrast synthesis from MRF could significantly decrease the imaging time.

Purpose: To improve clinical utility of MRF by synthesizing contrast-weighted MR images from the quantitative data provided by MRF, using U-nets that were trained for the synthesis task utilizing L1- and perceptual loss functions, and their combinations.

Study type: Retrospective.

Population: Knee joint MRI data from 184 subjects from Northern Finland 1986 Birth Cohort (ages 33–35, gender distribution not available).

Field strength and sequence: A 3 T, multislice-MRF, proton density (PD)-weighted 3D-SPACE (sampling perfection with application optimized contrasts using different flip angle evolution), fat-saturated T2-weighted 3D-space, water-excited double echo steady state (DESS).

Assessment: Data were divided into training, validation, test, and radiologist’s assessment sets in the following way: 136 subjects to training, 3 for validation, 3 for testing, and 42 for radiologist’s assessment. The synthetic and target images were evaluated using 5-point Likert scale by two musculoskeletal radiologists blinded and with quantitative error metrics.

Statistical tests: Friedman’s test accompanied with post hoc Wilcoxon signed-rank test and intraclass correlation coefficient. The statistical cutoff P <0.05 adjusted by Bonferroni correction as necessary was utilized.

Results: The networks trained in the study could synthesize conventional images with high image quality (Likert scores 3–4 on a 5-point scale). Qualitatively, the best synthetic images were produced with combination of L1- and perceptual loss functions and perceptual loss alone, while L1-loss alone led to significantly poorer image quality (Likert scores below 3). The interreader and intrareader agreement were high (0.80 and 0.92, respectively) and significant. However, quantitative image quality metrics indicated best performance for the pure L1-loss.

Data conclusion: Synthesizing high-quality contrast-weighted images from MRF data using deep learning is feasible. However, more studies are needed to validate the diagnostic accuracy of these synthetic images.

Evidence level: 4

Technical efficacy: Stage 1.

see all

Series: Journal of magnetic resonance imaging
ISSN: 1053-1807
ISSN-E: 1522-2586
ISSN-L: 1053-1807
Volume: 58
Issue: 2
Pages: 559 - 568
DOI: 10.1002/jmri.28573
Type of Publication: A1 Journal article – refereed
Field of Science: 113 Computer and information sciences
114 Physical sciences
217 Medical engineering
Funding: The authors gratefully acknowledge support from the Technology Industries of Finland Centennial Foundation and Jane & Aatos Erkko Foundation funds (the Future Makers –program), Finnish Cultural Foundation North Savo regional fund (grant #65211960), and Academy of Finland (grant: #325146). This work was partially supported by NIH R01 AR070297 and NIH P41 EB017183.
Academy of Finland Grant Number: 325146
Detailed Information: 325146 (Academy of Finland Funding decision)
Copyright information: © 2022 The Authors. Journal of Magnetic Resonance Imaging published by Wiley Periodicals LLC on behalf of International Society for Magnetic Resonance in Medicine. This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.