Deep‐Learning‐Based Contrast Synthesis From MRF Parameter Maps in the Knee Joint

• Published in: Journal of Magnetic Resonance Imaging
• Main Authors: Nykänen, Olli, Nevalainen, Mika, Casula, Victor, Isosalo, Antti, Inkinen, Satu I., Nikki, Marko, Lattanzi, Riccardo, Cloos, Martijn A., Nissi, Mikko J., Nieminen, Miika T.
• Other Authors: Academy of Finland, Jane ja Aatos Erkon Säätiö, National Institutes of Health
• Format: Article in Journal/Newspaper
• Language: English
• Published: Wiley 2022
• Subjects: Northern Finland
• Online Access: http://dx.doi.org/10.1002/jmri.28573; https://onlinelibrary.wiley.com/doi/pdf/10.1002/jmri.28573; https://onlinelibrary.wiley.com/doi/full-xml/10.1002/jmri.28573

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, ...