Premium
Using Deep Learning to Emulate the Use of an External Contrast Agent in Cardiovascular 4D Flow MRI
Author(s) -
Bustamante Mariana,
Viola Federica,
Carlhäll CarlJohan,
Ebbers Tino
Publication year - 2021
Publication title -
journal of magnetic resonance imaging
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.563
H-Index - 160
eISSN - 1522-2586
pISSN - 1053-1807
DOI - 10.1002/jmri.27578
Subject(s) - contrast (vision) , wilcoxon signed rank test , artificial intelligence , magnetic resonance imaging , similarity (geometry) , sørensen–dice coefficient , computer science , pattern recognition (psychology) , contrast to noise ratio , noise (video) , medicine , nuclear medicine , mathematics , segmentation , radiology , image quality , statistics , image segmentation , image (mathematics) , mann–whitney u test
Background Although contrast agents would be beneficial, they are seldom used in four‐dimensional (4D) flow magnetic resonance imaging (MRI) due to potential side effects and contraindications. Purpose To develop and evaluate a deep learning architecture to generate high blood–tissue contrast in noncontrast 4D flow MRI by emulating the use of an external contrast agent. Study Type Retrospective. Subjects Of 222 data sets, 141 were used for neural network (NN) training (69 with and 72 without contrast agent). Evaluation was performed on the remaining 81 noncontrast data sets. Field Strength/Sequences Gradient echo or echo‐planar 4D flow MRI at 1.5 T and 3 T . Assessment A cyclic generative adversarial NN was trained to perform image translation between noncontrast and contrast data. Evaluation was performed quantitatively using contrast‐to‐noise ratio (CNR), signal‐to‐noise ratio (SNR), structural similarity index (SSIM), mean squared error (MSE) of edges, and Dice coefficient of segmentations. Three observers performed a qualitative assessment of blood–tissue contrast, noise, presence of artifacts, and image structure visualization. Statistical Tests The Wilcoxon rank‐sum test evaluated statistical significance. Kendall's concordance coefficient assessed interobserver agreement. Results Contrast in the regions of interest (ROIs) in the NN enhanced images increased by 88%, CNR increased by 63%, and SNR improved by 48% (all P < 0.001). The SSIM was 0.82 ± 0.01, and the MSE of edges was 0.09 ± 0.01 (range [0,1]). Segmentations based on the generated images resulted in a Dice similarity increase of 15.25%. The observers managed to differentiate between contrast MR images and our results; however, they preferred the NN enhanced images in 76.7% of cases. This percentage increased to 93.3% for phase‐contrast MR angiograms created from the NN enhanced data. Visual grading scores were blood–tissue contrast = 4.30 ± 0.74, noise = 3.12 ± 0.98, and presence of artifacts = 3.63 ± 0.76. Image structures within and without the ROIs resulted in scores of 3.42 ± 0.59 and 3.07 ± 0.71, respectively ( P < 0.001). Data Conclusion The proposed approach improves blood–tissue contrast in MR images and could be used to improve data quality, visualization, and postprocessing of cardiovascular 4D flow data. Evidence Level 3 Technical Efficacy Stage 1