Deep Learning Approach for Generating MRA Images From 3D Quantitative Synthetic MRI Without Additional Scans

Abstract

Objectives Quantitative synthetic magnetic resonance imaging (MRI) enables synthesis of various contrast-weighted images as well as simultaneous quantification of T1 and T2 relaxation times and proton density. However, to date, it has been challenging to generate magnetic resonance angiography (MRA) images with synthetic MRI. The purpose of this study was to develop a deep learning algorithm to generate MRA images based on 3D synthetic MRI raw data. Materials and Methods Eleven healthy volunteers and 4 patients with intracranial aneurysms were included in this study. All participants underwent a time-of-flight (TOF) MRA sequence and a 3D-QALAS synthetic MRI sequence. The 3D-QALAS sequence acquires 5 raw images, which were used as the input for a deep learning network. The input was converted to its corresponding MRA images by a combination of a single-convolution and a U-net model with a 5-fold cross-validation, which were then compared with a simple linear combination model. Image quality was evaluated by calculating the peak signal-to-noise ratio (PSNR), structural similarity index measurements (SSIMs), and high frequency error norm (HFEN). These calculations were performed for deep learning MRA (DL-MRA) and linear combination MRA (linear-MR), relative to TOF-MRA, and compared with each other using a nonparametric Wilcoxon signed-rank test. Overall image quality and branch visualization, each scored on a 5-point Likert scale, were blindly and independently rated by 2 board-certified radiologists. Results Deep learning MRA was successfully obtained in all subjects. The mean PSNR, SSIM, and HFEN of the DL-MRA were significantly higher, higher, and lower, respectively, than those of the linear-MRA (PSNR, 35.3 ± 0.5 vs 34.0 ± 0.5, P < 0.001; SSIM, 0.93 ± 0.02 vs 0.82 ± 0.02, P < 0.001; HFEN, 0.61 ± 0.08 vs 0.86 ± 0.05, P < 0.001). The overall image quality of the DL-MRA was comparable to that of TOF-MRA (4.2 ± 0.7 vs 4.4 ± 0.7, P = 0.99), and both types of images were superior to that of linear-MRA (1.5 ± 0.6, for both P < 0.001). No significant differences were identified between DL-MRA and TOF-MRA in the branch visibility of intracranial arteries, except for ophthalmic artery (1.2 ± 0.5 vs 2.3 ± 1.2, P < 0.001). Conclusions Magnetic resonance angiography generated by deep learning from 3D synthetic MRI data visualized major intracranial arteries as effectively as TOF-MRA, with inherently aligned quantitative maps and multiple contrast-weighted images. Our proposed algorithm may be useful as a screening tool for intracranial aneurysms without requiring additional scanning time.

Variability and Standardization of Quantitative Imaging

“… 128 , 129 Synthetic MR angiography constructed by deep learning is also feasible based on the 3D-QALAS data of high resolution. 130 …”

3D Quantitative Synthetic MRI in the Evaluation of Multiple Sclerosis Lesions

“…The synthesis of MRA from 3D-QALAS data is also feasible. 26 One of the strengths of synthetic MR imaging that remains to be studied is the possibility of adjusting the synthetic TR, TE, and TI parameters to optimize them for each pathology, which has been shown in 2D synthetic MR imaging. 11 Although we have used preset parameters for creating synthetic images in this study, optimization of the contrast may improve the detection and delineation of lesions over conventional imaging.…”

Differentiation between multiple sclerosis and neuromyelitis optica spectrum disorders by multiparametric quantitative MRI using convolutional neural network

“…A previous study that combined functional MRI and diffusion tensor imaging with T1-weighted and FLAIR images for a support vector machine algorithm, achieved an accuracy of 88% in distinguishing MS and NMOSD [20], but these advanced MRI modalities are difficult to be incorporated into routine clinical scans. The multi-dynamic multi-echo sequence is now a clinical routine in some institutions, because conventional contrast-weighted images, such as T1-weighted, T2-weighted, and FLAIR images, and even magnetic resonance angiography, can be created using synthetic MRI [9,21]. Including other modalities that are clinically available, such as lumbar puncture results, antibody status, and quantitative spinal cord measures, may further increase the performance of our algorithm.…”