TY - JOUR
T1 - Deep Learning Approach for Generating MRA Images from 3D Quantitative Synthetic MRI without Additional Scans
AU - Fujita, Shohei
AU - Hagiwara, Akifumi
AU - Otsuka, Yujiro
AU - Hori, Masaaki
AU - Takei, Naoyuki
AU - Hwang, Ken Pin
AU - Irie, Ryusuke
AU - Andica, Christina
AU - Kamagata, Koji
AU - Akashi, Toshiaki
AU - Kunishima Kumamaru, Kanako
AU - Suzuki, Michimasa
AU - Wada, Akihiko
AU - Abe, Osamu
AU - Aoki, Shigeki
N1 - Funding Information:
Conflicts of interest and sources of funding: Naoyuki Takei is currently employed full-time at GE healthcare Japan. This work was supported by JSPS KAKENHI grant numbers 19K17177, 19K17150, 18K07692, 16K10327, and JP16H06280; Grant-in-Aid for Scientific Research on Innovative Areas–resource and technical support platforms for promoting research “Advanced Bioimaging Sup-port”; the Japan Agency for Medical Research and Development under grant numbers 18lk1010025s0101 and 19lk1010025h9902; and the Japanese Society for Magnetic Resonance in Medicine.
Publisher Copyright:
© Wolters Kluwer Health, Inc. All rights reserved.
PY - 2020/4/1
Y1 - 2020/4/1
N2 - 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.
AB - 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.
KW - QALAS
KW - convolutional neural network
KW - deep learning
KW - image synthesis
KW - machine learning
KW - magnetic resonance angiography
KW - magnetic resonance imaging
KW - quantitative synthetic MRI
KW - time-of-flight
UR - http://www.scopus.com/inward/record.url?scp=85079848188&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85079848188&partnerID=8YFLogxK
U2 - 10.1097/RLI.0000000000000628
DO - 10.1097/RLI.0000000000000628
M3 - Article
C2 - 31977603
AN - SCOPUS:85079848188
SN - 0020-9996
VL - 55
SP - 249
EP - 256
JO - Investigative radiology
JF - Investigative radiology
IS - 4
ER -