TY - JOUR
T1 - Autoencoder-Inspired Convolutional Network-Based Super-Resolution Method in MRI
AU - Park, Seonyeong
AU - Gach, H. Michael
AU - Kim, Siyong
AU - Lee, Suk Jin
AU - Motai, Yuichi
N1 - Publisher Copyright:
© 2013 IEEE.
PY - 2021
Y1 - 2021
N2 - Objective: To introduce an MRI in-plane resolution enhancement method that estimates High-Resolution (HR) MRIs from Low-Resolution (LR) MRIs. Method Materials: Previous CNN-based MRI super-resolution methods cause loss of input image information due to the pooling layer. An Autoencoder-inspired Convolutional Network-based Super-resolution (ACNS) method was developed with the deconvolution layer that extrapolates the missing spatial information by the convolutional neural network-based nonlinear mapping between LR and HR features of MRI. Simulation experiments were conducted with virtual phantom images and thoracic MRIs from four volunteers. The Peak Signal-to-Noise Ratio (PSNR), Structure SIMilarity index (SSIM), Information Fidelity Criterion (IFC), and computational time were compared among: ACNS; Super-Resolution Convolutional Neural Network (SRCNN); Fast Super-Resolution Convolutional Neural Network (FSRCNN); Deeply-Recursive Convolutional Network (DRCN). Results: ACNS achieved comparable PSNR, SSIM, and IFC results to SRCNN, FSRCNN, and DRCN. However, the average computation speed of ACNS was 6, 4, and 35 times faster than SRCNN, FSRCNN, and DRCN, respectively under the computer setup used with the actual average computation time of 0.15 s per $100\times100$ pixels. Conclusion: The result of this study implies the potential application of ACNS to real-time resolution enhancement of 4D MRI in MRI guided radiation therapy.
AB - Objective: To introduce an MRI in-plane resolution enhancement method that estimates High-Resolution (HR) MRIs from Low-Resolution (LR) MRIs. Method Materials: Previous CNN-based MRI super-resolution methods cause loss of input image information due to the pooling layer. An Autoencoder-inspired Convolutional Network-based Super-resolution (ACNS) method was developed with the deconvolution layer that extrapolates the missing spatial information by the convolutional neural network-based nonlinear mapping between LR and HR features of MRI. Simulation experiments were conducted with virtual phantom images and thoracic MRIs from four volunteers. The Peak Signal-to-Noise Ratio (PSNR), Structure SIMilarity index (SSIM), Information Fidelity Criterion (IFC), and computational time were compared among: ACNS; Super-Resolution Convolutional Neural Network (SRCNN); Fast Super-Resolution Convolutional Neural Network (FSRCNN); Deeply-Recursive Convolutional Network (DRCN). Results: ACNS achieved comparable PSNR, SSIM, and IFC results to SRCNN, FSRCNN, and DRCN. However, the average computation speed of ACNS was 6, 4, and 35 times faster than SRCNN, FSRCNN, and DRCN, respectively under the computer setup used with the actual average computation time of 0.15 s per $100\times100$ pixels. Conclusion: The result of this study implies the potential application of ACNS to real-time resolution enhancement of 4D MRI in MRI guided radiation therapy.
KW - Autoencoder
KW - MRI
KW - convolution neural network
KW - deep learning
KW - super resolution
UR - http://www.scopus.com/inward/record.url?scp=85105089687&partnerID=8YFLogxK
U2 - 10.1109/JTEHM.2021.3076152
DO - 10.1109/JTEHM.2021.3076152
M3 - Article
C2 - 34168920
AN - SCOPUS:85105089687
SN - 2168-2372
VL - 9
JO - IEEE Journal of Translational Engineering in Health and Medicine
JF - IEEE Journal of Translational Engineering in Health and Medicine
M1 - 9417192
ER -