TY - GEN
T1 - Deep Learning-based Deformable Registration of Dynamic Contrast-Enhanced MR Images of the Kidney
AU - Huang, James
AU - Guo, Junyu
AU - Pedrosa, Ivan
AU - Fei, Baowei
N1 - Funding Information:
This research was supported in part by the U.S. National Institutes of Health (NIH) grants (R01CA156775, R01CA204254, R01HL140325, R01CA154475 and R21CA231911), by the Cancer Prevention and Research Institute of Texas (CPRIT) grant RP190588, and by the Career Enhancement Program supported by the UT Southwestern SPORE.
Publisher Copyright:
© 2022 SPIE.
PY - 2022
Y1 - 2022
N2 - Respiratory motion is a major contributor to bias in quantitative analysis of magnetic resonance imaging (MRI) acquisitions. Deformable registration of three-dimensional (3D) dynamic contrast-enhanced (DCE) MRI data improves estimation of kidney kinetic parameters. In this study, we proposed a deep learning approach with two steps: a convolutional neural network (CNN) based affine registration network, followed by a U-Net trained for deformable registration between two MR images. The proposed registration method was applied successively across consecutive dynamic phases of the 3D DCE-MRI dataset to reduce motion effects in the different kidney compartments (i.e., cortex, medulla). Successful reduction in the motion effects caused by patient respiration during image acquisition allows for improved kinetic analysis of the kidney. Original and registered images were analyzed and compared using dynamic intensity curves of the kidney compartments, target registration error of anatomical markers, image subtraction, and simple visual assessment. The proposed deep learning-based approach to correct motion effects in abdominal 3D DCE-MRI data can be applied to various kidney MR imaging applications.
AB - Respiratory motion is a major contributor to bias in quantitative analysis of magnetic resonance imaging (MRI) acquisitions. Deformable registration of three-dimensional (3D) dynamic contrast-enhanced (DCE) MRI data improves estimation of kidney kinetic parameters. In this study, we proposed a deep learning approach with two steps: a convolutional neural network (CNN) based affine registration network, followed by a U-Net trained for deformable registration between two MR images. The proposed registration method was applied successively across consecutive dynamic phases of the 3D DCE-MRI dataset to reduce motion effects in the different kidney compartments (i.e., cortex, medulla). Successful reduction in the motion effects caused by patient respiration during image acquisition allows for improved kinetic analysis of the kidney. Original and registered images were analyzed and compared using dynamic intensity curves of the kidney compartments, target registration error of anatomical markers, image subtraction, and simple visual assessment. The proposed deep learning-based approach to correct motion effects in abdominal 3D DCE-MRI data can be applied to various kidney MR imaging applications.
KW - convolutional neural network (CNN)
KW - deep learning
KW - Deformable image registration
KW - dynamic contrast enhanced (DCE) MRI
KW - kidney
UR - http://www.scopus.com/inward/record.url?scp=85131909203&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85131909203&partnerID=8YFLogxK
U2 - 10.1117/12.2611768
DO - 10.1117/12.2611768
M3 - Conference contribution
C2 - 36793654
AN - SCOPUS:85131909203
T3 - Progress in Biomedical Optics and Imaging - Proceedings of SPIE
BT - Medical Imaging 2022
A2 - Linte, Cristian A.
A2 - Siewerdsen, Jeffrey H.
PB - SPIE
T2 - Medical Imaging 2022: Image-Guided Procedures, Robotic Interventions, and Modeling
Y2 - 21 March 2022 through 27 March 2022
ER -