TY - JOUR
T1 - 3D MRI image super-resolution for brain combining rigid and large diffeomorphic registration
AU - Liang, Zifei
AU - He, Xiaohai
AU - Teng, Qizhi
AU - Wu, Dan
AU - Qing, Lingbo
N1 - Funding Information:
This work was supported by the National Natural Science Foundation of China (grant nos. 61372174 and 61471248).
Publisher Copyright:
© The Institution of Engineering and Technology.
PY - 2017/12/1
Y1 - 2017/12/1
N2 - Most of the recent leading multiple magnetic resonance imaging (MRI) super-resolution techniques for brain are limited to rigid motion. In this study, the authors aim to develop a super-resolution technique with diffeomorphism mainly for longitudinal brain MRI data. For the images from different time slots, unpredicted deformation may occur. In previous studies, sole rigid registration or traditional non-rigid registration has been frequently used to achieve multi-plane super-resolution. However, non-rigid motion of two brains from different time slots is difficult to model, since brain contains a wealth of complex structure such as the cerebral cortex. In order to address such problem, rigid and large diffeomorphic registration has been embedded into their super-resolution framework. In addition, many previous researchers use L2 norm to achieve super-resolution framework. In this work, L1 norm minimisation and regularisation based on a bilateral prior are adopted. These operations ensure its robustness to the assumed model of data and noise. Their approach is evaluated using Alzheimer datasets from seven different resolutions. Results show that their reconstructions have advantages over rigid and conventional non-rigid registration-based super-resolution, in terms of the root-mean-square error and structure similarity. Furthermore, their reconstruction results improve the precision of brain automatic segmentation.
AB - Most of the recent leading multiple magnetic resonance imaging (MRI) super-resolution techniques for brain are limited to rigid motion. In this study, the authors aim to develop a super-resolution technique with diffeomorphism mainly for longitudinal brain MRI data. For the images from different time slots, unpredicted deformation may occur. In previous studies, sole rigid registration or traditional non-rigid registration has been frequently used to achieve multi-plane super-resolution. However, non-rigid motion of two brains from different time slots is difficult to model, since brain contains a wealth of complex structure such as the cerebral cortex. In order to address such problem, rigid and large diffeomorphic registration has been embedded into their super-resolution framework. In addition, many previous researchers use L2 norm to achieve super-resolution framework. In this work, L1 norm minimisation and regularisation based on a bilateral prior are adopted. These operations ensure its robustness to the assumed model of data and noise. Their approach is evaluated using Alzheimer datasets from seven different resolutions. Results show that their reconstructions have advantages over rigid and conventional non-rigid registration-based super-resolution, in terms of the root-mean-square error and structure similarity. Furthermore, their reconstruction results improve the precision of brain automatic segmentation.
UR - http://www.scopus.com/inward/record.url?scp=85039060983&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85039060983&partnerID=8YFLogxK
U2 - 10.1049/iet-ipr.2017.0517
DO - 10.1049/iet-ipr.2017.0517
M3 - Article
AN - SCOPUS:85039060983
SN - 1751-9659
VL - 11
SP - 1291
EP - 1301
JO - IET Image Processing
JF - IET Image Processing
IS - 12
ER -