Encrypted login | home

Program Information

Using Radial Basis Functions with Compact Support and Total Variations Regularization for Deformable Registration of Fetal MR Images

no image available
q en

Q En*, Y Xie, W Zhou, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, guangdong

SU-E-I-73 Sunday 3:00PM - 6:00PM Room: Exhibit Hall

Purpose: The human brain is extraordinarily complex, and yet its origin is a simple tubular structure. Characterizing its anatomy at different stages of human fetal brain development not only aids in understanding this highly ordered process but also provides clues to detecting abnormalities caused by genetic or environmental factors. magnetic resonance images (MRI) has been used for quantitative studies of brain development in utero. However, non-rigid registration of a sequence of MRI volumes remains to be a challenging problem. The authors present our recent results on the development of a computationally inexpensive radial basis functions (RBF) and total-variation(TV) regularization algorithm for elastic alignment of MRI images.

Methods:Our algorithm based on the landmarks and radial basis function with compact support ,to registration of MR images which have an improved locality ,allow to constrain elastic deformations to image parts where required .Then total-variation regularization to account for the motion discontinuity close to the contact surface between fetal and uterus wall. The algorithm has been compared to the symmetric forces Demons methods.

Results:Using a series of validation experiments on fetal cases. The authors demonstrate that using RBF with compact to find the region of interest (ROI) then using total variation registration techniques can all recover volume deformations in MRI image series with reasonable accuracy;Moreover,The proposed total variation registration technique has substantial computational advantage over the other approaches.

Conclusion:The proposed RBF and TV registration technique has the potential for implementation on a computationally inexpensive platform and has the capability of recovering non-rigid deformations in tissue with reasonable accuracy.

Funding Support, Disclosures, and Conflict of Interest: This work is supported in part by grants from National Natural Science Foundation of China (NSFC: 81171402), NSFC Joint Research Fund for Overseas Research Chinese, Hong Kong and Macao Young Scholars (30928030), National Basic Research Program 973 (2010CB732606) from Ministry of Science and Technology of China, Guangdong Innovative Research Team Program (No. 2011S013) of China, Science and Technological Program for Dongguan's Higher Education, Science and Research, and Health Care Institutions(Grant No.2011108101001), and grant Comprehensive Strategic Cooperation Project of Guangdong province and Chinese academy of sciences (Grant No.2011B090300079).

Contact Email: