Least-Squares Fitting of Two 3-D Point Sets
IEEE Transactions on Pattern Analysis and Machine Intelligence
Iconic feature based nonrigid registration: the PASHA algorithm
Computer Vision and Image Understanding - Special issue on nonrigid image registration
A Fast and Log-Euclidean Polyaffine Framework for Locally Linear Registration
Journal of Mathematical Imaging and Vision
Voxel-by-Voxel Functional Diffusion Mapping for Early Evaluation of Breast Cancer Treatment
IPMI '09 Proceedings of the 21st International Conference on Information Processing in Medical Imaging
A Non-rigid Registration Framework That Accommodates Resection and Retraction
IPMI '09 Proceedings of the 21st International Conference on Information Processing in Medical Imaging
A Demons Algorithm for Image Registration with Locally Adaptive Regularization
MICCAI '09 Proceedings of the 12th International Conference on Medical Image Computing and Computer-Assisted Intervention: Part I
Improved registration for large electron microscopy images
ISBI'09 Proceedings of the Sixth IEEE international conference on Symposium on Biomedical Imaging: From Nano to Macro
Hierarchical adaptive local affine registration for respiratory motion estimation from 3-D MRI
ISBI'10 Proceedings of the 2010 IEEE international conference on Biomedical imaging: from nano to Macro
Reliability-driven, spatially-adaptive regularization for deformable registration
WBIR'10 Proceedings of the 4th international conference on Biomedical image registration
MICCAI'12 Proceedings of the 4th international conference on Abdominal Imaging: computational and clinical applications
Hi-index | 0.00 |
Abdominal image non-rigid registration is a particularly challenging task due to the presence of multiple organs, many of which move independently, contributing to independent deformations. Local-affine registration methods can handle multiple independent movements by assigning prior definition of each affine component and its spatial extent which is less suitable for multiple soft-tissue structures as in the abdomen. Instead, we propose to use the local-affine assumption as a prior constraint within the dense deformation field computation. Our method use the dense correspondences field computed using the optical-flow equations to estimate the local-affine transformations that best represent the deformation associated with each voxel with Gaussian regularization to ensure the smoothness of the deformation field. Experimental results from both synthetic and 400 controlled experiments on abdominal CT images and Diffusion Weighted MRI images demonstrate that our method yields a smoother deformation field with superior registration accuracy compared to the demons and diffeomorphic demons algorithms.