Distance transformations in digital images
Computer Vision, Graphics, and Image Processing
Principal Warps: Thin-Plate Splines and the Decomposition of Deformations
IEEE Transactions on Pattern Analysis and Machine Intelligence
Image warping by radial basis functions: applications to facial expressions
CVGIP: Graphical Models and Image Processing
Medical image registration incorporating deformations
BMVC '95 Proceedings of the 6th British conference on Machine vision (Vol. 2)
Thin-Plate Splines and the Atlas Problem for Biomedical Images
IPMI '91 Proceedings of the 12th International Conference on Information Processing in Medical Imaging
A two-dimensional interpolation function for irregularly-spaced data
ACM '68 Proceedings of the 1968 23rd ACM national conference
Computer Methods and Programs in Biomedicine
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
Analyzing anatomical structures: leveraging multiple sources of knowledge
CVBIA'05 Proceedings of the First international conference on Computer Vision for Biomedical Image Applications
Articulated model registration of MRI/X-Ray spine data
ICIAR'10 Proceedings of the 7th international conference on Image Analysis and Recognition - Volume Part II
Automated skeleton based multi-modal deformable registration of head&neck datasets
MICCAI'12 Proceedings of the 15th international conference on Medical Image Computing and Computer-Assisted Intervention - Volume Part II
Hi-index | 0.01 |
Division of Radiological Sciences, Guy's Hospital, London Bridge, London SE1 9RT Medical image registration can provide useful clinical information relating images of the same patient acquired from different modalities, or from serial studies with a single modality. Current algorithms invariably assume that the objects in the images can be treated as a rigid body. In practice, some parts of a patient, usually bony structures, may move as rigid bodies while others may deform. To address this, we have developed a new technique that allows identified objects in the image to move as rigid bodies, while the remainder smoothly deforms. Euclidean distance transforms calculated from the rigid objects are used to weight a linear combination of pre-defined linear transformations, one for each rigid body in the image, and also to form a modified radial basis function. This ensures that the non-linear deformation tends to zero as we move towards the rigid body boundary. The resulting deformation technique is valid in any dimension, subject to the choice of the basis function.We demonstrate this technique in two dimensions on a pattern of rigid square structures to simulate the vertebral bodies of the spine, and on sagittal magnetic resonance images collected from a volunteer.