Active shape models—their training and application
Computer Vision and Image Understanding
Deformable M-Reps for 3D Medical Image Segmentation
International Journal of Computer Vision - Special Issue on Research at the University of North Carolina Medical Image Display Analysis Group (MIDAG)
Continuous medial models in two-sample statistics of shape
Continuous medial models in two-sample statistics of shape
Multi-figure anatomical objects for shape statistics
IPMI'05 Proceedings of the 19th international conference on Information Processing in Medical Imaging
Automatic cardiac MRI segmentation using a biventricular deformable medial model
MICCAI'10 Proceedings of the 13th international conference on Medical image computing and computer-assisted intervention: Part I
Optimal medial surface generation for anatomical volume representations
MICCAI'12 Proceedings of the 4th international conference on Abdominal Imaging: computational and clinical applications
A validation benchmark for assessment of medial surface quality for medical applications
ICVS'13 Proceedings of the 9th international conference on Computer Vision Systems
Deformation similarity measurement in quasi-conformal shape space
Graphical Models
Hi-index | 0.00 |
The medial model is a powerful shape representation method that models a 3D object by explicitly defining its skeleton (medial axis) and deriving the boundary geometry according to medial geometry. It has been recently extended to model complex shapes with multi-figures, i.e., shapes whose skeletons can not be described by a single sheet in 3D. This paper applied the medial model to a 2-chamber heart data set consisting of 428 cardiac shapes from 90 subjects. The results show that the medial model can capture the heart shape accurately. To demonstrate the usage of the medial model, the changes of the heart wall thickness over time are analyzed. We calculated the mean heart wall thickness map of 90 subjects for different phases of the cardiac cycle, as well as the mean thickness change between phases.