Model-Image Registration of Parametric Shape Models: Fitting a Shell to the Cochlea

Please use this identifier to cite or link to this publication:
Mathematical models are often used to describe natural phenomena, organisms and anatomy. This paper presents a Model-Image Registration framework that can be used to evaluate models of anatomical shape. An optimisation process is applied to the model parameters to fit the model to an organ of interest in a volumetric image. The fit is obtained by maximising a metric that measures how closely the model surface atches the image edge features, according to gradient magnitude and orientation with respect to the surface normal. The system was tested using a spiral shell model, with generated data as ground truth, and also with CT scans of the temporal bone. The parameters converge to within a close tolerance after a few hundred iterations on the test data, and show promising results on registering with the clinical data.
minus 2 Files (2Mb)
There is no code review at this time.

There is no review at this time. Be the first to review this publication!

Quick Comments

Download All

Statistics more
Global rating: starstarstarstarstar
Review rating: starstarstarstarstar [review]
Code rating:
Paper Quality: plus minus

Information more
Keywords: registration, modelling
Toolkits: ITK, CMake
Export citation:


Linked Publications more
N-Dimensional Phase Unwrapping N-Dimensional Phase Unwrapping
by Vigneault D., Wang W., Tee M., Bluemke D., Noble A.
Robust Scattered Data Points Approximation Using Finite Element Biomechanical Model Robust Scattered Data Points Approximation Using Finite Element Biomechanical Model
by Liu Y., Chrisochoides N.

View license
Loading license...

Send a message to the author
ISSN 2327-770X
Powered by Midas