Biography
Nishant Ravikumar is a Research Fellow at CISTIB, in the School of Computing, University of Leeds. He completed his PhD in 2017 at the University of Sheffield. Following this, he spent a couple of years as a postdoctoral researcher at the Pattern Recognition Lab, Friedrich-Alexander-University, Erlangen-Nuremberg. His previous work concentrated on shape registration and shape analysis, using probabilistic models. His current research interests are in developing algorithms that aid in the classification, segmentation and registration of medical images, for computer-aided diagnosis and interventions using machine learning.
Sparse Statistical Shape Modelling
|
Details
Description
The provided code is based on the work by A. Gooya et al. [1] which proposes a Gaussian mixture model based approach to training statistical shape models (SSMs). The novel feature of the proposed approach is the application of a symmetric Dirichlet prior on the mixture coefficients to enforce sparsity and search over a continuous space for the optimal number of Gaussian components, to address the common issue of over or under-fitting. Additionally, we provide code to reconstruct surfaces from the unstructured point sets generated, following SSM training. References [1] Gooya, Ali, Christos Davatzikos, and Alejandro F. Frangi. "A bayesian approach to sparse model selection in statistical shape models." SIAM Journal on Imaging Sciences 8.2 (2015): 858-887. File Format
TAR.GZ File DOI
http://dx.doi.org/10.6084/m9.figshare.1562325 Platform
Linux Size of download
3.33 MB People who contribute to this work
Nishant Ravikumar, Department of Mechanical Engineering, The University of Sheffield Ali Gooya School of Computing, University of Leeds Alejandro F. Frangi School of Computing, University of Leeds |