Projects:TissueClassificationWithNeighborhoodStatistics

Back to NA-MIC Collaborations, Utah Algorithms

Tissue Classification with Neighborhood Statistics

We have implemented the MRI Tissue Classification Algorithm described in the reference below. Classes for non-parametric density estimation and automatic parameter selection have been implemented as the basic framework on which we build the classification algorithm.

Description

• The stochastic non-parametric density estimation framework is very general and allows the user to change kernel types (we have coded isotropic Gaussian, but additional kernels can easily be derived from the same parent class) and sampler types (for example local vs. global image sampling as well as sampling in non-image data) as template parameters.

• The classification class uses the stochastic non-parametric density estimation framework to implement the algorithm in the reference below.

• An existing ITK bias correction method has been incorporated into the method.

• Currently, we are registering atlas images to our data using the stand-alone LandmarkInitializedMutualInformationRegistration application. Ideally, we'd like to incorporate an exiting registration algorithm into our code so that classification can be carried out in one step. The initialization to the registration can be provided as command line arguments.

Key Investigators

Tolga Tasdizen, Suyash Awate, Ross Whitaker

Publications

In Press

• Suyash P. Awate, Ross T. Whitaker: Feature-Preserving MRI Denoising: A Nonparametric Empirical Bayes Approach. IEEE Trans. Med. Imaging 26(9): 1242-1255 (2007).
• T Tasdizen, S Awate, R Whitaker, A nonparametric, entropy-minimizing MRI tissue classification algorithm implementation using ITK, MICCAI 2005 Open-Source Workshop.
• Tolga Tasdizen, Suyash P. Awate, Ross T. Whitaker, Norman L. Foster: MRI Tissue Classification with Neighborhood Statistics: A Nonparametric, Entropy-Minimizing Approach. MICCAI (2) 2005: 517-525

In Print

NA-MIC Publications Database