Difference between revisions of "Projects:ExpectationMaximizationSegmentation"

From NAMIC Wiki
Jump to: navigation, search
 
(7 intermediate revisions by one other user not shown)
Line 1: Line 1:
−
= Expectation Maximization Segmentation of MRI Images =
+
Back to [[Algorithm:MIT|MIT Algorithms]]
 +
__NOTOC__
 +
= Bayesian Segmentation of MRI Images =
  
−
The goal of this project is to learn a probability distribution such that samples drawn from that distribution tend to look like manual segmentations of other subjects. This is useful because such a distribution can then be used as a prior in automated segmentation algorithms.
+
Segmentation algorithms based on the Expectation Maximization (EM) theory
−
 
+
have proved themselves capable of results of an exceptional quality.
−
The proposed method extends the usual concept of probabilistic atlases in several ways; for instance, it yields sparse tetrahedral meshes that are less prone to overfitting to the training data than traditional atlases. These atlases are therefore better able to predict the antanomy in unseen subjects, especially when the number of training subjects is small.
+
Generally such results were obtained by carefully optimizing the parameters
−
 
+
for a specific MRI protocol and a specific anatomical region.
−
A Bayesian modeling approach is used throughout. The first level of Bayesian inference yields a non-rigid group-wise registration algorithm based on a topology preserving deformation prior; the registration criterion is closely related to the so-called congealing criterion. For the higher levels of inference, the method does Bayesian model comparison, which is known to be closely related to the Minimum Description Length principle when Gaussian approximations are used.
+
Besides the segmentation of a standard size MRI scan often requires
−
 
+
a processing time in the order of minutes or hours.
−
The method explicitly aims at finding the optimal deformation regularization, which involves approximating an integral over all possible deformations. An interesting alternative way to do this, proposed by Stephanie Allassonniere and co-workers, is to side-step the integration by sampling from the deformation posterior in an EM algorithm (although you'd still have to approximate the partition function if the deformation model is not Gaussian, as in our case).
+
Because of these contraints, EM algorithms have found a limited usability
 +
in the clinical environment.
 +
Our project aims at addressing these issues and designing a new framework
 +
that would be easily trackable by a clinician.
 +
The background of our team encompasses Computer Science and Radiology,
 +
as well as Research and Industry.
 +
Our focus will be threefold,
 +
first to identify the bottlenecks of existing EM algorithms,
 +
second to validate the quality of our method on a collection of real life scans,
 +
and finally to provide an implementation intuitive enough that it could be accepted
 +
in the hospital and therefore make a difference for the treatment of the patient.
  
 
==Key Investigators==
 
==Key Investigators==
−
 
 
*Sylvain Jaume, MIT
 
*Sylvain Jaume, MIT
 
*Koen Van Leemput, MGH
 
*Koen Van Leemput, MGH
Line 16: Line 27:
 
*Ron Kikinis, BWH
 
*Ron Kikinis, BWH
 
*Steve Pieper, BWH
 
*Steve Pieper, BWH
−
 
−
==Publications==
 
−
 
−
Automated Segmentation of Hippocampal Subfields from Ultra-High Resolution In Vivo MRI,
 
−
K. Van Leemput, A. Bakkour, T. Benner, G. Wiggins, L.L. Wald, J. Augustinack, B.C. Dickerson, P. Golland, B. Fischl,
 
−
Hippocampus, 2009.
 
−
 
−
Encoding Probabilistic Brain Atlases Using Bayesian Inference,
 
−
K. Van Leemput,
 
−
IEEE Transactions on Medical Imaging, 2009.
 

Latest revision as of 14:26, 24 April 2009

Home < Projects:ExpectationMaximizationSegmentation
Back to MIT Algorithms

Bayesian Segmentation of MRI Images

Segmentation algorithms based on the Expectation Maximization (EM) theory have proved themselves capable of results of an exceptional quality. Generally such results were obtained by carefully optimizing the parameters for a specific MRI protocol and a specific anatomical region. Besides the segmentation of a standard size MRI scan often requires a processing time in the order of minutes or hours. Because of these contraints, EM algorithms have found a limited usability in the clinical environment. Our project aims at addressing these issues and designing a new framework that would be easily trackable by a clinician. The background of our team encompasses Computer Science and Radiology, as well as Research and Industry. Our focus will be threefold, first to identify the bottlenecks of existing EM algorithms, second to validate the quality of our method on a collection of real life scans, and finally to provide an implementation intuitive enough that it could be accepted in the hospital and therefore make a difference for the treatment of the patient.

Key Investigators

  • Sylvain Jaume, MIT
  • Koen Van Leemput, MGH
  • Polina Golland, MIT
  • Ron Kikinis, BWH
  • Steve Pieper, BWH
Retrieved from "https://www.na-mic.org/w/index.php?title=Projects:ExpectationMaximizationSegmentation&oldid=36681"