Brain cine-MRI registration using MLSDO dynamic optimization algorithm

In this chapter, we propose to use a dynamic optimization algorithm to assess the deformations of the wall of the third cerebral ventricle in the case of a brain cine-MRI. In this method, a segmentation process is applied to a 2D+t cine-MRI sequence to detect the contours of a region of interest (i.e. lamina terminalis). Then, successive segmented contours are matched using a global alignment procedure, followed by a registration process. This registration process consists in optimizing an objective function that can be considered as a dynamic function. Thus, a dynamic optimization algorithm, called MLSDO, is used to solve the registration problem. The results obtained by MLSDO are compared to those of several well-known static optimization algorithms. This comparison shows the efficiency of MLSDO, and the relevance of using a dynamic optimization algorithm to solve this kind of problems.

[1]  Xin Yao,et al.  Benchmark Generator for CEC'2009 Competition on Dynamic Optimization , 2008 .

[2]  R. Storn,et al.  Differential Evolution: A Practical Approach to Global Optimization (Natural Computing Series) , 2005 .

[3]  Amir Nakib,et al.  A Dynamic Multi-Agent Algorithm applied to challenging benchmark problems , 2012, 2012 IEEE Congress on Evolutionary Computation.

[4]  Dinggang Shen,et al.  Estimating myocardial motion by 4D image warping , 2009, Pattern Recognit..

[5]  Amir Nakib,et al.  Third brain ventricle deformation analysis using fractional differentiation and evolution strategy in brain cine-MRI , 2010, Medical Imaging.

[6]  Naser Ahmadi,et al.  Determination of left ventricular mass on cardiac computed tomographic angiography. , 2009, Academic radiology.

[7]  Michael Brady,et al.  Improved Optimization for the Robust and Accurate Linear Registration and Motion Correction of Brain Images , 2002, NeuroImage.

[8]  Amir Nakib,et al.  A multiple local search algorithm for continuous dynamic optimization , 2013, J. Heuristics.

[9]  A. Rahmouni,et al.  Segmentation of cardiac cine-MR images and myocardial deformation assessment using level set methods. , 2005, Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society.

[10]  Changhe Li,et al.  A Generalized Approach to Construct Benchmark Problems for Dynamic Optimization , 2008, SEAL.

[11]  Nikolaus Hansen,et al.  Completely Derandomized Self-Adaptation in Evolution Strategies , 2001, Evolutionary Computation.