Effect of Number of Coupled Structures on the Segmentation of Brain Structures

Abstract

This paper reports the effect of the coupling information on the performance of model-based segmentation of the brain structures from magnetic resonance images (MRI). We have developed a three-dimensional, nonparametric, entropy-based, and multi-shape method that benefits from coupling of the shapes. The proposed method uses principal component analysis (PCA) to develop shape models that capture structural variability and integrates geometrical relationship among different structures into the algorithm by coupling them (limiting their independent deformations). At the same time, to allow variations of the coupled structures, it registers each structure individually when building the shape models. It defines an entropybased energy function which is minimized using quasiNewton algorithm. Probability density functions (pdf) are estimated iteratively using nonparametric Parzen window method. In the optimization algorithm, analytical derivatives are used for maximum speed and accuracy. Sample results are given for the segmentation of caudate, thalamus, putamen, pallidum, hippocampus, and amygdala illustrating superior performance of the proposed method compared to the most similar method in the literature. The similarity of the results obtained by the proposed method with the expert segmentation is 4% to 12% higher than that of the most similar method. Experimental studies show that the proposed coupling method, which regulates shape variability during segmentation, improves accuracy of the results of the proposed method by 6% and those of the other method by 1%. In addition, the more the structures are used in the coupling process, the more accurate the results are obtained.

Cortical brain structures segmentation using constrained optimization and intensity coupling

“…In addition, is used to calculate the cardinality which forms the number of members in a given set or region. In general, for any structure, points identified inside a given region of the structure are used to estimate the intensity of the pdf [2]. However, structures of the same type are known to have very similar pdfs and, as a result, can be used to develop a more robust estimation of pdfs.…”

“…In general, most segmentation methods consist of an energy function, a shape model, and an optimization strategy, and each plays an important role in the design of an accurate segmentation algorithm. In [2][3] we have introduced a coupled structures segmentation algorithm that is based on a principal component analysis (PCA) designed to extract shape relationships among structures. In [4] we have added constraint to the shape parameters to achieve a more robust segmentation algorithm.…”

Two‐stage multishape segmentation of brain structures using image intensity, tissue type, and location informationa)

“…Another problem in many of the segmentation methods is the sensitivity of the results to the initialization of the algorithm. 13,21,23 An important observation is that the fine tuning step improves the segmentation results by overcoming the limitations of the prior shape model ͑principal shapes extracted from the training datasets͒. In other words, each dataset has parts similar to the training datasets that are represented by the prior knowledge.…”

“…We use principal component analysis ͑PCA͒ to extract principal shapes of different structures. 13,21,23 The proposed method is robust, fast, and accurate with a small number of parameters to set. It integrates information obtained from different sources in the energy function.…”

“…This is a modified version of our method in Ref. 13 that improves the registration, the selection of the number of the principal components, and the optimization procedures. In the second step, we use a modified initialization, update the intensity pdf's iteratively, and also used location and tissue type information by adding the pdf for the location and the pmf for the tissue type information.…”