Automatic seed initialization for the expectation-maximization algorithm and its application in 3D medical imaging

Abstract

Statistical partitioning of images into meaningful areas is the goal of all region-based segmentation algorithms. The clustering or creation of these meaningful partitions can be achieved in number of ways but in most cases it is achieved through the minimization or maximization of some function of the image intensity properties. Commonly these optimization schemes are locally convergent, therefore initialization of the parameters of the function plays a very important role in the final solution. In this paper we perform an automatically initialized expectation-maximization algorithm to partition the data in medical MRI images. We present analysis and illustrate results against manual initialization and apply the algorithm to some common medical image processing tasks.

A modified approach of identification and tracking of heart boundary from MRI image sequences

“…The EM algorithm [12] attempts to classify data using a soft membership function as a weighted sum of a number of Gaussian distribution called Gaussian Mixture Model (GMM). The method aims to find the maximum likelihood estimate for an underlying distribution from a given dataset when the data is incomplete.…”

New methods in Brain MR Segmentation with Fuzzy EMalgorithm

“…The EM algorithm has been used by a number of medical image processing researchers for different kinds of studies [13], [11].…”

Brain MR Segmentation through Fuzzy Expectation Maximization and Histogram Based K-Means

“…The EM algorithm has been used by a number of medical image processing researchers for different kinds of studies [7], [8].…”