Markov Random Field Segmentation of Brain MR Images

TL;DR

This paper introduces a fully-automatic 3D brain MRI segmentation method using Markov random fields that effectively captures tissue features and handles noise and inhomogeneities, demonstrated through simulations and real images.

Contribution

The paper presents a novel automatic segmentation algorithm for brain MR images utilizing Markov random fields, incorporating non-parametric tissue distributions and neighborhood correlations.

Findings

Effective classification of brain tissues in single echo MR images

Robustness to noise and signal inhomogeneities demonstrated

Performance validated on simulated and real MR data

Abstract

We describe a fully-automatic 3D-segmentation technique for brain MR images. Using Markov random fields the segmentation algorithm captures three important MR features, i.e. non-parametric distributions of tissue intensities, neighborhood correlations and signal inhomogeneities. Detailed simulations and real MR images demonstrate the performance of the segmentation algorithm. The impact of noise, inhomogeneity, smoothing and structure thickness is analyzed quantitatively. Even single echo MR images are well classified into gray matter, white matter, cerebrospinal fluid, scalp-bone and background. A simulated annealing and an iterated conditional modes implementation are presented. Keywords: Magnetic Resonance Imaging, Segmentation, Markov Random Fields