Data-driven brain MRI segmentation supported on edge confidence and a priori tissue information

Abstract

Brain magnetic resonance imaging segmentation is accomplished in this work by applying nonparametric density estimation, using the mean shift algorithm in the joint spatial-range domain. The quality of the class boundaries is improved by including an edge confidence map, that represents the confidence of truly being in the presence of a border between adjacent regions; an adjacency graph is then constructed with the labeled regions, and analyzed and pruned to merge adjacent regions. In order to assign image regions to a cerebral tissue type, a spatial normalization between image data and standard probability maps is carried out, so that for each structure a maximum a posteriori probability criterion is applied. The method was applied to synthetic and real images, keeping all parameters constant throughout the process for each type of data. The combination of region segmentation and edge detection proved to be a robust technique, as adequate clusters were automatically identified, regardless of the noise level and bias. In a comparison with reference segmentations, average Tanimoto indexes of 0.90-0.99 were obtained for synthetic data and of 0.59-0.99 for real data, considering gray matter, white matter, and background.

A Segmentation Model Using Compound Markov Random Fields Based on a Boundary Model

“…The difference between these models and ours lies in the prior energy function which embodies the interactions between sites. The prior functions of the first [MLL, (12)], second [LP1, (13)], and third [LP2, (14)] models are given, respectively, in (12)- (14), shown at the bottom of the next page. Here, if , ; else .…”

“…The results show that the new model can give higher segmentation accuracy while preserving the extracted object boundary well. Other work applying MRF models to brain image segmentation can be found in [8], [10]- [14].…”

A Survey of MRI Segmentation Techniques for Brain Tumor Studies

“…To ease their work of segmenting tumors from MR images, automatic tumor segmentation methods are used. Most of the segmentation algorithms only segment either the healthy tissues [15]- [18] or tumors [7]- [12] from these images with a good accuracy. However, segmentation algorithms that segment both the healthy tissues along with the tumor affected regions of the brain can help in efficient medical diagnosis and treatment planning taking into account all of the other biological conditions of patients.…”

A Fuzzy Rules-Based Segmentation Method for Medical Images Analysis

“…Proceeding from the grounds of artificial intelligence, soft computing, A Fuzzy Rules-Based Segmentation Method for Medical Images Analysis 197 and image processing, for instance from [4], [9], [11], [18], [19] a number of authors have used these techniques to aid in the analysis of medical images, e.g. in [1], [2], [3], [5], [6]- [8], [10], [12]- [13], [20]- [22].…”