Abstract

Image segmentation is an indispensable process in the visualization of human tissues, particularly during clinical analysis of brain magnetic resonance (MR) images. For many human experts, manual segmentation is a difficult and time consuming task, which makes an automated brain MR image segmentation method desirable. In this regard, this paper presents a new segmentation method for brain MR images, integrating judiciously the merits of rough-fuzzy computing and multiresolution image analysis technique. The proposed method assumes that the major brain tissues, namely, gray matter, white matter, and cerebrospinal fluid from the MR images are considered to have different textural properties. The dyadic wavelet analysis is used to extract the scale-space feature vector for each pixel, while the rough-fuzzy clustering is used to address the uncertainty problem of brain MR image segmentation. An unsupervised feature selection method is introduced, based on maximum relevance-maximum significance criterion, to select relevant and significant textural features for segmentation problem, while the mathematical morphology based skull stripping preprocessing step is proposed to remove the non-cerebral tissues like skull. The performance of the proposed method, along with a comparison with related approaches, is demonstrated on a set of synthetic and real brain MR images using standard validity indices.

Highlights

  • Magnetic resonance imaging (MRI) is an important diagnostic imaging technique for the early detection of abnormal changes in tissues and organs, and majority of research in medical imaging concerns magnetic resonance (MR) images [1]

  • The proposed method integrates the merits of robust rough-fuzzy c-means [40], dyadic wavelets, and proposed skull stripping and unsupervised feature selection algorithms

  • M3: Using mask generated by brain extraction tool (BET) [41], wavelet analysis for feature extraction, using proposed feature selection algorithm, clustering using robust rough-fuzzy c-means (rRFCM); 4

Read more

Summary

Introduction

Magnetic resonance imaging (MRI) is an important diagnostic imaging technique for the early detection of abnormal changes in tissues and organs, and majority of research in medical imaging concerns MR images [1]. The rough-fuzzy clustering algorithms such as rough-fuzzy c-means [39] and robust rough-fuzzy c-means [40] can avoid the problems of noise sensitivity of fuzzy c-means [35] and the coincident clusters of possibilistic c-means [37] In this regard, the paper presents a texture-based brain MR image segmentation method, judiciously integrating the merits of multiresolution image analysis and rough-fuzzy computing. In wavelet-based image segmentation method, a number of insignificant and irrelevant features may be generated. As a result of that, S S[{Aj} and C C\Aj. The MRMS criterion based feature selection algorithm reported above is unsupervised in nature since it does not require any a priori knowledge about the segmented regions of brain MR image. It is defined as the size of the intersection of two sets divided by the size of their union, that is, J ðA; BÞ

B B ð27Þ
Experimental Results and Discussions
Conclusion
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call