Anatomy Dependent Multi-context Fuzzy Clustering for Separation of Brain Tissues in MR Images

Zhu, Chaozhe; Lin, Fengshan; Jiang, Tianzi

doi:10.1007/978-3-540-28626-4_24

Cited by 4 publications

(3 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On the other hand, one straightforward way to assess the quality of the registration is to evaluate how the tissues are deformed from one subject to the other, we therefore evaluate the registration quality by computing the overlap between the tissues of the reference image and the tissues of each floating image after registration. The extraction of white matter, gray matter and cerebral spinal fluid is performed using our previous technique (Zhu and Jiang, 2003). In this segmentation algorithm, multicontext fuzzy clustering (MCFC) is proposed for classifying MR data into tissues of white matter, gray matter, and cerebral spinal fluid automatically.…”

Section: Experiments On Datasets Of 14 Subjectsmentioning

confidence: 99%

Nonrigid registration of brain MRI using NURBS

Wang

Jiang

2007

Pattern Recognition Letters

View full text Add to dashboard Cite

Section: Experiments On Datasets Of 14 Subjectsmentioning

confidence: 99%

Nonrigid registration of brain MRI using NURBS

Wang

Jiang

2007

Pattern Recognition Letters

View full text Add to dashboard Cite

“…However, the main disadvantage of MRF-based methods is that the objective function associated with most nontrivial MRF problems is extremely nonconvex, which makes the corresponding minimization problem very time consuming. We combined a pixon-based image model with a Markov random field (MRF) model under a Bayesian framework [4]. The anisotropic diffusion equation was successfully used to form the pixons in our new pixon scheme.…”

Section: Brain Tissue Segmentationmentioning

confidence: 99%

Shape Analysis of Human Brain with Cognitive Disorders

Jiang

Shi

Zhu

et al. 2007

Digital Human Modeling

View full text Add to dashboard Cite

In this paper, we present some of our current studies on how human brain structures are influenced by cognitive disorders occurred from various neurological and psychiatric diseases based on magnetic resonance imaging (MRI). We first give a brief introduction about computational neuroanatomy, which is the basis of these studies. In Section 2, several novel methods on segmentations of brain tissue and anatomical substructures were presented. Section 3 presented some studies on brain image registration, which plays a core role in computational neuroanatomy. Shape analysis of substructures, cerebral cortical thickness and complexity was presented in Section 4. Finally, some prospects and future research directions in this field are also given.

show abstract

“…Clustering has a long history in the statistical literature and has recent applications in functional neuroimaging, particularly in fMRI. Our analyses focus on the classification of measured brain activity, but cluster analysis is also useful for anatomical segmentation of brain tissues [Zhu and Jiang, 2003]. Neuroimaging applications currently utilize a limited number of existing clustering algorithms, largely selected based on computational facility and speed.…”

Section: Introductionmentioning

confidence: 99%

Methods for detecting functional classifications in neuroimaging data

Bowman

Patel

2004

Human Brain Mapping

View full text Add to dashboard Cite

Data-driven statistical methods are useful for examining the spatial organization of human brain function. Cluster analysis is one approach that aims to identify spatial classifications of temporal brain activity profiles. Numerous clustering algorithms are available, and no one method is optimal for all areas of application because an algorithm's performance depends on specific characteristics of the data. K-means and fuzzy clustering are popular for neuroimaging analyses, and select hierarchical procedures also appear in the literature. It is unclear which clustering methods perform best for neuroimaging data. We conduct a simulation study, based on PET neuroimaging data, to evaluate the performances of several clustering algorithms, including a new procedure that builds on the kth nearest neighbor method. We also examine three stopping rules that assist in determining the optimal number of clusters. Five hierarchical clustering algorithms perform best in our study, some of which are new to neuroimaging analyses, with Ward's and the beta-flexible methods exhibiting the strongest performances. Furthermore, Ward's and the beta-flexible methods yield the best performances for noisy data, and the popular K-means and fuzzy clustering procedures also perform reasonably well. The stopping rules also exhibit good performances for the top five clustering algorithms, and the pseudo-T2 and pseudo-F stopping rules are superior for noisy data. Based on our simulations for both noisy and unscaled PET neuroimaging data, we recommend the combined use of the pseudo-F or pseudo-T2 stopping rule along with either Ward's or the beta-flexible clustering algorithm.

show abstract

Anatomy Dependent Multi-context Fuzzy Clustering for Separation of Brain Tissues in MR Images

Cited by 4 publications

References 11 publications

Nonrigid registration of brain MRI using NURBS

Nonrigid registration of brain MRI using NURBS

Shape Analysis of Human Brain with Cognitive Disorders

Methods for detecting functional classifications in neuroimaging data

Contact Info

Product

Resources

About