A fully automatic and robust brain MRI tissue classification method

Cocosco, Chris A.; Zijdenbos, Alex P.; Evans, Alan C.

doi:10.1016/s1361-8415(03)00037-9

Cited by 300 publications

(190 citation statements)

References 50 publications

Supporting

Mentioning

185

Contrasting

Unclassified

Order By: Relevance

“…In this numerical computation, all the MPI signal simulations were performed on a realistic human brain template (using T1 and PD weighted phantom images) obtained from BrainWeb (Cocosco et al, 2003). Brain segmentation (WM, GM, and CSF) of the template was performed using BrainSuite software (Klauschen et al, 2009).…”

Section: Methodsmentioning

confidence: 99%

Mapping the Brain’s electric fields with Magnetoelectric nanoparticles

et al. 2018

View full text Add to dashboard Cite

Background: Neurodegenerative diseases are devastating diagnoses. Examining local electric fields in response to neural activity in real time could shed light on understanding the origins of these diseases. To date, there has not been found a way to directly map these fields without interfering with the electric circuitry of the brain. This theoretical study is focused on a nanotechnology concept to overcome the challenge of brain electric field mapping in real time. The paper shows that coupling the magnetoelectric effect of multiferroic nanoparticles, known as magnetoelectric nanoparticles (MENs), with the ultra-fast and high-sensitivity imaging capability of the recently emerged magnetic particle imaging (MPI) can enable wirelessly conducted electric-field mapping with specifications to meet the requirements for monitoring neural activity in real time. Methods: The MPI signal is numerically simulated on a realistic human brain template obtained from BrainWeb, while brain segmentation was performed with BrainSuite software. The finite element mesh is generated with Computer Geometry Algorithm Library. The effect of MENs is modeled through local point magnetization changes according to the magnetoelectric effect. Results: It is shown that, unlike traditional magnetic nanoparticles, MENs, when coupled with MPI, provide information containing electric field's spatial and temporal patterns due to local neural activity with signal sensitivities adequate for detection of minute changes at the sub-cellular level corresponding to early stage disease processes. Conclusions: Like no other nanoparticles known to date, MENs coupled with MPI can be used for mapping electric field activity of the brain at the sub-neuronal level in real time. The potential applications span from prevention and treatment of neurodegenerative diseases to paving the way to fundamental understanding and reverse engineering the brain.

show abstract

Section: Methodsmentioning

confidence: 99%

Mapping the Brain’s electric fields with Magnetoelectric nanoparticles

et al. 2018

View full text Add to dashboard Cite

show abstract

“…Using these segmentations, the similarity index (SI) was calculated between groups for identifying the effect of spatial variability on probability map. Cocosco et al (2003) showed experimentally that the false positives in TPM as a training set for the supervised classifier amounted to just about 3% of all selected locations for the highest probability threshold. It means that the spatial locations which have a higher probability represent the core pattern of structural distribution.…”

Section: Evaluation Of Probabilistic Distributionmentioning

confidence: 98%

“…If these morphological differences caused by diseases were not considered in TPM, the accuracy and certainty of specific group studies would be greatly reduced. In addition, TPM is not a critical factor in tissue classification, but simply an initial estimate for that procedure (Ashburner, 2000;Cocosco et al, 2003;Kamber et al, 1995;Leemput et al, 1999a,b). However, the more similar the morphology of the subject is to the average of the population represented by the TPM, the better the utility of the entire classification procedure (Cocosco et al, 2003).…”

Section: Introductionmentioning

confidence: 99%

“…In addition, TPM is not a critical factor in tissue classification, but simply an initial estimate for that procedure (Ashburner, 2000;Cocosco et al, 2003;Kamber et al, 1995;Leemput et al, 1999a,b). However, the more similar the morphology of the subject is to the average of the population represented by the TPM, the better the utility of the entire classification procedure (Cocosco et al, 2003). In fact, voxel-based morphometry (VBM), developed for automated unbiased analysis of structural magnetic resonance imaging (MRI) scans, demonstrates the essential problem with this approach: MRI scans of patients may have a different geometry than those of healthy controls.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Quantitative analysis of group-specific brain tissue probability map for schizophrenic patients

et al. 2005

View full text Add to dashboard Cite

We developed group-specific tissue probability map (TPM) for gray matter (GM), white matter (WM) and cerebrospinal fluid (CSF) on the common spatial coordinates of an averaged brain atlas derived from normal controls (NC) and from schizophrenic patients (SZ). To identify differences in group-specific TPMs, we used quantitative evaluation methods based on differences in probabilistic distribution as a global criterion, and the mean probability and the similarity index (SI) by lobe as regional criteria. The SZ group showed more spatial variation with a lower mean probability than NC subjects. And, for the right temporal and left parietal lobes, the SI between each group was lower than the other lobes. It can be said that there were significant differences in spatial distribution between controls and schizophrenic patients at those areas. In case of female group, although group differences in the volumes of GM and WM were not significant, global difference in the probabilistic distribution of GM was more prominent and the SI was lower and its descent rate was greater in all lobes, compared with the male group. If these morphological differences caused by disease or group-specific features were not considered in TPM, the accuracy and certainty of specific group studies would be greatly reduced. Therefore, suitable TPM is required as a common framework for functional neuroimaging studies and an a priori knowledge of tissue classification. D

show abstract

“…Recent work on this task includes [5,6,13,14,15,16]. These approaches typically formulate the task in terms of probabilistic estimation or, equivalently, energy function minimization.…”

Section: Introductionmentioning

confidence: 99%

Segmentation of Sub-cortical Structures by the Graph-Shifts Algorithm

Corso¹,

Tu²,

Yuille

et al. 2007

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. We propose a novel algorithm called graph-shifts for performing image segmentation and labeling. This algorithm makes use of a dynamic hierarchical representation of the image. This representation allows each iteration of the algorithm to make both small and large changes in the segmentation, similar to PDE and split-and-merge methods, respectively. In particular, at each iteration we are able to rapidly compute and select the optimal change to be performed. We apply graph-shifts to the task of segmenting sub-cortical brain structures. First we formalize this task as energy function minimization where the energy terms are learned from a training set of labeled images. Then we apply the graphshifts algorithm. We show that the labeling results are comparable in quantitative accuracy to other approaches but are obtained considerably faster: by orders of magnitude (roughly one minute). We also quantitatively demonstrate robustness to initialization and avoidance of local minima in which conventional boundary PDE methods fall.

show abstract

A fully automatic and robust brain MRI tissue classification method

Cited by 300 publications

References 50 publications

Mapping the Brain’s electric fields with Magnetoelectric nanoparticles

Mapping the Brain’s electric fields with Magnetoelectric nanoparticles

Quantitative analysis of group-specific brain tissue probability map for schizophrenic patients

Segmentation of Sub-cortical Structures by the Graph-Shifts Algorithm

Contact Info

Product

Resources

About