Unbiased segmentation of diffusion-weighted magnetic resonance images of the brain using iterative clustering

Hadjiprocopis, Andreas; Rashid, Waqar; Tofts, PS

doi:10.1016/j.mri.2005.07.010

Cited by 22 publications

(21 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…By using an automated segmentation routine [19], registration [18] and BPV as a covariate, potential sources of methodological error in the analysis have been partially addressed. However, the results show the possible limitations that exist using DTI as a quantitative parameter to monitor the evolution of pathogenesis in-vivo in MS.…”

Section: ■ Methodological Considerationsmentioning

confidence: 99%

“…Extracerebral tissue was removed using BET (Brain Extraction Tool) [32] part of the FSL-FMRIB's Software Library; www.fmrib.ox.ac.uk. In addition the outer voxel of cerebral tissue was eroded as part of the segmentation algorithm in order to minimise potential partial volume error [19]. The b = 0 and inversion recovery images were registered using a normalised mutual information algorithm [18].…”

Section: ■ Mri Protocolmentioning

confidence: 99%

“…The b = 0 and inversion recovery images were registered using a normalised mutual information algorithm [18]. Finally, the registered images were segmented using an automated segmentation algorithm which has been described previously [19].…”

Section: ■ Mri Protocolmentioning

confidence: 99%

“…A further registration algorithm between structural and diffusion parameter images has been added to improve the accuracy of the methodology [18,19].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Longitudinal evaluation of clinically early relapsing-remitting multiple sclerosis with diffusion tensor imaging

et al. 2008

Self Cite

View full text Add to dashboard Cite

Diffusion tensor imaging (DTI) parameters such as mean diffusivity (MD) and fractional anisotropy (FA) assess aspects of structural integrity within tissue. In relapsing-remitting (RR) multiple sclerosis (MS), abnormalities in normal appearing brain tissue (NABT) have been shown cross-sectionally. The evolution of these abnormalities over time is unclear. We present a longitudinal study investigating early RR MS subjects. The aims were to determine DTI changes over two years and assess the potential of DTI as a longitudinal quantitative marker at this stage of MS. Fifteen controls and 28 patients with RR MS (median disease duration 1.9 years; median EDSS 1.5) had DTI yearly for two years. NABT and whole brain tissue (NABT plus lesions) FA and MD histograms analysed. At baseline, differences in FA were noted between patients and controls (mean [p = 0.042] and peak height [p = 0.008]), while at two years differences in MD were observed (mean [p = 0.008] and peak location [p = 0.024]). However there were no significant DTI differences in longitudinal rates of change between patients and cohorts. In conclusion, although subtle NABT abnormalities were detected in early RR MS, the absence of longitudinal change suggests a limited role for global DTI assessment of NABT in following the early disease course.

show abstract

Section: ■ Methodological Considerationsmentioning

confidence: 99%

Section: ■ Mri Protocolmentioning

confidence: 99%

Section: ■ Mri Protocolmentioning

confidence: 99%

“…A further registration algorithm between structural and diffusion parameter images has been added to improve the accuracy of the methodology [18,19].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Longitudinal evaluation of clinically early relapsing-remitting multiple sclerosis with diffusion tensor imaging

et al. 2008

Self Cite

View full text Add to dashboard Cite

show abstract

“…An important step in image analysis is to associate with each image pixel a particular tissue class based on the pixel's attributes which is called tissue segmentation [1]. Exact brain tumor segmentation plays a significant role in the treatment of malignant tumors [2].…”

Section: Introductionmentioning

confidence: 99%

Automatic Brain Tumor Segmentation Using Tissue Diffisivity Characteristics

Yazdan-Shahmorad

Jahanian

Patel

et al. 2007

2007 4th IEEE International Symposium on Biomedical Imaging: From Nano to Macro

View full text Add to dashboard Cite

Water diffusion measurements have been shown to be sensitive to tissue cellular size, extra cellular volume, and membrane permeability. Therefore, diffusion tensor imaging (DTI) by MRI can be used to characterize highly cellular regions of tumors versus acellular regions, distinguishing cystic regions from solid regions. An automatic segmentation method is proposed in this paper based on a multi-phase clustering algorithm to segment the brain tumors in a feature space extracted from DTI images. The algorithm is applied on images of a total of 20 patients with 4 different types of tumors. The tumor region segmentation was 92% accurate based on the segmentation results using anatomical images and 100% accurate based on biopsy results. In general, the segmentation results obtained by the proposed method revealed a strong agreement with the biopsy results and anatomical images, providing support for the accuracy and robustness of the proposed feature space and the segmentation procedure.

show abstract

Diffusion tensor‐based regional gray matter tissue segmentation using the international consortium for brain mapping atlases

Hasan¹,

Frye

2010

Human Brain Mapping

View full text Add to dashboard Cite

In this communication, we extended a previously described and validated diffusion tensor imaging (DTI) method for segmenting whole brain cerebrospinal fluid (CSF) and gray and white matter (WM) tissue to provide regional volume and DTI metrics of WM tract and cortical and subcortical gray matter. This DTI-based regional segmentation was implemented using the statistical parametric mapping (SPM) toolbox and used the international consortium for brain mapping atlases and Montreal Neurological Institute brain templates. We used our DTI-based segmentation approach to calculate the left putamen volume in a cohort of 136 healthy right-handed males and females aged 15.8-62.8 years. We validated our approach by demonstrating its sensitivity to age-related changes of the putamen. Indeed, our method found that the putamen volume decreased with age (r = -0.30; P < 0.001) while the corresponding fractional anisotropy (FA) increased with advancing age (r = 0.5; P < 0.00001). It is then demonstrated, on a subset of our cohort (n = 31), that the putamen volume obtained by our method correlated with measurements obtained from FreeSurfer (r = 0.396, P < 0.05). Our novel approach increases the information obtained with a DTI examination by providing routine volumetry measure, thereby eliminating separate scans to obtain volumetry data. In addition, the labeled volumes obtained with our method have the potential to increase the accuracy of fiber tracking. In the future, this new approach can be automated to analyze large data sets to help discover noninvasive neuroimaging markers for clinical trials and brain-function studies in both health and disease.

show abstract

Unbiased segmentation of diffusion-weighted magnetic resonance images of the brain using iterative clustering

Cited by 22 publications

References 19 publications

Longitudinal evaluation of clinically early relapsing-remitting multiple sclerosis with diffusion tensor imaging

Longitudinal evaluation of clinically early relapsing-remitting multiple sclerosis with diffusion tensor imaging

Automatic Brain Tumor Segmentation Using Tissue Diffisivity Characteristics

Diffusion tensor‐based regional gray matter tissue segmentation using the international consortium for brain mapping atlases

Contact Info

Product

Resources

About