Probabilistic segmentation of white matter lesions in MR imaging

Anbeek, Petronella; Vincken, Koen L.; Osch, Matthias J.P. van; Bisschops, Robertus H.C.; Grond, Jeroen van der

doi:10.1016/j.neuroimage.2003.10.012

Cited by 302 publications

(288 citation statements)

References 29 publications

Supporting

Mentioning

273

Contrasting

Unclassified

Order By: Relevance

“…Unlike different visual grading systems, it is very easy to compare the WMH findings from this method across different centers. The method relies on the properties of subject's own FLAIR image such as the intensity distribution of WMHs, the connectivity and the diffusivity of the WMHs for the WMH segmentation, which does not rely on any training dataset as do some of the reviewed methods (Kikinis, et al 1992;Swartz, et al 2002;Anbeek, et al 2004b;Anbeek, et al 2004a).…”

Section: Localization Of Wmhsmentioning

confidence: 99%

“…For example, K-Nearest Neighbor (KNN) classification method was used to automatically or semi-automatically label the T2-weighted MR brain images as gray matter, CSF and white matter lesions (Kikinis, et al 1992;Swartz, et al 2002;Anbeek, et al 2004b;Anbeek, et al 2004a). In this method, the classification of an image voxel from a new patient relies on the voxel intensities and spatial information of a previously manually classified training set.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A fully automated method for quantifying and localizing white matter hyperintensities on MR images

Rosano

Butters

et al. 2006

Psychiatry Research: Neuroimaging

173

165

View full text Add to dashboard Cite

White matter hyperintensities (WMH), commonly found on T2-weighted FLAIR brain MR images in the elderly, are associated with a number of neuropsychiatric disorders, including vascular dementia, Alzheimer's disease, and late-life depression. Previous MRI studies of WMHs have primarily relied on the subjective and global (i.e., full-brain) ratings of WMH grade. In the current study we implement and validate an automated method for quantifying and localizing WMHs. We adapt a fuzzy connected algorithm to automate the segmentation of WMHs and use a demons-based image registration to automate the anatomic localization of the WMHs using the Johns Hopkins University White Matter Atlas. The method is validated using the brain MR images acquired from eleven elderly subjects with late-onset late-life depression (LLD) and eight elderly controls. This dataset was chosen because LLD subjects are known to have significant WMH burden. The volumes of WMH identified in our automated method are compared with the accepted gold standard (manual ratings). A significant correlation of the automated method and the manual ratings is found (P<0.0001), thus demonstrating similar WMH quantifications of both methods. As has been shown in other studies e.g. (Taylor, et al. 2003)), we found there was a significantly greater WMH burden in the LLD subjects versus the controls for both the manual and automated method. The effect size was greater for the automated method, suggesting that it is a more specific measure. Additionally, we describe the anatomic localization of the WMHs in LLD subjects as well as in the control subjects, and detect the regions of interest (ROIs) specific for the WMH burden of LLD patients. Given the emergence of large neuroimage databases, techniques, such as that described here, will allow for a better understanding of the relationship between WMHs and neuropsychiatric disorders.

show abstract

Section: Localization Of Wmhsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A fully automated method for quantifying and localizing white matter hyperintensities on MR images

Rosano

Butters

et al. 2006

Psychiatry Research: Neuroimaging

173

165

View full text Add to dashboard Cite

show abstract

“…Editing tools such as "paint brush" and "eraser" are also included in this software package. The identification of Gd-enhanced lesions obtained using our method described above was quantitatively evaluated against those identified by the neuroradiologist based on the similarity measures as described by Anbeek et al (19). …”

Section: Validationmentioning

confidence: 99%

Segmentation of gadolinium‐enhanced lesions on MRI in multiple sclerosis

Datta

Sajja

et al. 2007

Magnetic Resonance Imaging

View full text Add to dashboard Cite

Purpose: To develop and implement a method for identification and quantification of gadolinium (Gd) enhancements with minimal human intervention. Materials and Methods:Dual fast spin echo (FSE), fluid attenuation inversion recovery (FLAIR), and pre-and postcontrast T1-weighted spin echo were acquired on 22 subjects. The enhancements were identified on the postcontrast T1-weighted images based on morphological operations. A single threshold based on the ratio of the difference of postcontrast and precontrast T1 images with that of precontrast T1 images is applied to the reconstructed images to reduce the false classifications. False classification of enhancements arising from enhancing vasculature and structures such as the choroid plexus that lack a blood-brain barrier were reduced by assuming that the true enhancements are always associated with hyperintense lesions on T2-weighted images (T2 lesions). The enhanced lesions were further delineated based on fuzzy connectivity. Results:The segmented Gd enhancements were evaluated quantitatively with manually identified enhancements based on similarity measures. The average similarity index (SI) of 0.76 suggests excellent performance of the proposed methodology. The Bland-Altman plot shows a close agreement between the results obtained manually and those based on the proposed methodology. Conclusion:The proposed algorithm identifies and quantifies Gd enhancements accurately with minimal human intervention.

show abstract

“…With the inclusion of the regularization terms, Eqn. (1) can be written as (3) where N k represents the neighbors of current voxel, and N R is the cardinality of N k . The regularization terms can be adjusted by setting the value of α and β in Eqn.…”

Section: A Multi-spectral Adaptive Fcmmentioning

confidence: 99%

“…The regularization terms can be adjusted by setting the value of α and β in Eqn. (3) to compromise between the sharp segmentation and the suppression of pulse noise 1,37.…”

Section: A Multi-spectral Adaptive Fcmmentioning

confidence: 99%

Volume and Shape in Feature Space on Adaptive FCM in MRI Segmentation

He¹,

Sajja²,

Datta³

et al. 2008

Ann Biomed Eng

View full text Add to dashboard Cite

Intensity non-uniformity (bias field) correction, contextual constraints over spatial intensity distribution and non-spherical cluster's shape in the feature space are incorporated into the fuzzy cmeans (FCM) for segmentation of three-dimensional multi-spectral MR images. The bias field is modeled by a linear combination of smooth polynomial basis functions for fast computation in the clustering iterations. Regularization terms for the neighborhood continuity of either intensity or membership are added into the FCM cost functions. Since the feature space is not isotropic, distance measures, other than the Euclidean distance, are used to account for the shape and volumetric effects of clusters in the feature space. The performance of segmentation is improved by combining the adaptive FCM scheme with the criteria used in Gustafson-Kessel (G-K) and Gath-Geva (G-G) algorithms through the inclusion of the cluster scatter measure. The performance of this integrated approach is quantitatively evaluated on normal MR brain images using the similarity measures. The improvement in the quality of segmentation obtained with our method is also demonstrated by comparing our results with those produced by FSL (FMRIB Software Library), a software package that is commonly used for tissue classification.

show abstract

Probabilistic segmentation of white matter lesions in MR imaging

Cited by 302 publications

References 29 publications

A fully automated method for quantifying and localizing white matter hyperintensities on MR images

A fully automated method for quantifying and localizing white matter hyperintensities on MR images

Segmentation of gadolinium‐enhanced lesions on MRI in multiple sclerosis

Volume and Shape in Feature Space on Adaptive FCM in MRI Segmentation

Contact Info

Product

Resources

About