Automated model-based bias field correction of MR images of the brain

Leemput, Koen Van; Maes, Frederik; Vandermeulen, Dirk; Suetens, Paul

doi:10.1109/42.811268

Cited by 538 publications

(439 citation statements)

References 26 publications

Supporting

Mentioning

430

Contrasting

Unclassified

Order By: Relevance

“…First, an expectation maximization segmentation (EMS) algorithm including correction for intensity inhomogeneity (31, 32) was applied to the T1w image with supplementary T2w image input, to separate skull, scalp, extracranial tissue, cerebellum, and brain stem (at the level of the diencephalon) from the rest of brain volume. The remaining brain volume was voxel-wise classified into fractions of cerebral white matter (WM), cortical gray matter (GM), and sulcal cerebrospinal fluid (CSF).…”

Section: Methodsmentioning

confidence: 99%

Patterns of Reduced Cortical Thickness in Late-Life Depression and Relationship to Psychotherapeutic Response

Mackin

Tosun

Mueller

et al. 2013

The American Journal of Geriatric Psychiatry

View full text Add to dashboard Cite

Objective Cortical atrophy has been associated with late life depression (LLD) and recent findings suggest that reduced right hemisphere cortical thickness is associated with familial risk for major depressive disorder but cortical thickness abnormalities in LLD have not been explored. Further, cortical atrophy has been posited as a contributor to poor antidepressant treatment response in LLD but the impact of cortical thickness on psychotherapy response is unknown. This study was conducted to evaluate patterns of cortical thickness in LLD and in relation to psychotherapy treatment outcomes. Methods Participants included 22 individuals with LLD and 12 age matched comparison subjects. LLD participants completed 12 weeks of psychotherapy and treatment response was defined as a 50% reduction in depressive symptoms. All participants participated in Magnetic Resonance Imaging (MRI) of the brain and cortical mapping of grey matter tissue thickness was calculated. Results LLD individuals demonstrated thinner cortex than controls prominently in the right frontal, parietal, and temporal brain regions. Eleven participants (50%) exhibited positive psychotherapy response after 12 weeks of treatment. Psychotherapy non-responders demonstrated thinner cortex in bilateral posterior cingulate and parahippocampal cortices, left paracentral, precuneus, cuneus, and insular cortices, and the right medial orbito-frontal and lateral occipital cortices relative to treatment responders. Conclusions Our findings suggest more distributed right hemisphere cortical abnormalities in LLD than have been previously reported. Additionally, our findings suggest that reduced bilateral cortical thickness may be an important phenotypic marker of individuals at higher risk for poor response to psychotherapy.

show abstract

Section: Methodsmentioning

confidence: 99%

Patterns of Reduced Cortical Thickness in Late-Life Depression and Relationship to Psychotherapeutic Response

Mackin

Tosun

Mueller

et al. 2013

The American Journal of Geriatric Psychiatry

View full text Add to dashboard Cite

show abstract

“…Van Leemput et al (13,14) extended the concept and developed automatic segmentation of MR images of normal brains by statistical classification, using an atlas prior for initialization and also for geometric constraints. A most recent extension detects brain lesions as outliers (15) and was successfully applied for detection of multiple sclerosis lesions.…”

Section: Introductionmentioning

confidence: 99%

“…This method builds on the previously published work done by Van Leemput, et al (13,14). Additionally, tumor and edema classes are added to the segmentation as was done by Moon et al (16).…”

Section: Introductionmentioning

confidence: 99%

Automatic brain tumor segmentation by subject specific modification of atlas priors1

Prastawa¹,

Bullitt

Moon³

et al. 2003

Academic Radiology

187

143

View full text Add to dashboard Cite

Rationale and Objectives-Manual segmentation of brain tumors from magnetic resonance (MR) images is a challenging and time-consuming task. The authors have developed an automated system for brain tumor segmentation that provides objective, reproducible segmentations that are close to the manual results. Additionally, the method segments white matter, grey matter, cerebrospinal fluid, and edema. The segmentation of pathology and healthy structures is crucial for surgical planning and intervention.Material and Methods-The method performs the segmentation of a registered set of MR images using an Expectation-Maximization scheme. The segmentation is guided by a spatial probabilistic atlas that contains expert prior knowledge about brain structures. This atlas is modified with the subject specific brain tumor prior that is computed based on contrast enhancement. Conclusion-The automated method can be applied to different types of tumors. Although the semi-automated method generates results that have higher level of agreement with the manual raters, the automatic method has the advantage of requiring no user supervision. Results-Five

show abstract

“…The Lagrange multiplier is adopted to include the constraints into the optimization and the augmented objective function becomes (46) Taking the derivative of F with u ik , for p>1, we have (47) and (48) by applying , we have The concrete norm is required to derive the updated cluster prototype. Generally the norm is given by (51) where L is a positive definite matrix, by using (16), for Euclidean norm, we have L=I, the identity matrix.…”

Section: Resultsmentioning

confidence: 99%

“…Therfore, for efficiency, the choice of basis functions for approximating the bias field is important. The smooth basis functions can be splines 43, radial basis functions 15, or polynomials of different orders 47,48. Of all these choices, the polynomial basis functions are the simplest and are used in our studies.…”

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

Automated model-based bias field correction of MR images of the brain

Cited by 538 publications

References 26 publications

Patterns of Reduced Cortical Thickness in Late-Life Depression and Relationship to Psychotherapeutic Response

Patterns of Reduced Cortical Thickness in Late-Life Depression and Relationship to Psychotherapeutic Response

Automatic brain tumor segmentation by subject specific modification of atlas priors1

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

Contact Info

Product

Resources

About