Limits...
Brain MRI segmentation with multiphase minimal partitioning: a comparative study.

Angelini ED, Song T, Mensh BD, Laine AF - Int J Biomed Imaging (2007)

Bottom Line: Postprocessing corrections with morphological operators were applied to refine the details of the global segmentation method.Quantitative evaluation of segmentation accuracy was performed with comparison to manual segmentation computing true positive and false positive volume fractions.A statistical comparison of the segmentation methods was performed through a Wilcoxon analysis of these error rates and results showed very high quality and stability of the multiphase three-dimensional level set method.

View Article: PubMed Central - PubMed

Affiliation: Ecole Nationale Supérieure des Télécommunications, Groupe des Ecoles des Télécommunications, CNRS UMR 5141, 75013 Paris, France.

ABSTRACT
This paper presents the implementation and quantitative evaluation of a multiphase three-dimensional deformable model in a level set framework for automated segmentation of brain MRIs. The segmentation algorithm performs an optimal partitioning of three-dimensional data based on homogeneity measures that naturally evolves to the extraction of different tissue types in the brain. Random seed initialization was used to minimize the sensitivity of the method to initial conditions while avoiding the need for a priori information. This random initialization ensures robustness of the method with respect to the initialization and the minimization set up. Postprocessing corrections with morphological operators were applied to refine the details of the global segmentation method. A clinical study was performed on a database of 10 adult brain MRI volumes to compare the level set segmentation to three other methods: "idealized" intensity thresholding, fuzzy connectedness, and an expectation maximization classification using hidden Markov random fields. Quantitative evaluation of segmentation accuracy was performed with comparison to manual segmentation computing true positive and false positive volume fractions. A statistical comparison of the segmentation methods was performed through a Wilcoxon analysis of these error rates and results showed very high quality and stability of the multiphase three-dimensional level set method.

No MeSH data available.


CSF segmentation. Three-dimensional rendering of theventricles extracted with: (a) IT, (b) M3DLS, (c) FC, (d) HMRF-EM,and (e) manual labeling.
© Copyright Policy - open-access
Related In: Results  -  Collection


getmorefigures.php?uid=PMC2211521&req=5

Figure 12: CSF segmentation. Three-dimensional rendering of theventricles extracted with: (a) IT, (b) M3DLS, (c) FC, (d) HMRF-EM,and (e) manual labeling.

Mentions: As observed in the error plots and illustrated inFigure 11, all methods except HMRF-EM performedsignificantly poorly on CSF than on WM and GM, corresponding tounder segmentation of the ventricles, whose pixels were assignedto white matter. On the other hand, the HMRF-EM segmentation wasvery sensitive but provided poor specificity. Very low resolutionat the ventricle borders explains in part this result. Inaddition, manual labeling of the MRI data for the ventricle canalso bear some error as localizations of its borders are difficulteven for an expert performing manual tracing. We illustrated inFigure 12 CSF segmentation with the different methodswith a three-dimensional rendering of the two lateral ventriclesand a section of the third ventricle.


Brain MRI segmentation with multiphase minimal partitioning: a comparative study.

Angelini ED, Song T, Mensh BD, Laine AF - Int J Biomed Imaging (2007)

CSF segmentation. Three-dimensional rendering of theventricles extracted with: (a) IT, (b) M3DLS, (c) FC, (d) HMRF-EM,and (e) manual labeling.
© Copyright Policy - open-access
Related In: Results  -  Collection

Show All Figures
getmorefigures.php?uid=PMC2211521&req=5

Figure 12: CSF segmentation. Three-dimensional rendering of theventricles extracted with: (a) IT, (b) M3DLS, (c) FC, (d) HMRF-EM,and (e) manual labeling.
Mentions: As observed in the error plots and illustrated inFigure 11, all methods except HMRF-EM performedsignificantly poorly on CSF than on WM and GM, corresponding tounder segmentation of the ventricles, whose pixels were assignedto white matter. On the other hand, the HMRF-EM segmentation wasvery sensitive but provided poor specificity. Very low resolutionat the ventricle borders explains in part this result. Inaddition, manual labeling of the MRI data for the ventricle canalso bear some error as localizations of its borders are difficulteven for an expert performing manual tracing. We illustrated inFigure 12 CSF segmentation with the different methodswith a three-dimensional rendering of the two lateral ventriclesand a section of the third ventricle.

Bottom Line: Postprocessing corrections with morphological operators were applied to refine the details of the global segmentation method.Quantitative evaluation of segmentation accuracy was performed with comparison to manual segmentation computing true positive and false positive volume fractions.A statistical comparison of the segmentation methods was performed through a Wilcoxon analysis of these error rates and results showed very high quality and stability of the multiphase three-dimensional level set method.

View Article: PubMed Central - PubMed

Affiliation: Ecole Nationale Supérieure des Télécommunications, Groupe des Ecoles des Télécommunications, CNRS UMR 5141, 75013 Paris, France.

ABSTRACT
This paper presents the implementation and quantitative evaluation of a multiphase three-dimensional deformable model in a level set framework for automated segmentation of brain MRIs. The segmentation algorithm performs an optimal partitioning of three-dimensional data based on homogeneity measures that naturally evolves to the extraction of different tissue types in the brain. Random seed initialization was used to minimize the sensitivity of the method to initial conditions while avoiding the need for a priori information. This random initialization ensures robustness of the method with respect to the initialization and the minimization set up. Postprocessing corrections with morphological operators were applied to refine the details of the global segmentation method. A clinical study was performed on a database of 10 adult brain MRI volumes to compare the level set segmentation to three other methods: "idealized" intensity thresholding, fuzzy connectedness, and an expectation maximization classification using hidden Markov random fields. Quantitative evaluation of segmentation accuracy was performed with comparison to manual segmentation computing true positive and false positive volume fractions. A statistical comparison of the segmentation methods was performed through a Wilcoxon analysis of these error rates and results showed very high quality and stability of the multiphase three-dimensional level set method.

No MeSH data available.