Limits...
Multiple sclerosis lesion detection using constrained GMM and curve evolution.

Freifeld O, Greenspan H, Goldberger J - Int J Biomed Imaging (2009)

Bottom Line: The proposed CGMM-CE algorithm is used to segment 3D MRI brain images with an arbitrary number of channels.The CGMM-CE algorithm is automated and does not require an atlas for initialization or parameter learning.Experimental results on both standard brain MRI simulation data and real data indicate that the proposed method outperforms previously suggested approaches, especially for highly noisy data.

View Article: PubMed Central - PubMed

Affiliation: Department of Biomedical Engineering, Tel-Aviv University, Tel Aviv 69978, Israel. orenf@eng.tau.ac.il

ABSTRACT
This paper focuses on the detection and segmentation of Multiple Sclerosis (MS) lesions in magnetic resonance (MRI) brain images. To capture the complex tissue spatial layout, a probabilistic model termed Constrained Gaussian Mixture Model (CGMM) is proposed based on a mixture of multiple spatially oriented Gaussians per tissue. The intensity of a tissue is considered a global parameter and is constrained, by a parameter-tying scheme, to be the same value for the entire set of Gaussians that are related to the same tissue. MS lesions are identified as outlier Gaussian components and are grouped to form a new class in addition to the healthy tissue classes. A probability-based curve evolution technique is used to refine the delineation of lesion boundaries. The proposed CGMM-CE algorithm is used to segment 3D MRI brain images with an arbitrary number of channels. The CGMM-CE algorithm is automated and does not require an atlas for initialization or parameter learning. Experimental results on both standard brain MRI simulation data and real data indicate that the proposed method outperforms previously suggested approaches, especially for highly noisy data.

No MeSH data available.


Related in: MedlinePlus

Illustration of the GMM representation. (a) Segmenting the brain image into three main tissues. (b) Adding a fourth class for MS lesions; Color Legend: Blue-CSF, Green-GM; Yellow-WM; Red-MS.
© Copyright Policy - open-access
Related In: Results  -  Collection


getmorefigures.php?uid=PMC2742654&req=5

fig1: Illustration of the GMM representation. (a) Segmenting the brain image into three main tissues. (b) Adding a fourth class for MS lesions; Color Legend: Blue-CSF, Green-GM; Yellow-WM; Red-MS.

Mentions: The main advantage of the CGMM framework is the ability to combine, in a tractable way, a local description of the spatial layout of a tissue with a global description of the tissue's intensity. The multiGaussian spatial model makes our approach much more robust to noise than intensity-based methods. Note that no prior atlas information is used in the modeling process. An illustration of the CGMM model applied to the three tissues (CSF, GM, and WM) is shown in Figure 1(a). In case of MS lesion segmentation we consider the lesion matter in the CGMM modeling as a fourth tissue in addition to the three healthy tissues (Figure 1(b)).


Multiple sclerosis lesion detection using constrained GMM and curve evolution.

Freifeld O, Greenspan H, Goldberger J - Int J Biomed Imaging (2009)

Illustration of the GMM representation. (a) Segmenting the brain image into three main tissues. (b) Adding a fourth class for MS lesions; Color Legend: Blue-CSF, Green-GM; Yellow-WM; Red-MS.
© Copyright Policy - open-access
Related In: Results  -  Collection

Show All Figures
getmorefigures.php?uid=PMC2742654&req=5

fig1: Illustration of the GMM representation. (a) Segmenting the brain image into three main tissues. (b) Adding a fourth class for MS lesions; Color Legend: Blue-CSF, Green-GM; Yellow-WM; Red-MS.
Mentions: The main advantage of the CGMM framework is the ability to combine, in a tractable way, a local description of the spatial layout of a tissue with a global description of the tissue's intensity. The multiGaussian spatial model makes our approach much more robust to noise than intensity-based methods. Note that no prior atlas information is used in the modeling process. An illustration of the CGMM model applied to the three tissues (CSF, GM, and WM) is shown in Figure 1(a). In case of MS lesion segmentation we consider the lesion matter in the CGMM modeling as a fourth tissue in addition to the three healthy tissues (Figure 1(b)).

Bottom Line: The proposed CGMM-CE algorithm is used to segment 3D MRI brain images with an arbitrary number of channels.The CGMM-CE algorithm is automated and does not require an atlas for initialization or parameter learning.Experimental results on both standard brain MRI simulation data and real data indicate that the proposed method outperforms previously suggested approaches, especially for highly noisy data.

View Article: PubMed Central - PubMed

Affiliation: Department of Biomedical Engineering, Tel-Aviv University, Tel Aviv 69978, Israel. orenf@eng.tau.ac.il

ABSTRACT
This paper focuses on the detection and segmentation of Multiple Sclerosis (MS) lesions in magnetic resonance (MRI) brain images. To capture the complex tissue spatial layout, a probabilistic model termed Constrained Gaussian Mixture Model (CGMM) is proposed based on a mixture of multiple spatially oriented Gaussians per tissue. The intensity of a tissue is considered a global parameter and is constrained, by a parameter-tying scheme, to be the same value for the entire set of Gaussians that are related to the same tissue. MS lesions are identified as outlier Gaussian components and are grouped to form a new class in addition to the healthy tissue classes. A probability-based curve evolution technique is used to refine the delineation of lesion boundaries. The proposed CGMM-CE algorithm is used to segment 3D MRI brain images with an arbitrary number of channels. The CGMM-CE algorithm is automated and does not require an atlas for initialization or parameter learning. Experimental results on both standard brain MRI simulation data and real data indicate that the proposed method outperforms previously suggested approaches, especially for highly noisy data.

No MeSH data available.


Related in: MedlinePlus