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

BrainWeb data with 9% noise level (a) T1, (b) T2,  (c) Pd.
© Copyright Policy - open-access
Related In: Results  -  Collection


getmorefigures.php?uid=PMC2742654&req=5

fig4: BrainWeb data with 9% noise level (a) T1, (b) T2, (c) Pd.

Mentions: Figure 4 shows slice 90 with different levels of noise. Visual inspection suggests that images with 9% noise present a challenge even for manual segmentation. We are aware that the noise level in real data is almost always less than 9%. We provide the 9% segmentation result to demonstrate the robustness of the CGMM-CE method.


Multiple sclerosis lesion detection using constrained GMM and curve evolution.

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

BrainWeb data with 9% noise level (a) T1, (b) T2,  (c) Pd.
© Copyright Policy - open-access
Related In: Results  -  Collection

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

fig4: BrainWeb data with 9% noise level (a) T1, (b) T2, (c) Pd.
Mentions: Figure 4 shows slice 90 with different levels of noise. Visual inspection suggests that images with 9% noise present a challenge even for manual segmentation. We are aware that the noise level in real data is almost always less than 9%. We provide the 9% segmentation result to demonstrate the robustness of the CGMM-CE method.

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