Limits...
Lesion identification using unified segmentation-normalisation models and fuzzy clustering.

Seghier ML, Ramlackhansingh A, Crinion J, Leff AP, Price CJ - Neuroimage (2008)

Bottom Line: Second, we adopt a fuzzy clustering procedure to identify outlier voxels in normalised gray and white matter segments.These two advances suppress misclassification of voxels and restrict lesion identification to gray/white matter lesions respectively.From a clinical perspective, our method should help to compute the total volume of lesion or to trace precisely lesion boundaries that might be pertinent for surgical or diagnostic purposes.

View Article: PubMed Central - PubMed

Affiliation: Wellcome Trust Centre for Neuroimaging, Institute of Neurology, UCL, London UK. m.seghier@fil.ion.ucl.ac.uk

ABSTRACT
In this paper, we propose a new automated procedure for lesion identification from single images based on the detection of outlier voxels. We demonstrate the utility of this procedure using artificial and real lesions. The scheme rests on two innovations: First, we augment the generative model used for combined segmentation and normalization of images, with an empirical prior for an atypical tissue class, which can be optimised iteratively. Second, we adopt a fuzzy clustering procedure to identify outlier voxels in normalised gray and white matter segments. These two advances suppress misclassification of voxels and restrict lesion identification to gray/white matter lesions respectively. Our analyses show a high sensitivity for detecting and delineating brain lesions with different sizes, locations, and textures. Our approach has important implications for the generation of lesion overlap maps of a given population and the assessment of lesion-deficit mappings. From a clinical perspective, our method should help to compute the total volume of lesion or to trace precisely lesion boundaries that might be pertinent for surgical or diagnostic purposes.

Show MeSH

Related in: MedlinePlus

Illustration of the boundaries of three real cases with lesions near to the ventricles (A–C) and one real case with a lesion near to the inter-hemispheric fissure (D) on coronal, axial, and sagittal views. Lesion boundaries are displayed at a threshold of U > 0.3.
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC2724121&req=5

fig9: Illustration of the boundaries of three real cases with lesions near to the ventricles (A–C) and one real case with a lesion near to the inter-hemispheric fissure (D) on coronal, axial, and sagittal views. Lesion boundaries are displayed at a threshold of U > 0.3.

Mentions: Patients with extensive lesions are shown in Fig. 8. In these four cases, lesions were identified correctly, including massive tissue loss (Fig. 8A) and extensive tissue damage in different parts of the brain (Fig. 8B–D). More challenging cases were the patients with tissue loss near to the ventricles (i.e., comparable T1 signal in lesions and ventricles). Fig. 9 shows the results in three patients; the boundaries of the lesions appear well distinguished from the ventricles, which confirms that our procedure minimised any contamination from ventricles during lesion identification. Lesion identification was successful in both left (Fig. 9A–B) and right hemispheres (Fig. 9C). The last real case is shown in Fig. 9D. The method was remarkably successful in this case, despite a lesion near the inter-hemispheric fissure (Fig. 9D).


Lesion identification using unified segmentation-normalisation models and fuzzy clustering.

Seghier ML, Ramlackhansingh A, Crinion J, Leff AP, Price CJ - Neuroimage (2008)

Illustration of the boundaries of three real cases with lesions near to the ventricles (A–C) and one real case with a lesion near to the inter-hemispheric fissure (D) on coronal, axial, and sagittal views. Lesion boundaries are displayed at a threshold of U > 0.3.
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC2724121&req=5

fig9: Illustration of the boundaries of three real cases with lesions near to the ventricles (A–C) and one real case with a lesion near to the inter-hemispheric fissure (D) on coronal, axial, and sagittal views. Lesion boundaries are displayed at a threshold of U > 0.3.
Mentions: Patients with extensive lesions are shown in Fig. 8. In these four cases, lesions were identified correctly, including massive tissue loss (Fig. 8A) and extensive tissue damage in different parts of the brain (Fig. 8B–D). More challenging cases were the patients with tissue loss near to the ventricles (i.e., comparable T1 signal in lesions and ventricles). Fig. 9 shows the results in three patients; the boundaries of the lesions appear well distinguished from the ventricles, which confirms that our procedure minimised any contamination from ventricles during lesion identification. Lesion identification was successful in both left (Fig. 9A–B) and right hemispheres (Fig. 9C). The last real case is shown in Fig. 9D. The method was remarkably successful in this case, despite a lesion near the inter-hemispheric fissure (Fig. 9D).

Bottom Line: Second, we adopt a fuzzy clustering procedure to identify outlier voxels in normalised gray and white matter segments.These two advances suppress misclassification of voxels and restrict lesion identification to gray/white matter lesions respectively.From a clinical perspective, our method should help to compute the total volume of lesion or to trace precisely lesion boundaries that might be pertinent for surgical or diagnostic purposes.

View Article: PubMed Central - PubMed

Affiliation: Wellcome Trust Centre for Neuroimaging, Institute of Neurology, UCL, London UK. m.seghier@fil.ion.ucl.ac.uk

ABSTRACT
In this paper, we propose a new automated procedure for lesion identification from single images based on the detection of outlier voxels. We demonstrate the utility of this procedure using artificial and real lesions. The scheme rests on two innovations: First, we augment the generative model used for combined segmentation and normalization of images, with an empirical prior for an atypical tissue class, which can be optimised iteratively. Second, we adopt a fuzzy clustering procedure to identify outlier voxels in normalised gray and white matter segments. These two advances suppress misclassification of voxels and restrict lesion identification to gray/white matter lesions respectively. Our analyses show a high sensitivity for detecting and delineating brain lesions with different sizes, locations, and textures. Our approach has important implications for the generation of lesion overlap maps of a given population and the assessment of lesion-deficit mappings. From a clinical perspective, our method should help to compute the total volume of lesion or to trace precisely lesion boundaries that might be pertinent for surgical or diagnostic purposes.

Show MeSH
Related in: MedlinePlus