Automatic 3D segmentation of intravascular ultrasound images using region and contour information.
Med Image Comput Comput Assist Interv
; 8(Pt 1): 319-26, 2005.
Article
em En
| MEDLINE
| ID: mdl-16685861
ABSTRACT
Intravascular ultrasound (IVUS) produces images of arteries that show the lumen in addition to the layered structure of the vessel wall. A new automatic 3D IVUS fast-marching segmentation model is presented. The method is based on a combination of region and contour information, namely the gray level probability density functions (PDFs) of the vessel structures and the image gradient. Accurate results were obtained on in-vivo and simulated data with average point to point distances between detected vessel wall boundaries and validation contours below 0.105 mm. Moreover, Hausdorff distances (that represent the worst point to point variations) resulted in values below 0.344 mm, which demonstrate the potential of combining region and contour information in a fast-marching scheme for 3D automatic IVUS image processing.
Buscar no Google
Coleções:
01-internacional
Base de dados:
MEDLINE
Assunto principal:
Vasos Sanguíneos
/
Inteligência Artificial
/
Interpretação de Imagem Assistida por Computador
/
Aumento da Imagem
/
Ultrassonografia de Intervenção
/
Ecocardiografia Tridimensional
/
Imageamento Tridimensional
Tipo de estudo:
Diagnostic_studies
/
Evaluation_studies
/
Prognostic_studies
Limite:
Humans
Idioma:
En
Revista:
Med Image Comput Comput Assist Interv
Assunto da revista:
DIAGNOSTICO POR IMAGEM
/
INFORMATICA MEDICA
Ano de publicação:
2005
Tipo de documento:
Article
País de afiliação:
Canadá