Multimodality cardiovascular image segmentation using a deformable contour model

✍ Scribed by A. Sebbahi; A. Herment; A. de Cesare; E. Mousseaux

• Publisher: Elsevier Science
• Year: 1997
• Tongue: English
• Weight: 1000 KB
• Volume: 21
• Category: Article
• ISSN: 0895-6111
• DOI: 10.1016/s0895-6111(96)00070-5

✦ Synopsis

An automatic segmentation method has been developed for cardiovascular multimodality imaging. A %mke" model based on a curve shaping and au energy-minimlzlug process is used to detect blood-wall interfaces on Cine-CT, MRI and ultrasomm images. De&mat&m of a reduced set of contour points was made according to a dlscretized global, regional and local miulmum energy criterion. A continuous regional optimization process was also integrated into the deformation model, it takes into account a cubic spllue interpolation and adaptive regularity constraints. The constraiuta provided rapid convergence toward a final contour position by successively stopping spline segments.