Automated detection of wall and plaque borders in intravascular ultrasound images

摘要: Intravascular ultrasound is a minimally invasive tomographic technique which produces 2-D cross-sectional images depicting vessel wall architecture and plaque morphology. Currently, no reliable automated approaches exist that offer segmentation of blood vascular wall. We have developed method for intravascular to differentiate among plaque, wall, blood. To achieve border detection in noisy images, priori knowledge incorporated the edge process using heuristic graph searching. The was validated from two phantoms were imaged under several pressure conditions. In first image set, our correctly identified borders 69/91 images. second successfully external internal all 36 Lumen areas correlated very well with distending both sets By comparison micrometer determined average thickness, mean absolute error thickness 0.02 +/- 0.01 mm.© (1994) COPYRIGHT SPIE--The International Society Optical Engineering. Downloading abstract permitted personal use only.