SEGMENTATION OF INTRAVASCULAR ULTRASOUND IMAGES - A KNOWLEDGE-BASED APPROACH

Intravascular ultrasound imaging of coronary arteries provides importa nt information about coronary lumen, wall, and plaque characteristics. Quantitative studies of coronary atherosclerosis using intravascular ultrasound and manual identification of wall and plaque borders are li mited by the need for observers with substantial experience and the te dious nature of manual border detection. We have developed a method fo r segmentation of intravascular ultrasound images that identifies the internal and external elastic laminae and the plaque-lumen interface. The border detection algorithm was evaluated in a set of 38 intravascu lar ultrasound images acquired from fresh cadaveric hearts using a 30 MHz imaging catheter. To assess the performance of our border detectio n method we compared five quantitative measures of arterial anatomy de rived from computer-detected borders with measures derived from border s manually defined by expert observers. Computer-detected and observer -defined lumen areas correlated very well (r = 0.96, y = 1.02x+ 0.52), as did plaque areas (r = 0.95, y = 1.07x- 0.48), and percent area ste nosis (r = 0.93, y = 0.99x- 1.34.) Computer-derived segmental plaque t hickness measurements were highly accurate. Our knowledge-based intrav ascular ultrasound segmentation method shows substantial promise for t he quantitative analysis of in vivo intravascular ultrasound image dat a.