Evaluation of three-dimensional segmentation algorithms for the identification of luminal and medial-adventitial borders in intravascular ultrasound images

Intravascular ultrasound (IVUS) provides direct depiction of coronary arter y anatomy, including plaque and vessel area, which is important in quantita tive studies on the progression or regression of coronary artery disease. T raditionally, these studies have relied on manual evaluation, which is labo rious, time consuming, and subject to large interobserver and intraobserver variability. A new technique, called active surface segmentation, alleviat es these limitations and makes strides toward routine analyses. However, fo r three-dimensional (3-D) plaque assessment or 3-D reconstruction to become a clinical reality, methods must be developed which can analyze many image s quickly, Presented is a comparison between two active surface techniques for three-dimensional segmentation of luminal and medial-adventitial border s, The force-acceleration technique and the neighborhood-search technique a ccurately detected both borders in vivo (r(2) = 0.95 and 0.99, Williams' in dex = 0.67 and 0.65, and r(2) = 0.95 and 0.99, WI = 0.67 and 0.70, respecti vely). However, the neighborhood-search technique was significantly faster and required less computation. Volume calculations for both techniques (r(2 ) = 0.99 and r(2) = 0.99) also agreed with a known-volume phantom. Active s urface segmentation allows 3-D assessment of coronary morphology and furthe r developments with this technology will provide clinical analysis tools.