Santos Filho E, Saijo Y, Tanaka A, Yoshizawa M
Department of Medical Engineering and Cardiology, Institute of Development, Aging, and Cancer, Tohoku University, Sendai, Japan.
Ultrasound Med Biol. 2008 Jan;34(1):160-5. doi: 10.1016/j.ultrasmedbio.2007.06.025. Epub 2007 Aug 29.
An innovative application of automatic thresholding is used for the detection of calcification regions in intravascular ultrasound images. A priori knowledge of the acoustic shadow that usually accompanies calcification regions is used to discriminate these from other bright regions in the image. A method for the calculation of the angle of calcification has also been developed. The proposed algorithms are applied to in-vivo images obtained from left anterior descending coronary arteries during percutaneous transluminal coronary angioplasty (n = 14). The resulting specificity is 72% and the sensitivity 84%. The receiver operating characteristic curve, the area under the curve being equal to 0.91, is plotted to evaluate the algorithm performance.
自动阈值处理的一种创新应用被用于检测血管内超声图像中的钙化区域。利用通常伴随钙化区域的声学阴影的先验知识，将这些钙化区域与图像中的其他明亮区域区分开来。还开发了一种计算钙化角度的方法。所提出的算法应用于经皮冠状动脉腔内血管成形术期间从左前降支冠状动脉获得的体内图像（n = 14）。得到的特异性为72%，敏感性为84%。绘制了受试者工作特征曲线，曲线下面积等于0.91，以评估算法性能。
