Fully automated media and lumen boundary detection in intravascular ultrasound images

Intravascular ultrasound (IVUS) imaging is a valuable method of quantifying the degree and severity of coronary atherosclerosis. Development of an automated method of this quantification has been hampered by the difficulty in automating the extraction of the lumen-intima interface and the media-adventitia interface. The authors describe how these interfaces can be automatically extracted using a combination of image processing techniques with the use of adaptive thresholding and a fuzzy logic decision process.