Meeting Banner
Abstract #4529

Computer-Aided Diagnosis Scheme for Detecting Significant Stenosis on Whole Heart Coronary MR Angiography Based on Signal Intensity and Luminal Diameter

Ryohei Nakayama1, Masaki Ishida1, Nobuo Nakako1, Motonori Nagata1, Kakuya Kitagawa1, Hajime Sakuma1

1Department of Radiology, Mie University School of Medicine, Tsu, Mie, Japan

A computer-aided diagnosis (CAD) was developed for detecting significant stenosis on whole heart coronary MRA. Coronary arterial segments were automatically classified according to AHA model. At each voxel on the centerline, a classifier based on the Mahalanobis distance for the changes of signal intensity and luminal diameter was employed for distinguishing between arteries with and without stenosis. In 34 patients with suspected coronary artery disease, the sensitivity and specificity of the CAD were 80% and 81%. The CAD scheme developed in this study showed high diagnostic performance and will have a substantial impact on interpretation of coronary MRA.

Abstract PDF

Keywords

according achieved adequately aided alterations analyzed analyzing angiography apparent arteries artery assessed association audience automated bifurcations breathing cardiac centerline channel circle classified classifier classifiers clinicians coils computer coronary correctly curvatures defined dependent detecting detection develop diagnosis diameter difficult disease distance distinguishing employed enhanced evaluated example expand finally free growing heart identification identified impact indicating intensity interpretation invasive japan lengths major medicine model noise observer orifices original overall patients position radiology radius reduced reduction relationship remains respectively retrospectively scheme school scientists segmentation segmented sensitivities sensitivity specificity subjects substantial suspected systems target territories tracing transformation tree underwent vessel vessels whole