摘要
Cardiovascular diseases (CVDs) are the worldwide leading cause of deaths. Based on ultrasound, the primary assessment of CVDs is measurement of the carotid intima-media thickness and brachial endothelial function. In this work we propose improvements to the automatic arterial lumen detection methodology, fundamental for the cited tests, presented in (Calderon et al., 2013); based on graphs and edge detection. We propose a bayesian approach for segmenting the minimum spanning tree of the graph created with intermediate points between edges. Lumen is located applying three criteria on segmented trajectories: length, dark and, our proposal, minimum variance. In 294 sonograms, mean error in brachial near wall detection was 14.6 mu m and standard deviation of 17.0 mu m. For far wall it was 15.1 mu m and standard deviation of 14.5 mu m. Our methodology maintains superior performance to results in recent literature that the original methodology presents; but surpasses it in overall accuracy.
- 出版日期2014-9