Li Xiaokun, Wee William G
TASC, Inc, 475 School Street SW, Washington, DC, 20024, USA,
J Digit Imaging. 2014 Feb;27(1):120-32. doi: 10.1007/s10278-013-9639-y.
Since blood vessel detection and characteristic measurement for ocular retinal images is a fundamental problem in computer-aided medical diagnosis, automated algorithms/systems for vessel detection and measurement are always demanded. To support computer-aided diagnosis, an integrated approach/solution for vessel detection and diameter measurement is presented and validated. In the proposed approach, a Dempster-Shafer (D-S)-based edge detector is developed to obtain initial vessel edge information and an accurate vascular map for a retinal image. Then, the appropriate path and the centerline of a vessel of interest are identified automatically through graph search. Once the vessel path has been identified, the diameter of the vessel will be measured accordingly by the algorithm in real time. To achieve more accurate edge detection and diameter measurement, mixed Gaussian-matched filters are designed to refine the initial detection and measures. Other important medical indices of retinal vessels can also be calculated accordingly based on detection and measurement results. The efficiency of the proposed algorithm was validated by the retinal images obtained from different public databases. Experimental results show that the vessel detection rate of the algorithm is 100 % for large vessels and 89.9 % for small vessels, and the error rate on vessel diameter measurement is less than 5 %, which are all well within the acceptable range of deviation among the human graders.
由于眼部视网膜图像的血管检测和特征测量是计算机辅助医学诊断中的一个基本问题，因此一直需要用于血管检测和测量的自动化算法/系统。为了支持计算机辅助诊断，本文提出并验证了一种用于血管检测和直径测量的集成方法/解决方案。在所提出的方法中，开发了一种基于Dempster-Shafer（D-S）的边缘检测器，以获取视网膜图像的初始血管边缘信息和准确的血管图。然后，通过图搜索自动识别感兴趣血管的合适路径和中心线。一旦确定了血管路径，算法将实时测量血管直径。为了实现更准确的边缘检测和直径测量，设计了混合高斯匹配滤波器来优化初始检测和测量。还可以根据检测和测量结果相应地计算视网膜血管的其他重要医学指标。通过从不同公共数据库获取的视网膜图像验证了所提算法的效率。实验结果表明，该算法对大血管的血管检测率为100%，对小血管的检测率为89.9%，血管直径测量的误差率小于5%，均在人类分级者可接受的偏差范围内。
