基于截面投影Otsu法的颈动脉内中膜超声图像分割

摘要

颈动脉内中膜厚度与多种心脑血管疾病密切相关，是预测该类心脑血管疾病的重要指标。对此，本文将基于截面投影Otsu法引入颈动脉内中膜分割，提出了一种高质量的颈动脉内中膜分割方法，该方法首先将截面投影Otsu法扩展到多阈值情况，以便处理颈动脉图像的多目标性；然后，采用微粒群算法搜索最优阈值，以提高算法效率。临床数据测试结果表明：该方法在抗噪性和时效性方面具有明显优势，可为心血管疾病预防、诊断、治疗及计算机辅助诊断提供重要参考。%Carotid artery intima-media thickness is closely related to the cardiovascular-cerebrovascular diseases.It is an important index for the prediction of cardiovascular and cerebrovascular diseases.In this regrad,the sectional projection-based Otsu method is introduced into the carotid artery intima-media segmentation,and the high quality carotid artery intima-media segmentation method is proposed.In this method,the Otsu method is extended to multi threshold to deal with the multi-objective of the image of the carotid artery.Then,the particle swarm algorithm is used to search for the optimal threshold to improve the efficiency of the algorithm.The test results of the clinical data show that the method has obvious advantages in anti-noise and aging, and it can provide important reference for prevention,diagnosis,treatment and computer aided diagnosis of cardiovascular diseases.