【摘要】 目的:提出一种甲状腺结节钙化特征的自动提取方法,从而提高应用钙化特征对甲状腺结节进行鉴别诊断的可重复性和准确性。方法:首先采用基于GVF Snake模型的分割算法和钙化灶的图像识别算法完成甲状腺结节钙化特征的自动提取。然后,在对30例甲状腺结节的回顾性研究中,通过受试者工作特征曲线(receiver operating characteristic curve,ROC)分析评估所提取的钙化指数(calcification index,CI)对甲状腺结节的鉴别诊断价值。结果:提取的钙化指数在良、恶性结节分类中具有一定的准确性(ROC曲线下面积为0.720)。以约登指数最大的分界点作为最佳的诊断界限点,准确性可达80%。结论:该方法能有效地提取甲状腺结节的钙化特征,所提取的钙化指数对甲状腺恶性结节的超声临床诊断具有一定的辅助作用。更多还原

【Abstract】 Objective To propose a kind of thyriod nodule calcification feature automatic extraction method so as to improve the repeatability and accuracy when using calcification feature to differentiate thyroid nodules.Methods The automatic extraction algorithm of the calcification feature of thyroid nodules was fulfilled based on GVF snake model segmentation and image recognition method of calcifications.Then,in a retrospective study of 30 cases of thyroid nodules,the value of extracted calcification index(CI) in the differential diagnosis of thyroid nodules was evaluated by ROC analysis.Results The CI obtained certain accuracy for differentiating between malignant and benign thyroid nodules,with the area under ROC curve being 0.720.For the diagnostic cut-off point whose Youden index was maximum,the accuracy was80%.Conclusion The proposed method can effectively extract the calcification feature of thyroid nodules,and the extracted CI can be an auxiliary tool when using ultrasound image to discriminate malignant thyroid nodules from benign ones.更多还原