基于三维CT影像的计算机辅助肺结节检测原型系统的临床应用  

The clinical application of computer aided pulmonary nodule detecting system on account of three-dimentional CT

作　　者：阳世雄[1] 曾建业[1] 金人超[2] 黄启良[1] 许向阳[2] 韦涌初[1] 黄思光[1] 卢苇[1] 王斌强[1] 

机构地区：[1]广西医科大学第三附属医院心胸外科,广西南宁530031 [2]华中科技大学计算机科学与技术学院

出　　处：《中华临床医师杂志（电子版）》2012年第4期40-42,共3页Chinese Journal of Clinicians(Electronic Edition)

基　　金：广西科技开发项目(桂科攻0816004-18)

摘　　要：目的探讨基于三维CT影像的计算机辅助肺结节检测原型系统在临床应用的效果。方法分析2009年6月至2011年6月68例肺结节病例,分别采用单纯螺旋CT检查和应用基于三维CT影像的计算机辅助肺结节检测原型系统检测,以术后病理学检查结果为"金标准",计算两种检查方法判断肺结节良恶性的准确度。结果单纯CT检查判断肺结节良恶性的准确度为75%,Kappa值0.504,术后病理检查结果一致性一般;基于三维CT影像的计算机辅助肺结节检测原型系统检测,判断肺结节良恶性的准确度为91.6%,Kappa值0.805,术后病理检查结果一致性较好。结论基于三维CT影像的计算机辅助肺结节检测原型系统具有较好的临床应用价值,可以用于辅助医师进行CT图像中肺癌等肺部疾病的早期诊断。Objective To investigate the clinical application effect of computer aided pulmonary nodule（PN）detecting system on account of three-dimentional CT（3DCT）imaging.Methods 68 cases with PN were included in this study in our hospital from Jun.2009 to Jun.2011.All cases underwent simple spiral CT scan and computer aided PN detecting system on account of 3DCT scan.Postoperative pathological result was considered as the ＂gold standard＂,the two checking methods were calculated to determine the diagnostic accuracy of benign and malignant PN.Results The accuracy of distinguishing benign from maligant PN through simple spiral CT scan was 0.75,the kappa value was 0.504,pathological result after operation had common correspondence,the accuracy of distinguishing benign from maligant PN through computer aided PN detecting system on account of 3DCT imaging was 0.916,the kappa value was 0.805,pathological result after operation had better correspondence.Conclusions Computer aided PN detecting system on account of 3DCT imaging has better clinical application value,and can help doctor carry out early diagnosis of lung disease（such cancer etc.）through CT image.

关 键 词：硬币病变 肺 诊断 计算机辅助 成像 三维 

分 类 号：R816.4[医药卫生—放射医学]