【摘要】 目的 探讨Bayes分析在孤立性肺结节(SPN)CT定性诊断中的价值。方法 利用Bayes分析从352例SPN训练集中得到恶性SPN的验前比及各临床和CT表现的似然比,求出各SPN的恶性概率。并前瞻性的在132例SPN测试集中予以检验。结果 根据似然比的高低得出,较能提示恶性SPN的特征为空泡征、短毛刺、深分叶等,较能提示良性SPN的特征为良性钙化模式、强化值<20 HU、“多边形”轮廓等;Bayes分析诊断测试集SPN的敏感度、特异度、符合率、阳性预测值及阴性预测值分别为88.5%、85.9%、87.1%、84.4%、89.7%,其诊断符合率与高年资甲、乙医生常规阅片比较无统计学差异(P均>0.05),但高于低年资丙、丁医生(P均<0.05)。对于非转移瘤SPN的诊断,Bayes分析的ROC曲线下面积(A_z)为0.957,大于高年资医生组(A_z=0.886,P=0.003)和低年资医生组(A_z=0.845,P=0.000)。结论 SPN相关的各临床和CT表现的似然比可以用来指导日常阅片;Bayes分析是一个有效的诊断辅助工具,可以提高医生鉴别SPN良恶性的能力,尤其对低年资医生的帮助较大。更多还原

【Abstract】 Objective To explore the value of Bayesian analysis in distinguishing between benign and malignant solitary pulmonary nodules(SPNs) with CT.Methods Utilizing Bayesian analysis,the prior odds of malignant SPNs and the likelihood ratios of clinical and CT findings were derived from the training set(352 SPNs),these derived values were then used to calculate the probability of malignancy in each SPN.SPNs with≥50% calculated probability were judged as malignancy and those with <50% calculated probability were judged as benign.The Bayesian analysis was also tested prospectively for its diagnostic validation on the test set(132 SPNs).Results Deduced from the hierarchy of likelihood ratios,the more significant features for malignant SPNs were vacuole sign,short spiculation,deep lobulation etc.,and those for benign SPNs were a benign pattern of calcification,net nodule enhancement <20 HU,polygonal contour,and so on;On the test set,the sensitivity,specificity,accuracy,positive predictive value,negative predictive value of the Bayesian analysis were 88.5%,85.9%,87.1%,84.4% and 89.7% respectively,its accuracy showed no statistically significant with chest radiologist A(80.3%,χ~2=2.37,P=0.122) and B(79.5%,χ~2=3.12,P=0.076)using routine diagnostic method,and was higher than radiological residents C(74.2%,χ~2=7.05,P=0.012) and D(74.2%,χ~2=6.56,P=0.009).As for non-metastatic SPNs,the area under the receiver operating characteristic curve(A_z) of the Bayesian analysis was 0.957,which was higher than chest radiologists(A_z=0.886,P=0.003) and radiological residents(A_z=0.845,P=0.000).Conclusion The likelihood ratios of clinical and CT findings associated with SPNs can be used to guide the interpretation of CT images for physicians in daily work.Bayesian analysis is an effective diagnostic aid which can help physicians differentiate benign from malignant SPNs,especially for less experienced physicians.更多还原