论文部分内容阅读
目的:探讨DWI的ADC值联合纹理特征鉴别良恶性软组织肿瘤的价值。方法:回顾性分析中国科学技术大学附属第一医院西区经病理证实的94例软组织肿瘤（恶性44例，良性50例）MRI及DWI图像。在GE ADW4.6工作站测量肿块的实性成分ADC值。在Tn 2WI脂肪抑制图像上的肿瘤最大层面手动勾画ROI并提取纹理特征；采用独立样本n t检验对良恶性软组织肿瘤的ADC值及纹理参数进行统计学分析，并多因素logistic回归分析建模，计算诊断效能。n 结果:良恶性软组织肿瘤的ADC值分别为（1.6±0.3）×10n -3 mmn 2/s、（1.2±0.5）×10n -3 mmn 2/s，差异有统计学意义（n t=-5.382，n P<0.05），以1.28×10n -3 mmn 2/s为诊断良恶性软组织肿瘤临界值，AUC为0.783，灵敏度为92.00%，特异度为65.91%。纹理特征中直方图特征（frequency size、skewness），灰度共生矩阵特征（Inertia_All Direction_offset7、Inverse Difference Moment_angle0_offset1、Inverse Difference Moment_angle0_offset7）及Haralick特征（Haralick Correlation_All Direction_offset4_SD）鉴别良恶性软组织肿瘤的曲线下面积分别为AUC 0.825、0.739、0.826、0.816、0.820、0.783。多因素logistic回归分析最佳预测模型鉴别良恶性软组织肿瘤的曲线下面积、灵敏度、特异度分别为0.930、88.00%、86.36%。n 结论:ADC值联合纹理特征对术前预测软组织良恶性肿瘤有较高的应用价值。“,”Objective:To investigate the value of ADC derived from DWI combined with texture analysis derived from Tn 2WI fat suppressed images in distinguishing benign and malignant soft tissue tumors.n Methods:The MRI and DWI images of 94 patients with soft tissue tumors (44 cases with malignant and 50 cases with benign) confirmed by pathology were analyzed retrospectively in the First Affiliated Hospital of USTCn West District. ADC values of solid components were measured at GE ADW4.6 workstation. The texture features were extracted by manually drawing the ROI on the maximum level of the Tn 2WI fat suppressed images; the ADC values and texture parameters between the two groups were statistically analyzed by SPSS17.0, and the multivariate logistic regression model were conducted to analyze and calculate the diagnostic performance.n Results:ADC value of benign and malignant soft tissue tumors was (1.6±0.3)×10n -3 mmn 2/s, (1.2±0.5)×10n -3 mmn 2/s, respectively, and the difference was statistically significant(n t=-5.382, n P<0.05). Taking 1.28×10n -3 mmn 2/s as the critical value, the area under curve (AUC) for the diagnosis of benign and malignant soft tissue tumors was 0.783, the sensitivity was 92.00%, and the specificity was 65.91%. Among the texture features, the AUC of frequency size, skewness, Inertia All Direction_offset7, Inverse Difference Moment angle0_offset1, Inverse Difference Moment angle0_offset7 and Haralick Correlation All Direction_offset4_SD distinguishing benign and malignant soft tissue tumors were 0.825, 0.739, 0.826, 0.816, 0.820 and 0.783, respectively. The AUC, sensitivity and specificity of the best predictive model distinguishing benign and malignant soft tissue tumors were 0.930, 88.00% and 86.36% respectively using multivariate logistic regression analysis.n Conclusion:ADC combined with texture analysis is of great value in preoperative differentiation of benign and malignant soft tissue tumors.