论文部分内容阅读
目的:探讨应用ROC曲线分析钙化点分布及形态特征对乳腺癌诊断的价值。方法:收集由超声影像检查发现钙化点并最终经病理诊断为乳腺癌的198例患者的影像资料,通过ROC曲线分析钙化点分布情况及其形态特征,包括单位面积个数、不同形态钙化的概率、区域平均直径、最长直径的差异等。采用ROC曲线分析数据,了解其对乳腺癌的诊断价值,并确认其最佳临界值。结果:恶性病变组中钙化点分布最佳单位面积个数是34个/m2,区域平均直径22.98mm,长径差异1.41mm,沙砾样钙化率占78.9%,线样分支状钙化率51.2%;ROC曲线下面积各为:0.745、0.756、0.678、0.860、0.900。其中线样分支状钙化率诊断准确率最高。结论:各种钙化分布的特征均有诊断效能,但单一的因素存在局限性,综合检测多项特征能有效的提高准确率。
Objective: To evaluate the value of ROC curve in the diagnosis of breast cancer by analyzing the distribution and morphological features of calcifications. Methods: The imaging data of 198 patients who were diagnosed as breast cancer by ultrasonic imaging were collected. The distribution of calcifications and their morphological characteristics were analyzed by ROC curve, including the number of unit area, the probability of different forms of calcification , The average regional diameter, the longest diameter of the difference. ROC curve analysis of data to understand its diagnostic value of breast cancer, and confirm the best cut-off value. Results: The best number of calcification points per unit area was 34 / m2 in the malignant group, the average diameter of the region was 22.98mm, the difference of the long diameter was 1.41mm, the rate of gravel calcification was 78.9% and the linear calcification rate was 51.2%. The area under the ROC curve is: 0.745, 0.756, 0.678, 0.860, 0.900. The line-like branch calcification rate of the highest diagnostic accuracy. CONCLUSION: The characteristics of various calcifications distribution have diagnostic efficacy, but the single factor has limitations. Comprehensive detection of multiple features can effectively improve the accuracy.