直方图分析方法在鉴别髓母细胞瘤和室管膜瘤中的应用

Application of the Histogram Analysis in Differentiating Between Medulloblastoma and Ependymoma

目的探讨基于全肿瘤的直方图分析方法在鉴别髓母细胞瘤和室管膜瘤中的应用价值。方法回顾性分析27例经病理证实的髓母细胞瘤（16例）和室管膜瘤（11例）,每例患者术前及其他治疗前均行3.0 T MR检查,在ADC图上画出各个层面的肿瘤（VOI）,并计算出其直方图参数,包括中位数、平均值、第25及75百分位数、峰度及偏度,应用独立样本t检验比较两组肿瘤间各参数值的差异,采用ROC曲线分析以上参数的诊断效能。结果髓母细胞瘤的中位数、平均值、第25及75百分位数低于室管膜瘤,髓母细胞瘤的峰度及偏度高于室管膜瘤,差异均具有统计学意义（t值分别为-7.065、-6.803、-6.598、-9.016、3.565、3.754,P值均〈0.01）。ROC曲线分析显示出良好的诊断敏感性和特异性。结论直方图分析方法在鉴别髓母细胞瘤和室管膜瘤中具有一定的应用价值。

Objective To explore the value of histogram analysis based on the entire tumor volume in differentiating between medulloblastoma and ependymoma. Methods To retrospectively analyze 27 patients with medulloblastoma（ n = 16）and ependymoma（ n = 11） undergoing 3. 0 T MR examination before surgery and other therapy. The VOI was drawn on the ADC map. And,the histogram parameters,including median,mean,25 th percentile,75 th percentile,kurtosis and skewness,were calculated. Comparison of the histogram parameters between the medulloblastoma and ependymoma was conducted using an independent-sample t test. Receiver operating characteristic（ ROC） curve were constructed to determine the diagnostic efficacy of the above parameters. Results The median,mean,25 th percentile,75 th percentile of ADC values for medulloblastoma were significantly lower than that of ependymoma（ P〈0. 01）. The kurtosis and skewness of ADC values for medulloblastoma were significantly higher than that of ependymoma（ t =-7. 065,-6. 803,-6. 598,-9. 016,3. 565,3. 754,respectively,P〈0. 01）. ROC curves all show high diagnostic efficiency. Conclusion Histogram analysis has an important clinical value in distinguishing between medulloblastoma and ependymoma.