基于3.0 T磁共振T2WI的纹理分析预测宫颈癌治疗后远期复发的价值

The Value of Texture Analysis Based on 3. 0 T MRI TWI to Predict Recurrence of Cervical Cancer after Treatment

目的探讨基于磁共振T2WI序列的纹理分析(TA)对宫颈癌治疗后远期复发的预测价值。方法回顾性分析本院收治的88例宫颈癌患者。按照患者治疗方式分为手术组和非手术组,再根据治疗后4年内是否复发或转移,分为复发组和非复发组。在T2WI图像上进行TA并获取病灶的纹理特征值。所得结果应用SPSS软件,采用独立样本t检验或Mann-Whitney U检验进行比较,P<0.05有统计学意义。绘制受试者工作特征曲线(ROC),采用Logistic回归分析影响宫颈癌患者复发的因素。结果手术组中复发组和非复发组的纹理特征间无明显统计学差异(P> 0.05);非手术组的复发组和非复发组中有8个纹理特征有统计学意义,其中LAHGLE的曲线下面积(AUC)最大,为0.764。Logistic回归分析显示LAHGLE、RV是影响晚期宫颈癌患者复发的独立因素。结论基于3.0 T磁共振的T2WI序列提取的纹理特征可在一定程度上预测晚期宫颈癌患者远期复发,对其预后评估有一定的价值。

Objective To explore the value of texture analysis(TA) based on MRI T2 WI in predicting long-term recurrence of cervical cancer after treatment. Methods Retrospective analysis of 88 cases with cervical cancer admitted to our hospital.Patients were divided into surgical group and non-surgical group according to the treatment methods, and then divided into recurrent group and non-recurrent group respectively according to whether there was recurrence or metastasis within 4 years after the treatment.TA was performed on the T2WI images, and the texture features were extracted.The results were compared by SPSS software,using independent sample t test or Mann-Whitney U test, P< 0.05 was statistically significant.The receiver operating characteristic curves(ROC) were drawn, and Logistic regression was used to analyze the factors affecting the recurrence of cervical cancer patients. Results There were no statistically significant differences in texture features between the recurrent and non-recurrent groups in the surgical group(P>0.05);In the non-surgicalgroup, there were 8 texture features with statistical significance, among these the area under the curve(AUC) of LAHGLE was the largest, which was 0. 764.Logistic regression analysis showed that LAHGLE and RV were independent factors influencing the recurrence of advanced cervical cancer. Conclusion The texture features extracted by T2WI imaging based on 3.0 T MRI can predict the long-term recurrence of advanced cervical cancer, which is significant for assessment of prognosis.