基于磁共振STIR纹理分析对早期强直性脊柱炎活动性研究

Study of Radiomics Texture Analysis in evaluating the Activity of Sacroiliac Joint in Early Ankylosing Spondylitis based on STIR Sequence

目的 基于短时间反转恢复(STIR)序列探讨影像组学纹理分析在强直性脊柱炎(AS)活动性的诊断价值。方法 搜集AS早期患者43例,采用骶髂关节STIR原始图像和病变ROI,通过A.K.软件提取病变的纹理特征参数,按7∶3的比例随机分为训练集(116个)与验证集(56个);采用Mann-Whitney U检验、mRMR、LASSO回归模型,计算影像组学评分(Radscore值)。通过ROC曲线评价Radscore值、SPARCC评分、ADC值3种方法的效能,采用Spearman相关性检验探讨3种方法与临床活动指标(BASDAI、ESR、CRP、ASDAS-ESR、ASDAS-CRP)的相关性。结果 优选出8个纹理特征子集具有价值;在训练集/验证集中,鉴别AS早期骶髂关节炎活动组与稳定组的最佳临界值(曲线下面积、准确度、敏感度、特异度、阳性预测值、阴性预测值):Radscore=51.46(0.81/0.87、76.72%/82.14%、81.25%/90.65%、66.67%/70.83%、84.42%/80.56%、61.54%/85.00%);ROC曲线效能:SPARCC评分>Radscore值>ADC值;与BASDAI、ESR、CRP、ASDAS-ESR、ASDAS-CRP呈低度相关(P<0.05)。结论 基于STIR序列纹理分析对AS活动性的诊断价值客观性更强。

Objective Explore the value of texture analysis of radiomics based on STIR to evaluate the activity in early AS.Methods A total of 43 patients with early AS were collected in our hospital,including 30 males and 13 females.According to the ratio of 7∶3,all the patients were randomly divided into the training cohort(n=116) and verification cohort(n=56).Optimal feature subsets were obtained by the Mann-Whitney U test,the minimum-Redundancy Maximum-Relevancy(mRMR),and then the least absolute shrinkage and selection operator(LASSO) using these texture feature parameters.The optimal feature subset was used to construct the final prediction model,and Radscore was obtained by summing the selected features after being weighted by their coefficients.The effectiveness of Radscore value,SPARCC score and ADC value was evaluated by ROC curve.The correlations between Radscore values and the values of SPARCC score,ADC,BASDAI,ESR,CRP,ASDAS-ESR,ASDAS-CRP were analyzed by the Spearman correlation test.Results Eight texture feature subsets were selected to identify the activity in early AS.In the training set/validation set,the best critical value(AUC,AC,SEN,SPE,PPV,NPV) to distinguish the active group and the stable group of sacroiliac joint bone marrow edema in the early stage of AS:Radscore=51.46(0.81/0.87,76.72%/82.14%,81.25%/90.65%,66.67%/70.83%,84.42%/80.56%,61.54%/85.00%).ROC curve efficiency:SPARCC score>Radscore value>ADC value,and Low correlation with BASDAI,ESR,CRP,ASDAS-ESR,ASDAS-CRP.Conclusion Radiomics analysis based on STIR texture analysis has a good prediction,and more objective evaluation method for AS activity.