基于皮肌炎/多发性肌炎相关间质性肺疾病患者影像组学特征构建机器学习影像分型的分类模型  

Construction of a classification model for image subtypes based on the radiomics features of patients with dermatomyositis/polymyositis-related interstitial lung disease for machine learning

作　　者：李春辉 何立宇 张静平[1] 韩婷婷 朱冰洁 郭佑民[1] 金晨望[1] Li Chunhui;He Liyu;Zhang Jingping;Han Tingting;Zhu Bingjie;Guo Youmin;Jin Chenwang(Department of Imaging,the First Affiliated Hospital of Xi′an Jiaotong University,Xi′an 710061,China)

机构地区：[1]西安交通大学第一附属医院影像科,西安710061

出　　处：《中华风湿病学杂志》2023年第8期521-526,I0003,共7页Chinese Journal of Rheumatology

摘　　要：目的探讨基于胸部CT影像组学特征,利用机器学习算法构建的模型对PM/DM相关间质性肺疾病(DM/PM-ILD)影像分型进行分类的可行性。方法回顾性分析2011年11月至2020年11月间就诊于西安交通大学第一附属医院,确诊为DM/PM-ILD的患者107例,共采集胸部CT 315例,由2名资深影像科医生对图像影像分型进行预分类[包括非特异性间质性肺炎(NSIP)105例,机化性肺炎(OP)90例,非特异性间质性肺炎合并机化性肺炎(NSIP+OP)66例,寻常型间质性肺炎(UIP)35例,弥漫性肺泡损伤(DAD)19例],采用ANOVA分析检验各影像分型组间的基线临床信息差异。以4∶1的比例通过分层随机抽样划分训练集与测试集,采用3D slicer分割各肺叶,重建为3 mm^(3)的体素后使用Pyradiomics库提取全肺及各肺叶影像组学特征。通过对5组分别构建随机森林基分类器后再投票集成为最终模型以实现多分类目标。在基分类器构建过程中,首先通过SMOTETomek综合采样实现样本组间平衡,随后通过独立样本t检验、L1项正则化的最小绝对收缩和选择算子(LASSO)回归进行特征筛选。基于影像组学特征构建Radiomics模型,增加性别、年龄信息构建Radiomics^(+)模型。基分类器、集成模型分别使用平均准确率、受试者工作特征曲线(ROC)曲线下面积(AUC)评价效能。结果NSIP、OP、NSIP+OP、UIP、DAD各组年龄[分别为(57±13)岁、(53±8)岁、(54±10)岁、(44±11)岁、(46±8)岁]比较差异有统计学意义(F=11.82,P<0.001)。在Radiomics模型中对NSIP、OP、NSIP+OP、UIP、DAD各组,训练集的AUC分别为0.87、0.91、0.91、0.96、0.99,测试集的AUC分别为0.81、0.82、0.79、0.93、0.89。在Radiomics^(+)模型中,对NSIP、OP、NSIP+OP、UIP、DAD各组,训练集的AUC分别为0.89、0.91、0.92、0.97、0.99,测试集的AUC分别为0.84、0.82、0.78、0.94、0.90。结论联合胸部CT影像组学特征及性别、年龄信息,利用机器学习构建的Radiomics^(+)模型对DObjective To investigate the feasibility of classifying imaging patterns of dermatomyositis/polymyositis-related interstitial lung disease(DM/PM-ILD)into subtypes based on chest CT radiomics features and a model was constructed by machine learning algorithms.Methods From November 2011 to November 2020,107 patients diagnosed with PM/DM-ILD at the First Affiliated Hospital of Xi′an Jiaotong University were retrospectively analyzed.A total of 315 cases with chest CT were collected.Doctors pre-classified image patterns,including 105 cases with non-specific interstitial pneumonia(NSIP),90 cases with organizing pneumonia(OP),and 66 cases with non-specific interstitial pneumonia combined with organizing pneumonia(NSIP+OP),35 cases with common interstitial pneumonia(UIP),and 19 cases with diffuse alveolar damage(DAD),ANOVA was used to test the difference of baseline clinical information among the imaging classification groups.All images were divided into the training set and the est set by stratified random sampling at a ratio of 4∶1.In each CT scan,3D slicer was used to segment each lung lobe,and then reconstructed into 3 mm^(3)of voxels,and Pyradiomics library was used to extract the radiomic features of the whole lung and each lobe.The multi-classification goal was achieved by constructing random forest base classifiers for each of the five groups and then voting as the final model.In the process of constructing the base classifier,firstly,the balance between sample groups was achieved by SMOTETomek comprehensive sampling,and the optimal feature set was selected by independent sample t test and L1 regularized least absolute shrinkage and selection operator(LASSO)regression.In this study,the Radiomics model was constructed based on chest CT radiomics features,and the Radiomics^(+)model was constructed by introducing gender and age information.The base classifier and the integration model use the mean accuracy and the area under the receiver operator characteristics analysis curve(AUC)to evaluate the performance,res

关 键 词：皮肌炎 多发性肌炎 肺疾病 间质性 影像基因组学 机器学习 

分 类 号：R593.2[医药卫生—内科学] R816.4[医药卫生—临床医学]