论文部分内容阅读
目的:建立基于多模态MRI的影像组学模型，比较不同模型鉴别诊断肺结节和肿块良性与恶性的效能。方法:回顾性分析2014年1月至2019年10月在南通市第一人民医院就诊的114例患者共115个肺结节的MR平扫影像资料。提取基于Tn 1WI图像、表观扩散系统（ADC）图像及Tn 2WI图像的纹理特征，分别建立logistic回归模型（LR）、支持向量机（SVM）、随机森林（RF）、k-近邻（KNN）模型。为控制建模特征数量降低模型不可解释性，选择性对超参数模型下部分参数手工修改得到的新模型为模型n a。114例病例轮流作为训练集和验证集。采用混淆矩阵及受试者操作特征曲线（ROC）评估各模型鉴别诊断肺结节和肿块良性与恶性的效能。n 结果:基于Tn 2WI图像构建的影像组学模型，验证集中LR模型鉴别诊断肺结节和肿块良性与恶性的ROC曲线下面积（AUC）为0.71、F1分数为0.57；基于Tn 1WI图像构建的影像组学模型，LR和SVM模型鉴别诊断肺结节和肿块良性与恶性的AUC较高，分别为0.77、0.78，部分参数手工修改得到的新模型（LRn a、SVMn a）鉴别诊断肺结节和肿块良性与恶性的准确度分别为0.67、0.70，AUC均为0.72。基于ADC图像构建的影像组学模型，各模型鉴别诊断肺结节和肿块良性与恶性的AUC及准确度均低于0.70。n 结论:多模态MR影像组学对肺结节和肿块良性与恶性的鉴别存在一定价值，以基于Tn 1WI模型表现最优。n “,”Objective:To develop a multimodal MRI-based radiomics model for the differential diagnosis of benign and malignant lung lesions, and to compare the discriminative abilities of different models.Methods:Totally 114 patients with 115 lesions (44 benign and 71 malignant) in Nantong First Peoples′s Hospital from January 2014 to October 2019 were included in the study. All patients underwent non-enhanced MR examination, and textural features from Tn 1WI,Tn 2WI and apparent diffusion coefficient (ADC) imaging were extracted. The feature selection methods included L1 based, mutual information, tree based, recursive feature elimination and F-test. Then we constructed a prediction model by using logistic regression (LR), support vector machine (SVM), random forest (RF) and k-nearest neighbor (KNN) respectively. In order to control the number of modeling features and reduce the ininterpretability of the model, the new model was obtained by manually modifying some parameters of the hyperparameter model. One hundred and fourteen cases were rotated as training and validation sets. The performance of each model was evaluated by confounding matrix and receiver operating characteristic (ROC) curve.n Results:The area under the curve (AUC) of Tn 2WI based LR model for the differential diagnosis of benign and malignant pulmonary nodules/masses was 0.71 and the F1 score was 0.57. Based on Tn 1WI images, LR and SVM model could be used to identify benign and malignant pulmonary nodules, the AUC before parameter adjustment were 0.77 and 0.78, the accuracy after parameter adjustment (LRn a,SVMn a) was 0.67, 0.70, and both the AUC were 0.72. However, no matter which feature or classifier was selected, both the AUC and accuracy of ADC-based model were less than 0.70.n Conclusion:Multimodal MRI-based radiomics model is valuable for the differential diagnosis of benign and malignant pulmonary nodules/masses, and Tn 1WI-based model shows the best discrimination.n