| 赵才勇,李焕国,郭俊华,等.基于增强CT影像组学预测非小细胞肺癌中医证型的初步研究[J].浙江中医药大学学报,2025,49(2):153-159. |
| 基于增强CT影像组学预测非小细胞肺癌中医证型的初步研究 |
| A Preliminary Study of Radiomics for Predicting the Traditional Chinese Medicine Syndromes of Non-small Cell Lung Cancer Based on Contrast-Enhanced CT Image |
| DOI：10.16466/j.issn1005-5509.2025.02.005 |
| 中文关键词: 非小细胞肺癌 中医证型 增强CT 影像组学 模型 虚证 实证 预测 |
| 英文关键词: non-small cell lung cancer TCM differentiation typing contrast-enhanced computed tomography radiomics model deficiency syndrome excess syndrome forecast |
| 基金项目:浙江省中医药科技计划项目(2023ZL102)；浙江省医药卫生科技计划项目(2024KY1395)；杭州市医药卫生科技计划项目(A20220438) |
|
| 摘要点击次数: 76 |
| 全文下载次数: 65 |
| 中文摘要: |
| [目的] 探讨基于增强CT影像组学在预测原发性非小细胞肺癌(non-small cell lung cancer，NSCLC)中医辨证分型中的价值。[方法] 回顾性分析2018年7月至2023年10月浙江中医药大学附属杭州市中医院经病理证实的130例NSCLC患者的临床资料，根据疾病中医诊断标准分为虚证(67例)和实证(63例)，并按照7:3的比例分成训练集(91例)和验证集(39例)。选择横轴位图像(平扫期、动脉期、静脉期)病灶最大层面，勾画感兴趣区域、提取影像组学特征。使用特征间线性相关检查和L1正则化依次进行特征筛选，基于各期相CT影像组学特征，采用逻辑回归分类器构建影像组学模型。绘制受试者工作特征(receiver operating characteristic， ROC)曲线，评估各模型预测NSCLC虚证、实证的效能，采用Delong检验比较各模型曲线下面积(area under curve， AUC)。[结果] 在训练集中，共建立7个诊断NSCLC中医证型的影像组学模型，包括3个单期组学模型、3个双期联合组学模型和1个三期联合组学模型。联合组学模型的AUC均大于单期组学模型，其中三期联合组学模型的AUC最大。在训练集和验证集中，三期联合组学模型AUC分别为0.876[95%可信区间(confidence interval，CI)(0.807~0.945)]、0.755[95%CI(0.603~0.908)]。[结论] 基于增强CT影像组学模型可有效预测NSCLC中医证型，其中三期联合组学模型的预测效能最佳。 |
| 英文摘要: |
| [Objective] To investigate the value of radiomics based on contrast-enhanced computed tomography(CT) image in predicting the traditional Chinese medicine(TCM) differentiation typing of primary non-small cell lung cancer(NSCLC). [Methods] A total of 130 patients diagnosed as NSCLC by pathology from July 2018 to October 2023 in Hangzhou TCM Hospital Affiliated to Zhejiang Chinese Medical University were retrospectively analyzed. According to the diagnostic criteria of TCM， all the enrolled patients were divided into deficiency syndrome group(67 cases) and excess syndrome group(63 cases)， and then assigned to training cohort(91 cases) and validation cohort(39 cases) in a ratio of 7:3. The largest diameter slice of lesion on cross-sectional images was selected and the regions of interest were contoured at unenhanced， arterial and venous phases respectively， and then the radiomics features were extracted. The linear correlation among features and L1 regularization were used for feature selection， and then logistic regression was used to construct the radiomics model based on radiomics features of each phase. The receiver operating characteristic(ROC) curve was used to evaluate the effectiveness of the model in predicting deficiency and excess syndromes of NSCLC. The Delong test was used for comparison of area under curve(AUC) between the two models. [Results] In the training cohort， a total of 7 radiomics models were constructed， including three single-phase radiomics models， three two-phase combination radiomics models and one three-phase combination radiomics model. The AUC of combination radiomics model was higher than that of the single-phase radiomics model. The AUC of three-phase combination radiomics model was the largest， which was 0.876[95% confidence interval(CI)(0.807~0.945)] and 0.755[95% CI(0.603~0.908)] in the training cohort and validation cohort respectively. [Conclusion] The radiomics model based on contrast-enhanced CT image has high efficacy in predicting the TCM differentiation typing of NSCLC， and the three-phase combination radiomics model demonstrates the best diagnostic efficacy. |
|
查看全文
查看/发表评论 下载PDF阅读器 |
| 关闭 |