| 蒋旭,曹海明,吴宇,等.基于 CT影像组学预测感染性肾结石的价值[J].安徽医药,2021,25(7):1401-1406. |
| 基于 CT影像组学预测感染性肾结石的价值 |
| Value of the prediction of infectious kidney stones based on CT radiomics |
| |
| DOI：10.3969/j.issn.1009-6469.2021.07.032 |
| 中文关键词: 尿路结石症 影像组学 泌尿道感染 电子计算机断层扫描 感染性结石 列线图 |
| 英文关键词: Urolithiasis Radiomics Urinary tract infections Computed tomography Infectious stones Nomogram. |
| 基金项目:蚌埠医学院自然科学类项目( BYKY2019164ZD) |
|
| 摘要点击次数: 1551 |
| 全文下载次数: 352 |
| 中文摘要: |
| 目的利用计算机辅助诊断技术探讨影像组学数据在鉴别结石成分的应用。方法回顾性分析 2018年 12月至 2020年 12月蚌埠医学院第二附属医院 140例采用经皮肾镜取石术(PCNL)治疗的病人，收集临床治疗前因素及 CT图像的相关数据，术后通过傅里叶转换红外光谱法测定结石成分，并以结石主成分 ≥70%定义结石性质。利用图像分析软件和计算机程序设计语言工具，从每位病人的 CT图像感兴趣区域中提取出 105个影像组学特征。按照 7∶3将数据分为训练集 98例和验证集 42例，采用 t检验、 χ2检验、秩和检验及 LASSO回归分析法对训练集进行变量选择，得到最佳特征选集，最终利用 R语言软件构建感染性结石的列线图预测模型，模型评价指标为分辨度和符合度，采用 ROC曲线下面积评价模型的分辨度，绘制校正曲线评价模型的符合度，外部验证利用验证集数据评估模型效果并绘制 ROC曲线。结果 140例病人术后结石成分分析报告显示感染性结石 49例，非感染性结石 91例。训练集数据临床治疗前因素的分析结果显示差异有统计学意义(P<0.05)为女性、尿蛋白、尿碱性、尿亚硝酸盐、尿培养、尿白细胞。感染性结石组尿白细胞数为 162(46.5，944.0)个，非感染性结石组 56(10.5，169.5)个， P=0.003；感染性结石组尿酸为(285.22±83.22)μmol/L，非感染性结石组(324.85±99.95)μmol/L，P=0.046。训练集影像组学 LASSO回归分析法筛选得到 8个相关性较高的影像组学特征变量。进一步 logistic多因素分析得出最佳特征选集包括 2个临床治疗前因素(女性、尿碱性)和 2个影像组学特征(群集阴影、大依赖性低灰度级强度)，训练集 AUC(0.892，95%CI:0.830~0.954)，验证集 AUC(0.842，95%CI: 0.702~0.981)，校正曲线表明模型符合度较好。结论计算机辅助诊断技术帮助下提取的影像组学特征，结合临床治疗前因素，有助于术前判断感染性肾结石的发生风险。 |
| 英文摘要: |
| Objective To explore the application of imaging data in differentiating stone components by computer-aided diagnosed. Methods One hundred and forty patients treated with percutaneous nephrolithotomy (PCNL) in the Second Affiliated Hospital ofBengbu Medical College from December 2018 to December 2020 were retrospectively analyzed, the data on pre-clinical factors and computed tomography (CT) images were collected, the calculi specimens were investigated by Fourier transform infrared spectroscope(FTIR) after the operation, and the stone character was defined by stone major components ≥70%. Using image analysis software andcomputer programming language tools, extraction of 105 imaging features from regions of CT images of interest for each patient. The data were assigned into 98 training sets and 42 testing sets according to 7:3. The several statistical analysis methods (t test, chi-squaretest, rank sum test and lasso regression analysis) were used to select the variables of the training set, and the best feature selection wasobtained. R language software was adopted to construct a prediction model for the histogram of infectious stones, the evaluation indexesof the model were resolution and conformity, the area under Receiver Operating Characteristic (ROC) Curve was used to evaluate theresolution of model, the correction curve was drawn to evaluate the conformity of model, external validation evaluated the model effectusing validation set data and ROC curve was drew.Results Analysis of stone composition in 140 patients showed 49 cases of infectious stones and 91 cases of non-infectious stones. Analysis of pre-clinical factors in training set data showed that there were significantdifferences in female, urine protein, alkaline urine, urine nitrite, urine culture, white blood cells in urine and number of white bloodcells in urine (P<0.05). The number of white blood cells in urine infectious stone group and non-infectious stone group was 162 (46.5, 944.0) and 56 (10.5, 169.5), respectively (P=0.003). The uric acid in urine infectious stone group and non-infectious stone group was (285.22±83.22) μmol/L and (324.85±99.95) μmol/L, respectively (P=0.046). Eight high correlation radiomics feature variables were obtained by training set after LASSO regression analysis. Multivariate Logistic regression analysis revealed that the best feature set included 2 pre-clinical factors (female, alkaline urine) and 2 radiomics features (glcm-Cluster Shade, gldm-Large Dependence Low Gray Level Emphasis). The AUC was (0.892, 95%CI: 0.830~0.954) in the training set, the AUC was (0.842, 95%CI: 0.702~0.981) in the training set. The calibration curve showed that the model fits well.Conclusion The radiomics features extracted with the help of computer-aided diagnostic techniques, combined with pre-clinical factors, is helpful to judge the risk of infectious renal calculi before an operation. |
|
查看全文
查看/发表评论 下载PDF阅读器 |
| 关闭 |
|
|
|
