平扫CT纹理分析鉴别肿块型胰腺炎与胰腺导管腺癌的诊断准确性
回顾性纳入2012年1月至2017年12月术前接受平扫CT的109例患者(肿块型胰腺炎30例 vs 胰腺导管腺癌79例),提取396个影像组学特征并用随机森林建模,模型敏感度92.2%、特异度94.2%、准确率93.3%,留组交叉验证汇总平均敏感度82.6%、特异度80.8%、准确率82.1%。作者认为平扫CT纹理分析可能成为鉴别两者的无创方法。
要点
- 平扫CT纹理分析模型鉴别肿块型胰腺炎与胰腺导管腺癌的敏感度92.2%、特异度94.2%、准确率93.3%。
- 留组交叉验证汇总平均敏感度82.6%、特异度80.8%、准确率82.1%,提示模型相对可靠稳定。
- 最终模型基于4个最具预测价值的纹理参数构建。
核心结论
- 平扫CT纹理分析可能成为鉴别肿块型胰腺炎与胰腺导管腺癌的无创方法。
研究设计与样本
- 回顾性研究,纳入109例患者(肿块型胰腺炎30例 vs 胰腺导管腺癌79例),均于2012年1月至2017年12月间接受术前平扫CT。
- 采用合成少数类过采样技术(SMOTE)算法重建并平衡两组样本,对肿块型胰腺炎和胰腺导管腺癌患者应用200%的SMOTE后得到肿块型胰腺炎90例 vs 胰腺导管腺癌120例。
- 从平扫CT图像提取396个影像组学特征,经Mann-Whitney U检验和最小冗余最大相关(MRMR)方法降维。
- 采用随机森林(RF)方法构建预测模型,并用留组交叉验证(LGOCV)方法验证。
诊断标准与关键数值
- 经Mann-Whitney U检验和MRMR方法降维后得到30个影像组学特征,经随机森林方法保留10个影像组学特征。
- 采用4个最具预测价值的参数(GreyLevelNonuniformity_angle90_offset1、VoxelValueSum、HaraVariance、ClusterProminence_AllDirection_offset1_SD)构建预测模型。
- 预测模型诊断性能:敏感度92.2%、特异度94.2%、准确率93.3%、阳性预测值92.2%、阴性预测值94.2%。
- 留组交叉验证分析中汇总平均敏感度82.6%、特异度80.8%、准确率82.1%。
临床应用与阅片要点
- 作者认为平扫CT纹理分析可能成为鉴别肿块型胰腺炎与胰腺导管腺癌的无创方法。
局限性
- 原文未报告局限性。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
英文原文(摘要)· 点击展开
PURPOSE: To investigate the value of texture analysis on unenhanced computed tomography (CT) to potentially differentiate mass-forming pancreatitis (MFP) from pancreatic ductal adenocarcinoma (PDAC).
METHODS: A retrospective study consisting of 109 patients (30 MFP patients vs 79 PDAC patients) who underwent preoperative unenhanced CT between January 2012 and December 2017 was performed. Synthetic minority oversampling technique (SMOTE) algorithm was adopted to reconstruct and balance MFP and PDAC samples. A total of 396 radiomic features were extracted from unenhanced CT images. Mann-Whitney U test and minimum redundancy maximum relevance (MRMR) methods were used for the purpose of dimension reduction. Predictive models were constructed using random forest (RF) method, and were validated using leave group out cross-validation (LGOCV) method. Diagnostic performance of the predictive model, including sensitivity, specificity, accuracy, positive predicting value (PPV), and negative predicting value (NPV), was recorded.
RESULTS: We applied 200% of SMOTE to MFP and PDAC patients, resulting in 90 MFP patients compared with 120 PDAC patients. Dimension reduction steps yielded 30 radiomic features using Mann-Whitney U test and MRMR methods. Ten radiomic features were retained using RF method. Four most predictive parameters, including GreyLevelNonuniformity_angle90_offset1, VoxelValueSum, HaraVariance, and ClusterProminence_AllDirection_offset1_SD, were used to generate the predictive model with preferable 92.2% sensitivity, 94.2% specificity, 93.3% accuracy, 92.2% PPV, and 94.2% NPV. Finally, in LGOCV analysis, a high pooled mean sensitivity, specificity, and accuracy (82.6%, 80.8%, and 82.1%, respectively) indicate a relatively reliable and stable predictive model.
CONCLUSIONS: Unenhanced CT texture analysis can be a promising noninvasive method in discriminating MFP from PDAC.
引用
- Ren S, Zhao R, Zhang J, et al. Diagnostic accuracy of unenhanced CT texture analysis to differentiate mass-forming pancreatitis from pancreatic ductal adenocarcinoma. Abdom Radiol (NY). 2020. PMID: 32279101. doi:10.1007/s00261-020-02506-6
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。