MRI影像组学与机器学习模型:评估胰腺导管腺癌肿瘤-间质比的新方法
本研究回顾性纳入148例接受MR扫描及手术切除的胰腺导管腺癌患者,提取1409个影像组学特征并用LASSO逻辑回归降维,基于110例训练集构建XGBoost分类器评估肿瘤-间质比,在38例验证集中验证。模型训练集AUC为0.82,验证集AUC为0.78,显示良好的判别能力,可作为无创评估TSR的工具。
要点
- MRI影像组学XGBoost模型可无创评估胰腺导管腺癌的肿瘤-间质比(TSR)。
- 训练集AUC 0.82,验证集AUC 0.78,验证集特异度达92.86%。
- TSR-low组生存期显著更长(log-rank检验)。
局限性
- 回顾性研究设计。
- 样本量有限(训练集110例,验证集38例)。
- 单中心研究。
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
OBJECTIVE: To develop and validate a magnetic resonance imaging (MRI)-based machine learning classifier for evaluating the tumor-stroma ratio (TSR) in patients with pancreatic ductal adenocarcinoma (PDAC).
MATERIALS AND METHODS: In this retrospective study, 148 patients with PDAC underwent an MR scan and surgical resection. We used hematoxylin and eosin to quantify the TSR. For each patient, we extracted 1,409 radiomics features and reduced them using the least absolute shrinkage and selection operator logistic regression algorithm. The extreme gradient boosting (XGBoost) classifier was developed using a training set comprising 110 consecutive patients, admitted between December 2016 and December 2017. The model was validated in 38 consecutive patients, admitted between January 2018 and April 2018. We determined the performance of the XGBoost classifier based on its discriminative ability, calibration, and clinical utility.
RESULTS: A log-rank test revealed significantly longer survival in the TSR-low group. The prediction model displayed good discrimination in the training (area under the curve [AUC], 0.82) and validation set (AUC, 0.78). While the sensitivity, specificity, accuracy, positive predictive value, and negative predictive value for the training set were 77.14%, 75.00%, 0.76%, 0.84%, and 0.65%, respectively, those for the validation set were 58.33%, 92.86%, 0.71%, 0.93%, and 0.57%, respectively.
CONCLUSION: We developed an XGBoost classifier based on MRI radiomics features, a non-invasive prediction tool that can evaluate the TSR of patients with PDAC. Moreover, it will provide a basis for interstitial targeted therapy selection and monitoring.
引用
- Meng Y, Zhang H, Li Q, et al. Magnetic Resonance Radiomics and Machine-learning Models: An Approach for Evaluating Tumor-stroma Ratio in Patients with Pancreatic Ductal Adenocarcinoma. Acad Radiol. 2021. PMID: 34563443. doi:10.1016/j.acra.2021.08.013
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。