基于CT的机器学习影像组学预测可切除胰腺导管腺癌Ki-67表达水平及其与总生存期的关系
本研究为单中心回顾性研究,纳入2017年1月至2023年3月接受手术治疗的124例胰腺导管腺癌患者,从动脉期和门静脉期CT图像提取影像组学特征,构建预测Ki-67表达的影像组学模型,并联合临床指标建立列线图预测1、2、3年总生存期。Ki-67表达率最佳截断值为50%,影像组学模型在训练组和验证组的AUC分别为0.806和0.801,高影像组学评分、CA19-9升高和接受辅助化疗是总生存期的独立预后因素。
要点
- Ki-67表达率最佳截断值为50%,高于与低于该值的患者总生存期存在显著差异。
- 基于双期增强CT的影像组学模型预测Ki-67表达,训练组AUC 0.806、验证组AUC 0.801。
- 影像组学评分、CA19-9升高和接受辅助化疗是总生存期的独立预后因素。
核心结论
- 影像组学-临床列线图提供了一种无创且高效的方法,用于预测胰腺导管腺癌患者的Ki-67表达和总生存期,可能有助于指导临床决策并改善患者结局。
研究设计与样本
- 单中心回顾性研究,纳入2017年1月至2023年3月接受手术治疗的124例胰腺导管腺癌患者,按Ki-67表达率分组,使用3D Slicer v5.0.3从动脉期和门静脉期CT图像提取影像组学特征,构建并验证预测Ki-67表达的影像组学模型,并联合临床指标建立预测1、2、3年总生存期的列线图。
诊断标准与关键数值
- Ki-67表达率最佳截断值为50%,高于与低于该值的患者总生存期存在显著差异。
- 影像组学模型预测Ki-67表达的AUC在训练组为0.806、验证组为0.801。
- 高影像组学评分、CA19-9升高和接受辅助化疗被确定为总生存期的独立预后因素。
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
BACKGROUND: The prognostic prediction of pancreatic ductal adenocarcinoma (PDAC) remains challenging. This study aimed to develop a radiomics model to predict Ki-67 expression status in PDAC patients using radiomics features from dual-phase enhanced CT, and integrated clinical characteristics to create a radiomics-clinical nomogram for prognostic prediction.
METHODS: In this retrospective study, data were collected from 124 PDAC patients treated surgically at a single center, from January 2017 to March 2023. Patients were categorized according to the Ki-67 expression rate. Radiomics features were extracted from arterial and portal venous phase CT images using 3D Slicer v5.0.3. A radiomics model was formulated and validated to predict the Ki-67 expression, and a nomogram combining clinical indicators and the radiomics model was developed to predict 1, 2 and 3 year overall survival (OS).
RESULTS: The optimal Ki-67 expression rate cutoff was identified as 50%, with significant OS differences. The developed radiomics model showed good predictive ability with area under the curves of 0.806 and 0.801 in the training and validation groups, respectively. High radiomics score, elevated carbohydrate antigen 19-9 (CA19-9), and receipt of adjuvant chemotherapy were identified as independent prognostic factors for OS. The radiomics-clinical nomogram accurately predicted 1, 2 and 3 year OS in PDAC patients.
CONCLUSIONS: The radiomics-clinical nomogram provides a non-invasive and efficient method for predicting Ki-67 expression and overall survival in PDAC patients, which could potentially guide clinical decision-making and improve patient outcomes.
引用
- Chen J, Ma Z, Xu Y, et al. CT-based machine learning radiomics predicts Ki-67 expression level and its relationship with overall survival in resectable pancreatic ductal adenocarcinoma. Abdom Radiol (NY). 2025. PMID: 39841230. doi:10.1007/s00261-025-04798-y
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。