基于患者信息的模型预测肝脏碘对比剂强化
本研究纳入1577例胸部/腹部/盆腔CT扫描,按70%训练、30%验证测试划分,利用高斯函数拟合每位患者对比剂灌注曲线的早期动脉期、晚期动脉期和门静脉期,并结合药代动力学模型与机器学习预测高斯参数。药代动力学模型联合两层神经网络在测试数据上预测精度最高(R2=0.61),显著优于单独药代动力学模型(R2=0.11);模型指导调整对比剂给药可使临床强化不一致性降低最多40%。
要点
- 基于患者属性(体重、身高、年龄、性别、BMI)的机器学习模型可预测肝脏对比剂强化时相曲线。
- 药代动力学模型联合两层神经网络预测精度R2=0.61,显著高于单独药代动力学模型的R2=0.11。
- 模型指导调整对比剂给药可能使临床强化不一致性降低最多40%。
核心结论
- 使用高斯函数和监督机器学习可构建肝脏实质对比剂强化预测模型,该模型在临床环境中可能有助于优化并提高增强肝脏成像的一致性。
研究设计与样本
- 研究纳入1577例胸部/腹部/盆腔CT扫描,按70%训练、30%验证测试划分;使用高斯函数近似每位患者对比剂灌注曲线的早期动脉期、晚期动脉期和门静脉期,基于患者的团注跟踪和诊断扫描数据;采用机器学习模型以患者属性(体重、身高、年龄、性别、BMI)预测高斯参数;采用Pearson系数、平均绝对误差和均方根误差评估预测精度。
诊断标准与关键数值
- 药代动力学模型联合两层神经网络在测试数据上预测精度最高,R2=0.61。
- 单独药代动力学模型在测试数据上R2=0.11。
- 模型指导调整对比剂给药可使临床强化不一致性降低最多40%。
临床应用与阅片要点
- 作者认为该模型在临床环境中可能有助于优化并提高增强肝脏成像的一致性。
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
OBJECTIVE: To devise a patient-informed time series model that predicts liver contrast enhancement, by integrating clinical data and pharmacokinetics models, and to assess its feasibility to improve enhancement consistency in contrast-enhanced liver CT scans.
METHODS: The study included 1577 Chest/Abdomen/Pelvis CT scans, with 70-30% training/validation-testing split. A Gaussian function was used to approximate the early arterial, late arterial, and the portal venous phases of the contrast perfusion curve of each patient using their respective bolus tracking and diagnostic scan data. Machine learning models were built to predict the Gaussian parameters of each patient using the patient attributes (weight, height, age, sex, BMI). Pearson's coefficient, mean absolute error, and root mean squared error were used to assess the prediction accuracy.
RESULTS: The integration of the pharmacokinetics model with a two-layered neural network achieved the highest prediction accuracy on the test data (R2 = 0.61), significantly exceeding the performance of the pharmacokinetics model alone (R2 = 0.11). Applying the model demonstrated that adjusting the contrast administration directed by the model may reduce clinical enhancement inconsistency by up to 40 %.
CONCLUSIONS: A new model using a Gaussian function and supervised machine learning can be used to build liver parenchyma contrast enhancement prediction model. The model can have utility in clinical settings to optimize and improve consistency in contrast-enhanced liver imaging.
引用
- Setiawan H, Chen C, Abadi E, et al. A patient-informed approach to predict iodinated-contrast media enhancement in the liver. Eur J Radiol. 2022. PMID: 36265222. doi:10.1016/j.ejrad.2022.110555
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。