钆塞酸二钠增强MRI影像组学与深度学习模型预测肝细胞癌病理分化程度
本研究纳入来自三家医院的409例术前接受钆塞酸二钠增强MRI的肝细胞癌患者(训练集304例、验证集105例),构建临床-影像组学-深度学习联合模型预测病理分化程度。验证集中联合模型AUC为0.794,高于影像组学(0.771)、深度学习(0.669)、临床影像(0.606)及影像组学联合深度学习(0.776)模型。
要点
- 年龄、AFP、包膜及肝胆期瘤周低信号是肝细胞癌分化程度的独立预测因素。
- 验证集中联合模型AUC 0.794,高于影像组学0.771、深度学习0.669、临床影像0.606。
- 联合模型与临床影像模型(P=0.026)、深度学习模型(P=0.013)的AUC差异有统计学意义。
核心结论
- 联合深度学习、影像组学与临床及常规影像特征对预测肝细胞癌分化程度有一定价值,可帮助医生为患者制定更有利的治疗方案。
研究设计与样本
- 回顾性纳入三家医院409例术前接受钆塞酸二钠增强MRI的肝细胞癌患者,训练集304例、验证集105例;采用FeAture Explorer软件提取影像组学特征、3D ResNet-18提取器提取深度学习特征,以机器学习算法构建临床影像、影像组学、深度学习、影像组学联合深度学习及临床-影像组学-深度学习联合模型,以AUC、敏感度、特异度评估,并用DCA曲线和校准曲线验证。
关键影像表现/征象
- 肝胆期瘤周低信号是肝细胞癌分化程度的独立预测因素。
- 年龄、AFP、包膜亦为肝细胞癌分化程度的独立预测因素。
诊断标准与关键数值
- 验证集中临床-影像组学-深度学习联合模型AUC=0.794,高于影像组学模型AUC=0.771。
- 验证集中联合模型AUC=0.794,高于深度学习模型AUC=0.669。
- 验证集中联合模型AUC=0.794,高于临床影像模型AUC=0.606。
- 验证集中联合模型AUC=0.794,高于影像组学联合深度学习模型AUC=0.776。
- 联合模型与临床影像模型AUC差异P=0.026,与深度学习模型AUC差异P=0.013,均有统计学意义。
临床应用与阅片要点
- 可将年龄、AFP、包膜及肝胆期瘤周低信号作为预测肝细胞癌分化程度的参考因素。
- 校准曲线和DCA曲线提示联合模型对分化程度预测具有较高准确性和良好净获益。
- 作者认为联合模型可帮助医生为患者制定更有利的治疗方案。
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 investigate the value of Gd-EOB-DTPA enhanced MRI radiomics and deep learning models with clinical-radiologic characteristics in predicting the pathological differentiation degree in hepatocellular carcinoma (HCC).
METHODS: This study included 409 (training set: 304; validation set: 105) HCC patients who underwent preoperative Gd-EOB-DTPA-enhanced MRI from three hospitals. Clinical and radiological (CR) characteristics were selected using univariate and multivariate analyses. Radiomics and deep learning (DL) features were extracted based on FeAture Explorer software and the 3D ResNet-18 extractor, respectively. CR, radiomics, DL, radiomics combined DL (DLR) and CR-DLR models were built using machine learning algorithms. The predictive capacity of the models was assessed by the area under the receiver operating characteristic curve (AUC), sensitivity, and specificity. DCA curves and the calibration curves were used as model validation.
RESULTS: Age, AFP, capsule, and peritumoral hypointensity in HBP were independent predictors of the differentiation degree in HCC. In the validation set, the CR-DLR model (AUC = 0.794) were higher than that of the radiomics (AUC = 0.771),DL (AUC = 0.669) CR (AUC = 0.606) and DLR (AUC = 0.776) models. And the differences were statistically significant between the CR-DLR and CR (P = 0.026) or DL models (P = 0.013). The calibration and DCA curves suggesting that the CR-DLR model has a high prediction accuracy and a good net benefit for predicting differentiation degree.
CONCLUSION: Combining deep learning, radiomics models with clinical and conventional radiological features has certain value and can help doctors formulate more favorable treatment plans for patients.
引用
- Wu K, Zhu Z, Xu D, et al. Gd-EOB-DTPA-enhanced MRI radiomics and deep learning models for predicting the pathological differentiation degree in hepatocellular carcinoma. Eur J Radiol. 2025. PMID: 41161266. doi:10.1016/j.ejrad.2025.112487
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。