基于多区域MR生境成像与机器学习分类器的决策融合模型预测肝细胞癌微血管侵犯
该研究回顾性纳入300例肝细胞癌患者,基于动脉期MR图像将瘤内及瘤周区域分割为不同生境并提取影像组学与深度学习特征,用六种机器学习分类器构建临床影像、传统影像组学、深度学习影像组学、特征融合及决策融合模型;基于逻辑回归的决策融合模型(VOI-Peri10-1)在测试队列中取得最高AUC 0.808(95%CI 0.807-0.912),校准良好且具有临床净获益。
要点
- 基于逻辑回归的决策融合模型整合临床影像、影像组学和深度学习特征,术前预测MVI的测试集AUC为0.808。
- 决策融合模型VOI-Peri10-1校准良好(Hosmer-Lemeshow检验P>0.050)并具有临床净获益。
- 研究比较了六种机器学习分类器及特征融合与决策融合策略,决策融合模型表现最优。
核心结论
- 基于逻辑回归的决策融合模型整合临床影像、影像组学与深度学习特征,对肝细胞癌微血管侵犯的术前预测显示出前景,有助于患者预后判断和个体化治疗规划。
研究设计与样本
- 回顾性纳入300例肝细胞癌患者,基于动脉期MR图像分割瘤内及瘤周区域为不同生境,采用ICC分析、PCC过滤和RFE降维,用DT、KNN、LR、RF、SVM和XGBoost六种分类器构建预测模型及特征融合与决策融合模型,以ROC AUC、校准曲线和决策曲线分析验证性能。
诊断标准与关键数值
- 基于逻辑回归的决策融合模型(VOI-Peri10-1)整合临床影像、影像组学和深度学习特征,在测试队列中AUC为0.808(95%CI 0.807-0.912),Hosmer-Lemeshow检验P>0.050。
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
RATIONALE AND OBJECTIVES: Accurate prediction of microvascular invasion (MVI) in hepatocellular carcinoma (HCC) is crucial for guiding treatment. This study evaluates and compares the performance of clinicoradiologic, traditional radiomics, deep-learning radiomics, feature fusion, and decision fusion models based on multi-region MR habitat imaging using six machine-learning classifiers.
MATERIALS AND METHODS: We retrospectively included 300 HCC patients. The intratumoral and peritumoral regions were segmented into distinct habitats, from which radiomics and deep-learning features were extracted using arterial phase MR images. To reduce feature dimensionality, we applied intra-class correlation coefficient (ICC) analysis, Pearson correlation coefficient (PCC) filtering, and recursive feature elimination (RFE). Based on the selected optimal features, prediction models were constructed using decision tree (DT), K-nearest neighbors (KNN), logistic regression (LR), random forest (RF), support vector machine (SVM), and XGBoost (XGB) classifiers. Additionally, fusion models were developed utilizing both feature fusion and decision fusion strategies. The performance of these models was validated using the area under the receiver operating characteristic curve (ROC AUC), calibration curves, and decision curve analysis.
RESULTS: The decision fusion model (VOI-Peri10-1) using LR and integrating clinicoradiologic, radiomics, and deep-learning features achieved the highest AUC of 0.808 (95% confidence interval [CI]: 0.807-0.912) in the test cohort, with good calibration (Hosmer-Lemeshow test, P > 0.050) and clinical net benefit.
CONCLUSION: The LR-based decision fusion model integrating clinicoradiologic, radiomics, and deep-learning features shows promise for preoperative prediction of MVI in HCC, aiding in patient outcome predictions and personalized treatment planning.
引用
- Huang Z, Huang W, Jiang L, et al. Decision Fusion Model for Predicting Microvascular Invasion in Hepatocellular Carcinoma Based on Multi-MR Habitat Imaging and Machine-Learning Classifiers. Acad Radiol. 2024. PMID: 39472207. doi:10.1016/j.acra.2024.10.007
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。