基于动态对比增强MRI的机器学习模型用于术前鉴别肝细胞癌与混合型肝细胞-胆管细胞癌
本研究回顾性分析194例经组织病理学诊断的混合型肝细胞-胆管细胞癌(cHCC-CC,n=52)或肝细胞癌(HCC,n=142)患者的临床和MRI数据,提取高通量特征并建立放射组学模型、临床模型和融合模型。基于逻辑回归的融合模型在测试集动脉期AUC为0.878(95%CI:0.766-0.949),敏感度/特异度为0.844/0.714,优于临床模型和放射组学模型。结论认为基于DCE-MRI动脉期的融合模型较传统方法可显著提高cHCC-CC与HCC的诊断率。
要点
- 动脉期融合模型测试集AUC 0.878(95%CI:0.766-0.949),敏感度/特异度0.844/0.714。
- 临床模型测试集AUC 0.759(95%CI:0.663-0.861),放射组学模型AUC 0.838(95%CI:0.719-0.921)。
- cHCC-CC与HCC在肝硬化、肿瘤数目、形态、边缘、动脉期瘤周强化和脂质方面差异有统计学意义(p<0.05)。
核心结论
- 基于DCE-MRI动脉期的融合模型较传统方法可显著提高cHCC-CC与HCC的诊断率。
研究设计与样本
- 回顾性分析194例经组织病理学诊断的cHCC-CC(n=52)或HCC(n=142)患者的临床和MRI数据,使用ITK-SNAP软件勾画三维病灶并提取高通量特征,基于Pearson相关系数和LASSO回归进行特征选择,采用六种机器学习分类器建立放射组学模型、临床模型和融合模型。
关键影像表现/征象
- cHCC-CC与HCC患者在肝硬化、肿瘤数目、形态、边缘、动脉期瘤周强化和脂质方面差异有统计学意义(p<0.05)。
诊断标准与关键数值
- 融合模型(逻辑回归)测试集动脉期AUC为0.878(95%CI:0.766-0.949),敏感度/特异度为0.844/0.714。
- 临床模型测试集AUC为0.759(95%CI:0.663-0.861)。
- 放射组学模型测试集AUC为0.838(95%CI:0.719-0.921)。
临床应用与阅片要点
- 基于DCE-MRI动脉期的融合模型可能有助于术前鉴别cHCC-CC与HCC。
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
AIM: To establish a machine-learning model based on dynamic contrast-enhanced (DCE) magnetic resonance imaging (MRI) to differentiate combined hepatocellular-cholangiocarcinoma (cHCC-CC) from hepatocellular carcinoma (HCC) before surgery.
MATERIALS AND METHODS: Clinical and MRI data of 194 patients with histopathologically diagnosed cHCC-CC (n=52) or HCC (n=142) were analysed retrospectively. ITK-SNAP software was used to delineate three-dimensional (3D) lesions and extract high-throughput features. Feature selection was carried out based on Pearson's correlation coefficient and least absolute shrinkage and selection operator (LASSO) regression analysis. A radiomics model (radiomics features), a clinical model (i.e., clinical-image features), and a fusion model (i.e., radiomics features + clinical-image features) were established using six machine-learning classifiers. The performance of each model in distinguishing between cHCC-CC and HCC was evaluated with the receiver operating characteristic (ROC) curve, the area under the ROC curve (AUC), sensitivity, and specificity.
RESULTS: Significant differences in liver cirrhosis, tumour number, shape, edge, peritumoural enhancement in the arterial phase, and lipid were identified between cHCC-CC and HCC patients (p<0.05). The AUC of the fusion model based on logistic regression was 0.878 (95% CI: 0.766-0.949) in the arterial phase in the test set, and the sensitivity/specificity was 0.844/0.714; however, the AUC of the clinical and radiomics models was 0.759 (95% CI: 0.663-0.861) and 0.838 (95% CI: 0.719-0.921) in the test set, respectively.
CONCLUSION: The fusion model based on DCE-MRI in the arterial phase can significantly improve the diagnostic rate of cHCC-CC and HCC as compared with conventional approaches.
引用
- Deng X, Liao Z. A machine-learning model based on dynamic contrast-enhanced MRI for preoperative differentiation between hepatocellular carcinoma and combined hepatocellular-cholangiocarcinoma. Clin Radiol. 2024. PMID: 38413354. doi:10.1016/j.crad.2024.02.001
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。