Department of Radiology, Jiangsu Key Laboratory of Molecular and Functional Imaging, Zhongda Hospital, Medical School of Southeast University, Nanjing, China.
Department of Pathology, Zhongda Hospital, Medical School of Southeast University, Nanjing, China.
J Magn Reson Imaging. 2021 Aug;54(2):526-536. doi: 10.1002/jmri.27575. Epub 2021 Feb 23.
BACKGROUND: Computed tomography (CT) and magnetic resonance imaging (MRI) are both capable of predicting microvascular invasion (MVI) in hepatocellular carcinoma (HCC). However, which modality is better is unknown. PURPOSE: To intraindividually compare CT and MRI for predicting MVI in solitary HCC and investigate the added value of radiomics analyses. STUDY TYPE: Retrospective. SUBJECTS: Included were 402 consecutive patients with HCC (training set:validation set = 300:102). FIELD STRENGTH/SEQUENCE: T2-weighted, diffusion-weighted, and contrast-enhanced T1-weighted imaging MRI at 3.0T and contrast-enhanced CT. ASSESSMENT: CT- and MR-based radiomics signatures (RS) were constructed using the least absolute shrinkage and selection operator regression. CT- and MR-based radiologic (R) and radiologic-radiomics (RR) models were developed by univariate and multivariate logistic regression. The performance of the RS/models was compared between two modalities. To investigate the added value of RS, the performance of the R models was compared with the RR models in HCC of all sizes and 2-5 cm in size. STATISTICAL TESTS: Model performance was quantified by the area under the receiver operating characteristic curve (AUC) and compared using the Delong test. RESULTS: Histopathologic MVI was identified in 161 patients (training set:validation set = 130:31). MRI-based RS/models tended to have a marginally higher AUC than CT-based RS/models (AUCs of CT vs. MRI, P: RS, 0.801 vs. 0.804, 0.96; R model, 0.809 vs. 0.832, 0.09; RR model, 0.835 vs. 0.872, 0.54). The improvement of RR models over R models in all sizes was not significant (P = 0.21 at CT and 0.09 at MRI), whereas the improvement in 2-5 cm was significant at MRI (P < 0.05) but not at CT (P = 0.16). DATA CONCLUSION: CT and MRI had a comparable predictive performance for MVI in solitary HCC. The RS of MRI only had significant added value for predicting MVI in HCC of 2-5 cm. LEVEL OF EVIDENCE: 3 TECHNICAL EFFICACY: Stage 2.
背景：计算机断层扫描（CT）和磁共振成像（MRI）均能预测肝细胞癌（HCC）的微血管侵犯（MVI）。然而，哪种方法更好尚不清楚。
目的：旨在对 CT 和 MRI 预测单发 HCC 中的 MVI 进行个体内比较，并探讨影像组学分析的附加价值。
研究类型：回顾性。
受试者：纳入了 402 例连续 HCC 患者（训练集：验证集=300：102）。
磁场强度/序列：3.0T 下的 T2 加权、弥散加权和对比增强 T1 加权成像 MRI 以及对比增强 CT。
评估：使用最小绝对收缩和选择算子回归构建 CT 和 MRI 基于的影像组学特征（RS）。通过单变量和多变量逻辑回归构建 CT 和 MRI 基于的放射学（R）和放射学-影像组学（RR）模型。比较两种模态之间 RS/模型的性能。为了研究 RS 的附加价值，比较了大小为所有 HCC 和 2-5cm 的 HCC 的 R 模型与 RR 模型的性能。
统计检验：通过受试者工作特征曲线下的面积（AUC）定量评估模型性能，并使用 Delong 检验进行比较。
结果：在 161 例患者（训练集：验证集=130：31）中发现了组织病理学 MVI。MRI 基于的 RS/模型的 AUC 倾向于略高于 CT 基于的 RS/模型（CT 与 MRI 的 AUC，P：RS，0.801 与 0.804，0.96；R 模型，0.809 与 0.832，0.09；RR 模型，0.835 与 0.872，0.54）。RR 模型相对于 R 模型在所有大小中的改进不显著（CT 时为 P=0.21，MRI 时为 P=0.09），而在 2-5cm 时的改进在 MRI 中显著（P<0.05），但在 CT 中不显著（P=0.16）。
数据结论：CT 和 MRI 对单发 HCC 中的 MVI 具有相当的预测性能。MRI 的 RS 仅对预测 2-5cm HCC 的 MVI 具有显著的附加价值。
证据水平：3 级 技术功效：2 级
World J Gastroenterol. 2021-5-7
Front Oncol. 2025-2-6
World J Gastrointest Oncol. 2025-1-15
Zotero 插件