Prediction of Microvascular Invasion in Hepatocellular Carcinoma With a Multi-Disciplinary Team-Like Radiomics Fusion Model on Dynamic Contrast-Enhanced Computed Tomography.
Prediction of Microvascular Invasion in Hepatocellular Carcinoma With a Multi-Disciplinary Team-Like Radiomics Fusion Model on Dynamic Contrast-Enhanced Computed Tomography.
复制标题
利用动态对比增强计算机断层扫描的多学科团队式放射组学融合模型预测肝细胞癌的微血管侵犯
DOI：
10.3389/fonc.2021.660629
复制
发表时间：
2021
影响因子：
4.7
通讯作者：
Jiang X
中科院分区：
文献类型：
--
作者：
Zhang W;Yang R;Liang F;Liu G;Chen A;Wu H;Lai S;Ding W;Wei X;Zhen X;Jiang X
目的 通过动态对比增强（DCE）计算机断层扫描（CT）上的无创多学科团队（MDT）类放射组学融合模型来研究肝癌的微血管侵犯（MVI）。方法 这项回顾性研究纳入了 111 例经病理证实的肝细胞癌患者，其中 MVI 阳性患者 57 例，MVI 阴性患者 54 例。在四个 DCE CT 阶段上描绘了感兴趣的目标体积 (VOI)。获得肿瘤核心的体积 (V tc ) 和七个外围肿瘤区域 (V pt ，距肿瘤边缘的不同距离 2、4、6、8、10、12 和 14 mm)。从不同时相和 VOI 组合中提取的放射组学特征通过 150 个分类模型进行交叉验证。确定最佳相位和 VOI（或组合）。通过训练/验证集的交叉验证对顶级预测模型进行排名和筛选。模型融合是一个类似于多学科咨询的过程，在前 3 个模型上进行，以生成最终模型，并在独立测试集上进行验证。结果从门静脉期 (PVP) 的 V tc +V pt(12mm) 提取的图像特征显示出主导的预测性能。 PVP 中来自 V tc +V pt(12mm) 的排名靠前的特征包括一个基于灰度大小区域矩阵 (GLSZM) 的特征和四个基于一阶的特征。模型融合在 MVI 预测中优于单一模型。加权融合方法在独立测试集上取得了最佳预测性能，AUC为0.81，准确度为78.3%，敏感性为81.8%，特异性为75%。结论从V tc +V pt(12mm)的PVP中提取的图像特征是指示MVI的最可靠的特征。类似 MDT 的放射组学融合模型是一种很有前途的工具，可以在 HCC 的 MVI 状态预测中生成准确且可重复的结果。
Objective To investigate microvascular invasion (MVI) of HCC through a noninvasive multi-disciplinary team (MDT)-like radiomics fusion model on dynamic contrast enhanced (DCE) computed tomography (CT). Methods This retrospective study included 111 patients with pathologically proven hepatocellular carcinoma, which comprised 57 MVI-positive and 54 MVI-negative patients. Target volume of interest (VOI) was delineated on four DCE CT phases. The volume of tumor core (V tc ) and seven peripheral tumor regions (V pt , with varying distances of 2, 4, 6, 8, 10, 12, and 14 mm to tumor margin) were obtained. Radiomics features extracted from different combinations of phase(s) and VOI(s) were cross-validated by 150 classification models. The best phase and VOI (or combinations) were determined. The top predictive models were ranked and screened by cross-validation on the training/validation set. The model fusion, a procedure analogous to multidisciplinary consultation, was performed on the top-3 models to generate a final model, which was validated on an independent testing set. Results Image features extracted from V tc +V pt(12mm) in the portal venous phase (PVP) showed dominant predictive performances. The top ranked features from V tc +V pt(12mm) in PVP included one gray level size zone matrix (GLSZM)-based feature and four first-order based features. Model fusion outperformed a single model in MVI prediction. The weighted fusion method achieved the best predictive performance with an AUC of 0.81, accuracy of 78.3%, sensitivity of 81.8%, and specificity of 75% on the independent testing set. Conclusion Image features extracted from the PVP with V tc +V pt(12mm) are the most reliable features indicative of MVI. The MDT-like radiomics fusion model is a promising tool to generate accurate and reproducible results in MVI status prediction in HCC.
登录
查看更多内容
DOI：
10.1158/1078-0432.ccr-16-0702
发表时间：
2016-12-01
期刊：
Clinical cancer research : an official journal of the American Association for Cancer Research
影响因子：
--
作者：
Kickingereder P;Götz M;Muschelli J;Wick A;Neuberger U;Shinohara RT;Sill M;Nowosielski M;Schlemmer HP;Radbruch A;Wick W;Bendszus M;Maier-Hein KH;Bonekamp D
通讯作者：
Bonekamp D
影响因子：
18.6
作者：
He, Qiang;Li, Xin;Zhou, Linghong
通讯作者：
Zhou, Linghong
影响因子：
16.9
作者：
Lei, Zhengqing;Li, Jun;Shen, Feng
通讯作者：
Shen, Feng
影响因子：
4.5
作者：
Bashir, Saba;Qamar, Usman;Khan, Farhan Hassan
通讯作者：
Khan, Farhan Hassan
影响因子：
--
作者：
Matsui, Osamu;Kobayashi, Satoshi;Gabata, Toshifumi
通讯作者：
Gabata, Toshifumi