From the Departments of Radiology (M. Li, C.L., A.L., L.Z., Jinhui Zhou, D.Z., H.C., Y.X., J.W.) and Pathology (Jing Zhou), The Third Affiliated Hospital, Sun Yat-Sen University, No. 600 Tianhe Rd, Guangzhou, Guangdong, 510630, People's Republic of China; Medical AI Laboratory, School of Biomedical Engineering, Medical School, Shenzhen University, Shenzhen, People's Republic of China (Y.F., B.H.); Department of Radiology, The First Affiliated Hospital, Sun Yat-Sen University, Guangzhou, Guangdong, People's Republic of China (H.Y.); Department of Radiology, Sun Yat-Sen University Cancer Center, Guangzhou, People's Republic of China (M. Luo); and Department of Clinical Science, Philips Healthcare China, Shanghai, People's Republic of China (X.Y., W.D., Z.Z.).
Radiology. 2023 Aug;308(2):e230255. doi: 10.1148/radiol.230255.
Background It is unknown whether the additional information provided by multiparametric dual-energy CT (DECT) could improve the noninvasive diagnosis of the aggressive macrotrabecular-massive (MTM) subtype of hepatocellular carcinoma (HCC). Purpose To evaluate the diagnostic performance of dual-phase contrast-enhanced multiparametric DECT for predicting MTM HCC. Materials and Methods Patients with histopathologic examination-confirmed HCC who underwent contrast-enhanced DECT between June 2019 and June 2022 were retrospectively recruited from three independent centers (center 1, training and internal test data set; centers 2 and 3, external test data set). Radiologic features were visually analyzed and combined with clinical information to establish a clinical-radiologic model. Deep learning (DL) radiomics models were based on DL features and handcrafted features extracted from virtual monoenergetic images and material composition images on dual phase using binary least absolute shrinkage and selection operators. A DL radiomics nomogram was developed using multivariable logistic regression analysis. Model performance was evaluated with the area under the receiver operating characteristic curve (AUC), and the log-rank test was used to analyze recurrence-free survival. Results A total of 262 patients were included (mean age, 54 years ± 12 [SD]; 225 men [86%]; training data set, = 146 [56%]; internal test data set, = 35 [13%]; external test data set, = 81 [31%]). The DL radiomics nomogram better predicted MTM than the clinical-radiologic model (AUC = 0.91 vs 0.77, respectively, for the training set [ < .001], 0.87 vs 0.72 for the internal test data set [ = .04], and 0.89 vs 0.79 for the external test data set [ = .02]), with similar sensitivity (80% vs 87%, respectively; = .63) and higher specificity (90% vs 63%; < .001) in the external test data set. The predicted positive MTM groups based on the DL radiomics nomogram had shorter recurrence-free survival than predicted negative MTM groups in all three data sets (training data set, = .04; internal test data set, = .01; and external test data set, = .03). Conclusion A DL radiomics nomogram derived from multiparametric DECT accurately predicted the MTM subtype in patients with HCC. © RSNA, 2023 See also the editorial by Chu and Fishman in this issue.
背景 多参数双能 CT（DECT）提供的附加信息是否能提高侵袭性大条索状-巨块型（MTM）肝细胞癌（HCC）的无创诊断效果尚不清楚。
目的 评估双期对比增强多参数 DECT 对预测 HCC 中 MTM 亚型的诊断性能。
材料与方法 回顾性分析 2019 年 6 月至 2022 年 6 月期间在 3 个独立中心（中心 1：培训和内部测试数据集；中心 2 和 3：外部测试数据集）接受对比增强 DECT 检查并经组织病理学检查证实为 HCC 的患者的临床资料。对放射学特征进行视觉分析，并结合临床信息建立临床-放射学模型。基于深度学习（DL）特征和双能虚拟单能量图像和物质成分图像提取的手工特征，建立基于 DL 的放射组学模型。采用多变量逻辑回归分析建立基于 DL 的放射组学列线图。采用受试者工作特征曲线下面积（AUC）评估模型性能，采用对数秩检验分析无复发生存率。
结果 共纳入 262 例患者（平均年龄，54 岁±12[标准差]；225 例男性[86%]）。训练数据集为 146 例（56%），内部测试数据集为 35 例（13%），外部测试数据集为 81 例（31%）。与临床-放射学模型相比，DL 放射组学列线图对 MTM 的预测更好（训练集 AUC：0.91 比 0.77， <.001；内部测试数据集 AUC：0.87 比 0.72， =.04；外部测试数据集 AUC：0.89 比 0.79， =.02），且在外部测试数据集中具有相似的敏感性（分别为 80%和 87%， =.63）和更高的特异性（分别为 90%和 63%， <.001）。在所有 3 个数据集的基于 DL 放射组学列线图的预测阳性 MTM 组中，无复发生存率均短于预测阴性 MTM 组（训练数据集， <.001；内部测试数据集， =.01；外部测试数据集， =.03）。
结论 基于多参数 DECT 的 DL 放射组学列线图可准确预测 HCC 患者的 MTM 亚型。
Zotero 插件