Department of Radiology, Sun Yat-Sen University Cancer Center, State Key Laboratory of Oncology in Southern China, No. 651 Dongfeng East Road, Guangzhou, 510060, People's Republic of China.
Department of Hepatic Surgery, First Affiliated Hospital, Sun Yat-Sen University, Guangzhou, 510080, People's Republic of China.
Radiol Med. 2024 Aug;129(8):1130-1142. doi: 10.1007/s11547-024-01845-4. Epub 2024 Jul 13.
The accurate identification of microvascular invasion (MVI) in patients with hepatocellular carcinoma (HCC) is of great clinical importance.
To develop a radiomics nomogram based on susceptibility-weighted imaging (SWI) and T2-weighted imaging (T2WI) for predicting MVI in early-stage (Barcelona Clinic Liver Cancer stages 0 and A) HCC patients.
A prospective cohort of 189 participants with HCC was included for model training and testing, and an additional 34 participants were enrolled for external validation. ITK-SNAP was used to manually segment the tumour, and PyRadiomics was used to extract radiomic features from the SWI and T2W images. Variance filtering, student's t test, least absolute shrinkage and selection operator regression and random forest (RF) were applied to select meaningful features. Four machine learning classifiers, including K-nearest neighbour, RF, logistic regression and support vector machine-based models, were established. Independent clinical and radiological risk factors were also determined to establish a clinical model. The best radiomics and clinical models were further evaluated in the validation set. In addition, a nomogram was constructed from the radiomic model and independent clinical factors. Diagnostic efficacy was evaluated by receiver operating characteristic curve analysis with fivefold cross-validation.
AFP levels greater than 400 ng/mL [odds ratio (OR) 2.50; 95% confidence interval (CI) 1.239-5.047], tumour diameter greater than 5 cm (OR 2.39; 95% CI 1.178-4.839), and absence of pseudocapsule (OR 2.053; 95% CI 1.007-4.202) were found to be independent risk factors for MVI. The areas under the curve (AUCs) of the best radiomic model were 1.000 and 0.882 in the training and testing cohorts, respectively, while those of the clinical model were 0.688 and 0.6691. In the validation set, the radiomic model achieved better diagnostic performance (AUC = 0.888) than the clinical model (AUC = 0.602). The combination of clinical factors and the radiomic model yielded a nomogram with the best diagnostic performance (AUC = 0.948).
SWI and T2WI-derived radiomic features are valuable for noninvasively and accurately identifying MVI in early-stage HCC. Furthermore, the integration of radiomics and clinical factors yielded a predictive nomogram with satisfactory diagnostic performance and potential clinical benefits.
准确识别肝细胞癌（HCC）中的微血管侵犯（MVI）具有重要的临床意义。
基于磁敏感加权成像（SWI）和 T2 加权成像（T2WI）开发一种预测早期（巴塞罗那临床肝癌分期 0 和 A）HCC 患者 MVI 的放射组学列线图。
前瞻性纳入 189 名 HCC 患者进行模型训练和测试，另外纳入 34 名患者进行外部验证。使用 ITK-SNAP 手动分割肿瘤，使用 PyRadiomics 从 SWI 和 T2W 图像中提取放射组学特征。采用方差过滤、学生 t 检验、最小绝对值收缩和选择算子回归以及随机森林（RF）来选择有意义的特征。建立了包括 K-最近邻、RF、逻辑回归和基于支持向量机的模型在内的四种机器学习分类器。还确定了独立的临床和影像学危险因素，以建立临床模型。在验证集中进一步评估最佳放射组学和临床模型。此外，从放射组学模型和独立的临床因素构建了一个列线图。使用五重交叉验证的受试者工作特征曲线分析评估诊断效能。
甲胎蛋白（AFP）水平大于 400ng/ml（优势比[OR]2.50；95%置信区间[CI]1.239-5.047）、肿瘤直径大于 5cm（OR 2.39；95%CI 1.178-4.839）和无假包膜（OR 2.053；95%CI 1.007-4.202）被发现是 MVI 的独立危险因素。最佳放射组学模型在训练和测试队列中的曲线下面积（AUC）分别为 1.000 和 0.882，而临床模型的 AUC 分别为 0.688 和 0.6691。在验证集中，放射组学模型的诊断性能优于临床模型（AUC=0.888 vs AUC=0.602）。临床因素和放射组学模型的结合产生了一个具有最佳诊断性能（AUC=0.948）的列线图。
SWI 和 T2WI 衍生的放射组学特征可用于无创且准确地识别早期 HCC 中的 MVI。此外，放射组学和临床因素的整合产生了具有令人满意的诊断性能和潜在临床益处的预测列线图。
