Department of Radiology, The First Affiliated Hospital of USTC, Division of Life Sciences and Medicine, University of Science and Technology of China, Hefei, 230001, Anhui, China.
Department of Radiology, The first affiliated hospital of guangzhou medical university, Guangzhou, 510000, Guangdong, China.
Abdom Radiol (NY). 2024 Nov;49(11):4131-4139. doi: 10.1007/s00261-024-04437-y. Epub 2024 Jun 19.
To evaluate the diagnostic potential of radiomic analyses based on machine learning that rely on contrast-enhanced computerized tomography (CT) for categorizing ovarian sex cord-stromal tumors (SCSTs) and epithelial ovarian cancers (EOCs).
We included a total of 225 patients with 230 tumors, who were randomly divided into training and test cohorts with a ratio of 8:2. Radiomic features were extracted from each tumor and dimensionally reduced using LASSO. We used univariate and multivariate analyses to identify independent predictors from clinical features and conventional CT parameters. Clinic-radiological model, radiomics model and mixed model were constructed respectively. We evaluated model performance via analysis of the receiver operating characteristic (ROC) curve and area under ROC curves (AUCs), and compared it across models using the Delong test.
We selected a support vector machine as the best classifier. Both radiomic and mixed model achieved good classification accuracy with AUC values of 0.923/0.930 in the training cohort, and 0.879/0.909 in the test cohort. The mixed model performed significantly better than the model based on clinical radiological information, with AUC values of 0.930 versus 0.826 (p = 0.000) in the training cohort and 0.905 versus 0.788 (p = 0.042) in the test cohort.
Radiomic analysis based on CT images is a reliable and noninvasive tool for identifying SCSTs and EOCs, outperforming experience radiologists.
评估基于机器学习的放射组学分析在基于增强计算机断层扫描（CT）对卵巢性索-间质肿瘤（SCST）和上皮性卵巢癌（EOC）进行分类中的诊断潜力。
共纳入 225 例 230 个肿瘤患者，随机分为训练组和测试组，比例为 8:2。从每个肿瘤中提取放射组学特征，并使用 LASSO 进行降维。使用单变量和多变量分析从临床特征和常规 CT 参数中识别独立预测因子。分别构建临床-放射学模型、放射组学模型和混合模型。通过接收者操作特征（ROC）曲线分析和 ROC 曲线下面积（AUC）评估模型性能，并使用 Delong 检验比较模型间的差异。
我们选择支持向量机作为最佳分类器。放射组学模型和混合模型在训练组中的 AUC 值分别为 0.923/0.930，在测试组中的 AUC 值分别为 0.879/0.909，均具有良好的分类准确性。混合模型的性能明显优于基于临床放射学信息的模型，训练组中的 AUC 值分别为 0.930 与 0.826（p=0.000），测试组中的 AUC 值分别为 0.905 与 0.788（p=0.042）。
基于 CT 图像的放射组学分析是一种可靠且无创的识别 SCST 和 EOC 的工具，优于经验丰富的放射科医生。
