Liu Yifei, Luo Chao, Wu Yongshun, Zhou Shumin, Ruan Guangying, Li Haojiang, Chen Wanyuan, Lin Yi, Liu Lizhi, Quan Tingting, He Xiaodong
Department of Radiology, Sun Yat-sen University Cancer Center, State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, 651 Dongfeng Road East, Guangzhou 510060, Guangdong, China (Y.L., C.L., S.Z., G.R., H.L., L.L., T.Q.).
Department of Radiology, Guangzhou First People's Hospital, Guangzhou 511457, Guangdong, China (Y.W.).
Acad Radiol. 2025 Jun;32(6):3258-3268. doi: 10.1016/j.acra.2025.01.010. Epub 2025 Feb 18.
Accurately distinguishing histological subtypes and risk categorization of thymomas is difficult. To differentiate the histologic risk categories of thymomas, we developed a combined radiomics model based on non-enhanced and contrast-enhanced computed tomography (CT) radiomics, clinical, and semantic features.
In total, 360 patients with pathologically-confirmed thymomas who underwent CT examinations were retrospectively recruited from three centers. Patients were classified using improved pathological classification criteria as low-risk (LRT: types A and AB) or high-risk (HRT: types B1, B2, and B3). The training and external validation sets comprised 274 (from centers 1 and 2) and 86 (center 3) patients, respectively. A clinical-semantic model was built using clinical and semantic variables. Radiomics features were filtered using intraclass correlation coefficients, correlation analysis, and univariate logistic regression. An optimal radiomics model (Rad_score) was constructed using the AutoML algorithm, while a combined model was constructed by integrating Rad_score with clinical and semantic features. The predictive and clinical performances of the models were evaluated using receiver operating characteristic/calibration curve analyses and decision-curve analysis, respectively.
Radiomics and combined models (area under curve: training set, 0.867 and 0.884; external validation set, 0.792 and 0.766, respectively) exhibited performance superior to the clinical-semantic model. The combined model had higher accuracy than the radiomics model (0.79 vs. 0.78, p<0.001) in the entire cohort. The original_firstorder_median of venous phase had the highest relative importance among features in the radiomics model.
Radiomics and combined radiomics models may serve as noninvasive discrimination tools to differentiate thymoma risk classifications.
准确区分胸腺瘤的组织学亚型和风险分类具有挑战性。为了区分胸腺瘤的组织学风险类别，我们基于平扫和增强计算机断层扫描（CT）的影像组学、临床及语义特征开发了一种联合影像组学模型。
从三个中心回顾性纳入了360例经病理证实且接受过CT检查的胸腺瘤患者。采用改良的病理分类标准将患者分为低风险（LRT：A型和AB型）或高风险（HRT：B1型、B2型和B3型）。训练集和外部验证集分别包含274例（来自中心1和2）和86例（中心3）患者。使用临床和语义变量构建临床语义模型。采用组内相关系数、相关性分析和单因素逻辑回归对影像组学特征进行筛选。使用自动机器学习算法构建最佳影像组学模型（Rad_score），并通过将Rad_score与临床和语义特征相结合构建联合模型。分别采用受试者操作特征/校准曲线分析和决策曲线分析评估模型的预测性能和临床性能。
影像组学模型和联合模型（曲线下面积：训练集分别为0.867和0.884；外部验证集分别为0.792和0.766）的性能优于临床语义模型。在整个队列中，联合模型的准确性高于影像组学模型（0.79对0.78, p<0.001）。静脉期的original_firstorder_median在影像组学模型的特征中相对重要性最高。
影像组学模型和联合影像组学模型可作为区分胸腺瘤风险分类的非侵入性鉴别工具。
