Ai Jiangshan, Wang Zhaofeng, Ai Shiwen, Li Hengyan, Gao Huijiang, Shi Guodong, Hu Shiyu, Liu Lin, Zhao Lianzheng, Wei Yucheng
Department of Thoracic Surgery, The Affiliated Hospital of Qingdao University, Qingdao, China.
Department of Thoracic Surgery, Affiliated Hospital of Jining Medical University, Jining, China.
Acad Radiol. 2025 Jan;32(1):506-517. doi: 10.1016/j.acra.2024.07.037. Epub 2024 Aug 5.
The preoperative diagnosis of small prevascular mediastinal nodules (SPMNs) presents a challenge, often leading to unnecessary surgical interventions. Our objective was to develop a nomogram based on preoperative CT-radiomics features, serving as a non-invasive diagnostic tool for SPMNs.
Patients with surgically resected SPMNs from two medical centers between January 2018 and December 2022 were retrospectively reviewed. Radiomics features were extracted and screened from preoperative CT images. Logistic regression was employed to establish clinical, radiomics, and hybrid models for differentiating thymic epithelial tumors (TETs) from cysts. The performance of these models was validated in both internal and external test sets by area under the receiver operating characteristic curve (AUC), while also comparing their diagnostic capability with human experts.
The study enrolled a total of 363 patients (median age, 53 years [IQR:45-59 years]; 175 [48.2%] males) for model development and validation, including 136 TETs and 227 cysts. Lesions' enhancement status, shape, calcification, and rad-score were identified as independent factors for distinction. The hybrid model demonstrated superior diagnostic performance compared to other models and human experts, with an AUC of 0.95 (95% CI:0.92-0.98), 0.94 (95% CI:0.89-0.99), and 0.93 (95% CI:0.83-1.00) in the training set, internal test set, and external test set respectively. The calibration curve of the model demonstrated excellent fit, while decision curve analysis underscored its clinical value.
The radiomics-based nomogram effectively discriminates between the most prevalent types of SPMNs, namely TETs and cysts, thus presenting a promising tool for treatment guidance.
前纵隔小肿块（SPMNs）的术前诊断具有挑战性，常常导致不必要的手术干预。我们的目标是基于术前CT影像组学特征开发一种列线图，作为SPMNs的非侵入性诊断工具。
回顾性分析2018年1月至2022年12月期间在两个医疗中心接受手术切除的SPMNs患者。从术前CT图像中提取并筛选影像组学特征。采用逻辑回归建立区分胸腺上皮肿瘤（TETs）和囊肿的临床、影像组学及混合模型。通过受试者操作特征曲线下面积（AUC）在内部和外部测试集中验证这些模型的性能，同时将它们的诊断能力与人类专家进行比较。
该研究共纳入363例患者（中位年龄53岁[四分位间距：45 - 59岁]；175例[48.2%]为男性）用于模型开发和验证，包括136例TETs和227例囊肿。病变的强化状态、形状、钙化和rad评分被确定为区分的独立因素。混合模型在诊断性能上优于其他模型和人类专家，在训练集、内部测试集和外部测试集中的AUC分别为0.95（95%CI：0.92 - 0.98）、0.94（95%CI：0.89 - 0.99）和0.93（95%CI：0.83 - 1.00）。模型的校准曲线显示拟合良好，决策曲线分析强调了其临床价值。
基于影像组学的列线图能有效区分最常见的SPMNs类型，即TETs和囊肿，因此是一种有前景的治疗指导工具。
