Araujo-Filho Jose Arimateia Batista, Mayoral Maria, Zheng Junting, Tan Kay See, Gibbs Peter, Shepherd Annemarie Fernandes, Rimner Andreas, Simone Charles B, Riely Gregory, Huang James, Ginsberg Michelle S
Department of Radiology, Memorial Sloan Kettering Cancer Center, New York, New York; Department of Radiology, Hospital Sirio-Libanes, São Paulo, Brazil.
Diagnostic Imaging Center, Hospital Clínic of Barcelona, University of Barcelona, Barcelona, Catalonia, Spain.
Ann Thorac Surg. 2022 Mar;113(3):957-965. doi: 10.1016/j.athoracsur.2021.03.084. Epub 2021 Apr 9.
To explore the performance of a computed tomography based radiomics model in the preoperative prediction of resectability status and TNM staging in thymic epithelial tumors.
We reviewed the last preoperative computed tomography scan of patients with thymic epithelial tumors prior to resection and pathology evaluation at our institution between February 2008 and June 2019. A total of 101 quantitative features were extracted and a radiomics model was trained using elastic net penalized logistic regressions for each aim. In the set-aside testing sets, discriminating performance of each model was assessed with area under receiver operating characteristic curve.
Our final population consisted of 243 patients with: 153 (87%) thymomas, 23 (9%) thymic carcinomas, and 9 (4%) thymic carcinoids. Incomplete resections (R1 or R2) occurred in 38 (16%) patients, and 67 (28%) patients had more advanced stage tumors (stage III or IV). In the set-aside testing sets, the radiomics model achieved good performance in preoperatively predicting incomplete resections (area under receiver operating characteristic curve: 0.80) and advanced stage tumors (area under receiver operating characteristic curve: 0.70).
Our computed tomography radiomics model achieved good performance to predict resectability status and staging in thymic epithelial tumors, suggesting a potential value for the evaluation of radiomic features in the preoperative prediction of surgical outcomes in thymic malignancies.
探讨基于计算机断层扫描的影像组学模型在胸腺上皮肿瘤术前预测可切除性状态和TNM分期中的表现。
我们回顾了2008年2月至2019年6月期间在本机构接受手术切除和病理评估的胸腺上皮肿瘤患者的最后一次术前计算机断层扫描。共提取了101个定量特征，并针对每个目标使用弹性网惩罚逻辑回归训练了影像组学模型。在预留测试集中，使用受试者操作特征曲线下面积评估每个模型的鉴别性能。
我们的最终研究人群包括243例患者：153例（87%）胸腺瘤、23例（9%）胸腺癌和9例（4%）胸腺类癌。38例（16%）患者发生不完全切除（R1或R2），67例（28%）患者患有更晚期肿瘤（III期或IV期）。在预留测试集中，影像组学模型在术前预测不完全切除（受试者操作特征曲线下面积：0.80）和晚期肿瘤（受试者操作特征曲线下面积：0.70）方面表现良好。
我们的计算机断层扫描影像组学模型在预测胸腺上皮肿瘤的可切除性状态和分期方面表现良好，提示影像组学特征在胸腺恶性肿瘤手术结果术前预测中的潜在评估价值。
