Tian Dong, Yan Hao-Ji, Shiiya Haruhiko, Sato Masaaki, Shinozaki-Ushiku Aya, Nakajima Jun
Department of Thoracic Surgery, The University of Tokyo Graduate School of Medicine, Tokyo, Japan; Heart and Lung Transplant Research Laboratory, Affiliated Hospital of North Sichuan Medical College, Nanchong, China; Department of Thoracic Surgery, West China Hospital, Sichuan University, Chengdu, China.
School of Medical Imaging, North Sichuan Medical College, Nanchong, China.
J Thorac Cardiovasc Surg. 2023 Feb;165(2):502-516.e9. doi: 10.1016/j.jtcvs.2022.05.046. Epub 2022 Jul 20.
For patients with thymic epithelial tumors, accurately predicting clinicopathological outcomes remains challenging. We aimed to investigate the performance of machine learning-based radiomic computed tomography phenotyping for predicting pathological (World Health Organization [WHO] type and TNM stage) and survival outcomes (overall and progression-free survival) in patients with thymic epithelial tumors.
This retrospective study included patients with thymic epithelial tumors between January 2001 and January 2022. The radiomic features were extracted from preoperative unenhanced computed tomography images. After strict feature selection, random forest and random survival forest models were fitted to predict pathological and survival outcomes, respectively. The model performance was assessed by the area under the curve (AUC) and validated internally by the bootstrap method.
In total, 124 patients with a median age of 61 years were included. The radiomics random forest models of WHO type and TNM stage showed satisfactory performance with an AUC of 0.898 (95% CI, 0.753-1.000) and an AUC of 0.766 (95% CI, 0.642-0.886). For overall survival and progression-free survival prediction, the radiomics random survival forest models showed good performance (integrated AUCs, 0.923; 95% CI, 0.691-1.000 and 0.702; 95% CI, 0.513-0.875, respectively), and the integrated AUCs increased to 0.935 (95% CI, 0.705-1.000) and 0.811 (95% CI, 0.647-0.942), respectively, when combined with clinicopathological features.
Machine learning-based radiomic computed tomography phenotyping might allow for the satisfactory prediction of pathological and survival outcomes and further improve prognostic performance when integrated with clinicopathological features in patients with thymic epithelial tumors.
对于胸腺上皮肿瘤患者，准确预测临床病理结果仍然具有挑战性。我们旨在研究基于机器学习的放射组学计算机断层扫描表型分析在预测胸腺上皮肿瘤患者的病理（世界卫生组织[WHO]分型和TNM分期）及生存结果（总生存期和无进展生存期）方面的性能。
这项回顾性研究纳入了2001年1月至2022年1月期间患有胸腺上皮肿瘤的患者。从术前未增强的计算机断层扫描图像中提取放射组学特征。经过严格的特征选择后，分别拟合随机森林和随机生存森林模型来预测病理和生存结果。通过曲线下面积（AUC）评估模型性能，并采用自助法进行内部验证。
共纳入124例患者，中位年龄为61岁。WHO分型和TNM分期的放射组学随机森林模型表现出令人满意的性能，AUC分别为0.898（95%CI，0.753 - 1.000）和0.766（95%CI，0.642 - 0.886）。对于总生存期和无进展生存期预测，放射组学随机生存森林模型表现良好（综合AUC分别为0.923；95%CI，0.691 - 1.000和0.702；95%CI，0.513 - 0.875），当与临床病理特征相结合时，综合AUC分别提高到0.935（95%CI，0.705 - 1.000）和0.811（95%CI，0.647 - 0.942）。
基于机器学习的放射组学计算机断层扫描表型分析可能能够令人满意地预测胸腺上皮肿瘤患者的病理和生存结果，并且在与临床病理特征相结合时可进一步提高预后性能。
