Zheng Sunyi, Guo Jiapan, Langendijk Johannes A, Both Stefan, Veldhuis Raymond N J, Oudkerk Matthijs, van Ooijen Peter M A, Wijsman Robin, Sijtsema Nanna M
Department of Radiation Oncology, University of Groningen, University Medical Center Groningen, The Netherlands; Artificial Intelligence and Biomedical Image Analysis Lab, School of Engineering, Westlake University, China; Institute of Advanced Technology, Westlake Institute for Advanced Study, China.
Department of Radiation Oncology, University of Groningen, University Medical Center Groningen, The Netherlands; Bernoulli Institute for Mathematics, Computer Science and Artificial Intelligence, University of Groningen, The Netherlands.
Radiother Oncol. 2023 Mar;180:109483. doi: 10.1016/j.radonc.2023.109483. Epub 2023 Jan 20.
The aim of this study was to develop and evaluate a prediction model for 2-year overall survival (OS) in stage I-IIIA non-small cell lung cancer (NSCLC) patients who received definitive radiotherapy by considering clinical variables and image features from pre-treatment CT-scans.
NSCLC patients who received stereotactic radiotherapy were prospectively collected at the UMCG and split into a training and a hold out test set including 189 and 81 patients, respectively. External validation was performed on 228 NSCLC patients who were treated with radiation or concurrent chemoradiation at the Maastro clinic (Lung1 dataset). A hybrid model that integrated both image and clinical features was implemented using deep learning. Image features were learned from cubic patches containing lung tumours extracted from pre-treatment CT scans. Relevant clinical variables were selected by univariable and multivariable analyses.
Multivariable analysis showed that age and clinical stage were significant prognostic clinical factors for 2-year OS. Using these two clinical variables in combination with image features from pre-treatment CT scans, the hybrid model achieved a median AUC of 0.76 [95 % CI: 0.65-0.86] and 0.64 [95 % CI: 0.58-0.70] on the complete UMCG and Maastro test sets, respectively. The Kaplan-Meier survival curves showed significant separation between low and high mortality risk groups on these two test sets (log-rank test: p-value < 0.001, p-value = 0.012, respectively) CONCLUSION: We demonstrated that a hybrid model could achieve reasonable performance by utilizing both clinical and image features for 2-year OS prediction. Such a model has the potential to identify patients with high mortality risk and guide clinical decision making.
本研究的目的是通过考虑临床变量和治疗前CT扫描的图像特征，开发并评估I-IIIA期非小细胞肺癌（NSCLC）患者接受根治性放疗后的2年总生存期（OS）预测模型。
前瞻性收集在格罗宁根大学医学中心接受立体定向放疗的NSCLC患者，并分为训练集和保留测试集，分别包括189例和81例患者。对在马斯特里赫特诊所接受放疗或同步放化疗的228例NSCLC患者进行外部验证（Lung1数据集）。使用深度学习实现了一个整合图像和临床特征的混合模型。从治疗前CT扫描中提取的包含肺肿瘤的立方块中学习图像特征。通过单变量和多变量分析选择相关临床变量。
多变量分析显示，年龄和临床分期是2年OS的显著预后临床因素。结合这两个临床变量和治疗前CT扫描的图像特征，混合模型在完整的格罗宁根大学医学中心测试集和马斯特里赫特测试集上的中位AUC分别为0.76 [95% CI：0.65-0.86]和0.64 [95% CI：0.58-0.70]。Kaplan-Meier生存曲线显示，在这两个测试集上，低死亡风险组和高死亡风险组之间有显著差异（对数秩检验：p值分别<0.001和p值 = 0.012）。结论：我们证明，通过利用临床和图像特征进行2年OS预测，混合模型可以取得合理的性能。这样的模型有潜力识别高死亡风险患者并指导临床决策。
