Ouyang Ming-Li, Zheng Rui-Xuan, Wang Yi-Ran, Zuo Zi-Yi, Gu Liu-Dan, Tian Yu-Qian, Wei Yu-Guo, Huang Xiao-Ying, Tang Kun, Wang Liang-Xing
Key Laboratory of Heart and Lung, Division of Pulmonary Medicine, The First Affiliated Hospital of Wenzhou Medical University, Wenzhou, China.
Department of Medical Engineering, The First Affiliated Hospital of Wenzhou Medical University, Wenzhou, China.
Front Oncol. 2022 Jul 7;12:915871. doi: 10.3389/fonc.2022.915871. eCollection 2022.
The aim of this work was to determine the feasibility of using a deep learning approach to predict occult lymph node metastasis (OLM) based on preoperative FDG-PET/CT images in patients with clinical node-negative (cN0) lung adenocarcinoma.
Dataset 1 (for training and internal validation) included 376 consecutive patients with cN0 lung adenocarcinoma from our hospital between May 2012 and May 2021. Dataset 2 (for prospective test) used 58 consecutive patients with cN0 lung adenocarcinoma from June 2021 to February 2022 at the same center. Three deep learning models: PET alone, CT alone, and combined model, were developed for the prediction of OLM. The performance of the models was evaluated on internal validation and prospective test in terms of accuracy, sensitivity, specificity, and areas under the receiver operating characteristic curve (AUCs).
The combined model incorporating PET and CT showed the best performance, achieved an AUC of 0.81 [95% confidence interval (CI): 0.61, 1.00] in the prediction of OLM in internal validation set (n = 60) and an AUC of 0.87 (95% CI: 0.75, 0.99) in the prospective test set (n = 58). The model achieved 87.50% sensitivity, 80.00% specificity, and 81.00% accuracy in the internal validation set and achieved 75.00% sensitivity, 88.46% specificity, and 86.60% accuracy in the prospective test set.
This study presented a deep learning approach to enable the prediction of occult nodal involvement based on the PET/CT images before surgery in cN0 lung adenocarcinoma, which would help clinicians select patients who would be suitable for sublobar resection.
本研究旨在确定基于术前氟代脱氧葡萄糖正电子发射断层扫描/计算机断层扫描（FDG-PET/CT）图像，采用深度学习方法预测临床淋巴结阴性（cN0）肺腺癌患者隐匿性淋巴结转移（OLM）的可行性。
数据集1（用于训练和内部验证）包括2012年5月至2021年5月期间我院376例连续的cN0肺腺癌患者。数据集2（用于前瞻性测试）采用了同一中心2021年6月至2022年2月期间58例连续的cN0肺腺癌患者。开发了三种深度学习模型：单独PET、单独CT以及联合模型，用于预测OLM。在内部验证和前瞻性测试中，根据准确性、敏感性、特异性以及受试者操作特征曲线下面积（AUC）对模型性能进行评估。
结合PET和CT的联合模型表现最佳，在内部验证集（n = 60）中预测OLM时的AUC为0.81 [95%置信区间（CI）：0.61，1.00]，在前瞻性测试集（n = 58）中的AUC为0.87（95% CI：0.75，0.99）。该模型在内部验证集中的敏感性为87.50%，特异性为80.00%，准确性为81.00%；在前瞻性测试集中的敏感性为75.00%，特异性为88.46%，准确性为86.60%。
本研究提出了一种深度学习方法，能够基于cN0肺腺癌术前PET/CT图像预测隐匿性淋巴结受累情况，这将有助于临床医生选择适合亚肺叶切除的患者。
