Zhang Li, Li Hailin, Zhao Shaohong, Tao Xuemin, Li Meng, Yang Shouxin, Zhou Lina, Liu Mengwen, Zhang Xue, Dong Di, Tian Jie, Wu Ning
Department of Diagnostic Radiology, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China.
Beijing Advanced Innovation Center for Big Data-Based Precision Medicine, School of Engineering Medicine, Beihang University, Beijing, China.
J Natl Cancer Cent. 2024 Feb 1;4(3):233-240. doi: 10.1016/j.jncc.2024.01.005. eCollection 2024 Sep.
To develop a deep learning model to predict lymph node (LN) status in clinical stage IA lung adenocarcinoma patients.
This diagnostic study included 1,009 patients with pathologically confirmed clinical stage T1N0M0 lung adenocarcinoma from two independent datasets (699 from Cancer Hospital of Chinese Academy of Medical Sciences and 310 from PLA General Hospital) between January 2005 and December 2019. The Cancer Hospital dataset was randomly split into a training cohort (559 patients) and a validation cohort (140 patients) to train and tune a deep learning model based on a deep residual network (ResNet). The PLA Hospital dataset was used as a testing cohort to evaluate the generalization ability of the model. Thoracic radiologists manually segmented tumors and interpreted high-resolution computed tomography (HRCT) features for the model. The predictive performance was assessed by area under the curves (AUCs), accuracy, precision, recall, and F1 score. Subgroup analysis was performed to evaluate the potential bias of the study population.
A total of 1,009 patients were included in this study; 409 (40.5%) were male and 600 (59.5%) were female. The median age was 57.0 years (inter-quartile range, IQR: 50.0-64.0). The deep learning model achieved AUCs of 0.906 (95% CI: 0.873-0.938) and 0.893 (95% CI: 0.857-0.930) for predicting pN0 disease in the testing cohort and a non-pure ground glass nodule (non-pGGN) testing cohort, respectively. No significant difference was detected between the testing cohort and the non-pGGN testing cohort ( = 0.622). The precisions of this model for predicting pN0 disease were 0.979 (95% CI: 0.963-0.995) and 0.983 (95% CI: 0.967-0.998) in the testing cohort and the non-pGGN testing cohort, respectively. The deep learning model achieved AUCs of 0.848 (95% CI: 0.798-0.898) and 0.831 (95% CI: 0.776-0.887) for predicting pN2 disease in the testing cohort and the non-pGGN testing cohort, respectively. No significant difference was detected between the testing cohort and the non-pGGN testing cohort ( = 0.657). The recalls of this model for predicting pN2 disease were 0.903 (95% CI: 0.870-0.936) and 0.931 (95% CI: 0.901-0.961) in the testing cohort and the non-pGGN testing cohort, respectively.
The superior performance of the deep learning model will help to target the extension of lymph node dissection and reduce the ineffective lymph node dissection in early-stage lung adenocarcinoma patients.
开发一种深度学习模型，用于预测临床IA期肺腺癌患者的淋巴结（LN）状态。
这项诊断性研究纳入了2005年1月至2019年12月期间来自两个独立数据集（中国医学科学院肿瘤医院699例，解放军总医院310例）的1009例经病理确诊的临床T1N0M0期肺腺癌患者。肿瘤医院数据集被随机分为训练队列（559例患者）和验证队列（140例患者），以基于深度残差网络（ResNet）训练和调整深度学习模型。解放军总医院数据集用作测试队列，以评估该模型的泛化能力。胸科放射科医生为该模型手动分割肿瘤并解读高分辨率计算机断层扫描（HRCT）特征。通过曲线下面积（AUC）、准确性、精确率、召回率和F1分数评估预测性能。进行亚组分析以评估研究人群的潜在偏倚。
本研究共纳入1009例患者；男性409例（40.5%），女性600例（59.5%）。中位年龄为57.0岁（四分位间距，IQR：50.0 - 64.0）。深度学习模型在测试队列和非纯磨玻璃结节（non-pGGN）测试队列中预测pN0疾病的AUC分别为0.906（95%CI：0.873 - 0.938）和0.893（95%CI：0.857 - 0.930）。测试队列和non-pGGN测试队列之间未检测到显著差异（ = 0.622）。该模型在测试队列和non-pGGN测试队列中预测pN0疾病的精确率分别为0.979（95%CI：0.963 - 0.995）和0.983（95%CI：0.967 - 0.998）。深度学习模型在测试队列和non-pGGN测试队列中预测pN2疾病的AUC分别为0.848（95%CI：0.798 - 0.898）和0.831（95%CI：0.776 - 0.887）。测试队列和non-pGGN测试队列之间未检测到显著差异（ = 0.657）。该模型在测试队列和non-pGGN测试队列中预测pN2疾病的召回率分别为0.903（95%CI：0.870 - 0.936）和0.931（95%CI：0.901 - 0.961）。
深度学习模型的卓越性能将有助于确定淋巴结清扫范围，减少早期肺腺癌患者无效的淋巴结清扫。
