Department of Radiology, The First Affiliated Hospital of Zhejiang Chinese Medical University (Zhejiang Provincial Hospital of Chinese Medicine), Hangzhou, Zhejiang, China; Department of Radiology, Tongde Hospital of Zhejiang Province, Hangzhou, Zhejiang, China.
Department of Radiology, The First Affiliated Hospital of Bengbu Medical University, Bengbu, Anhui, China.
Acad Radiol. 2024 Dec;31(12):5237-5247. doi: 10.1016/j.acra.2024.05.010. Epub 2024 Jun 6.
Lymphovascular invasion (LVI) plays a significant role in precise treatments of non-small cell lung cancer (NSCLC). This study aims to build a non-invasive LVI prediction diagnosis model by combining preoperative CT images with deep learning technology.
This retrospective observational study included a series of consecutive patients who underwent surgical resection for non-small cell lung cancer (NSCLC) and received pathologically confirmed diagnoses. The cohort was randomly divided into a training group comprising 70 % of the patients and a validation group comprising the remaining 30 %. Four distinct deep convolutional neural network (DCNN) prediction models were developed, incorporating different combination of two-dimensional (2D) and three-dimensional (3D) CT imaging features as well as clinical-radiological data. The predictive capabilities of the models were evaluated by receiver operating characteristic curves (AUC) values and confusion matrices. The Delong test was utilized to compare the predictive performance among the different models.
A total of 3034 patients with NSCLC were recruited in this study including 106 LVI+ patients. In the validation cohort, the Dual-head Res2Net_3D23F model achieved the highest AUC of 0.869, closely followed by the models of Dual-head Res2Net_3D3F (AUC, 0.868), Dual-head Res2Net_3D (AUC, 0.867), and EfficientNet-B0_2D (AUC, 0.857). There was no significant difference observed in the performance of the EfficientNet-B0_2D model when compared to the Dual-head Res2Net_3D3F and Dual-head Res2Net_3D23F.
Findings of this study suggest that utilizing deep convolutional neural network is a feasible approach for predicting pathological LVI in patients with NSCLC.
淋巴血管侵犯（LVI）在非小细胞肺癌（NSCLC）的精准治疗中起着重要作用。本研究旨在结合术前 CT 图像和深度学习技术，构建一种非侵入性的 LVI 预测诊断模型。
本回顾性观察性研究纳入了一系列接受手术切除且经病理证实为 NSCLC 的连续患者。该队列被随机分为训练组（包含 70%的患者）和验证组（包含剩余的 30%患者）。开发了四个不同的深度卷积神经网络（DCNN）预测模型，结合了二维（2D）和三维（3D）CT 成像特征以及临床影像学数据的不同组合。通过受试者工作特征曲线（AUC）值和混淆矩阵评估模型的预测能力。采用 Delong 检验比较不同模型的预测性能。
本研究共纳入 3034 例 NSCLC 患者，其中 106 例为 LVI+患者。在验证队列中，Dual-head Res2Net_3D23F 模型的 AUC 最高，为 0.869，紧随其后的是 Dual-head Res2Net_3D3F 模型（AUC，0.868）、Dual-head Res2Net_3D 模型（AUC，0.867）和 EfficientNet-B0_2D 模型（AUC，0.857）。与 Dual-head Res2Net_3D3F 和 Dual-head Res2Net_3D23F 相比，EfficientNet-B0_2D 模型的性能没有显著差异。
本研究结果表明，利用深度卷积神经网络是预测 NSCLC 患者病理 LVI 的一种可行方法。
