Department of Radiation Oncology, Stanford University School of Medicine, Stanford California, USA.
Department of Gastric Surgery, Sun Yat-sen University Cancer Centre, Guangzhou, China.
Br J Surg. 2021 May 27;108(5):542-549. doi: 10.1002/bjs.11928.
Lymph node metastasis (LNM) in gastric cancer is a prognostic factor and has implications for the extent of lymph node dissection. The lymphatic drainage of the stomach involves multiple nodal stations with different risks of metastases. The aim of this study was to develop a deep learning system for predicting LNMs in multiple nodal stations based on preoperative CT images in patients with gastric cancer.
Preoperative CT images from patients who underwent gastrectomy with lymph node dissection at two medical centres were analysed retrospectively. Using a discovery patient cohort, a system of deep convolutional neural networks was developed to predict pathologically confirmed LNMs at 11 regional nodal stations. To gain understanding about the networks' prediction ability, gradient-weighted class activation mapping for visualization was assessed. The performance was tested in an external cohort of patients by analysis of area under the receiver operating characteristic (ROC) curves (AUC), sensitivity and specificity.
The discovery and external cohorts included 1172 and 527 patients respectively. The deep learning system demonstrated excellent prediction accuracy in the external validation cohort, with a median AUC of 0·876 (range 0·856-0·893), sensitivity of 0·743 (0·551-0·859) and specificity of 0·936 (0·672-0·966) for 11 nodal stations. The imaging models substantially outperformed clinicopathological variables for predicting LNMs (median AUC 0·652, range 0·571-0·763). By visualizing nearly 19 000 subnetworks, imaging features related to intratumoral heterogeneity and the invasive front were found to be most useful for predicting LNMs.
A deep learning system for the prediction of LNMs was developed based on preoperative CT images of gastric cancer. The models require further validation but may be used to inform prognosis and guide individualized surgical treatment.
胃癌的淋巴结转移（LNM）是一个预后因素，与淋巴结清扫的范围有关。胃的淋巴引流涉及多个淋巴结站，其转移风险不同。本研究旨在开发一种基于术前 CT 图像预测胃癌多个淋巴结站 LNM 的深度学习系统。
回顾性分析了在两个医学中心接受胃切除术和淋巴结清扫术的患者的术前 CT 图像。使用发现患者队列，开发了一种深度卷积神经网络系统，以预测 11 个区域性淋巴结站的病理证实的 LNM。为了了解网络的预测能力，评估了用于可视化的梯度加权类激活映射。通过分析受试者工作特征（ROC）曲线下面积（AUC）、敏感性和特异性，在外部患者队列中测试性能。
发现队列和外部队列分别纳入了 1172 例和 527 例患者。深度学习系统在外部验证队列中表现出优异的预测准确性，中位数 AUC 为 0.876（范围 0.856-0.893），敏感性为 0.743（0.551-0.859），特异性为 0.936（0.672-0.966），适用于 11 个淋巴结站。成像模型在预测 LNM 方面明显优于临床病理变量（中位数 AUC 为 0.652，范围 0.571-0.763）。通过可视化近 19000 个子网络，发现与肿瘤内异质性和侵袭前沿相关的影像学特征对预测 LNM 最有用。
基于胃癌术前 CT 图像开发了一种预测 LNM 的深度学习系统。这些模型需要进一步验证，但可能用于提供预后信息并指导个体化手术治疗。
