Department of Thoracic Surgery, West China Hospital, Sichuan University, Chengdu, China.
Department of General Thoracic Surgery, Juntendo University School of Medicine, Tokyo, Japan.
Ann Surg Oncol. 2024 Aug;31(8):5011-5020. doi: 10.1245/s10434-024-15197-w. Epub 2024 Mar 23.
Noninvasively and accurately predicting subcarinal lymph node metastasis (SLNM) for patients with non-small cell lung cancer (NSCLC) remains challenging. This study was designed to develop and validate a tumor and subcarinal lymph nodes (tumor-SLNs) dual-region computed tomography (CT) radiomics model for predicting SLNM in NSCLC.
This retrospective study included NSCLC patients who underwent lung resection and SLNs dissection between January 2017 and December 2020. The radiomic features of the tumor and SLNs were extracted from preoperative CT, respectively. Ninety machine learning (ML) models were developed based on tumor region, SLNs region, and tumor-SLNs dual-region. The model performance was assessed by the area under the curve (AUC) and validated internally by fivefold cross-validation.
In total, 202 patients were included in this study. ML models based on dual-region radiomics showed good performance for SLNM prediction, with a median AUC of 0.794 (range, 0.686-0.880), which was superior to those of models based on tumor region (median AUC, 0.746; range, 0.630-0.811) and SLNs region (median AUC, 0.700; range, 0.610-0.842). The ML model, which is developed by using the naive Bayes algorithm and dual-region features, had the highest AUC of 0.880 (range of cross-validation, 0.825-0.937) among all ML models. The optimal logistic regression model was inferior to the optimal ML model for predicting SLNM, with an AUC of 0.727.
The CT radiomics showed the potential for accurately predicting SLNM in NSCLC patients. The ML model with dual-region radiomic features has better performance than the logistic regression or single-region models.
对于非小细胞肺癌（NSCLC）患者，非侵入性且准确地预测隆突下淋巴结转移（SLNM）仍然具有挑战性。本研究旨在开发和验证一种肿瘤和隆突下淋巴结（肿瘤-SLNs）双区域 CT 放射组学模型，用于预测 NSCLC 中的 SLNM。
本回顾性研究纳入了 2017 年 1 月至 2020 年 12 月期间接受肺切除术和 SLNs 解剖的 NSCLC 患者。分别从术前 CT 中提取肿瘤和 SLNs 的放射组学特征。基于肿瘤区域、SLNs 区域和肿瘤-SLNs 双区域，建立了 90 个机器学习（ML）模型。通过曲线下面积（AUC）评估模型性能，并通过五折交叉验证进行内部验证。
本研究共纳入 202 例患者。基于双区域放射组学的 ML 模型在 SLNM 预测方面表现出良好的性能，AUC 的中位数为 0.794（范围为 0.686-0.880），优于基于肿瘤区域（AUC 的中位数为 0.746；范围为 0.630-0.811）和 SLNs 区域（AUC 的中位数为 0.700；范围为 0.610-0.842）的模型。基于朴素贝叶斯算法和双区域特征的 ML 模型的 AUC 最高，为 0.880（交叉验证范围为 0.825-0.937）。用于预测 SLNM 的最佳逻辑回归模型的 AUC 低于最佳 ML 模型，为 0.727。
CT 放射组学显示出准确预测 NSCLC 患者 SLNM 的潜力。具有双区域放射组学特征的 ML 模型的性能优于逻辑回归或单区域模型。
