Wang Yueling, Fan Xuhui, Luo Zai, Wang Qingguo, Fang Yuan, Han Chao, Qiu Zhengjun, Wang Han, Huang Chen
Department of Gastrointestinal Surgery, Shanghai General Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, 200080, China.
Wuxi School of Medicine, Jiangnan University, Wuxi, 214122, Jiangsu, China.
Radiol Med. 2025 Apr 1. doi: 10.1007/s11547-025-01993-1.
Perineural invasion (PNI) is closely related to the prognosis of gastric cancer (GC) patients. However, a noninvasive tool for accurately and reliably predicting the PNI is lacking.
The clinical and imaging data of 278 patients from institution I and 39 patients from institution II were retrospectively analyzed. Radiomic features were extracted from the intratumoral and peritumoral regions. Seven independent machine learning (ML) algorithms are used to develop the models. Kaplan-Meier survival analysis and Cox proportional hazards analysis were carried out to compare 3-year and 5-year overall survival (OS) differences among various subgroups based on PNI and radiomic scores.
T stage and lymphovascular invasion (LVI) were significantly correlated with the PNI (P < 0.01). The OS of patients with different PNI status was significantly different (P < 0.05). Gradient boosting tree is the best ML algorithm. The area-under-the-curve (AUC) values of the optimal radiomics model in the internal test set and external test set were 0.901 and 0.886, respectively. After the introduction of clinical variables T stage and LVI, the performance of the model further improved in predicting the PNI of GC patients, with the AUC of 0.904 in the internal test set and 0.886 in the external test set. The difference in 3-year OS (P = 0.005) and 5-year OS (P = 0.015) among patients with varying radiomic scores was statistically significant.
Radiomics combined with intratumoral and peritumoral features is feasible for evaluating the PNI of GC patients. The prognosis of patients with different radiomic scores was statistically significant.
神经周围侵犯（PNI）与胃癌（GC）患者的预后密切相关。然而，目前缺乏一种准确可靠地预测PNI的非侵入性工具。
回顾性分析了来自机构I的278例患者和机构II的39例患者的临床及影像数据。从肿瘤内和肿瘤周围区域提取放射组学特征。使用七种独立的机器学习（ML）算法建立模型。进行Kaplan-Meier生存分析和Cox比例风险分析，以比较基于PNI和放射组学评分的不同亚组之间的3年和5年总生存（OS）差异。
T分期和淋巴管侵犯（LVI）与PNI显著相关（P < 0.01）。不同PNI状态患者的OS有显著差异（P < 0.05）。梯度提升树是最佳的ML算法。最佳放射组学模型在内部测试集和外部测试集的曲线下面积（AUC）值分别为0.901和0.886。引入临床变量T分期和LVI后，模型在预测GC患者PNI方面的性能进一步提高，内部测试集的AUC为0.904，外部测试集的AUC为0.886。不同放射组学评分患者的3年OS（P = 0.005）和5年OS（P = 0.015）差异具有统计学意义。
放射组学结合肿瘤内和肿瘤周围特征可用于评估GC患者的PNI。不同放射组学评分患者的预后具有统计学意义。
