外淋巴软组织转移（ESTM）的潜在预后价值已经通过对胃癌（GC）的增加研究得到确定。然而，ESTM的黄金标准是通过手术后的病理检查确定的，目前尚无术前评估ESTM的方法。本多中心研究旨在开发一种基于深度学习的放射学模型，以术前识别ESTM并评估其预后价值。共有959例GC患者纳入两个中心，并分为训练组（N = 551）和测试组（N = 236）进行ESTM评估。此外，还包括外部生存队列（N = 172）进行预后分析。基于临床特征和多相计算机断层扫描（CT）图像建立了四种模型，用于术前识别ESTM，包括深度学习模型、手工制作的放射学模型、临床模型和组合模型。使用C指数、决策曲线和校准曲线评估模型的性能。进行生存分析以探索对总生存期（OS）的分层能力。组合模型在ESTM的鉴别方面表现良好 [训练组C指数（95%置信区间，CI）：0.770（0.729-0.812），测试组C指数（95%CI）：0.761（0.718-0.805）]，其表现优于深度学习模型、放射学模型和临床模型。分层分析显示，该模型不受患者肿瘤大小、淋巴血管侵犯的存在和Lauren分类的影响（p < 0.05）。此外，模型评分与OS呈强烈一致性（内部生存队列C指数（95%CI）：0.723（0.658-0.789，p < 0.0001），外部生存队列C指数（95%CI）：0.715（0.650-0.779，p < 0.0001））。更有趣的是，单变量分析显示模型评分与术前诊断漏诊的远处转移（p < 0.05）显著相关。结合CT图像和临床特征的模型对ESTM和预后具有令人印象深刻的预测能力，有望作为术前TNM分期系统的有效补充。 © 2023美国医学物理学协会。

The potential prognostic value of extranodal soft tissue metastasis (ESTM) has been confirmed by increasing studies about gastric cancer (GC). However, the gold standard of ESTM is determined by pathologic examination after surgery, and there are no preoperative methods for assessment of ESTM yet.This multicenter study aimed to develop a deep learning-based radiomics model to preoperatively identify ESTM and evaluate its prognostic value.A total of 959 GC patients were enrolled from two centers and split into a training cohort (N = 551) and a test cohort (N = 236) for ESTM evaluation. Additionally, an external survival cohort (N = 172) was included for prognostic analysis. Four models were established based on clinical characteristics and multiphase computed tomography (CT) images for preoperative identification of ESTM, including a deep learning model, a hand-crafted radiomic model, a clinical model, and a combined model. C-index, decision curve, and calibration curve were utilized to assess the model performances. Survival analysis was conducted to explore the ability of stratifying overall survival (OS).The combined model showed good discrimination of the ESTM [C-indices (95% confidence interval, CI): 0.770 (0.729-0.812) and 0.761 (0.718-0.805) in training and test cohorts respectively], which outperformed deep learning model, radiomics model, and clinical model. The stratified analysis showed this model was not affected by patient's tumor size, the presence of lymphovascular invasion, and Lauren classification (p < 0.05). Moreover, the model score showed strong consistency with the OS [C-indices (95%CI): 0.723 (0.658-0.789, p < 0.0001) in the internal survival cohort and 0.715 (0.650-0.779, p < 0.0001) in the external survival cohort]. More interestingly, univariate analysis showed the model score was significantly associated with occult distant metastasis (p < 0.05) that was missed by preoperative diagnosis.The model combining CT images and clinical characteristics had an impressive predictive ability of both ESTM and prognosis, which has the potential to serve as an effective complement to the preoperative TNM staging system.© 2023 American Association of Physicists in Medicine.