开发一种结合 CT 扫描和临床信息的深度学习模型，以预测晚期肝细胞癌 (HCC) 的总体生存率。这项回顾性研究纳入了 2018 年至 2022 年间来自 52 个跨国内部中心接受免疫治疗的晚期 HCC 患者。 -提出了使用基线和首次随访 CT 图像以及 7 个临床变量的模态预后模型。开发了卷积循环神经网络 (CRNN)，用于从自动选择的代表性 2D CT 切片中提取时空信息以提供放射学评分，然后与基于 Cox 的临床评分融合以提供生存风险。使用受试者工作曲线下的时间依赖性面积（AUC）评估模型的有效性，并使用对数秩检验进行风险组分层。将多模态输入的预后表现与缺失模态模型以及基于体型的 RECIST 标准进行比较。纳入了 207 名患者（平均年龄，61 岁±12 [SD]，180 名男性）。多模态 CRNN 模型在验证集和测试集中的 1 年总体生存预测的 AUC 分别为 0.777 和 0.704。该模型根据训练集的中位风险评分，在验证集（风险比 [HR] = 3.330，p = 0.008）和测试集（HR = 2.024，p = 0.047）中实现了显着的风险分层。缺少模态的模型（基于单模态成像的模型和仅包含基线扫描的模型）仍然可以实现良好的风险分层性能（所有 p< 0.05，除了一个 p = 0.053）。此外，结果证明了基于深度学习的模型相对于RECIST标准的优越性。CT扫描和临床数据的深度学习分析可以为晚期HCC患者提供重要的预后见解。建立的模型可以帮助监测患者的疾病状态并识别患者的病情。首次随访时预后不良的患者，帮助临床医生做出明智的治疗决策，以及早期及时的干预措施。针对跨国患者，开发了基于人工智能的晚期 HCC 预后模型。该模型从 CT 扫描中提取时空信息，并将其与临床变量相结合以进行预测。与传统的基于尺寸的 RECIST 方法相比，该模型表现出卓越的预后能力。© 2024。作者。

To develop a deep learning model combining CT scans and clinical information to predict overall survival in advanced hepatocellular carcinoma (HCC).This retrospective study included immunotherapy-treated advanced HCC patients from 52 multi-national in-house centers between 2018 and 2022. A multi-modal prognostic model using baseline and the first follow-up CT images and 7 clinical variables was proposed. A convolutional-recurrent neural network (CRNN) was developed to extract spatial-temporal information from automatically selected representative 2D CT slices to provide a radiological score, then fused with a Cox-based clinical score to provide the survival risk. The model's effectiveness was assessed using a time-dependent area under the receiver operating curve (AUC), and risk group stratification using the log-rank test. Prognostic performances of multi-modal inputs were compared to models of missing modality, and the size-based RECIST criteria.Two-hundred seven patients (mean age, 61 years ± 12 [SD], 180 men) were included. The multi-modal CRNN model reached the AUC of 0.777 and 0.704 of 1-year overall survival predictions in the validation and test sets. The model achieved significant risk stratification in validation (hazard ratio [HR] = 3.330, p = 0.008), and test sets (HR = 2.024, p = 0.047) based on the median risk score of the training set. Models with missing modalities (the single-modal imaging-based model and the model incorporating only baseline scans) can still achieve favorable risk stratification performance (all p < 0.05, except for one, p = 0.053). Moreover, results proved the superiority of the deep learning-based model to the RECIST criteria.Deep learning analysis of CT scans and clinical data can offer significant prognostic insights for patients with advanced HCC.The established model can help monitor patients' disease statuses and identify those with poor prognosis at the time of first follow-up, helping clinicians make informed treatment decisions, as well as early and timely interventions.An AI-based prognostic model was developed for advanced HCC using multi-national patients. The model extracts spatial-temporal information from CT scans and integrates it with clinical variables to prognosticate. The model demonstrated superior prognostic ability compared to the conventional size-based RECIST method.© 2024. The Author(s).