可靠且全面的口咽癌（OPC）癌症预后模型可以更好地帮助个体化治疗。在这项工作中，我们开发了一种基于视觉转换器（基于 ViT）的多标签模型，具有多模态输入，可以从可用的预处理数据中学习补充信息，并预测 OPC 患者放疗的多个相关终点。 512 名 OPC 患者的数据集用于模型训练和评估。使用规划 CT 图像、原发性大体肿瘤体积 (GTVp) 掩模和代表患者人口统计、诊断和治疗的 16 个临床变量作为输入。为了提取具有全局注意力的深层图像特征，我们使用了 ViT 模块。临床变量与学习到的图像特征连接起来，并馈送到全连接层以合并跨模态特征。为了了解特征和相关生存结果之间的映射，例如总体生存（OS）、局部无失败生存（LFFS）、区域无失败生存（RFFS）和远处无失败生存（DFFS），我们采用四个多任务逻辑回归 (MTLR) 层。通过结合不同预测目标的 MTLR 负对数似然损失来优化所提出的模型。我们采用 C 指数和 AUC 指标分别评估我们的模型在事件发生时间预测和特定时间二元预测方面的性能。我们提出的模型在所有预测标签上都优于相应的单模态和单标签模型，其 OS、LFFS、RFFS 和 DFFS 的 C 指数分别为 0.773、0.765、0.776 和 0.773。不同时间点不同任务的 AUC 值范围在 0.799 至 0.844 之间。此外，当使用预测风险的中位数作为识别高风险和低风险患者组的阈值时，对数秩检验结果显示不同的无事件生存率之间存在显着更大的分离。我们开发了第一个能够预测多个风险的模型同时为OPC添加标签。与相应的单模态模型和单标签模型相比，我们的模型对所有预测目标都表现出更好的预后能力。版权所有 © 2023 Elsevier Inc. 保留所有权利。

A reliable and comprehensive cancer prognosis model for oropharyngeal cancers (OPCs) could better assist in personalizing treatment. In this work, we developed a vision transformer-based (ViT-based) multi-label model with multi-modal input to learn complimentary information from available pretreatment data and predict multiple associated endpoints for OPC patient radiotherapy.In our study, a publicly available dataset of 512 OPC patients was utilized for both model training and evaluation. Planning CT images, primary gross tumor volume (GTVp) masks and 16 clinical variables representing patient demographic, diagnosis, and treatment were used as input. To extract deep image features with global attention, we utilized a ViT module. Clinical variables were concatenated with the learnt image features and fed to fully-connection layers to incorporate cross-modality features. To learn the mapping between the features and correlated survival outcomes, such as overall survival (OS), local failure-free survival (LFFS), regional failure-free survival (RFFS), and distant failure-free survival (DFFS), we employed four Multi-Task Logistic Regression (MTLR) layers. The proposed model was optimized by combining the MTLR negative-log likelihood losses of different prediction targets.We employed the C-index and AUC metrics to assess the performance of our model for time-to-event prediction and time-specific binary prediction, respectively. Our proposed model outperformed corresponding single-modality and single-label models on all prediction labels, which achieved C-indices of 0.773, 0.765, 0.776, and 0.773 for OS, LFFS, RFFS, and DFFS, respectively. The AUC values ranged between 0.799 and 0.844 for different tasks at different time points. Furthermore, when using the medians of predicted risks as the thresholds to identify high-risk and low-risk patient groups, the log-rank test results showed significant larger separations in different event-free survivals.We developed the first model capable of predicting multiple labels for OPC simultaneously. Our model demonstrated better prognostic ability for all the prediction targets compared with corresponding single-modality models and single-label models.Copyright © 2023 Elsevier Inc. All rights reserved.