放疗是鼻咽癌的主要治疗方法。放疗引起的颞叶损伤（TLI）在早期可能会减退或消失，但在后期则是不可逆的。但是，目前没有研究提出了早期检测的基于风险的跟踪计划。当剂量 - 体积直方图（DVH）参数相似且优化终止时，计划评估是困难的。这项多中心回顾性研究包括2014年至2018年间的6065名患者。在培训和验证队列中开发了基于3D ResNet的深度学习模型，并使用内部和外部测试队列中的一致性指数进行了独立测试。因此，将患者分成风险组，并使用模型预测的风险来开发基于风险的跟踪计划。该计划与放射治疗肿瘤学研究组（RTOG）建议进行了比较（在前2年内每3个月进行一次，在3-5年内每6个月进行一次）。此外，该模型被用于评估DVH参数相似的方案。我们的模型分别获得了0.831、0.818和0.804的一致性指数，优于传统的预测模型（所有P < 0.001）。所有队列的颞叶被分成三组，并且其TLI无意义的生存存在差异。为每个风险组制定的个性化后续计划可以比RTOG建议更早地检测出TLI，时间提前了1.9个月。根据更高的中位预测3年TLI无意义生存率（99.25% vs. 99.15%，P < 0.001），该模型确定了比以前模型更好的计划。深度学习模型可以更精确地预测TLI。模型确定的基于风险的跟踪计划可以更早地检测到TLI。该模型确定的更好计划的TLI风险更低，因此计划评估更精细。该研究受到孙逸仙大学临床研究5010项目（2015020）、广东省基础及应用基础研究基金（2022A1515110356）、广东省医学科学研究基金（A2022367）和广州市科技计划项目（2023A04J1788）的支持。 © 2023 作者（S）

Radiotherapy is the mainstay of treatment for nasopharyngeal carcinoma. Radiation-induced temporal lobe injury (TLI) can regress or resolve in the early phase, but it is irreversible at a later stage. However, no study has proposed a risk-based follow-up schedule for its early detection. Planning evaluation is difficult when dose-volume histogram (DVH) parameters are similar and optimization is terminated.This multicenter retrospective study included 6065 patients between 2014 and 2018. A 3D ResNet-based deep learning model was developed in training and validation cohorts and independently tested using concordance index in internal and external test cohorts. Accordingly, the patients were stratified into risk groups, and the model-predicted risks were used to develop risk-based follow-up schedules. The schedule was compared with the Radiation Therapy Oncology Group (RTOG) recommendation (every 3 months during the first 2 years and every 6 months in 3-5 years). Additionally, the model was used to evaluate plans with similar DVH parameters.Our model achieved concordance indexes of 0.831, 0.818, and 0.804, respectively, which outperformed conventional prediction models (all P < 0.001). The temporal lobes in all the cohorts were stratified into three groups with discrepant TLI-free survival. Personalized follow-up schedules developed for each risk group could detect TLI 1.9 months earlier than the RTOG recommendation. According to a higher median predicted 3-year TLI-free survival (99.25% vs. 99.15%, P < 0.001), the model identified a better plan than previous models.The deep learning model predicted TLI more precisely. The model-determined risk-based follow-up schedule detected the TLI earlier. The planning evaluation was refined because the model identified a better plan with a lower risk of TLI.The Sun Yat-sen University Clinical Research 5010 Program (2015020), Guangdong Basic and Applied Basic Research Foundation (2022A1515110356), Medical Scientific Research Foundation of Guangdong Province (A2022367), and Guangzhou Science and Technology Program (2023A04J1788).© 2023 The Author(s).