深度学习辅助脑部勾画与头颈癌生存者系列神经认知监测:一项前瞻性研究
该前瞻性研究纳入新诊断头颈癌患者,在放疗前及放疗后6、12个月完成综合神经心理测验,并用深度学习辅助勾画估算八个脑区平均剂量。小脑和颞叶中位Dmean最高,顶叶最低;各认知域随访有轻度改善,区域剂量与认知表现无显著相关。
要点
- 头颈癌放疗中 incidental 脑部剂量以小脑和颞叶最高,顶叶最低。
- 随访6和12个月各认知域评分有轻度改善。
- 区域剂量与认知表现无显著相关,多数估计值在-0.1至0.1之间。
核心结论
- 头颈癌治疗中 incidental 脑部放疗在诊断后第一年内未与早期神经认知下降相关。
研究设计与样本
- 前瞻性研究纳入新诊断头颈癌患者,基线神经心理测验n=47,放疗开始后6个月n=30、12个月n=24完成随访。
- 采用深度学习辅助勾画估算八个脑区的平均辐射剂量(Dmean)。
- 用Pearson相关系数及95%CI评估区域剂量与认知变化的关系。
主要发现
- 最高中位Dmean见于小脑(430.7 cGy;IQR:302.3-646.2)和颞叶(108.5 cGy;IQR:72.4-161.2),顶叶最低(27.5 cGy;IQR:18.9-39.6)。
- 两个随访时间点各认知域评分均显示轻度改善。
- 区域特异性剂量与认知表现间无显著相关,多数估计值在-0.1至0.1之间。
临床怎么用
- 本研究提示头颈癌放疗中 incidental 脑部剂量在第一年内未伴随可检测的神经认知下降。
- 深度学习辅助勾画结合纵向认知评估可用于头颈癌生存者的剂量-认知监测。
局限性
- 随访样本量随时间的减少(基线n=47,6个月n=30,12个月n=24)。
- 研究为前瞻性单组观察,需未来更大规模研究验证。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
Patients treated for head and neck cancer (HNC) receive incidental, non-target radiation to intracranial structures. This prospective study investigated the relationship between regional brain radiation dosimetry and neurocognitive performance during the first year of survivorship. Patients with newly diagnosed HNC completed a comprehensive neuropsychological battery at baseline-prior to or within the first week of radiation therapy, or before induction chemotherapy-(n = 47), and again at 6 months (n = 30) and 12 months (n = 24) after initiating radiation therapy. Cognitive domains assessed included language, learning and memory, and attention, processing speed, and executive function (APE). Deep-learning-assisted contouring was applied to estimate mean radiation doses (Dmean) to eight brain regions. Associations between regional dosimetry and cognitive change were evaluated using Pearson correlation coefficients with 95% confidence intervals (CIs). The highest median Dmean were observed in the cerebellum (430.7 cGy; IQR: 302.3-646.2) and temporal lobes (108.5 cGy; IQR: 72.4-161.2), while the parietal lobe received the lowest (27.5 cGy; IQR: 18.9-39.6). Neurocognitive scores demonstrated modest improvement across domains at both follow-up time points. No significant correlations were identified between region-specific doses and cognitive performance, with most estimates between -0.1 and 0.1. Incidental brain radiation during HNC treatment was not associated with early neurocognitive decline within the first year after diagnosis. This prospective study illustrates the utility of integrating advanced dosimetry with longitudinal cognitive assessments and lays the groundwork for future larger-scale investigations.
引用
- Kim S, Schofield E, Simeth J, et al. Deep-learning-assisted brain contouring and serial neurocognitive monitoring in head and neck cancer survivorship: a prospective study. Clin Transl Radiat Oncol. 2026. PMID: 42662372. doi:10.1016/j.ctro.2026.101253
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。