自动深度学习[18F]FDG PET/CT肿瘤体积在头颈癌预后建模中非劣于手动GTV
本研究在头颈癌患者中比较自动深度学习生成的PET肿瘤体积(AI-PET-GTV)与手动勾画的大体肿瘤体积(GTV)在预测局部区域失败(LRF)和远处转移(DM)中的预后价值。采用竞争风险回归,主要终点为3年AUC,非劣效界值为5个百分点。AI-PET-GTV在LRF和DM预测中均非劣于手动GTV,支持AI体积用于可重复、可扩展的风险分层。
要点
- AI-PET-GTV预测3年LRF的AUC为72.9%,手动GTV为72.8%,满足非劣效。
- 1年LRF预测AUC分别为77.3%和76.9%,DM预测模式相似且Brier评分 favoring AI。
- 基于预测风险的高危组3年LRF累积发生率两者均为38.4%。
核心结论
- 自动深度学习生成的PET肿瘤体积在头颈癌LRF和DM预后建模中非劣于手动GTV。
研究设计与样本
- 采用竞争风险回归比较AI-PET-GTV与手动GTV的预后预测性能,主要终点为3年AUC,非劣效界值5个百分点。
主要发现
- AI-PET-GTV预测3年LRF的AUC为72.9%(95%CI 67.9–77.9%),手动GTV为72.8%(95%CI 67.8–77.9%),p=0.02。
- 1年LRF的AUC分别为77.3%(95%CI 72.2–82.4%)和76.9%(95%CI 71.9–82.0%),p=0.02。
- DM预测在1年和3年也观察到相似模式(所有p<0.01),Brier评分在两个时间点均支持AI-PET-GTV(p<0.02)。
- 基于预测风险分层的高危组3年LRF累积发生率两者均为38.4%(95%CI 32.6–44.2%)。
关键数值与推荐
- 非劣效界值为5个百分点,主要终点为3年AUC。
临床怎么用
- AI-PET-GTV可用于头颈癌可重复、可扩展的早期风险分层,替代手动GTV用于预后建模。
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
BACKGROUND: Manual segmentation of gross tumour volumes (GTV) on [18F]FDG PET/CT is time-consuming and subject to interobserver variability, limiting its scalability for prognostic modelling in head and neck cancer. We investigated whether deep learning-based PET tumour volumes (AI-PET-GTV) could replace manually defined GTVs in risk prediction models for loco-regional failure (LRF) and distant metastasis (DM). RESULTS: Using competing risk regression, we tested whether AI-PET-GTV was non-inferior to manual GTV in predicting LRF, with the primary outcome being area under the receiver operating characteristic curve (AUC) at 3 years, using a non-inferiority margin of 5 percentage points. AI-PET-GTV achieved a 3-year AUC of 72.9% (95% CI: 67.9–77.9%) compared to 72.8% (95% CI: 67.8–77.9%) for manual GTV (p = 0.02). At 1 year, AUCs were 77.3% (95% CI: 72.2–82.4%) and 76.9% (95% CI: 71.9–82.0%) for AI and manual GTV, respectively (p = 0.02). Similar patterns were observed for DM prediction at 1 and 3 years (all p < 0.01), and Brier scores also favoured AI-PET-GTV at both timepoints (p < 0.02). Stratification based on predicted risk yielded nearly identical cumulative incidence estimates. For example, the 3-year cumulative incidence of LRF in the high-risk group was 38.4% (95% CI: 32.6–44.2%) for both models. CONCLUSIONS: Automated deep learning-based PET tumour volumes are non-inferior to manual GTVs for prognostic modelling of LRF and DM in head and neck cancer. These findings support clinical implementation of AI-derived volumes for reproducible, scalable, and earlier risk stratification in oncology workflows.
引用
- Kovacs DG, Håkansson K, Rasmussen J, et al. Non-inferiority of automated deep learning-based [18F]FDG PET/CT tumour volume compared to manual GTV for prognostic modelling in head and neck cancer. EJNMMI Res. 2026. PMID: 41652257. doi:10.1186/s13550-026-01377-0
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。