利用视觉Transformer改善脑转移患者局部失败风险评估:多中心开发与验证研究
本研究基于AURORA回顾性试验中7家医院352例接受手术切除后立体定向放疗的脑转移患者,利用术前MRI训练视觉Transformer(ViT)预测无局部失败生存(FFLF)。模型在99例外部队列中取得C-Index 0.7982,优于所有临床、CNN及混合基线,Kaplan-Meier分析显示显著的FFLF风险分层,显著性图聚焦于脑转移核心与专家观察一致。
要点
- ViT模型在外部测试队列C-Index达0.7982,超越临床、CNN及混合基线。
- Kaplan-Meier分析显示模型可显著分层FFLF风险。
- 显著性图聚焦脑转移核心,模型解释与专家观察一致。
核心结论
- 基于ViT的模型可为脑转移患者个性化治疗策略和随访方案提供潜在支持。
- 该模型作为稳健的自动化工具,可替代放射组学用于临床工作流程。
研究设计与样本
- AURORA回顾性试验中,从7家医院收集352例接受手术切除后术后立体定向放疗的脑转移患者。
- 在T1-CE和FLAIR序列上训练ViT直接完成图像到风险的预测任务,并融合临床特征。
- 采用五折交叉验证和集成学习评估模型,并使用数据集内99例外部队列评估泛化能力。
主要发现
- 在测试队列中取得C-Index 0.7982,超越所有临床、CNN和混合基线。
- Kaplan-Meier分析显示显著的FFLF风险分层。
- 显著性图聚焦于脑转移核心,证实模型解释与专家观察一致。
临床怎么用
- 该ViT模型可作为自动化工具用于脑转移患者术后SRT前的风险分层。
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 AND PURPOSE: This study investigates the use of Vision Transformers (ViTs) to predict Freedom from Local Failure (FFLF) in patients with brain metastases using pre-operative MRI scans. The goal is to develop a model that enhances risk stratification and informs personalized treatment strategies. MATERIALS AND METHODS: Within the AURORA retrospective trial, patients (n = 352) who received surgical resection followed by post-operative stereotactic radiotherapy (SRT) were collected from seven hospitals. We trained our ViT for the direct image-to-risk task on T1-CE and FLAIR sequences and combined clinical features along the way. We employed segmentation-guided image modifications, model adaptations, and specialized patient sampling strategies during training. The model was evaluated with five-fold cross-validation and ensemble learning across all validation runs. An external, international test cohort (n = 99) within the dataset was used to assess the generalization capabilities of the model, and saliency maps were generated for explainability analysis. RESULTS: We achieved a competent C-Index score of 0.7982 on the test cohort, surpassing all clinical, CNN-based, and hybrid baselines. Kaplan-Meier analysis showed significant FFLF risk stratification. Saliency maps focusing on the BM core confirmed that model explanations aligned with expert observations. CONCLUSION: Our ViT-based model offers a potential for personalized treatment strategies and follow-up regimens in patients with brain metastases. It provides an alternative to radiomics as a robust, automated tool for clinical workflows, capable of improving patient outcomes through effective risk assessment and stratification.
引用
- Erdur AC, Scholz D, Nguyen QM, et al. Improving risk assessment of local failure in brain metastases patients using vision transformers - A multicentric development and validation study. Radiother Oncol. 2025. PMID: 40618900. doi:10.1016/j.radonc.2025.111031
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。