AI一键生成前列腺放疗计划，1秒内完成且效果不输人工
AI End-to-End Radiation Treatment Planning Under One Second
- 直接从CT和轮廓图生成可执行的放疗计划，端到端无中间迭代
- 1秒内完成单弧调强计划，靶区均匀性指数0.10±0.01，器官保护达标
- 适合追求高效标准化放疗流程的医院与临床团队
基于人工智能的放射治疗（RT）计划有望缩短规划时间并减少不同医师间的差异，提升临床工作流的效率与一致性。现有大多数自动化方法依赖多次剂量评估与修正，导致计划生成时间长达数分钟。本文提出AIRT（Artificial Intelligence-based Radiotherapy），一个端到端深度学习框架，可直接从CT图像和结构轮廓推导出可交付的治疗计划。AIRT在单块Nvidia A100 GPU上实现从影像输入到叶片序列生成的单弧VMAT前列腺计划生成时间低于1秒。该框架包含可微分剂量反馈、对抗性射野强度整形及计划生成增强机制，以提升计划质量与鲁棒性。模型在超过10,000例完整前列腺病例上训练。非劣效性检验表明，其在靶区覆盖与危及器官（OAR）保护指标上不逊于RapidPlan Eclipse参考计划。采用AcurosXB评估，靶区均匀性（HI = 0.10 ± 0.01）与OAR保护效果与参考计划相当。该成果标志着超快速标准化放疗规划的重要进展，推动临床工作流优化。
原文摘要 · Abstract (English)
Artificial intelligence-based radiation therapy (RT) planning has the potential to reduce planning time and inter-planner variability, improving efficiency and consistency in clinical workflows. Most existing automated approaches rely on multiple dose evaluations and corrections, resulting in plan generation times of several minutes. We introduce AIRT (Artificial Intelligence-based Radiotherapy), an end-to-end deep-learning framework that directly infers deliverable treatment plans from CT images and structure contours. AIRT generates single-arc VMAT prostate plans, from imaging and anatomical inputs to leaf sequencing, in under one second on a single Nvidia A100 GPU. The framework includes a differentiable dose feedback, an adversarial fluence map shaping, and a plan generation augmentation to improve plan quality and robustness. The model was trained on more than 10,000 intact prostate cases. Non-inferiority to RapidPlan Eclipse was demonstrated across target coverage and OAR sparing metrics. Target homogeneity (HI = 0.10 $\pm$ 0.01) and OAR sparing were similar to reference plans when evaluated using AcurosXB. These results represent a significant step toward ultra-fast standardized RT planning and a streamlined clinical workflow.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。