Abstract
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.
Abstract (translated)
基于人工智能的放射治疗（RT）计划有可能减少规划时间并降低不同规划者之间的差异，从而提高临床工作流程中的效率和一致性。大多数现有的自动化方法依赖于多次剂量评估和修正，导致生成方案的时间长达几分钟。我们介绍了AIRT（基于人工智能的放射治疗），这是一种端到端深度学习框架，可以直接从CT图像和结构轮廓中推断出可交付的治疗计划。AIRT能够在一个Nvidia A100 GPU上，在不到一秒的时间内，根据影像学及解剖学输入生成单弧VMAT前列腺治疗方案，并进行叶片序列设计。该框架包括一个可微剂量反馈、对抗性束流分布整形以及一种用于提高计划质量和鲁棒性的计划生成增强方法。模型是在超过10,000例完整前列腺病例上训练出来的。AIRT在靶区覆盖和器官保护指标方面与RapidPlan Eclipse表现无显著差异。使用AcurosXB评估时，靶区均匀度（HI = 0.10 ± 0.01）和组织保护措施与参考方案相似。 这些结果代表了向超快速标准化放射治疗计划和精简临床工作流程迈出的重要一步。
URL
https://arxiv.org/abs/2603.06338
