AI End-to-End Radiation Treatment Planning Under One Second
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866910043722481664 |
|---|---|
| author | Arberet, Simon Gao, Riqiang Kraus, Martin Ghesu, Florin C. Verbakel, Wilko Diallo, Mamadou Magliari, Anthony Karuppusamy, Venkatesan Beriwal, Sushil Consortium, REQUITE Kamen, Ali Comaniciu, Dorin |
| author_facet | Arberet, Simon Gao, Riqiang Kraus, Martin Ghesu, Florin C. Verbakel, Wilko Diallo, Mamadou Magliari, Anthony Karuppusamy, Venkatesan Beriwal, Sushil Consortium, REQUITE Kamen, Ali Comaniciu, Dorin |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_06338 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | AI End-to-End Radiation Treatment Planning Under One Second Arberet, Simon Gao, Riqiang Kraus, Martin Ghesu, Florin C. Verbakel, Wilko Diallo, Mamadou Magliari, Anthony Karuppusamy, Venkatesan Beriwal, Sushil Consortium, REQUITE Kamen, Ali Comaniciu, Dorin Image and Video Processing Artificial Intelligence Machine Learning Systems and Control Medical Physics 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. |
| title | AI End-to-End Radiation Treatment Planning Under One Second |
| topic | Image and Video Processing Artificial Intelligence Machine Learning Systems and Control Medical Physics |
| url | https://arxiv.org/abs/2603.06338 |