What question did this study set out to answer?

April 4, 2026Open Access

Development and Clinical Validation of a Protocol-Agnostic Machine Learning Platform for Automated Treatment Planning in External-Beam Radiotherapy

Key Points

The research aims to create and validate a machine learning platform for automated treatment planning in external-beam radiotherapy.
Developed machine learning models using 5334 retrospective photon-beam treatment plans
Internally tested models on 72 retrospective clinical plans
Compared dose metrics for multiple organ-at-risk across different anatomical sites
Predictive Plans showed lower mean doses for several organs-at-risk compared to Conventional Plans
For H&N, mean dose to crucial organs like Brain and Optic Chiasm was significantly lower with Predictive Plans
Significant improvements were noted in dose management for abdominal and pelvic organs as well

Abstract

Purpose: To develop and validate a protocol-agnostic machine learning platform ("Predictive Planning") for knowledge-based planning (KBP) in external-beam radiotherapy. Materials and Methods: 5334 retrospective photon-beam treatment plans (1145 Head and Neck (H PP), without objective value changes. Dose metrics were compared for 25, 11, 8, and 7 OARs for H&N, Thoracic, Abdominal, and Pelvis plans, respectively, and for PTVs. Results: In the plan comparison study, there were no OAR dose metrics for which PP were statistically significantly greater than CP. For H&N, PP mean dose (Gy) was significantly lower for Brain (5. 8 vs. 7. 3, p=0. 0003), Brainstem (9. 6 vs. 13. 8, p<0. 0001), Glottis (26. 9 vs. 31. 9, p=0. 0017), OpticChiasm (7. 3 vs. 12. 2, p<0. 0001), ParotidL/R (19. 0/20. 8 vs. 22. 3/25. 7, p<0. 0001/<0. 0001) and SpinalCord (10. 1 vs. 15. 7, p<0. 0001). For Abdominal, PP mean dose was significantly lower for Heart (2. 2 vs. 3. 4, p=0. 0039), KidneyR (6. 2 vs. 8. 6, p=0. 002), SpinalCanal (4. 8 vs. 6. 7, p=0. 0004), and Stomach (9. 1 vs. 10. 9, p=0. 002). For Pelvis, PP mean dose was significantly lower for Bladder (30. 7 vs. 33. 7, p<0. 0001), FemurHeadL/R (13. 8/13. 9 vs. 17. 0/16. 5, p=0. 0026/0. 0046), PenileBulb (15. 8 vs. 21. 9, p=0. 0039), and Rectum (28. 1 vs. 34. 2, p=0. 0002). Mean PTV coverage was significantly higher for H&N and Thoracic, and equivalent for Abdominal and Pelvis. Conclusions: Predictive Planning represents a shift in KBP from protocol-specific models trained with small, uniform datasets to protocol-agnostic, disease-site-specific models trained with large, heterogenous datasets. Plans generated using optimization objectives predicted by the models had equivalent or superior dosimetric outcomes.

Bookmark

View Full Paper

Cite This Study

Shade et al. (Wed,) studied this question.

synapsesocial.com/papers/69d0ae68659487ece0fa4633 https://doi.org/https://doi.org/10.1016/j.adro.2026.102036

Bookmark

View Full Paper