Learning to Optimize Radiotherapy Plans via Fluence Maps Diffusion Model Generation and LSTM-based Optimization
For radiation oncology, this work reduces VMAT planning time while maintaining plan quality, but the method is domain-specific and incremental over existing end-to-end planners.
The paper tackles the time-consuming inverse optimization in VMAT radiotherapy planning by introducing a diffusion-driven Learning-to-Optimize method that generates fluence maps via a distilled diffusion model and refines them with an LSTM-based optimizer, achieving improved planning efficiency, flexibility, and deliverability on prostate cancer cohorts.
Volumetric Modulated Arc Therapy (VMAT) is a cornerstone of modern radiation therapy, enabling highly conformal tumor irradiation and healthy-tissue sparing. Yet, its planning solves inverse and nested optimization for multi-leaf collimators, monitor units and dose parameters, while enforcing their consistency to ensure mechanical deliverability. Nevertheless, this process often requires repeated re-optimization when treatment configurations change, resulting in substantial planning time per patient. To address these problems, we present a diffusion-driven Learning-to-Optimize (L2O) method for end-to-end VMAT planning. A distribution-matching distilled diffusion model learns a clinically feasible manifold of fluence maps, enabling their one-shot generation. On top of this, an LSTM-based L2O module learns gradient update dynamics to swiftly refine fluence maps toward prescribed dose objectives during inference. Experimental results on clinical and public prostate cancer cohorts demonstrate improved planning efficiency, flexibility, and machine deliverability over currently available end-to-end VMAT planners.