An Iterative LLM Framework for SIBT utilizing RAG-based Adaptive Weight Optimization
This work addresses automation challenges in SIBT planning for cancer treatment, representing an incremental improvement by integrating LLMs with existing methods.
The study tackled the inefficiency and suboptimal results in seed implant brachytherapy (SIBT) planning by proposing an LLM-driven adaptive weight optimization framework, which produced plans comparable to or exceeding clinically approved ones in dose homogeneity and organ sparing across 23 patient cases.
Seed implant brachytherapy (SIBT) is an effective cancer treatment modality; however, clinical planning often relies on manual adjustment of objective function weights, leading to inefficiencies and suboptimal results. This study proposes an adaptive weight optimization framework for SIBT planning, driven by large language models (LLMs). A locally deployed DeepSeek-R1 LLM is integrated with an automatic planning algorithm in an iterative loop. Starting with fixed weights, the LLM evaluates plan quality and recommends new weights in the next iteration. This process continues until convergence criteria are met, after which the LLM conducts a comprehensive evaluation to identify the optimal plan. A clinical knowledge base, constructed and queried via retrieval-augmented generation (RAG), enhances the model's domain-specific reasoning. The proposed method was validated on 23 patient cases, showing that the LLM-assisted approach produces plans that are comparable to or exceeding clinically approved and fixed-weight plans, in terms of dose homogeneity for the clinical target volume (CTV) and sparing of organs at risk (OARs). The study demonstrates the potential use of LLMs in SIBT planning automation.