A Large Language Model Framework for Seed Implant Brachytherapy: Adaptive Weight Optimization via Retrieval-Augmented Generation

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 retrospectively validated on 23 patient cases who underwent head-and-neck SIBT, showing that the LLM-assisted approach maintained clinical target volume (CTV) coverage and reduced excessive target dose relative to fixed-weight planning; in the eight patients with available organs at risk (OARs) contours, OAR dose metrics showed favorable numerical trends. The study demonstrates the potential of LLMs as assistive tools for SIBT planning under clinician supervision.