LLM-driven Multimodal Target Volume Contouring in Radiation Oncology
This addresses the challenging problem of target volume contouring for radiation oncologists, offering a more accurate and efficient tool, though it is incremental as it builds on existing LLM and multimodal AI methods.
The authors tackled target volume contouring in radiation therapy by developing LLMSeg, a novel LLM-driven multimodal AI that integrates clinical text and images, demonstrating improved performance over unimodal models with robust generalization and data efficiency in breast cancer cases.
Target volume contouring for radiation therapy is considered significantly more challenging than the normal organ segmentation tasks as it necessitates the utilization of both image and text-based clinical information. Inspired by the recent advancement of large language models (LLMs) that can facilitate the integration of the textural information and images, here we present a novel LLM-driven multimodal AI, namely LLMSeg, that utilizes the clinical text information and is applicable to the challenging task of target volume contouring for radiation therapy, and validate it within the context of breast cancer radiation therapy target volume contouring. Using external validation and data-insufficient environments, which attributes highly conducive to real-world applications, we demonstrate that the proposed model exhibits markedly improved performance compared to conventional unimodal AI models, particularly exhibiting robust generalization performance and data efficiency. To our best knowledge, this is the first LLM-driven multimodal AI model that integrates the clinical text information into target volume delineation for radiation oncology.