LLM-driven multimodal target volume contouring in radiation oncology
Yujin Oh, Sang Joon Park, Hwa Kyung Byun, Yeona Cho, Ik Jae Lee, Jin Sung Kim, Jong Chul Ye
Abstract
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 an LLM-driven multimodal artificial intelligence (AI), namely LLMSeg, that utilizes the clinical information and is applicable to the challenging task of 3-dimensional context-aware target volume delineation for radiation oncology. We validate our proposed LLMSeg within the context of breast cancer radiotherapy using external validation and data-insufficient environments, which attributes highly conducive to real-world applications. We demonstrate that the proposed multimodal LLMSeg exhibits markedly improved performance compared to conventional unimodal AI models, particularly exhibiting robust generalization performance and data-efficiency. The integration of multimodal knowledge would be essential for radiation oncologist to determine the therapeutic treatment. Here, inspired by the large language models facilitating the integration of textural information and images, this group reports a 3D multimodal clinical target volume delineation model combining image and text-based clinical information for decision-making in radiation oncology.