박상준 (연세대학교 의과대학) | 한빛사논문 > 한빛사

한빛사논문

조회238

연세대학교 의과대학

CV File 322 kb

Nat. Commun., Oct 24 2024, 15 (1) 9186 | https://doi.org/10.1038/s41467-024-53387-y LLM-driven multimodal target volume contouring in radiation oncology

Yujin Oh ^1,8, Sangjoon Park ^2,3,8, Hwa Kyung Byun⁴, Yeona Cho ⁵, Ik Jae Lee ², Jin Sung Kim ^2,6 & Jong Chul Ye⁷

¹Department of Radiology, Massachusetts General Hospital (MGH) and Harvard Medical School, Boston, MA, USA.

²Department of Radiation Oncology, Yonsei University College of Medicine, Seoul, South Korea.

³Institute for Innovation in Digital Healthcare, Yonsei University, Seoul, South Korea.

⁴Department of Radiation Oncology, Yongin Severance Hospital, Yongin, Gyeonggi-do, South Korea.

⁵Department of Radiation Oncology, Gangnam Severance Hospital, Seoul, South Korea.

⁶Oncosoft Inc., Seoul, South Korea.

⁷Kim Jaechul Graduate School of AI, Korea Advanced Institute of Science and Technology (KAIST), Daejeon, South Korea.

⁸These authors contributed equally: Yujin Oh, Sangjoon Park.

Corresponding authors

Correspondence to Jin Sung Kim or 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.

논문정보

형식Research article
게재일2024년 10월 (BRIC 등록일 2024-10-30)
연구진국내(교신)+국외 연구진
분야 바이오·의료융합 > 의료기기

댓글 작성 로그인

CV 열람하기

연락처 보기