Holistic Evaluation of GPT-4V for Biomedical Imaging

In this paper, we present a large-scale evaluation probing GPT-4V's capabilities and limitations for biomedical image analysis. GPT-4V represents a breakthrough in artificial general intelligence (AGI) for computer vision, with applications in the biomedical domain. We assess GPT-4V's perf...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2023-11
Main Authors: Liu, Zhengliang, Jiang, Hanqi, Zhong, Tianyang, Wu, Zihao, Ma, Chong, Li, Yiwei, Yu, Xiaowei, Zhang, Yutong, Pan, Yi, Peng Shu, Lyu, Yanjun, Zhang, Lu, Yao, Junjie, Dong, Peixin, Cao, Chao, Xiao, Zhenxiang, Wang, Jiaqi, Zhao, Huan, Xu, Shaochen, Yaonai Wei, Chen, Jingyuan, Dai, Haixing, Wang, Peilong, He, Hao, Wang, Zewei, Wang, Xinyu, Zhang, Xu, Zhao, Lin, Liu, Yiheng, Zhang, Kai, Liheng Yan, Sun, Lichao, Liu, Jun, Ning Qiang, Bao Ge, Cai, Xiaoyan, Zhao, Shijie, Hu, Xintao, Yuan, Yixuan, Li, Gang, Zhang, Shu, Zhang, Xin, Jiang, Xi, Zhang, Tuo, Shen, Dinggang, Li, Quanzheng, Liu, Wei, Li, Xiang, Zhu, Dajiang, Liu, Tianming
Format: Article
Language:English
Subjects:
Anatomy
Artificial intelligence
Computer vision
Diagnosis
Image analysis
Large language models
Localization
Medical diagnosis
Medical electronics
Medical imaging
Ophthalmology
Recognition
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this paper, we present a large-scale evaluation probing GPT-4V's capabilities and limitations for biomedical image analysis. GPT-4V represents a breakthrough in artificial general intelligence (AGI) for computer vision, with applications in the biomedical domain. We assess GPT-4V's performance across 16 medical imaging categories, including radiology, oncology, ophthalmology, pathology, and more. Tasks include modality recognition, anatomy localization, disease diagnosis, report generation, and lesion detection. The extensive experiments provide insights into GPT-4V's strengths and weaknesses. Results show GPT-4V's proficiency in modality and anatomy recognition but difficulty with disease diagnosis and localization. GPT-4V excels at diagnostic report generation, indicating strong image captioning skills. While promising for biomedical imaging AI, GPT-4V requires further enhancement and validation before clinical deployment. We emphasize responsible development and testing for trustworthy integration of biomedical AGI. This rigorous evaluation of GPT-4V on diverse medical images advances understanding of multimodal large language models (LLMs) and guides future work toward impactful healthcare applications.
ISSN:2331-8422