ChatGPT生成的肌骨影像的有效性
本研究评估ChatGPT4生成肩、肘、腕、髋、膝、踝六个大关节标注冠状解剖示意图的能力,采用4种提示词变体共生成24幅插图,由4名评估者按解剖正确性、标注正确性、美观性、论文可用性和成本效益5个维度以5点Likert量表评分。结果显示解剖设计差至中等,标注正确性和论文可用性均低于平均水平,评估者间一致性良好(ICC=0.61)。结论认为当前LLM生成图像尚不能满足肌骨放射学研究标准。
要点
- ChatGPT4生成24幅关节示意图中,标注正确性全部低于平均水平,多数评为差。
- 所有插图在研究论文中的可用性均评为低于平均水平。
- 四个评估维度间评估者一致性良好(ICC=0.61)。
核心结论
- ChatGPT4等LLM在快速生成图像方面有前景,但当前能力尚不能满足肌骨放射学研究的严格标准。
- 未来应聚焦迭代优化流程以提升LLM生成肌骨示意图的真实感。
研究设计与样本
- 研究使用ChatGPT4生成肩、肘、腕、髋、膝、踝六个大关节的冠状标注解剖示意图。
- 每个关节采用4种文本提示词变体,共生成24幅插图。
- 由4名评估者采用5点Likert量表从解剖正确性、标注正确性、美观性、论文可用性和成本效益5个维度评估。
关键影像表现/征象
- 解剖设计评分范围为差至中等。
- 所有插图的标注正确性评分低于平均水平,多数评为差。
- 所有插图在研究论文中的可用性评分均低于平均水平。
局限性
- 原文在结论中指出当前LLM能力尚不能满足肌骨放射学研究的严格标准,并建议未来聚焦迭代优化。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
英文原文(摘要)· 点击展开
OBJECTIVE: In the evolving landscape of medical research and radiology, effective communication of intricate ideas is imperative, with visualizations playing a crucial role. This study explores the transformative potential of ChatGPT4, a powerful Large Language Model (LLM), in automating the creation of schematics and figures for radiology research papers, specifically focusing on its implications for musculoskeletal studies.
MATERIALS AND METHODS: Deploying ChatGPT4, the study aimed to assess the model's ability to generate anatomical images of six large joints-shoulder, elbow, wrist, hip, knee, and ankle. Four variations of a text prompt were utilized, to generate a coronal illustration with annotations for each joint. Evaluation parameters included anatomical correctness, correctness of annotations, aesthetic nature of illustrations, usability of figures in research papers, and cost-effectiveness. Four panellists performed the assessment using a 5-point Likert Scale.
RESULTS: Overall analysis of the 24 illustrations encompassing the six joints of interest (4 of each) revealed significant limitations in ChatGPT4's performance. The anatomical design ranged from poor to good, all of the illustrations received a below-average rating for annotation, with the majority assessed as poor. All of them ranked below average for usability in research papers. There was good agreement between raters across all domains (ICC = 0.61).
CONCLUSION: While LLMs like ChatGPT4 present promising prospects for rapid figure generation, their current capabilities fall short of meeting the rigorous standards demanded by musculoskeletal radiology research. Future developments should focus on iterative refinement processes to enhance the realism of LLM-generated musculoskeletal schematics.
引用
- Ajmera P, Nischal N, Ariyaratne S, et al. Validity of ChatGPT-generated musculoskeletal images. Skeletal Radiol. 2024. PMID: 38438538. doi:10.1007/s00256-024-04638-y
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。