Jove
Visualize
联系我们
JoVE
x logofacebook logolinkedin logoyoutube logo
关于 JoVE
概览领导团队博客JoVE 帮助中心
作者
出版流程编辑委员会范围与政策同行评审常见问题投稿
图书馆员
用户评价订阅访问资源图书馆顾问委员会常见问题
研究
JoVE JournalMethods CollectionsJoVE Encyclopedia of Experiments存档
教育
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab Manual教师资源中心教师网站
使用条款与条件
隐私政策
政策

相关概念视频

Improving Translational Accuracy02:07

Improving Translational Accuracy

2.5K
2.5K

您也可能阅读

相关文章

通过共同作者、期刊和引用图与本文相关的文章。

排序
Same author

Ambient AI Scribes to Create Educational Feedback Notes for Medical Students: Randomized Trial.

JMIR medical education·2026
Same author

A Prototype "Smart" 3-Dimensionally Printed Model Showcasing Interactivity: Implementing Voice Command for the Ventricular and Cisternal Systems.

Journal of computer assisted tomography·2025
Same author

AI-powered Hyperrealism: Next Step in Cinematic Rendering?

Radiology·2024
Same author

Remote Patient Monitoring for Hypertension: Feasibility and Outcomes of a Clinic-Based Pilot in a Minority Population.

Journal of primary care & community health·2023
Same author

Pearls and pitfalls in emergency CT neuroangiography through the lens of bias and error.

Emergency radiology·2023
Same author

ChatGPT's Potential Role in Interventional Radiology.

Cardiovascular and interventional radiology·2023

相关实验视频

Updated: Jun 13, 2025

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

519

在放射学中优化大型语言模型和缓解陷:快速工程和微调.

Theodore Taehoon Kim1, Michael Makutonin1, Reza Sirous1

  • 1From the Department of Radiology, George Washington University School of Medicine and Health Sciences, 2300 I St NW, Washington, DC 20052 (T.T.K., R.J.); Yale School of Medicine, New Haven, Conn (M.M.); and University of California San Francisco, San Francisco, Calif (R.S.).

Radiographics : a review publication of the Radiological Society of North America, Inc
|March 6, 2025
PubMed
概括

大型语言模型 (LLM) 在放射学中提供了潜力,但面临着幻觉和偏见等挑战. 通过快速工程和微调优化LLMs对于安全有效的医疗应用至关重要.

更多相关视频

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

6.8K
Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.2K

相关实验视频

Last Updated: Jun 13, 2025

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

519
Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

6.8K
Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.2K

科学领域:

  • 人工智能在医学中的应用
  • 医学成像信息学 医疗成像信息学

背景情况:

  • 大型语言模型 (LLM),包括生成预训练变压器 (GPT),越来越多地被用于医学和放射学应用.
  • 了解LLM对于医疗保健专业人员至关重要,因为它们的社会影响和日益融入临床工作流程.

研究的目的:

  • 为医学和放射学用例提供优化LLM的技术.
  • 描述与在医疗保健中实施LLM相关的挑战和局限性.
  • 为放射科医生提供LLM技术的基础知识和应用的最佳实践.

主要方法:

  • 探索快速工程技术,以提高LLM响应的准确性和可取性.
  • 细调过程的解释,以适应一般的LLM用于特定的医疗任务,如临床笔记总结.
  • 审查目前在放射学文献中LLMs的概念验证应用.

主要成果:

  • 快速工程和微调是提高LLM可靠性和在医疗环境中的相关性的关键方法.
  • 在医疗保健中,LLM存在独特的挑战,包括概率输出",幻觉",偏见和安全风险.
  • 目前在放射学领域的LLM应用,如决策支持和报告生成,主要是概念验证,因为现有的局限性.

结论:

  • 在放射学中,LLM具有显著的潜力,但其概率和复杂的性质需要仔细优化和理解.
  • 解决幻觉,偏见和可靠性等挑战对于在医学中广泛采用LLM至关重要.
  • 放射科医生需要对LLM技术的基础知识,即时工程和微调才能有效和安全地利用这些工具.