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

Computed Tomography01:10

Computed Tomography

7.9K
Tomography refers to imaging by sections. Computed tomography (CT) is a non-invasive imaging technique that uses computers to analyze several cross-sectional X-rays to reveal minute details about structures in the body.
The technique was invented in the 1970s and is based on the principle that as X-rays pass through the body, they are absorbed or reflected at different levels. In the technique, a patient lies on a motorized platform while a computerized axial tomography (CAT) scanner rotates...
7.9K

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

Radiology report quality improvement through structured provider feedback: a data-driven initiative.

Abdominal radiology (New York)·2026
Same author

Reply to "Artificial Intelligence in Radiology: The Paradox Between Efficiency and Burnout".

AJR. American journal of roentgenology·2026
Same author

Iterative immunoprecipitation and phage pre-wash dramatically improve epitope-resolved serology by VirScan.

Frontiers in virology (Lausanne, Switzerland)·2026
Same author

Artificial Intelligence Sees the Image, Radiologists See the Patient.

AJR. American journal of roentgenology·2026
Same author

Proximity proteomics reveals a role for IFI16 during human coronavirus infection.

bioRxiv : the preprint server for biology·2026
Same author

Modeling heart rate patterns to quantify neonatal opioid withdrawal syndrome.

Pediatric research·2026

相关实验视频

Updated: Jan 10, 2026

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

1000

验证放射学人工智能模型在光子计数CT图像上的性能,使用大型语言模型进行基准真相提取.

Yee Seng Ng1, Mohammed M Kanani2, William E King1

  • 1Department of Radiology, University of Washington, Seattle, Washington.

Journal of the American College of Radiology : JACR
|November 20, 2025
PubMed
概括

大型语言模型 (LLM) 自动从放射学报告中提取地面真相标签,使人工智能 (AI) 工具的可扩展评估成为可能. 这种方法可靠地验证AI性能,即使使用新的成像硬件,如光子计数CT扫描仪.

关键词:
人工智能的人工智能是人工智能.在MLOps中,MLOps是最大的.地面真相提取 提取大型语言模型.模型验证模型验证用光子计数CTCT进行测试.放射学 放射学是指放射学

更多相关视频

Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization
05:49

Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization

Published on: February 23, 2024

1.3K
Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
05:47

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

Published on: June 13, 2025

1.3K

相关实验视频

Last Updated: Jan 10, 2026

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

1000
Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization
05:49

Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization

Published on: February 23, 2024

1.3K
Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
05:47

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

Published on: June 13, 2025

1.3K

科学领域:

  • 放射学 放射学是一门学科.
  • 人工智能的人工智能
  • 医疗信息学 医疗信息学

背景情况:

  • 放射性人工智能 (AI) 工具需要持续监测和验证.
  • 手动从放射学报告中提取地面真相标签是耗时且资源密集的.
  • 新的成像硬件,如光子计数CT (PCCT) 扫描仪,可以引入影响AI性能的输入漂移.

研究的目的:

  • 评估使用大型语言模型 (LLM) 来自动从放射学报告中提取地面真实标签的可行性.
  • 为了使放射性AI工具的可扩展评估和监测.
  • 在新的PCCT扫描仪上验证AI模型的性能.

主要方法:

  • 针对肺栓塞,内出血,椎骨折和脊椎压缩骨折的四种FDA批准的AI工具的回顾性分析.
  • LLM (Llama 3.3) 用于从PCCT的放射学报告和传统扫描仪数据中提取二进制基准真实标签.
  • 人工智能输出与LLM提取的标签的比较,与人类注释者裁决的不一致案件.
  • 使用Fleiss的 κ测试测量Interrater可靠性;在LLM错误纠正后重新计算性能指标.

主要成果:

  • 在所有四个诊断任务中,LLM提取的标签促进了快速AI性能评估.
  • 在PCCT和非PCCT队列之间没有观察到统计学上显著的绩效差异.
  • LLM标签与最终的人类注释有很强的一致性 (κ = 0.731),相当于读者之间的一致性 (κ = 0.720),证实了LLM标签的可靠性.

结论:

  • 大型语言模型提供了一个可扩展和高效的自动化解决方案,用于从放射学报告中提取地面真实标签.
  • 这种基于LLM的方法支持人工智能工具的快速本地验证,有效地应对新成像硬件和输入漂移带来的挑战.