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

Magnetic Resonance Imaging01:24

Magnetic Resonance Imaging

10.0K
Magnetic resonance imaging (MRI) is a noninvasive medical imaging technique based on a phenomenon of nuclear physics discovered in the 1930s, in which matter exposed to magnetic fields and radio waves was found to emit radio signals. In 1970, a physician and researcher named Raymond Damadian noticed that malignant (cancerous) tissue gave off different signals than normal body tissue. He applied for a patent for the first MRI scanning device in clinical use by the early 1980s. The early MRI...
10.0K

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

A Systematic Evaluation of Image Preprocessing in Deep Learning Detection and Segmentation of Intracranial Metastatic Disease.

AJNR. American journal of neuroradiology·2026
Same author

Alignment of Policy, Practice, and Patient Safety for Trustworthy AI in Radiology.

Radiology. Artificial intelligence·2026
Same author

Explainable Artificial Intelligence (AI) for Medical Imaging: A Framework for Bridging the AI Trust Gap.

AJR. American journal of roentgenology·2026
Same author

Mapping the Complexity of Cancer Screening and Multi-Disciplinary Care Coordination in Safety-Net Systems.

Journal of the American College of Radiology : JACR·2026
Same author

Chronic Subdural Hematoma Segmentation: A Dedicated Model to Overcome the Limitations of Acute Hemorrhage Segmentation Across Chronic Subdural Hematoma Subtypes and Density Variations.

Journal of imaging informatics in medicine·2026
Same author

Portrayal of Medical Students in Artificial Intelligence- Generated Images.

WMJ : official publication of the State Medical Society of Wisconsin·2026

相关实验视频

Updated: Feb 21, 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

1.2K

使用大型语言模型标准化异质MRI系列描述元数据.

Peter I Kamel1,2,3, Florence X Doo4,5,6, Dharmam Savani4,5,7

  • 1Department of Neuroradiology, Division of Diagnostic Imaging, MD Anderson Cancer Center, Houston, TX, USA. peterkamelmd.correspondence@gmail.com.

Journal of imaging informatics in medicine
|May 29, 2025
PubMed
概括
此摘要是机器生成的。

大型语言模型 (LLM) 可以有效地分类异构的MRI系列描述 (SD),提高数据标准化. GPT-4o取得了最高的表现,证明了LLMs的最高表现.

关键词:
DICOM 的元数据.统一化 统一化 统一化大型语言模型.系列描述 系列描述标准化 标准化 标准化

更多相关视频

A Standardized Pipeline for Examining Human Cerebellar Grey Matter Morphometry using Structural Magnetic Resonance Imaging
11:50

A Standardized Pipeline for Examining Human Cerebellar Grey Matter Morphometry using Structural Magnetic Resonance Imaging

Published on: February 4, 2022

4.6K
Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly
12:50

Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly

Published on: April 14, 2014

40.9K

相关实验视频

Last Updated: Feb 21, 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

1.2K
A Standardized Pipeline for Examining Human Cerebellar Grey Matter Morphometry using Structural Magnetic Resonance Imaging
11:50

A Standardized Pipeline for Examining Human Cerebellar Grey Matter Morphometry using Structural Magnetic Resonance Imaging

Published on: February 4, 2022

4.6K
Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly
12:50

Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly

Published on: April 14, 2014

40.9K

科学领域:

  • 医学成像和人工智能 医学成像和人工智能
  • 放射学和机器学习应用程序

背景情况:

  • 磁共振成像元数据,特别是自由文本系列描述 (SDs),由于来自制造商和技术人员的输入变化,表现出显著的异质性.
  • 这种变异性使MRI序列的准确识别变得复杂,影响了诸如悬挂协议选择和数据集策划等基本任务.

研究的目的:

  • 评估大型语言模型 (LLM) 在自动分类异质MRI系列描述 (SD) 中的有效性.
  • 为了评估各种LLM的性能与神经放射学家对MRISDs的基本真相分类相比.

主要方法:

  • 在2016年至2022年期间进行的无对比脑部MRI检查的分析.
  • 由执业的神经放射学家将独特系列描述 (SD) 手动分类到预定义的类别 (T1,T2,T2/FLAIR,SWI,DWI,ADC,其他).
  • 多个LLM (GPT 3.5 Turbo,GPT-4,GPT-4o,Llama 3 8b,Llama 3 70b) 的性能评估,使用曲线下的面积 (AUC) 作为主要指标,GPT-4o还负责生成正则表达式模板.

主要成果:

  • 观察到高度的变化,在1395个独特的SD中,52.1%的SD只出现在一次.
  • 当提供详细提示时,GPT-4o获得了最高的性能,所有系列的平均AUC为0.983 ± 0.020.
  • GPT模型显著优于Llama模型;GPT-4o的正则表达式生成显示出不一致的性能 (AUC为0.774±0.161).

结论:

  • 大型语言模型 (LLM) 在解释和标准化异质MRI系列描述 (SD) 中表现出显著的有效性.
  • 该研究强调了LLM在提高MRI数据管理和分析的准确性和效率方面的潜力.