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

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

Accuracy and precision of automated kidney stone detection on CT.

Abdominal radiology (New York)·2026
Same author

Large language models are poor clinical administrators: An evaluation of structured queries in real-world electronic health records.

PLOS digital health·2026
Same author

Post-deployment monitoring of foundation models in radiology: Why outputs aren't enough.

European radiology·2026
Same author

Evaluating the Association of Nontumor Kidney Perirenal Fat Characteristics With Long-Term Renal Function and Mortality After Radical Nephrectomy.

Mayo Clinic proceedings·2026
Same author

A Deep Learning Framework for Enhanced Ovarian Adnexal Mass Classification Using Routinely Acquired Ultrasound Images.

Journal of imaging informatics in medicine·2026
Same author

Carotid revascularization and hemispheric white matter disease progression.

Journal of stroke and cerebrovascular diseases : the official journal of National Stroke Association·2026
Same journal

Kolmogorov-Arnold Guided Local-Global Attention for Medical Image Classification.

Journal of imaging informatics in medicine·2026
Same journal

Artificial Intelligence-Assisted Inner Ear Computed Tomography Analysis: Radiomics-Based Comparison of Affected and Unaffected Ears in Idiopathic Sudden Sensorineural Hearing Loss.

Journal of imaging informatics in medicine·2026
Same journal

High Adoption, Higher Expectations: A Cross-Sectional Survey of Radiologist Engagement with Artificial Intelligence in the United Arab Emirates.

Journal of imaging informatics in medicine·2026
Same journal

Complex-valued Multi-scale Hybrid Attention Network for Fast MRI via Sparsified Data Learning.

Journal of imaging informatics in medicine·2026
Same journal

Automatic Phase and Sequence Identification in Gd-EOB-DTPA-Enhanced Liver MRI Using Deep Convolutional and Sequential Learning.

Journal of imaging informatics in medicine·2026
Same journal

Ultrasound-Based AI in Predicting Hormone Receptor Status in Breast Cancer: Is "Digital Biopsy" Possible.

Journal of imaging informatics in medicine·2026
查看所有相关文章

相关实验视频

Updated: Mar 18, 2026

Author Spotlight: Improving Radiation Therapy Access with Radiation Planning Assistant
05:18

Author Spotlight: Improving Radiation Therapy Access with Radiation Planning Assistant

Published on: October 6, 2023

2.0K

放射学协议的自动预测使用检索增强代增强代.

Conrad Testagrose1, Panagiotis Korfiatis2, Justin Benfield2

  • 1Center for Augmented Intelligence in Imaging, Mayo Clinic, Jacksonville, FL, 32224, USA. Testagrose.Conrad@mayo.edu.

Journal of imaging informatics in medicine
|March 17, 2026
PubMed
概括
此摘要是机器生成的。

大型语言模型 (LLM) 显示了自动化放射性协议选择的前景. 检索增强生成 (RAG) 在某些站点提高了准确性,但需要特定站点的调以获得最佳性能.

关键词:
深度学习是一种深度学习.大型语言模型.放射学 放射学是一门学科.检索增强生成的增强生成

更多相关视频

Radiation Planning Assistant - A Streamlined, Fully Automated Radiotherapy Treatment Planning System
08:25

Radiation Planning Assistant - A Streamlined, Fully Automated Radiotherapy Treatment Planning System

Published on: April 11, 2018

16.1K
Automation of a Positron-emission Tomography PET Radiotracer Synthesis Protocol for Clinical Production
10:20

Automation of a Positron-emission Tomography PET Radiotracer Synthesis Protocol for Clinical Production

Published on: October 26, 2018

12.0K

相关实验视频

Last Updated: Mar 18, 2026

Author Spotlight: Improving Radiation Therapy Access with Radiation Planning Assistant
05:18

Author Spotlight: Improving Radiation Therapy Access with Radiation Planning Assistant

Published on: October 6, 2023

2.0K
Radiation Planning Assistant - A Streamlined, Fully Automated Radiotherapy Treatment Planning System
08:25

Radiation Planning Assistant - A Streamlined, Fully Automated Radiotherapy Treatment Planning System

Published on: April 11, 2018

16.1K
Automation of a Positron-emission Tomography PET Radiotracer Synthesis Protocol for Clinical Production
10:20

Automation of a Positron-emission Tomography PET Radiotracer Synthesis Protocol for Clinical Production

Published on: October 26, 2018

12.0K

科学领域:

  • 放射学中的人工智能
  • 临床决策支持系统 临床决策支持系统
  • 医疗信息学 医疗信息学

背景情况:

  • 放射学协议的选择是复杂的,耗时的,容易出现错误.
  • 自动化方法面临着诸如阶级不平衡和特定地点的变化等挑战.
  • 大型语言模型 (LLM) 提供了提高协议选择效率的潜力.

研究的目的:

  • 评估LLM在大规模放射性协议选择中的有效性.
  • 为了比较检索增强生成 (RAG) 与直接微调的协议选择.
  • 评估RAG对不同临床场所的准确性,弃权率和适应能力的影响.

主要方法:

  • 经过培训的特定站点的Llama 3.2 3B LLMs使用三个梅奥诊所站点的患者报告.
  • 通过整合分区范围的FAISS索引来实现RAG的上下文证据.
  • 微调非RAG和RAG增强模型的性能比较,使用宏和加权F1分数.

主要成果:

  • 无论是RAG还是非RAG模型,在各个地点都表现出强的基线性能.
  • 在亚利桑那州和佛罗里达州,RAG显著改善了宏观F1,但在罗切斯特没有.
  • 在大多数地点,RAG引入了一个可解释的弃权机制,基线率较低 (1-2.5%).

结论:

  • LLM,特别是RAG,可以支持可靠的放射性协议大规模选择.
  • 在不同站点上,RAG的有效性是异质的,需要特定站点的调整.
  • RAG的可适应的检索索引和弃权机制为临床工作流集成提供了运营优势.