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

Multiple Bar Graph01:07

Multiple Bar Graph

As the name suggests, a multiple bar graph is the same as a bar graph but has multiple bars to depict relationships between different data values. One can include as many parameters as possible. However, each parameter must have the same unit of measurement.
Each bar or column in the multiple bar graph represents a data value. These graphs are used primarily in interrelating two or more sets of data. The categories of different kinds of data are listed along the horizontal or x-axis, whereas...

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

Association between surgical timing and postoperative outcome in patients with residual esophageal cancer after neoadjuvant chemoradiotherapy.

Journal of gastrointestinal oncology·2026
Same author

Network architecture follows coupling in multiphysics systems: single vs. multiple branches in DeepONet and S-DeepONet.

Communications engineering·2026
Same author

Integrating Wound Images and Clinical Text for Pressure Injury Assessment and Treatment Recommendation.

Bioengineering (Basel, Switzerland)·2026
Same author

Implementing generative artificial intelligence in precision oncology: safety, governance, and significance.

Journal of hematology & oncology·2026
Same author

A clinically applicable and generalizable deep learning model for anterior mediastinal tumors in CT images across multiple institutions.

Scientific reports·2026
Same author

Risk factors for bacterial translocation after loop ileostomy closure in patients with colorectal cancer.

International journal of colorectal disease·2025

相关实验视频

Updated: Jun 6, 2026

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

可解读的医疗图像 视觉问题 通过多模式关系图表学习回答问题.

Xinyue Hu1, Lin Gu2, Kazuma Kobayashi3

  • 1The University of Texas Arlington, Arlington, 76010, TX, USA.

Medical image analysis
|July 30, 2024
PubMed
概括

本研究介绍了Medical-CXR-VQA,这是一个大规模的数据集,用于使用胸部X射线进行医学视觉问答 (VQA). 它还介绍了一种新的基于图形的VQA方法,用于在多模式大语言模型中改进临床推理.

关键词:
思想的链条 思想的链条图表神经网络的神经网络大型语言模型医疗数据集是一个医疗数据集.多模态大型视觉语言模型视觉问题答案 视觉问题答案

更多相关视频

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.7K
A Knowledge Graph Approach to Elucidate the Role of Organellar Pathways in Disease via Biomedical Reports
07:35

A Knowledge Graph Approach to Elucidate the Role of Organellar Pathways in Disease via Biomedical Reports

Published on: October 13, 2023

1.6K

相关实验视频

Last Updated: Jun 6, 2026

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
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.7K
A Knowledge Graph Approach to Elucidate the Role of Organellar Pathways in Disease via Biomedical Reports
07:35

A Knowledge Graph Approach to Elucidate the Role of Organellar Pathways in Disease via Biomedical Reports

Published on: October 13, 2023

1.6K

科学领域:

  • 人工智能的人工智能
  • 医疗成像医学成像
  • 自然语言处理自然语言处理.

背景情况:

  • 医疗视觉问题答案 (VQA) 对于医疗保健中的多模式大语言模型 (LLM) 是至关重要的.
  • 现有的医疗VQA数据集的规模和问题复杂性有限,缺乏临床推理能力.
  • 以前基于规则的VQA方法在标签提取中表现出高的错误率.

研究的目的:

  • 为了解决当前医疗VQA数据集和方法的局限性.
  • 开发一个大规模的,临床相关的VQA数据集,专注于胸部X射线图像.
  • 提出一种新的VQA方法,以提高医疗应用中的推理和忠实性.

主要方法:

  • 开发了一个大规模的医疗VQA数据集 (Medical-CXR-VQA),使用LLMs进行胸部X射线分析.
  • 与基于规则的方法相比,接受了LLM培训,提高了62%的标签提取精度.
  • 提出了一种新的VQA方法,利用空间,语义和隐性关系图形,并将图形关注为逻辑推理.

主要成果:

  • 拟议的基于图形的VQA方法有效地学习逻辑推理路径.
  • 医学-CXR-VQA数据集包含有关胸部X射线中的异常,位置和类型的详细问题.
  • 该方法展示了证据和忠实性,这是临床部署的关键品质.

结论:

  • 医疗-CXR-VQA数据集和基于图形的VQA方法提升了医疗VQA的能力.
  • 这项工作为微调和培训更复杂的多模式医学LLM提供了基础.
  • 开发的推理路径可以集成到LLM提示工程和思维链流程中,以增强临床决策支持.