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

4.6K
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...
4.6K

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

Corrigendum to 'Synthesis and structure-activity relationships of N - (3 - (1H-imidazol-2-yl) phenyl) - 3-phenylpropionamide derivatives as a novel class of covalent inhibitors of p97/VCP ATPase' [ Eur. J. Med. Chem. 248 (2023) 115094].

European journal of medicinal chemistry·2026
Same author

Screens and Youth Sleep.

JAMA pediatrics·2026
Same author

Highly ionic-dispersed oxygen electrode for reversible proton ceramic electrochemical cells.

Nature communications·2026
Same author

Dictamnine Inhibits WNT Pathway and EMT Progression in Prostate Cancer and Remodels the Tumor Microenvironment.

Cancers·2026
Same author

Gut microbiota and macrophage crosstalk: implications for colitis-associated colorectal cancer.

Frontiers in cellular and infection microbiology·2026
Same author

Impact of Order Set Design on Pediatric Intravenous Fluid Guideline Adherence: A National Study.

Hospital pediatrics·2026

相关实验视频

Updated: Jul 13, 2025

Author Spotlight: An Efficient and Robust Software for Automated Fusion of Multiple Preclinical Imaging Modalities
07:13

Author Spotlight: An Efficient and Robust Software for Automated Fusion of Multiple Preclinical Imaging Modalities

Published on: October 27, 2023

1.2K

基于视觉先验的交叉模式对齐网络,用于生成放射学报告.

Sheng Zhang1, Chuan Zhou1, Leiting Chen1

  • 1Key Laboratory of Digital Media Technology of Sichuan Province, University of Electronic Science and Technology of China, Chengdu, 611731, China.

Computers in biology and medicine
|October 11, 2023
PubMed
概括

本研究介绍了一种基于视觉先验的跨模态对齐网络,用于自动生成放射学报告. 该模型通过结合视觉先验和改进图像-文本对齐来提高准确性,优于现有方法.

关键词:
相反的注意力注意力.交叉模式的调整.多头注意力注意力多头注意力放射学报告的生成视觉先验 视觉先验 视觉先验

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

2.8K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

439

相关实验视频

Last Updated: Jul 13, 2025

Author Spotlight: An Efficient and Robust Software for Automated Fusion of Multiple Preclinical Imaging Modalities
07:13

Author Spotlight: An Efficient and Robust Software for Automated Fusion of Multiple Preclinical Imaging Modalities

Published on: October 27, 2023

1.2K
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

2.8K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

439

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:

  • 自动化放射学报告生成旨在减少放射科医生的工作量并提高诊断准确性.
  • 现有的方法在整合视觉先验和对准图像-文本特征方面扎.

研究的目的:

  • 开发一个先进的自动化放射学报告生成模型,解决先前方法的局限性.
  • 改善异常区域的识别和放射图像与生成的报告之间的一致性.

主要方法:

  • 提出了一个基于视觉先验的交叉模式对齐网络.
  • 引入对比 注意从图像中提取视觉前置 (差异信息).
  • 开发了一种交叉模式对齐网络,用于使用预先训练的模型进行图像-文本特征对齐.
  • 实现视觉预先引导多头注意力,用于将视觉预先集成到报告生成中.

主要成果:

  • 拟议的模型在IU-Xray和MIMIC-CXR数据集上表现出卓越的性能.
  • 获得了高的BLEU-4分数 (0.188,0.116) 和CIDEr分数 (0.409,0.240),超过了最先进的模型.
  • 有效地识别异常,改善图像-文本一致性.

结论:

  • 基于视觉先验的交叉模式对齐网络显著推进了自动化放射学报告的生成.
  • 整合视觉先验和交叉模式对齐可以提高模型的准确性和可靠性.
  • 这种方法对医学成像分析中的临床应用具有前景.