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

Proteoglycan-Mimetic Bottle-Brush Polymer Brushes for Osteoarthritis Therapy: Lubrication Enhancement and Multifunctional Disease Modulation.

Macromolecular rapid communications·2026
Same author

Ultrasound-Driven Piezoelectric Nanomaterial Platform Enables Wireless Neuromodulation for Parkinson's Disease.

Acta biomaterialia·2026
Same author

Dynamic evolution of higher alcohols from CO<sub>2</sub> on Fe<sub>3</sub>O<sub>4</sub>-Fe<sub>5</sub>C<sub>2</sub>-Cu catalytic interfaces with amorphous Ti layout.

Nature communications·2026
Same author

An in silico evaluation of tri-allelic SNPs from 1kGP Phase IV data for distant kinship identification and mixture analysis.

Forensic science international. Genetics·2026
Same author

Oral self-assembly nanoemulsion drives <i>in vivo</i> hepatic stellate cell-targeting drug delivery in liver fibrosis.

Drug delivery·2026
Same author

Synthesis and Mechanisms of Scale and Corrosion Inhibition by Ethylenediamine-Benzenesulfonic Acid-Modified Polyaspartic Acid.

Polymers·2026

相关实验视频

Updated: Jul 16, 2025

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

440

MR-Trans:用于医疗图像分割的多分辨率变压器.

Yibo Zou1, Yan Ge1, Linlin Zhao1

  • 1School of Information, Shanghai Ocean University, Shanghai, 201306, China.

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

本研究介绍了MR-Trans,这是一种用于医疗图像细分的新框架,可以保留高分辨率和低分辨率的特征. 通过避免在其他基于变压器的方法中常见的信息丢失,MR-Trans提高了细分精度.

关键词:
功能融合的特点是:医疗图像细分 医疗图像细分多个分辨率的多个分辨率.变压器变压器变压器

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
Author Spotlight: Segmentation and VR for Advanced Neurovascular Interventions
06:18

Author Spotlight: Segmentation and VR for Advanced Neurovascular Interventions

Published on: April 5, 2024

1.1K

相关实验视频

Last Updated: Jul 16, 2025

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

440
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
Author Spotlight: Segmentation and VR for Advanced Neurovascular Interventions
06:18

Author Spotlight: Segmentation and VR for Advanced Neurovascular Interventions

Published on: April 5, 2024

1.1K

科学领域:

  • 医疗成像医学成像
  • 计算机视觉 计算机视觉
  • 人工智能的人工智能

背景情况:

  • 基于变压器的方法,如TransUNet和SwinUNet,用于医疗图像细分.
  • 当前的高低分辨率网络在编码过程中可能会丢失关键的低级语义信息.

研究的目的:

  • 提出一个新的框架,MR-Trans,同时保持高分辨率和低分辨率的特征表示.
  • 通过解决现有方法中的信息丢失来提高医疗图像细分的准确性.

主要方法:

  • MR-Trans使用分支分区模块来创建多分辨率分支.
  • 带有Swin变压器的编码器模块提取远程依赖关系,并采用了一种新的功能融合策略.
  • 一个解码模块结合了PSPNet和FPNet,用于增强的多尺度识别.

主要成果:

  • 与最先进的方法相比,MR-Trans在两个医疗图像细分数据集上表现出卓越的性能.
  • 拟议的方法有效地保留了在传统的高低分辨率网络中丢失的低级语义信息.

结论:

  • 通过保留多分辨率功能,MR-Trans提供了一种有效的医疗图像细分方法.
  • 该框架显示了在医疗图像分析和细分领域的进步的巨大潜力.