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

[An analysis of the cause and countermeasure of death of patients with severe obstructive sleep apnea hypopnea syndrome].

Zhonghua er bi yan hou tou jing wai ke za zhi = Chinese journal of otorhinolaryngology head and neck surgery·2010
Same author

Involvement of ERK 1/2 activation in electroacupuncture pretreatment via cannabinoid CB1 receptor in rats.

Brain research·2010
Same author

The Regional Network for Asian Schistosomiasis and Other Helminth Zoonoses (RNAS(+)) target diseases in face of climate change.

Advances in parasitology·2010
Same author

Monomeric type I and type III transforming growth factor-β receptors and their dimerization revealed by single-molecule imaging.

Cell research·2010
Same author

Quantitative prediction of the thermal motion and intrinsic disorder of protein cofactors in crystalline state: a case study on halide anions.

Journal of theoretical biology·2010
Same author

Structure determination of selaginellins G and H from Selaginella pulvinata by NMR spectroscopy.

Magnetic resonance in chemistry : MRC·2010

相关实验视频

Updated: Sep 17, 2025

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

529

多方案跨层次的注意力嵌入式U形变压器用于MRI语义细分的语义细分.

Qiang Wang1,2, Yongchong Xue3

  • 1UAV Industry Academy, Chengdu Aeronautic Polytechnic, Chengdu, 610100, China. wq@cap.edu.cn.

Scientific reports
|July 2, 2025
PubMed
概括

这项研究介绍了MSCL-SwinUNet,这是一种用于准确的MRI图像分割的新型变压器模型. 它增强了边界检测和定位,通过先进的注意力机制改善了疾病诊断.

关键词:
跨层次的注意力战略.磁力共振成像语义细分 语义细分多方案注意力机制.在U形变压器.

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

3.0K
Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies
04:25

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Published on: December 15, 2023

2.9K

相关实验视频

Last Updated: Sep 17, 2025

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

529
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

3.0K
Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies
04:25

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Published on: December 15, 2023

2.9K

科学领域:

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

背景情况:

  • 磁共振成像 (MRI) 的精确细分对于疾病诊断至关重要.
  • 目前基于变压器的方法难以捕捉细节,导致边界不准确.
  • 现有的模型缺乏MRI特定的注视模块嵌入策略,限制了性能.

研究的目的:

  • 提出一种新的变压器模型,MSCL-SwinUNet,用于增强MRI图像细分.
  • 为了解决当前方法中细节捕获和MRI特定特征表示的局限性.
  • 提高医疗成像中基于变压器的细分的准确性和通用性.

主要方法:

  • 开发了嵌入式U形变压器 (MSCL-SwinUNet) 的多方案跨层次注意力.
  • 综合跨层次的空间智能注意力 (SW-Attention) 用于详细的信息传输.
  • 整合了跨阶段的通道智能注意力 (CW-Attention) 和多阶段的规模智能注意力 (ScaleW-Attention),用于功能改进.

主要成果:

  • 在ACDC,MM-WHS和Synapse数据集上,MSCL-SwinUNet表现出卓越的准确性和概括性.
  • 该模型有效地保留了详细的边界,超过了最先进的方法.
  • 可视化证实了模型在精确细分和定位方面的能力.

结论:

  • 在医疗成像应用中,MSCL-SwinUNet显著推进了基于变压器的细分.
  • 提出的注意力机制为设计MRI特定嵌入模式提供了新的见解.
  • 这项工作通过提高MRI细分精度来增强诊断能力.