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

Association Areas of the Cortex01:21

Association Areas of the Cortex

8.8K
Association areas are regions of the cerebral cortex that do not have a specific sensory or motor function. Instead, they integrate and interpret information from various sources to enable higher cognitive processes such as memory, learning, and decision-making. Some key association areas include the following:
Prefrontal Association Area: This area is located in the frontal lobe and is involved in planning, decision-making, and moderating social behavior. It connects with primary motor areas,...
8.8K

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

Comparative Morphometric Study of the Osseous Labyrinth in Humans and Animal Models Using Centerline Analysis.

Noise & health·2026
Same author

Morphology-associated ocular surface toxicity of micro- and nanoplastics: Fiber embedding contributes to persistent injury.

Ecotoxicology and environmental safety·2026
Same author

Multiomics analysis of primary metabolism reveals the genetic basis of nitrogen partitioning modulated by ZmAVT1A-1 in maize.

Nature genetics·2026
Same author

A system-level DOI discrimination method based on SSDA for a brain-dedicated DOI-PET scanner.

Physics in medicine and biology·2026
Same author

High-entropy LDH coupled with Ru nanoclusters for efficient overall seawater splitting.

Dalton transactions (Cambridge, England : 2003)·2026
Same author

Huanglian Wendan ameliorates depression via gut-brain axis-related PPAR-α/allo pathways.

Phytomedicine : international journal of phytotherapy and phytopharmacology·2026

相关实验视频

Updated: Jan 11, 2026

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

729

全球特征关注网络 (GFANet):全球特征关注网络,用于聚体细分.

Leping Lin1, Wenjie Huang1, Ning Ouyang2

  • 1School of Information and Communication, Guilin University of Electronic Technology, Guilin, 541004, China.

Journal of imaging informatics in medicine
|November 10, 2025
PubMed
概括

一个新的深度学习模型,GFANet,通过整合几何方向和多尺度特征,准确地细分结直肠息肉. 这种方法可以更好地检测小息肉,并提高结直肠癌的诊断准确度.

关键词:
功能注意力,注意力,注意力.全球特征方向,全球特征方向.多个尺度的信息聚合.聚片细分的细分方法

更多相关视频

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

1.0K
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

3.3K

相关实验视频

Last Updated: Jan 11, 2026

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

729
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

1.0K
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

3.3K

科学领域:

  • 医疗成像医学成像
  • 人工智能的人工智能
  • 在瘤学瘤学.

背景情况:

  • 结直肠多是结直肠癌的关键指标,需要精确的细分来诊断和治疗.
  • 当前的深度学习模型因大小,形状,颜色和模糊边界的变化而与多片细分斗争.

研究的目的:

  • 开发一个先进的深度学习网络,GFANet,以改善结直肠多的自动细分.
  • 解决现有方法的局限性,包括对几何特征的处理不佳,对小息肉的敏感性低,以及不够的多尺度信息融合.

主要方法:

  • 引入GFANet,其中包括一个全局特征方向编码器 (GFDE),特征注意模块 (FAM) 和多尺度信息聚合 (MIA).
  • GFDE增强了具有具有挑战性的视觉特征的息肉的局部化.
  • FAM精简了特征表示,并抑制了背景噪音.
  • MIA聚合了多个尺度和语义特征,以进行全面的细分.

主要成果:

  • 与五个数据集中的十种最先进的方法相比,GFANet表现出更好的性能.
  • 在CVC-300数据集上实现了90.2%的mDice和83.5%的mIoU,超过了现有的方法.
  • 在ETIS-LaribPolypDB数据集上的mDice显著超过PranNet17.2%,显示出强烈的概括性.

结论:

  • GFANet有效地解决了结直肠多片细分方面的关键挑战,提供了更高的准确性和灵敏性.
  • 该网络的创新模块有助于在识别各种大小和复杂性的多重体方面提供卓越的性能.
  • 在结直肠癌的诊断和管理中,GFANet具有显著的临床应用潜力.