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

LTPNet: Lesion-Aware Triple-Path Feature Fusion Network for Skin Lesion Segmentation.

Journal of imaging·2026
Same author

Association of Recurrent Atrial Fibrillation With Subsequent Kidney Function Decline in Adults Receiving Rhythm Control Therapy.

American journal of kidney diseases : the official journal of the National Kidney Foundation·2026
Same author

GenX induces offspring vascular endothelial ferroptosis by targeting GPX4 for ubiquitination-dependent degradation.

Current research in toxicology·2025
Same author

DIZZiness treatment through implementation and clinical strategy Tactics-2 (DIZZTINCT-2) project-a clinical trial protocol.

Trials·2025
Same author

Cascade Aggregation Network for Accurate Polyp Segmentation.

IET systems biology·2025
Same author

Adjuvanted Recombinant Zoster Vaccine is Effective Against Herpes Zoster Ophthalmicus, and is Associated With Lower Risk of Acute Myocardial Infarction and Stroke in Adults Aged ≥50 Years.

Clinical infectious diseases : an official publication of the Infectious Diseases Society of America·2025

相关实验视频

Updated: Sep 11, 2025

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

493

MRANet:用于精确的多片细分的多维残留注意力网络.

Li Zhang1,2, Yu Zeng1, Yange Sun1

  • 1School of Computer and Information Techonology, Xinyang Normal University, Xinyang, China.

IET systems biology
|August 18, 2025
PubMed
概括
此摘要是机器生成的。

一个新的AI模型,多维残留注意网络 (MRANet),改善了用于早期结直肠癌检测的自动化聚细分. 它有效地处理多种多重体特征,提高诊断准确度.

关键词:
特性提取 特性提取图像分割 图像细分 图像细分医疗图像处理 医疗图像处理

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

2.9K
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

2.8K

相关实验视频

Last Updated: Sep 11, 2025

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

493
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

2.9K
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

2.8K

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:

  • 结肠直肠癌是全球死亡的主要原因之一.
  • 通过聚检测进行早期诊断至关重要.
  • 目前的细分方法与多变异性作斗争.

研究的目的:

  • 引入一个新的AI网络,MRANet,用于强大的多体细分.
  • 增强特征表示,以提高诊断准确度.
  • 确保跨多种临床数据集的可靠性能.

主要方法:

  • 开发了多维残留注意网络 (MRANet).
  • 集成的剩余自我注意力,用于功能改进.
  • 使用多个核心和扩展率卷曲 (CMKD) 具有注意力机制.
  • 利用基于注意力的尺度交互模块 (ASIM) 和基于残余的尺度融合模块 (RSFM) 进行特征合并和细节保存.

主要成果:

  • 在细分多体方面,MRANet表现出卓越的性能.
  • 该模型有效地处理了多胞体大小,形状和分布的变化.
  • 实现了对边界模糊的息肉进行强大的细分.

结论:

  • MRANet在自动化多片细分方面取得了重大进展.
  • 拟议的网络增强了早期结直肠癌的诊断.
  • MRANet为各种临床应用提供了可靠的工具.