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

Single-cell profiling identifies an AIM2-dependent macrophage program amplifying T cell-mediated acute cardiac allograft rejection.

International immunopharmacology·2026
Same author

MPND Loss Epigenetically Activates TGF-β/SMAD3 Signaling to Drive Tumor Progression and Metastasis in Non-small Cell Lung Cancer.

Cancer research·2026
Same author

Hypoxia-induced ADAM8⁺ macrophages and FAP⁺ fibroblasts form an extracellular matrix-remodeling niche at the tumor boundary in HCC.

Cancer immunology research·2026
Same author

Double-Pronged NAD Preservation: Delaying Cellular Senescence and Initiating Musculoskeletal Regeneration.

Aging cell·2026
Same author

Effect of a Computer-Aided Device for Detecting Gastric Neoplasms: A Multicenter, Randomized Controlled Trial.

Gastroenterology·2026
Same author

A Photothermal Transducer Regulates Transmembrane Calcium Flow for Synergistic Osteoarthritis Therapy.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2026

相关实验视频

Updated: Jun 29, 2025

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

395

多尺度嵌套UNet带变压器用于结直肠多片细分.

Zenan Wang1, Zhen Liu1, Jianfeng Yu1

  • 1Department of Gastroenterology, Beijing Chaoyang Hospital, the Third Clinical Medical College of Capital Medical University, Beijing, China.

Journal of applied clinical medical physics
|March 29, 2024
PubMed
概括

这项研究引入了一种新的深度学习模型,用于结肠多细分,其性能优于现有的方法. 增强的架构有效地捕捉了本地和全球特征,提高了各种多尺寸的准确性.

关键词:
结肠直肠多胞体的发生.深度学习是一种深度学习.聚的细分化聚的细分化变压器的变压器是一个变压器.

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

2.7K
Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
05:56

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

2.5K

相关实验视频

Last Updated: Jun 29, 2025

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

395
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

2.7K
Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
05:56

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

2.5K

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:

  • 对结肠镜检测和局部化片的检测和局部化对于结肠镜检查至关重要.
  • 像U-Net这样的卷积神经网络 (CNN) 在细分方面表现出色,但在长距离依赖方面扎.
  • 有限的受体场阻碍了精确的多重体细分.

研究的目的:

  • 开发一种用于聚细分的新型架构.
  • 将局部特征提取与远程依赖模型集成在一起.
  • 提高多片细分模型的准确性和概括性.

主要方法:

  • 开发了一个混合CNN-Transformer架构,集成了一个多尺度嵌套的U-Net与变压器层.
  • 在编码器和解码器之间嵌入了变压器层,以捕获全球上下文和远程语义信息.
  • 引入了一个多尺度特征融合 (MSFF) 单元,通过融合多分辨率特征来处理多胞体大小的变化.

主要成果:

  • 拟议的模型在多个数据集上实现了高精度 (Kvasir-SEG:0.942平均子得分,CVC-ClinicDB:0.950平均子得分).
  • 与最先进的方法相比,交叉数据集验证证明了优越的概括能力.
  • 废弃性研究证实了单个模型组件的有效性.

结论:

  • 新的混合模型显著提高了对现有方法的聚细分精度.
  • 该模型对不同大小的息肉进行细分的能力表明,在结肠镜中具有很强的临床应用潜力.