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

EmoPoseFace: Head Pose Aware Speech-Driven 3D Emotional Facial Animation Using Latent Diffusion.

IEEE transactions on visualization and computer graphics·2026
Same author

Incremental feature fusion based time series forecasting with cumulative risk constraint for longitudinal overall survival prediction.

Medical physics·2026
Same author

A Unified Viscoelastic Solver for Multiphase Fluid Simulation Based on a Mixture Model.

IEEE transactions on visualization and computer graphics·2026
Same author

Augmented reality navigation for precise implantation of LC2 pelvic tunnel screws in minimally invasive surgery.

Fundamental research·2026
Same author

Patch2Space: a registration-free segmentation method for misaligned multimodal medical images.

Physics in medicine and biology·2026
Same author

Online Health-Seeking Behaviors and Information Needs Among Patients With Lymphoma in China: Study of Regional and Temporal Trends.

Journal of medical Internet research·2025

相关实验视频

Updated: Jul 6, 2025

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

1.9K

自主监督轻量级深度估计在内镜结合CNN和变压器.

Zhuoyue Yang, Junjun Pan, Ju Dai

    IEEE transactions on medical imaging
    |January 10, 2024
    PubMed
    概括

    这项研究引入了一个轻量级网络,将卷积神经网络 (CNN) 和变压器结合起来,用于医学成像中的自主监督深度估计. 这种新的方法实现了竞争性结果,同时显著减少了模型尺寸.

    科学领域:

    • 医疗工程 医学工程
    • 计算机视觉 计算机视觉
    • 人工智能的人工智能

    背景情况:

    • 3D重建对于医疗工程任务至关重要,如手术导航和机器人.
    • 自主监督的深度估计对于内镜手术很有价值,避免了对地面真相数据的需求.
    • 现有的方法往往需要大量的参数计数,这激励了开发高效模型的动机.

    研究的目的:

    • 提出一个轻量级,自我监督的医疗成像深度估计网络.
    • 通过紧密合卷积神经网络 (CNN) 和变压器来增强特征提取.
    • 通过多头注意力机制来提高姿势预测的准确性.

    主要方法:

    • 一个新的网络架构,集成不同编码器尺度的CNN和变压器模块.
    • 利用CNN用于本地纹理感知和转换器用于在等级结构内的全球形状提取.
    • 将多头注意力模块纳入姿势网络以提高准确性.

    主要成果:

    • 拟议的轻量级网络在两个数据集上实现了与现有方法可比的性能.
    • 该模型有效地压缩了参数,为深度估计提供了更有效的解决方案.
    • 层次化的特征提取利用了CNN和变形金刚的互补优势.

    更多相关视频

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

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

    Published on: July 5, 2024

    405
    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

    相关实验视频

    Last Updated: Jul 6, 2025

    A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
    04:23

    A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

    Published on: April 21, 2023

    1.9K
    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
    04:48

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

    Published on: July 5, 2024

    405
    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

    结论:

    • 开发的轻量级CNN-Transformer网络为医疗应用中的自我监督深度估计提供了有效的解决方案.
    • 这种方法展示了紧密合的CNN-Transformer架构在高效准确的3D重建方面的潜力.
    • 该方法为推进需要精确深度信息的医学成像技术提供了一个有希望的方向.