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

Ultrasonography01:17

Ultrasonography

7.2K
Ultrasonography is an imaging technique that uses high-frequency sound waves to visualize the body's internal structures. It is a non-invasive and safe procedure that does not involve the use of ionizing radiation, making it widely used in various medical fields. Ultrasonography is used to study heart function, blood flow in the neck or extremities, certain conditions such as gallbladder disease, and fetal growth and development.
During an ultrasonography procedure, a handheld device called...
7.2K

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

Explainable residual ensemble modelling for EuroQol-5 dimensions-based quality-of-life assessment and stratification in patients with knee osteoarthritis.

Digital health·2026
Same author

J³SPM AI: An integrated open-source platform for AI-assisted image analysis and image-guided workflows in scanning probe microscopy.

Micron (Oxford, England : 1993)·2026
Same author

RFDNet: Robust Frequency-Based Denoising Network for 3D Ultrasound Vascular Imaging Using a Row-Column Addressed Array.

Ultrasonic imaging·2025
Same author

Purification of Tin Iodide through Solid-State Reaction for Efficient Tin-Lead Mixed Perovskite Solar Cells.

Small (Weinheim an der Bergstrasse, Germany)·2025
Same author

Ultrasound localization microscopy lite (ULM lite): ultrasound localization microscopy with resource-efficient signal processing scheme.

Ultrasonics·2025
Same author

Chemically Anchored PbS-2PACz CQDs Inks for Scalable HTL in Narrow-Bandgap and All-Perovskite Tandem Solar Cells.

Small (Weinheim an der Bergstrasse, Germany)·2025

相关实验视频

Updated: Jan 7, 2026

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

3.1K

DAUS-Net:朝着超声波扫描仪-不可知领域的通用化 强大而准确的细分

Sangheon Lee1, Dongkyu Jung1, Nizar Guezzi1

  • 1Department of Robotics and Mechatronics Engineering, DGIST, Daegu, Republic of Korea.

Ultrasonic imaging
|December 26, 2025
PubMed
概括

一个新的深度学习模型,DAUS-Net,在超声波图像中有效地对乳腺瘤进行细分,无论设备的变化如何. 这克服了数据采集的挑战,改善了医疗成像细分任务的诊断准确性.

关键词:
深度频率过的使用方法深度学习是一种深度学习.域名通用化域名通用化扫描仪-无神论学习学习超声波图像细分 超声波图像细分

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

3.3K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

719

相关实验视频

Last Updated: Jan 7, 2026

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

3.1K
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
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

719

科学领域:

  • 医疗成像医学成像
  • 人工智能的人工智能
  • 生物医学工程 生物医学工程

背景情况:

  • 准确的医疗图像细分对于诊断至关重要,但深度学习模型需要大量的标记数据,这是昂贵的和耗时的.
  • 超声波成像表现出显著的设备依赖的特征变化,需要设备特定的模型培训,并带来实际挑战.

研究的目的:

  • 开发一个强大而准确的细分网络,用于超声波乳腺瘤检测,独立于特定的超声波设备.
  • 提高医疗成像细分中的深度学习模型的通用性.

主要方法:

  • 将深频过 (DFF) 模块集成到U-Net架构中.
  • 频率过在编码器层潜伏空间中的应用,用于适应性组件选择.
  • 用实例规范化取代批量规范化,以消除特定风格的特征.

主要成果:

  • 与传统的U-Net相比,拟议的DAUS-Net在未见的数据集上表现出卓越的性能.
  • 在BUS-BRA数据集上获得0.76的子得分,明显超过U-Net的0.61.
  • 在不同扫描仪上一致检测和细分乳腺瘤,归因于DFF和实例正常化.

结论:

  • DAUS-Net提供了超声波乳腺瘤细分的通用解决方案,克服了设备的变化.
  • 该模型的性能突显了改善临床细分任务的潜力,并降低了数据采集成本.
  • 公共可用的源代码促进了医学成像AI的进一步研究和开发.