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

<i>Radix pseudostellariae</i> Saponins Promote Immunocyte Migration and Chemotaxis via the CCL5/CCR4 Signaling Axis.

Animals : an open access journal from MDPI·2026
Same author

Lightweight Medical Image Segmentation with UNet Architecture.

Studies in health technology and informatics·2026
Same author

Co-occurrence of youth violence, depressive symptoms, and suicidality: A neglected public health situation.

Public health·2026
Same author

The need for protection: a cross-sectional analysis of direct exposure to firearm violence, attitudes towards firearms for protection, and firearm acquisition in California and Louisiana.

Injury epidemiology·2026
Same author

Modification and validation of the teen vaccine hesitancy scale toward vaccines for adolescents.

Vaccine·2026
Same author

Implementation of the National Collegiate Athletic Association Sickle Cell Trait Screening Policy: Methods and Staff and Athlete Perspectives.

Public health genomics·2026

相关实验视频

Updated: Jun 17, 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

1.8K

DAC-Net:一个轻量级的U形网络,基于高效的卷积和对甲状腺结节细分的关注.

Yingwei Yang1, Haiguang Huang1, Yingsheng Shao1

  • 1College of Computer Science and Artificial Intelligence, Wenzhou University, Wenzhou 325000, China.

Computers in biology and medicine
|August 10, 2024
PubMed
概括

轻量级的U形网络DAC-Net实现了高性能甲状腺结节细分. 它显著降低了参数和计算成本,同时性能优于现有方法.

关键词:
注意力机制注意力机制卷积 卷积是指卷积的过程.深度学习是一种深度学习.轻量级的模型轻量级的模型.甲状腺结节细分的细分一个U形网络.

更多相关视频

Author Spotlight: Integrating Ultrasound Imaging with Biochemical Markers for Thyroid Disease Diagnosis
05:41

Author Spotlight: Integrating Ultrasound Imaging with Biochemical Markers for Thyroid Disease Diagnosis

Published on: February 9, 2024

566
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

相关实验视频

Last Updated: Jun 17, 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

1.8K
Author Spotlight: Integrating Ultrasound Imaging with Biochemical Markers for Thyroid Disease Diagnosis
05:41

Author Spotlight: Integrating Ultrasound Imaging with Biochemical Markers for Thyroid Disease Diagnosis

Published on: February 9, 2024

566
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

科学领域:

  • 医疗成像医学成像
  • 计算机视觉 计算机视觉
  • 人工智能的人工智能

背景情况:

  • 甲状腺结节细分算法变得越来越复杂,增加参数数量和计算需求.
  • 临床环境中的资源限制阻碍了复杂的细分模型的实施.
  • 需要高效和高性能算法用于甲状腺结节细分.

研究的目的:

  • 开发一个轻量级的U形网络,DAC-Net,以实现高效准确的甲状腺结节细分.
  • 与现有的最先进模型相比,减少参数数量和计算复杂性.
  • 为了实现适合临床应用的竞争性细分性能.

主要方法:

  • 推出DAC-Net,一个轻量级的U形网络,采用深度可分离卷积和挤压刺激 (DWSE) 进行增强的特征提取.
  • 使用基于注意力的双层注意力 (ADA) 模块,具有Split Atrous卷积,用于全面的全球和本地特征捕获.
  • 实施道和空间尺度连接 (CSSC) 以在不同尺度上有效融合多阶段特征.
  • 在DDTI和TN3K数据集上评估模型.

主要成果:

  • 与最先进的甲状腺结节细分架构相比,DAC-Net表现出优越的细分性能.
  • 该模型实现了参数 (73倍) 和计算成本 (56倍) 的显著降低.
  • 在细分精度方面,DAC-Net的表现优于TransUNet.

结论:

  • DAC-Net为甲状腺结节细分提供了一个计算高效和高性能解决方案.
  • 拟议的架构有效地整合了多个规模的功能,同时保持了轻量级的设计.
  • 由于其减少了资源需求,DAC-Net为临床实施提供了一个可行的替代方案.