Search research articles

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 Journal Methods Collections JoVE Encyclopedia of Experiments 存档

教育

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual 教师资源中心教师网站

使用条款与条件

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

Machine Learning for Predicting Coronary Heart Disease Risk in Patients with Hypertension: An Ensemble Modeling Approach.

Healthcare informatics research·2026

Same author

DF-OSELM: a dynamic feedback feature learning model for air quality online prediction.

Environmental monitoring and assessment·2025

Same author

Leveraging transfer learning with deep learning for crime prediction.

PloS one·2024

Same author

Hybrid of deep learning and exponential smoothing for enhancing crime forecasting accuracy.

PloS one·2022

Same author

Origin of the N-coordinated single-atom Ni sites in heterogeneous electrocatalysts for CO<sub>2</sub> reduction reaction.

Chemical science·2021

Same author

Insight into the inhibitory mechanism of inorganic ligands on the adsorption of tetracycline onto hematite.

Journal of environmental management·2021

Search research articles

相关实验视频

Updated: Sep 12, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

MixKNet:一个修改后的U形网络,具有用于医疗图像分割的混合通道卷积.

Kun Zhou¹, Fadratul Hafinaz Hassan²

¹Zhejiang Business Technology Institute; Universiti Sains Malaysia.

Journal of visualized experiments : JoVE

|August 4, 2025

概括

这项研究引入了一个修改后的U形网络用于医疗图像细分,显著减少参数,同时提高准确性. 增强的模型为不同的数据集提供了更好的学习能力和细分性能.

科学领域:

计算机视觉计算机视觉
人工智能的人工智能
医疗成像医学成像

背景情况:

U-Net及其变体在医疗图像细分任务中取得了成功,例如病变检测和细胞细分.
基于人工神经网络的图像处理正在迅速发展,具有广泛的应用.

研究的目的:

呈现一个修改后的U形网络,具有降低的参数和增强的学习能力,用于医疗图像细分.
改进不同目标大小的数据集的细分性能.

主要方法:

减少网络深度和增加网络通道以减少参数.
引入了混合通道卷积模块和通道注意力机制.
采用混合深度卷积来处理不同的细分目标大小.

主要成果:

在MoNuseg和GlasS数据集上取得了最先进的结果.
显示平均子分数分别增加了1.0%和1.37%.
将模型参数降低到1.71M,与UCtransNet相比减少了38.6倍.

结论:

修改后的U-Net架构增强了学习能力和细分性能.

更多相关视频

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

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

Published on: April 14, 2023

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

相关实验视频

Last Updated: Sep 12, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

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

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

Published on: April 14, 2023

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

混合深度卷积有效地解决了在细分中具有不同目标大小的挑战.

拟议的模型为医疗图像细分提供了计算效率高,准确的解决方案.