相关实验视频

Updated: May 5, 2026

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

从MRI图像中自动细分骨肌肉,使用修改的U-Net和一种新的数据增强方法

Zhicheng Lin¹, William H Henson², Lisa Dowling³

¹Department of Automatic Control and Systems Engineering, University of Sheffield, Sheffield, United Kingdom.

Frontiers in bioengineering and biotechnology

|March 8, 2024

概括

深度学习模型从MRI扫描中准确地对绝经后妇女的下肢肌肉进行细分. 一种新的数据增强技术进一步提高了细分性能,特别是对于小型数据集.

科学领域:

生物医学成像技术生物医学成像技术
医学图像分析医学图像分析
肌肉骨成像系统的成像

背景情况:

在MRI中手动肌肉细分是劳动密集型的,容易出现错误.
绝经后的女性经历肌肉体积下降,需要精确的监测.
准确的细分对于诊断和管理肌肉骨疾病至关重要.

研究的目的:

评估深度学习 (DL) 模型用于绝经后妇女的自动肌肉细分.
为了比较U-Net,UNet++,特征融合-UNet (FFU) 和注意力-特征融合-UNet (AFFU) 模型的性能.
引入和评估一种新的数据增强方法,以提高DL模型的性能.

主要方法:

四个DL模型 (U-Net,UNet++,FFU,AFFU) 被训练并测试了绝经后妇女的MRI扫描.
在三个独立的数据集中对16个下肢肌肉进行了细分.
应用了数据增强方法来扩大培训数据集.
使用子相似系数 (DSC),相对体积误差 (RVE) 和豪斯多夫距离 (HD) 来量化性能.

主要成果:

注意-特征-融合-UNet (AFFU) 模型在所有数据集中显示出最佳性能.
AFFU获得了高的DSC分数 (例如,肥胖的绝经后妇女的0.862±0.048).
数据增强显著改善了U-Net和AFFU的DSC,1-RVE和HD分数.

结论:

深度学习模型可用于绝经后妇女的自动肌肉细分.
在AFFU模型中显示出这个任务的优异性能.
拟议的数据增强方法有效地提高了DL模型的性能,特别是在有限的数据.

关键词:

自动细分自动细分自动细分数据增强数据增强深度学习是一种深度学习.肌肉肌肉肌肉肌肉肌肉神经网络的神经网络的神经网络

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

相关概念视频

Skeletal Muscle Anatomy

Skeletal Muscle Anatomy

Skeletal muscle is the most abundant type of muscle in the body. Tendons are the connective tissue that attaches skeletal muscle to bones. Skeletal muscles pull on tendons, which in turn pull on bones to carry out voluntary movements.

Classification of Skeletal Muscle Fibers

Classification of Skeletal Muscle Fibers

Skeletal muscles continuously produce ATP to provide the energy that enables muscle contractions. Skeletal muscle fibers can be categorized into three types based on differences in their contraction speed and how they produce ATP, as well as physical differences related to these factors. Most human muscles contain all three muscle fiber types, albeit in varying proportions.
Slow-Twitch Muscle Fibers
Slow oxidative, muscle fibers appear red due to large numbers of capillaries and high levels of...