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

YAP1 lactylation confers cisplatin resistance and prognostic value by suppressing ferroptosis via FOSL1 in bladder cancer.

Cell reports·2026
Same author

Impact-Tolerant Batteries Enabled by High-Conductivity Shear Thickening Electrolytes.

Small (Weinheim an der Bergstrasse, Germany)·2026
Same author

A caddisfly larva case-mimicked gel polymer electrolyte with high toughness and enhanced ion transport for safe lithium metal batteries.

Science advances·2026
Same author

Heavy metal in water deposits over the past 60 years in karst depression.

Environmental pollution (Barking, Essex : 1987)·2026
Same author

Impact of Virtual Reality-Based Therapies on Cognition and Depression in Patients With Parkinson Disease: Systematic Review and Meta-Analysis of Randomized Controlled Trials.

JMIR serious games·2026
Same author

Effects of Y<sub>2</sub>O<sub>3</sub>/ZrO<sub>2</sub> Particles on Dielectric Properties and Voltage Resistance of Polyimide Films.

Materials (Basel, Switzerland)·2026

相关实验视频

Updated: Jul 5, 2025

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

基于DenseNet的多模式脑瘤图像分割.

Xiaoqin Wu1, Xiaoli Yang1, Zhenwei Li1

  • 1School of Medical Technology and Engineering, Henan University of Science and Technology, Luoyang, P. R. China.

PloS one
|January 18, 2024
PubMed
概括

这项研究引入了一种改进的深度学习模型,用于MRI扫描中的脑瘤细分. 这种新的方法增强了特征传输,并使用混合损失函数,在诊断和治疗脑瘤方面获得更高的准确性.

科学领域:

  • 医疗成像医学成像
  • 人工智能的人工智能
  • 神经科学是一个神经科学.

背景情况:

  • 脑瘤细分对于诊断和治疗计划至关重要.
  • 传统的U-net模型面临的挑战是,在多模态MRI中,阶级不平衡和特征丧失.
  • 准确的细分需要强大的算法来保护关键信息.

研究的目的:

  • 开发一个先进的网络模型,用于多模式脑瘤图像细分.
  • 解决现有方法中的类失衡和特征信息丢失问题.
  • 为了提高脑瘤细分算法的准确性和可靠性.

主要方法:

  • 提出了一个结合U-net和DenseNet架构的新型网络模型.
  • 标准的卷积块被更换为密集的块,以增强特征传输.
  • 使用了混合损失函数,结合了二进制交叉和特维斯基系数.

主要成果:

  • 与U-Net,U-Net++和PA-Net相比,提出的算法显示了与U-Net,U-Net++和PA-Net相比显著改善的细分精度.
  • 子系数达到了0.846 (WT),0.861 (TC) 和0.782 (ET).
  • 该算法在瘤核心细分方面表现出卓越的性能,灵敏度指数为0.924.

更多相关视频

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies
04:25

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Published on: December 15, 2023

2.4K
Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images
06:48

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images

Published on: January 7, 2019

8.9K

相关实验视频

Last Updated: Jul 5, 2025

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
Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies
04:25

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Published on: December 15, 2023

2.4K
Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images
06:48

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images

Published on: January 7, 2019

8.9K

结论:

  • 开发的U-net和DenseNet组合模型提供了增强的特征传输和细分精度.
  • 混合损失函数有效地减轻了不相关特征对细分的影响.
  • 这种算法对脑瘤的诊断和治疗具有重要的研究和临床价值.