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

Mechanism of action of Houttuynia cordata extract and its application in animal production.

Frontiers in veterinary science·2026
Same author

A versatile method for accurately predicting electronic absorption spectra of tetrapyrrole macrocycles.

Scientific reports·2026
Same author

Defining Activity-Based Subgroups in Multiple Sclerosis: A Review and Framework Proposal.

European journal of neurology·2026
Same author

Vertical Interaction between Thiourea and Perovskite Surface Results in Obviously Enhanced Performance with PCE Surpassing 24% Efficiency.

ACS applied materials & interfaces·2026
Same author

Association of combined ultra-processed food intake (ultra-processed dietary pattern) with cognitive function impairment: a meta-analysis of prospective cohort studies.

Journal of neurology·2026
Same author

Fatty Acid-Binding Protein 4 and Major Adverse Cardiovascular Events: A Dose-Response Meta-Analysis of Prospective Cohort Studies.

European journal of preventive cardiology·2026

相关实验视频

Updated: Sep 18, 2025

Author Spotlight: Understanding the Ultrastructural Basis of Retinal Synaptic Connectivity and Neurotransmitter Localization in Mice
05:15

Author Spotlight: Understanding the Ultrastructural Basis of Retinal Synaptic Connectivity and Neurotransmitter Localization in Mice

Published on: July 12, 2024

497

MSLI-Net:基于多段局部化和多尺度相互作用的视网膜疾病检测网络.

Zhenjia Qi1, Jin Hong1, Jilan Cheng1

  • 1School of Information Engineering, Nanchang University, Nanchang, China.

Frontiers in cell and developmental biology
|June 23, 2025
PubMed
概括
此摘要是机器生成的。

一个新的AI框架,MSLI-Net,使用增强的光学连贯断层扫描 (OCT) 图像分析准确地分类视网膜病变. 这种深度学习模型改善了视网膜疾病的早期诊断,有助于预防视力障碍.

关键词:
病变的局部化 病变的局部化多级特征聚变的多级特征聚变噪音抑制可以抑制噪音.视网膜疾病检测检测 视网膜疾病检测波形变换波形变换波形变换.

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

3.0K
Using Retinal Imaging to Study Dementia
09:17

Using Retinal Imaging to Study Dementia

Published on: November 6, 2017

21.8K

相关实验视频

Last Updated: Sep 18, 2025

Author Spotlight: Understanding the Ultrastructural Basis of Retinal Synaptic Connectivity and Neurotransmitter Localization in Mice
05:15

Author Spotlight: Understanding the Ultrastructural Basis of Retinal Synaptic Connectivity and Neurotransmitter Localization in Mice

Published on: July 12, 2024

497
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

3.0K
Using Retinal Imaging to Study Dementia
09:17

Using Retinal Imaging to Study Dementia

Published on: November 6, 2017

21.8K

科学领域:

  • 眼科和医学成像学
  • 医疗保健中的人工智能
  • 生物医学信号处理

背景情况:

  • 视网膜病变会导致不可逆转的视力损伤,需要早期诊断和精确的识别.
  • 光学连贯断层扫描 (OCT) 对眼科至关重要,但在解释复杂结构和噪声方面面临挑战.
  • 准确的AI辅助诊断视网膜疾病对于有效的疾病管理至关重要.

研究的目的:

  • 开发一个新的AI框架,MSLI-Net,用于改进视网膜图像的分析.
  • 提高使用OCT诊断视网膜疾病的准确性和效率.
  • 为应对用于AI应用的OCT成像中的结构复杂性和噪声的挑战.

主要方法:

  • 拟议的MSLI-Net框架使用ResNet50骨干与多尺度扩展融合 (MDF) 模块进行全球受感场增强.
  • 在修改的特征金字塔网络 (FPN) 中集成的多段损伤定位 (LLM),用于特征提取和噪声抑制.
  • 采用波段子波段空间注意 (WSSA) 模块,通过处理低频和高频波段子波段来降低噪声.

主要成果:

  • 在OCT-C8数据集上,MSLI-Net在视网膜病变分类中实现了96.72%的准确性.
  • 展示了强大的区分性表现,突出了该模型在临床应用中的潜力.
  • 该框架有效处理复杂的视网膜结构和噪声干扰.

结论:

  • MSLI-Net为早期视网膜疾病诊断提供了新的研究方向.
  • 该模型有助于推进高精度医学成像辅助诊断系统的发展.
  • 这种人工智能方法在改善眼科患者的治疗结果方面显著有前途.