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

The Retina

The Retina

The retina is a layer of nervous tissue at the back of the eye that transduces light into neural signals. This process, called phototransduction, is carried out by rod and cone photoreceptor cells in the back of the retina.

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

Discomfort Avoidance and Desire for Normality Are Decision-Making Drivers of Footwear Choice in Underserved Communities at Risk of Diabetic Foot Ulcer.

Journal of foot and ankle research·2026

Same author

Nutritional Modulation of Biochemical Stress using <b>Azolla pinnata</b> in <i>E. coli</i> challenged Broiler Chickens Vaccinated with IBDV.

Avian pathology : journal of the W.V.P.A·2026

Same author

Masked invaders: A case series on uncommon manifestations of extrapulmonary tuberculosis.

Lung India : official organ of Indian Chest Society·2026

Same author

Clinical and primary cell evidence reveals complex CFTR function-phenotype relationships.

bioRxiv : the preprint server for biology·2026

Same author

CFTR function in nasal airway cells from symptomatic and asymptomatic CF heterozygotes.

bioRxiv : the preprint server for biology·2026

Same author

Implementation research to develop and optimize delivery models for evidence-based anemia control interventions in India: Protocol for the precision-driven response for anemia control and sustainable health (PRAKASH) study.

PloS one·2026

Search research articles

相关实验视频

Updated: May 22, 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

一个多模型深度网络与可解释的人工智能基础框架用于糖尿病视网膜病变细分和分类.

Neeraj Sharma¹, Praveen Lalwani²

¹School of Computing Sciences and Engineering, VIT Bhopal University, Kothrikalan, Sehore, 466114, Madhya Pradesh, India. neeraj.sharma2019@vitbhopal.ac.in.

Scientific reports

|March 14, 2025

概括

这项研究引入了一个用于诊断糖尿病视网膜病变 (DR) 的AI系统,可以克服图像质量问题. 这种新的方法显著提高了诊断准确度,有助于早期发现和治疗DR.

关键词:

适应性加博波器过器糖尿病视网膜病变糖尿病视网膜病变可以解释的AI和GradCam 修改后的U-Net网络多重折叠的特征是多重折叠的特征自适应的北方高斯霍克优化

更多相关视频

Deep Neural Networks for Image-Based Dietary Assessment

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

Retinal Pathophysiological Evaluation in a Rat Model

Retinal Pathophysiological Evaluation in a Rat Model

Published on: May 6, 2022

相关实验视频

Last Updated: May 22, 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

Deep Neural Networks for Image-Based Dietary Assessment

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

Retinal Pathophysiological Evaluation in a Rat Model

Retinal Pathophysiological Evaluation in a Rat Model

Published on: May 6, 2022

科学领域:

医疗成像医学成像
人工智能的人工智能
眼科医生眼科眼科

背景情况:

糖尿病视网膜病变 (DR) 是糖尿病患者视力丧失的主要原因,需要准确及时诊断.
当前的人工智能驱动的DR诊断系统面临的挑战是图像质量问题,如低对比度,噪音和不均的照明,影响性能.
有效的DR诊断对于预防不可逆转的视力损伤至关重要.

研究的目的:

开发一种基于人工智能的先进系统,用于准确诊断糖尿病视网膜病变.
解决和克服现有的AI模型在处理质量差的视网膜图像方面的局限性.
通过改进的图像处理和分类技术来提高DR检测的性能.

主要方法:

基于混沌地图的自适应性加博波器 (AGF) 已开发,以提高图像质量.
采用了多功能提取技术,包括局部二进制模式 (LBP),加快强特征 (SURF) 和纹理能量测量 (TEM).
使用了一种包含注意层,DenseNet和由自适应性北方鱼优化 (SANGO) 算法优化的优化门循环单元 (OGRU) 的分类模型.
使用Grad Cam验证了细分和分类性能.

主要成果:

拟议的系统在三个数据集中显示出高的诊断准确性:DiaRetDB1 (99.01%),APTOS 2019 (98.98%) 和EyePacs (99.12%).
使用IoU,准确性,精度,回忆,F1-测量和子相似系数 (DSC) 等指标严格评估性能.
该系统在处理各种数据集和图像条件时被证明是稳健可靠的.

结论:

开发的AI系统有效地解决了糖尿病视网膜病诊断中的图像质量挑战.
集成AGF,先进的特征提取和复杂的分类模型显著提高了诊断性能.
这种人工智能驱动的方法为早期DR检测提供了可靠和准确的解决方案,有可能减少糖尿病患者的视力丧失.