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

Diabetic Retinopathy

Diabetic Retinopathy

DefinitionDiabetic retinopathy is a microvascular complication of diabetes affecting the retinal blood vessels.Risk FactorsDiabetic retinopathy is present in almost all individuals with type 1 diabetes and more than 60% of those with type 2 diabetes after two decades of disease.The risk increases with poor glycemic control, hypertension, dyslipidemia, smoking, pregnancy, and puberty.Although cataracts and glaucoma are also more frequent in people with diabetes, retinopathy remains the leading...

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

Correction: Shah et al. Visualization of Critical Limits and Critical Values Facilitates Interpretation. <i>Diagnostics</i> 2025, <i>15</i>, 604.

Diagnostics (Basel, Switzerland)·2026

Same author

High-Dimensional Flow Cytometry Identifies Immune Signatures Associated with Septic Shock Severity in Critically Ill Postoperative Patients.

Anaesthesia, critical care & pain medicine·2026

Same author

Integrated immune and endothelial profiling predicts 90-day mortality in postoperative sepsis and septic shock.

EBioMedicine·2026

Same author

Combined explainable deep learning model to predict pediatric sleep apnea from ECG and SpO<sub>2</sub>.

Measurement : journal of the International Measurement Confederation·2026

Same author

The potential of clustering methods for pre-test triage in sleep medicine: A systematic review.

Sleep medicine reviews·2026

Same author

An explainable deep learning approach for sleep staging in sleep apnea patients across all age subgroups from pulse oximetry signals.

Engineering applications of artificial intelligence·2026

Search research articles

相关实验视频

Updated: Jul 8, 2026

Using Retinal Imaging to Study Dementia

Using Retinal Imaging to Study Dementia

Published on: November 6, 2017

基于注意力的深度学习框架用于自动底部图像处理,以帮助糖尿病视网膜病变分级.

Roberto Romero-Oraá¹, María Herrero-Tudela², María I López¹

¹Biomedical Engineering Group, University of Valladolid, Valladolid, 47011, Spain; Centro de Investigación Biomédica en Red en Bioingeniería, Biomateriales y Nanomedicina (CIBER-BBN), Spain.

Computer methods and programs in biomedicine

|April 7, 2024

概括

这项研究引入了一种新的深度学习框架,用于糖尿病视网膜病变 (DR) 的分级,将黑暗和明亮的视网膜病变分开,以提高准确性和可解释性. 该方法产生可解释的注意力图,帮助临床医生在早期DR检测和诊断.

关键词:

注意力机制注意力机制深度学习是一种深度学习.糖尿病视网膜病变分级的分级可解释的人工智能基金图片基金图片

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

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

相关实验视频

Last Updated: Jul 8, 2026

Using Retinal Imaging to Study Dementia

Using Retinal Imaging to Study Dementia

Published on: November 6, 2017

Deep Neural Networks for Image-Based Dietary Assessment

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

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

科学领域:

眼科医生眼科眼科
医疗成像医学成像
人工智能的人工智能

背景情况:

检测糖尿病视网膜病变 (DR) 对于预防视力丧失至关重要,但手动分级是耗时的.
自动化DR分级系统往往难以同时检测不同类型的病变.
需要可解释AI (XAI) 来支持DR查中的临床决策.

研究的目的:

开发一个端到端的深度学习框架,自动将DR分为5个严重程度.
通过独立处理深色 (红色) 和明亮的视网膜病变来优化DR分类.
为临床医生提供可解释的注意力图,以加强诊断支持.

主要方法:

开发了一种新的注意力机制,分解视网膜图像以分别关注黑暗和明亮的结构.
该框架包括图像质量评估,数据增强,转移学习和微调.
使用Xception架构和焦点损失函数进行特征提取和处理数据不平衡.

主要成果:

拟议的方法实现了83.7%的准确性和0.78的平方加权卡帕在5类DR分级.
独立的注意力图被生成,区分红色病变 (例如,微动脉瘤,出血) 和明亮病变 (例如,硬排泄物).
这些注意力图为模型的预测提供了至关重要的解释能力.

结论:

开发的框架有效地自动化了糖尿病视网膜病变分级.
对不同类型的病变进行分离的注意力优化了分类性能.
生成的注意力图增强了视觉解释,将该方法定位为早期DR检测的有价值的诊断辅助.