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

相关实验视频

Updated: Jul 23, 2025

Using Retinal Imaging to Study Dementia
09:17

Using Retinal Imaging to Study Dementia

Published on: November 6, 2017

21.7K

细粒度的注意力和基于知识的协作网络,用于糖尿病视网膜病变的分级.

Miao Tian1, Hongqiu Wang1, Yingxue Sun1

  • 1School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, 611731, China.

Heliyon
|July 14, 2023
PubMed
概括

一个新的深度学习模型,FA+KC-Net,通过将细粒度的注意力与医学知识相结合,改善了糖尿病视网膜病变 (DR) 的分级. 这种方法提高了检测微妙病变的准确性,以便更好地规划治疗.

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

Longitudinal and cross-sectional study of retinal and choroidal changes in primary aldosteronism.

Graefe's archive for clinical and experimental ophthalmology = Albrecht von Graefes Archiv fur klinische und experimentelle Ophthalmologie·2026
Same author

Corrigendum to "Development and Validation of a Risk Prediction Model for Postoperative Pulmonary Infection in Renal Transplant Patients" Transplantation Proceedings, 58(2026), 511-519.

Transplantation proceedings·2026
Same author

Effects of maize plant type and row width in ginger/maize intercropping system on yield, economy, and interspecific competition.

Frontiers in plant science·2026
Same author

Patient voices from the chronic wound care journey: A meta-synthesis of experiences with negative pressure therapy.

Journal of vascular nursing : official publication of the Society for Peripheral Vascular Nursing·2026
Same author

Predictors of treatment response to subthreshold micropulse laser and oral spironolactone therapy for central serous chorioretinopathy.

BMC ophthalmology·2026
Same author

Joint effects and dynamic trajectories of metabolic insulin resistance and systemic inflammation in the risk of renal cell carcinoma: a UK Biobank cohort analysis.

World journal of urology·2026

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:

  • 准确的糖尿病视网膜病变 (DR) 分级对于预防视力丧失至关重要.
  • 目前的深度学习 (DL) 系统正在与微妙的DR损伤作斗争,缺乏医学知识的整合.
  • 这限制了自动化DR分级系统的实际应用和可解释性.

研究的目的:

  • 开发一个新的深度学习模型,FA+KC-Net,以改善糖尿病视网膜病变 (DR) 的分级.
  • 通过结合细粒度的注意力和医学知识来解决现有的DL模型的局限性.
  • 提高临床使用DR分级的准确性和可解释性.

主要方法:

  • 提出了一个新的FA+KC-Net,结合了精细的注意网络和基于知识的协作网络.
  • 细粒度的注意力网络从 fundus 图像中捕捉到微妙的,小的图像特征.
  • 基于知识的网络提取了DR病变 (MA,SE,EX,HE) 的先验医学知识特征.
  • 决策规则将两个网络的结果合并为最终的DR分级.

主要成果:

  • 在四个数据集 (DDR,Messidor,APTOS,EyePACS) 中,FA+KC-Net表现出高准确性和稳定性.
关键词:
注意力机制注意力机制糖尿病视网膜病变分级的分级精细粒度的 细粒度的基于知识的网络网络.医疗图像分析 医学图像分析

更多相关视频

Behavioral Assessment of Visual Function via Optomotor Response and Cognitive Function via Y-Maze in Diabetic Rats
07:41

Behavioral Assessment of Visual Function via Optomotor Response and Cognitive Function via Y-Maze in Diabetic Rats

Published on: October 23, 2020

5.9K
Quantification of Diabetes-induced Adherent Leukocytes in Retinal Vasculature
05:54

Quantification of Diabetes-induced Adherent Leukocytes in Retinal Vasculature

Published on: January 24, 2025

340

相关实验视频

Last Updated: Jul 23, 2025

Using Retinal Imaging to Study Dementia
09:17

Using Retinal Imaging to Study Dementia

Published on: November 6, 2017

21.7K
Behavioral Assessment of Visual Function via Optomotor Response and Cognitive Function via Y-Maze in Diabetic Rats
07:41

Behavioral Assessment of Visual Function via Optomotor Response and Cognitive Function via Y-Maze in Diabetic Rats

Published on: October 23, 2020

5.9K
Quantification of Diabetes-induced Adherent Leukocytes in Retinal Vasculature
05:54

Quantification of Diabetes-induced Adherent Leukocytes in Retinal Vasculature

Published on: January 24, 2025

340
  • 在DDR,Messidor和APTOS数据集上实现了最先进的性能.
  • 该模型有效地捕捉了微妙的病变,并整合了医疗知识,以改善分级.

    • 结论:

    • 拟议的FA+KC-Net显著提高了糖尿病视网膜病变分级的准确性.
    • 将细粒度的注意力与医学知识相结合,为眼科人工智能提供了一个有希望的方向.
    • 该模型的性能表明,在临床环境中可能有实际应用的潜力.