相关实验视频

Updated: Jul 8, 2025

Assessing Early Stage Open-Angle Glaucoma in Patients by Isolated-Check Visual Evoked Potential

Assessing Early Stage Open-Angle Glaucoma in Patients by Isolated-Check Visual Evoked Potential

Published on: May 25, 2020

一个深度网络DeepOpacityNet用于从色底照片中检测白内障

Amr Elsawy¹, Tiarnan D L Keenan¹, Qingyu Chen¹

¹National Center for Biotechnology Information, National Library of Medicine, National Institutes of Health, Bethesda, MD, 20894, USA.

Communications medicine

|December 16, 2023

概括

一个新的AI工具DeepOpacityNet可以通过彩色底部摄影 (CFP) 以比眼科医生更高的准确度检测白内障. 这一突破通过分析易于获得的眼睛图像,提高了可访问的白内障查.

科学领域:

眼科医生眼科眼科
人工智能的人工智能
医疗成像医学成像

背景情况:

传统上,白内障诊断需要眼科医生亲自评估.
彩色底部摄影 (CFP) 是广泛可用的,提供了远程查的潜力.
来自CFP的自动白内障检测可以提高查的可访问性.

研究的目的:

开发和验证DeepOpacityNet,这是一个AI工具,用于从CFP自动检测白内障.
为了比较DeepOpacityNet与人类眼科医生的表现.
确定主要的CFP特征表明白内障.

主要方法:

在AREDS2研究中,DeepOpacityNet对17514个CFP进行了培训.
该模型在20%的测试组中进行了内部验证,并与眼科医生进行了比较.
在三个SEED数据集上进行了外部验证;使用了特征可视化.

主要成果:

DeepOpacityNet实现了更高的内部精度 (0.66) 和AUC (0.72).
人工智能模型的准确性 (0.75) 超过了最好的眼科医生 (0.67).
外部验证显示AUC得分高 (0.86-0.89),表明可以通用.

结论:

DeepOpacityNet有效地检测到CFP的白内障,其性能超过了眼科医生.
人工智能提供了可解释的结果,突出了诸如血管可见性和模糊区域等特征.
这项研究表明,人工智能在增强可访问性白内障查方面的潜力.

更多相关视频

Integrated Photoacoustic Ophthalmoscopy and Spectral-domain Optical Coherence Tomography

Integrated Photoacoustic Ophthalmoscopy and Spectral-domain Optical Coherence Tomography

Published on: January 15, 2013

Quantitative Fundus Autofluorescence for the Evaluation of Retinal Diseases

Quantitative Fundus Autofluorescence for the Evaluation of Retinal Diseases

Published on: March 11, 2016

相关概念视频

Photoreceptors and Visual Pathways

Photoreceptors and Visual Pathways

At the molecular level, visual signals trigger transformations in photopigment molecules, resulting in changes in the photoreceptor cell's membrane potential. The photon's energy level is denoted by its wavelength, with each specific wavelength of visible light associated with a distinct color. The spectral range of visible light, classified as electromagnetic radiation, spans from 380 to 720 nm. Electromagnetic radiation wavelengths exceeding 720 nm fall under the infrared category,...