使用卷积神经网络对眼科图像进行分类的人工智能驱动方法:一项实验研究
Shagundeep Singh1, Raphael Banoub2, Harshal A Sanghvi1,3,4
1Department of CEECS, Florida Atlantic University, FL, USA.
Current medical imaging
|May 9, 2024
概括
一个新的深度学习模型增强了VGG-16架构,从视网膜图像中检测出白内障,绿内障和糖尿病视网膜病变等常见眼睛疾病的准确率达到98%. 这一进步为眼科早期诊断和治疗提供了巨大的潜力.
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:
- 早期发现眼病对于及时治疗和减轻视力损失至关重要.
- 深度学习 (DL) 模型,特别是卷积神经网络 (CNN),越来越多地用于眼科中分析临床图像.
- 现有的DL算法,如DenseNet,ResNet和VGG-16,显示出疾病检测的前景.
研究的目的:
- 开发和评估一种新的组合深度学习CNN模型,用于分类视网膜色底图像 (RCFI).
- 评估模型在识别特定眼部疾病方面的表现:白内障,绿内障和糖尿病视网膜病变.
- 确定模型作为这些疾病的查工具的诊断潜力.
主要方法:
- 该研究涉及通过增加VGG-16架构的额外卷积层来创建组合深度学习CNN模型.
- 该模型在一组混合的RCFI数据集上进行了训练和评估,这些RCFI显示了各种眼部疾病的特征.
- 绩效指标侧重于分类准确性和对二进制疾病检测的诊断潜力.
主要成果:
- 拟议的模型是一个增强的VGG-16,增加了卷积层,显著提高了性能.
- 该模型在对RCFI进行分类时达到98% (p<0.05) 的高准确性.
- 改进后的模型显示了用于检测白内障,绿内障和糖尿病视网膜病变的良好诊断潜力.
结论:
- 开发的深度学习模型是准确的,适合整合到眼科临床决策支持系统.
- 该模型的高精度和诊断潜力支持其作为常见眼睛疾病的早期查工具的使用.
- 这项研究强调了先进的DL技术在改善眼科诊断方面的价值.
相关概念视频
01:24Vision
53.2K
Vision is the result of light being detected and transduced into neural signals by the retina of the eye. This information is then further analyzed and interpreted by the brain. First, light enters the front of the eye and is focused by the cornea and lens onto the retina—a thin sheet of neural tissue lining the back of the eye. Because of refraction through the convex lens of the eye, images are projected onto the retina upside-down and reversed.
53.2K
01:26Visual System
574
Light enters the eye through the cornea, a transparent, dome-shaped surface covering the surface of the eyeball that helps to direct and focus incoming light. This light is then channeled toward the pupil, an adjustable opening whose size is controlled by the iris. The iris, a pigmented muscle, regulates the amount of light entering the eye by contracting or dilating the pupil, thereby ensuring optimal light levels for clear vision.
Once through the pupil, the light passes through the lens, a...
Once through the pupil, the light passes through the lens, a...
574