一个残余连接启用了深度神经网络模型用于光盘和光杯细分,用于青光眼的诊断
1Department of Computer Engineering, College of Computer and Information Sciences, King Saud University, Riyadh, Saudi Arabia.
Science progress
|September 25, 2023
概括
早期的青光眼诊断可以防止视力丧失. 这项研究引入了一种新的残留连接深度神经网络 (RC-DNN),用于准确的光杯和光盘细分,提高了青光眼查效率和可靠性.
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:
- 早期的青光眼诊断对于预防视力丧失至关重要,并且需要准确的杯对盘比 (CDR) 估计.
- 当前的自动CDR计算方法往往缺乏准确性和高度复杂性,阻碍其在诊断系统中的使用.
- 现有的深度学习模型用于青光眼的诊断是计算密集的,由于许多参数,需要大量的培训和测试时间.
研究的目的:
- 提出一种新的残余连接深度神经网络 (RC-DNN),以实现高效和准确的联合光盘 (OD) 和光杯 (OC) 分段.
- 通过降低模型复杂性和提高青光眼查诊断精度来解决现有方法的局限性.
主要方法:
- 开发了一个剩余连接深度神经网络 (RC-DNN),利用非身份剩余连接来联合OC和OD检测.
- 该模型采用高效的剩余连接,以实现同时分割,减轻消失梯度,并促进用更少层进行分割.
- 在RIM-ONE和DRISHTI-GS数据集上训练和评估RC-DNN模型.
主要成果:
- RC-DNN模型在两个数据集的OC细分中实现了高性能.
- 关键指标包括子系数为92.62% (DRISHTI-GS) 和86.52% (RIM-ONE),雅卡系数为86.87% (DRISHTI-GS) 和77.54% (RIM-ONE),灵敏度为94.21% (DRISHTI-GS) 和95.36% (RIM-ONE),特异性为99.83% (DRISHTI-GS) 和99.639% (RIM-ONE),以及平衡精度为94.2% (DRISHTI-GS) 和98.9% (RIM-ONE).
- 证明了联合OC和OD细分的显著性能提升,并降低了计算复杂度.
结论:
- 开发的RC-DNN模型为青光眼诊断提供了更好的疗效,稳定性和可靠性.
- 该模型的复杂性降低和高准确性使其适合在人口规模的玻璃眼查计划中部署.
- 突出了高效的深度学习架构的潜力,以推进眼科诊断.
相关概念视频
Anatomy of the Eyeball
7.2K
The eye is a spherical, hollow structure composed of three tissue layers. The outer layer — the fibrous tunic, comprises the sclera — a white structure — and the cornea, which is transparent. The sclera encompasses some of the ocular surface, most of which is not visible. However, the 'white of the eye' is distinctively visible in humans compared to other species. The cornea, a clear covering at the front of the eye, enables light penetration. The eye's middle...
7.2K
Glaucoma: Overview
614
Glaucoma is an eye condition characterized by increased intraocular pressure that damages the retina and optic nerve, leading to irreversible blindness if left untreated. The human eye has various components, including the cornea, iris, pupil, lens, and optic nerve. Aqueous humor is secreted by the epithelium of the ciliary body in the posterior chamber and flows through the trabecular meshwork and canal of Schlemm, maintaining normal intraocular pressure. The trabecular meshwork and the canal...
614


