期刊
OPHTHALMIC TECHNOLOGIES XXXII
卷 11941, 期 -, 页码 -出版社
SPIE-INT SOC OPTICAL ENGINEERING
DOI: 10.1117/12.2607610
关键词
Van Herick technique; Primary Angle Closure Glaucoma; Narrow Anterior Chamber Angle measurements; ophthalmic Instrumentation; Imaging measurement methods; Deep Learning; Artificial Intelligence; Convolutional Neural Networks
类别
This paper presents a deep learning algorithm for automatically determining the Van Herick grade, with the performances of three different Convolutional Neural Networks verified on eye images of 80 patients. The networks demonstrate sufficient accuracy for Van Herick grade classification in a screening system and can offer real-time response after proper training.
Van Herick technique is a qualitative tool for assessing the anterior chamber angle and can be exploited as a simple screening alternative to gonioscopy. In our previous papers, we presented a novel instrument able to automatically perform the Van Herick manoeuvre. Therefore, to fully automate the screening method from the acquired images, it is still necessary to automatically determine the Van Herick grade. In this paper, we present a deep learning algorithm for automatically determining the Van Herick grade. In particular, the performances of three different Convolutional Neural Networks have been verified by acquiring the eye images of 80 patients. All the networks return the Van Herick grade classification with sufficient accuracy for a screening system and, after proper training, can offer a real-time response.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据