A method for the automatic detection of myopia in Optos fundus images based on deep learning,International Journal for Numerical Methods in Biomedical Engineering

当前位置： X-MOL 学术 › Int. J. Numer. Method. Biomed. Eng. › 论文详情

Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)

A method for the automatic detection of myopia in Optos fundus images based on deep learning
International Journal for Numerical Methods in Biomedical Engineering ( IF 2.2 ) Pub Date : 2021-03-26 , DOI: 10.1002/cnm.3460
Zhengjin Shi ₁ , Tianyu Wang ₁ , Zheng Huang _{2,

3,

4} , Feng Xie ₁ , Guoli Song _{2,

3}

Affiliation

Myopia detection is significant for preventing irreversible visual impairment and diagnosing myopic retinopathy. To improve the detection efficiency and accuracy, a Myopia Detection Network (MDNet) that combines the advantages of dense connection and Residual Squeeze-and-Excitation attention is proposed in this paper to automatically detect myopia in Optos fundus images. First, an automatic optic disc recognition method is applied to extract the Regions of Interest and remove the noise disturbances; then, data augmentation techniques are implemented to enlarge the data set and prevent overfitting; moreover, an MDNet composed of Attention Dense blocks is constructed to detect myopia in Optos fundus images. The results show that the Mean Absolute Error of the Spherical Equivalent detected by this network can reach 1.1150 D (diopter), which verifies the feasibility and applicability of this method for the automatic detection of myopia in Optos fundus images.

中文翻译：

基于深度学习的Optos眼底图像近视自动检测方法

近视检测对于预防不可逆的视力障碍和诊断近视性视网膜病变具有重要意义。为了提高检测效率和准确性，本文提出了一种结合密集连接和残余挤压和激发注意优点的近视检测网络（MDNet）来自动检测Optos眼底图像中的近视。首先，应用自动视盘识别方法提取感兴趣区域并去除噪声干扰；然后，实施数据增强技术以扩大数据集并防止过度拟合；此外，构建了一个由注意力密集块组成的 MDNet 来检测 Optos 眼底图像中的近视。结果表明，该网络检测到的球面等效的平均绝对误差可以达到1.1150 D（屈光度），

更新日期：2021-03-26

点击分享查看原文

点击收藏

阅读更多本刊最新论文本刊介绍/投稿指南11