Sarki Rubina, Ahmed Khandakar, Wang Hua, Zhang Yanchun
Victoria University, Ballarat Road, Melbourne, VIC 3011 USA.
Health Inf Sci Syst. 2020 Oct 8;8(1):32. doi: 10.1007/s13755-020-00125-5. eCollection 2020 Dec.
Diabetic eye disease is a collection of ocular problems that affect patients with diabetes. Thus, timely screening enhances the chances of timely treatment and prevents permanent vision impairment. Retinal fundus images are a useful resource to diagnose retinal complications for ophthalmologists. However, manual detection can be laborious and time-consuming. Therefore, developing an automated diagnose system reduces the time and workload for ophthalmologists. Recently, the image classification using Deep Learning (DL) in between healthy or diseased retinal fundus image classification already achieved a state of the art performance. While the classification of mild and multi-class diseases remains an open challenge, therefore, this research aimed to build an automated classification system considering two scenarios: (i) mild multi-class diabetic eye disease (DED), and (ii) multi-class DED. Our model tested on various datasets, annotated by an opthalmologist. The experiment conducted employing the top two pretrained convolutional neural network (CNN) models on ImageNet. Furthermore, various performance improvement techniques were employed, i.e., , , and . Maximum accuracy of 88.3% obtained on the VGG16 model for multi-class classification and 85.95% for mild multi-class classification.
糖尿病眼病是一系列影响糖尿病患者的眼部问题。因此，及时筛查可增加及时治疗的机会并预防永久性视力损害。视网膜眼底图像是眼科医生诊断视网膜并发症的有用资源。然而，人工检测可能既费力又耗时。因此，开发一个自动诊断系统可以减少眼科医生的时间和工作量。最近，在健康或患病视网膜眼底图像分类中使用深度学习（DL）的图像分类已经取得了领先的性能。然而，轻度和多类疾病的分类仍然是一个悬而未决的挑战，因此，本研究旨在构建一个考虑两种情况的自动分类系统：（i）轻度多类糖尿病眼病（DED），和（ii）多类DED。我们的模型在由眼科医生标注的各种数据集上进行了测试。实验采用了在ImageNet上排名前两位的预训练卷积神经网络（CNN）模型。此外，还采用了各种性能改进技术，即 ， ，和 。在VGG16模型上，多类分类获得了88.3%的最高准确率，轻度多类分类获得了85.95%的最高准确率。
