糖尿病视网膜病变眼底图像筛查研究  

Fundus Image Screening for Diabetic Retinopathy

作　　者：李家昱 陈明惠 杨瑞君 马文飞 赖湘玲 黄鐸文 刘渡新 马昕宏 沈越 Li Jiayu;Chen Minghui;Yang Ruijun;Ma Wenfei;Lai Xiangling;Huang Duowen;Liu Duxin;Ma Xinhong;Shen Yue(Shanghai Engineering Research Center of Interventional Medical,the Ministry of Education of Medical Optical Engineering Center,Department of Biomedical Engineering,School of Medical Instrument and Food Engineering,University of Shanghai for Science and Technology,Shanghai 200093,China;The Third People’s Hospital of Mianyang City,Mianyang 621000,Sichuan,China)

机构地区：[1]上海理工大学医疗器械与食品学院生物医学工程系,上海介入医疗器械工程技术研究中心,教育部医学光学工程中心,上海200093 [2]四川省绵阳市第三人民医院,四川绵阳621000

出　　处：《中国激光》2022年第11期127-137,共11页Chinese Journal of Lasers

基　　金：国家自然科学基金青年科学基金(61308115);上海市科委产学研医项目(15DZ1940400)。

摘　　要：眼底照相是获取眼部图像的主要技术之一。利用眼底相机对视网膜病变区域进行拍摄可以获得清晰的图像,从获取的图像中能够直接观察到眼球中的渗出物、出血点和微血管瘤,根据检测出的病灶类型、数量和位置等信息可进行糖尿病视网膜病变分类。基于此,本文利用深度神经网络对糖尿病视网膜病变进行自动分类识别,提出了一种体系结构简单、在通用设备上运行速度快的卷积神经网络CA-RepVGG(CA代表Channel Attention, RepVGG为现有模块)。利用单路极简结构的RepVGG模块替代复杂的可使用性较差的模块作为分类模型的主体部位,并选用高效通道注意力机制ECA替代压缩注意力机制SE,以此来提升模型对病变分级的能力。此外,本文还将CA-RepVGG模型与传统的分类模型VGG-16、Inception-V3、ResNet-50和ResNext-50模型进行了比较。从比较结果可以看出,虽然CA-RepVGG模型的参数量最大,但由于其是单分支结构,且只有3×3卷积块,因此它的模型复杂度并不高,分类速度很快,比另外4个模型中分类速度最快的ResNet-50还高出15.3%。另外,利用两个混淆矩阵展示了所提模型的分类结果,其在两个数据集上的准确度都超过了92.4%,精确度不低于91.6%,灵敏度在93.8%以上。从实验结果可知,所提模型不仅可对糖尿病视网膜病变进行分类,而且相比其他现有模型具有一定的优越性。若将该模型应用在临床上,可以提高专业眼科医生在眼科疾病上的诊断效率。Objective Diabetes is a worldwide chronic disease, which can cause changes in vascular performance and result in complications such as diabetic retinopathy(DR). If a patient has DR and it goes undetected, the patient’s eyesight may be lost. Therefore, early detection and early treatment of DR is important for reducing the blindness rate in various countries. At present, the acquisition of fundus images mainly depends on nonmydriasis color fundus photography, which can clearly capture the soft and hard exudates, bleeding points, microvessels, and so on. Currently, the ophthalmologists who observe fundus images have to endure heavy workloads and massive job-related stress owing to problems such as insufficient expert resources. To reduce their workload, it is necessary to use computer-aided diagnosis. Moreover, computer-aided diagnosis is more accurate. In the field of medical imaging, using classical machine learning and deep learning to classify medical images has become key research areas and gradually the subfield of retinal fundus image classification has developed. However, there is a serious problem with machine learning and deep learning algorithms for fundus image classification developed by many researchers, that is, they continuously increase the complexity of the model to pursue high accuracy. This results in a corresponding increase in computational complexity in terms of the number of floating-point operations and the size of the parameters of the network model, thus reducing the speed and increasing the memory utilization. An inefficient classification model is less likely to be used in clinical practice. The purpose of this paper is to propose a simple network model. Compared with the most advanced model, our model has not only high accuracy, precision, and sensitivity but also high speed. More importantly, it has the potential to be used in clinical practice.Methods We improved the network architecture of the RepVGG model proposed by the Kuangshi’s group and proposed a novel model Channel Atten

关 键 词：医用光学 眼科 糖尿病视网膜病变分级 眼底照相机 深度学习 眼底图像 自动检测 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]