Department of Mechanical Engineering, Ferdowsi University of Mashhad, Mashhad, Iran.
Department of Industrial Engineering, Urmia University of Technology (UUT), P.O. Box 57166-419, Urmia, Iran.
Comput Intell Neurosci. 2021 Jul 26;2021:7714351. doi: 10.1155/2021/7714351. eCollection 2021.
Diabetic retinopathy is characteristic of a local distribution that involves early-stage risk factors and can forecast the evolution of the illness or morphological lesions related to the abnormality of retinal blood flows. Regional variations in retinal blood flow and modulation of retinal capillary width in the macular area and the retinal environment are also linked to the course of diabetic retinopathy. Despite the fact that diabetic retinopathy is frequent nowadays, it is hard to avoid. An ophthalmologist generally determines the seriousness of the retinopathy of the eye by directly examining color photos and evaluating them by visually inspecting the fundus. It is an expensive process because of the vast number of diabetic patients around the globe. We used the IDRiD data set that contains both typical diabetic retinopathic lesions and normal retinal structures. We provided a CNN architecture for the detection of the target region of 80 patients' fundus imagery. Results demonstrate that the approach described here can nearly detect 83.84% of target locations. This result can potentially be utilized to monitor and regulate patients.
糖尿病性视网膜病变的特征是局部分布，涉及早期危险因素，可以预测疾病的演变或与视网膜血流异常相关的形态损伤。视网膜血流的区域变化以及黄斑区和视网膜环境中视网膜毛细血管宽度的调节也与糖尿病性视网膜病变的病程有关。尽管如今糖尿病性视网膜病变很常见，但很难避免。眼科医生通常通过直接检查彩色照片并通过眼底视觉检查来评估这些照片来确定眼睛的视网膜病变的严重程度。由于全球有大量的糖尿病患者，因此这是一个昂贵的过程。我们使用了包含典型糖尿病性视网膜病变病变和正常视网膜结构的 IDRiD 数据集。我们为 80 名患者眼底图像的目标区域检测提供了一个卷积神经网络架构。结果表明，这里描述的方法几乎可以检测到 83.84%的目标位置。该结果可用于监测和调节患者。
