Akhtar Samia, Aftab Shabib, Ali Oualid, Ahmad Munir, Khan Muhammad Adnan, Abbas Sagheer, Ghazal Taher M
Department of Computer Science, Virtual University of Pakistan, Lahore, 54000, Pakistan.
Computer Sciences Department, College of Arts & Science, Applied Science University, P.O.Box 5055, Manama, Kingdom of Bahrain.
Sci Rep. 2025 Jan 30;15(1):3763. doi: 10.1038/s41598-025-87171-9.
Diabetic retinopathy stands as a leading cause of blindness among people. Manual examination of DR images is labor-intensive and prone to error. Existing methods to detect this disease often rely on handcrafted features which limit the adaptability and classification accuracy. Thus, the aim of this research is to develop an automated and efficient system for early detection and accurate grading of diabetic retinopathy severity with less time consumption. In our research, we have developed a deep neural network named RSG-Net (Retinopathy Severity Grading) to classify DR into 4 stages (multi-class classification) and 2 stages (binary classification). The dataset utilized in this study is Messidor-1. In preprocessing, we have used Histogram Equalization to improve image contrast and denoising techniques to remove noise and artifacts which enhanced the clarity of the fundus images. We applied data augmentation techniques to our preprocessed images in order to tackle class imbalance issues. Augmentation techniques involve flipping, rotation, zooming and adjustment of color, contrast and brightness. The proposed RSG-Net model contains convolutional layers to perform automatic feature extraction from the input images and batch normalization layers to improve training speed and performance. The model also contains max pooling, drop out and fully connected layers. Our proposed RSG-Net model achieved a testing accuracy of 99.36%, specificity of 99.79% and a sensitivity of 99.41% in classifying diabetic retinopathy into 4 grades and it achieved 99.37% accuracy, 100% sensitivity and 98.62% specificity in classifying DR into 2 grades. The performance of RSG-Net is also compared with other state-of-the-art methodologies where it outperformed these methods.
糖尿病视网膜病变是导致人们失明的主要原因之一。糖尿病视网膜病变（DR）图像的人工检查劳动强度大且容易出错。现有的检测这种疾病的方法通常依赖手工特征，这限制了适应性和分类准确性。因此，本研究的目的是开发一种自动化、高效的系统，用于早期检测糖尿病视网膜病变并准确分级其严重程度，同时减少时间消耗。在我们的研究中，我们开发了一种名为RSG-Net（视网膜病变严重程度分级）的深度神经网络，将糖尿病视网膜病变分为4个阶段（多类分类）和2个阶段（二分类）。本研究中使用的数据集是Messidor-1。在预处理中，我们使用直方图均衡化来提高图像对比度，并使用去噪技术去除噪声和伪影，从而提高了眼底图像的清晰度。我们对预处理后的图像应用数据增强技术，以解决类别不平衡问题。增强技术包括翻转、旋转、缩放以及颜色、对比度和亮度的调整。所提出的RSG-Net模型包含卷积层，用于从输入图像中自动提取特征，以及批归一化层，以提高训练速度和性能。该模型还包含最大池化、随机失活和全连接层。我们提出的RSG-Net模型在将糖尿病视网膜病变分为4个等级时，测试准确率达到99.36%，特异性为99.79%，灵敏度为99.41%；在将糖尿病视网膜病变分为2个等级时，准确率达到99.37%，灵敏度为100%，特异性为98.62%。RSG-Net的性能也与其他先进方法进行了比较，结果表明它优于这些方法。
