Automatic Diabetic Retinopathy Grading System Based on Detecting Multiple Retinal Lesions
Automatic Diabetic Retinopathy Grading System Based on Detecting Multiple Retinal Lesions
复制标题
基于多重视网膜病变检测的糖尿病视网膜病变自动分级系统
DOI：
10.1109/access.2021.3052870
复制
发表时间：
2021-01-01
期刊：
影响因子：
3.9
通讯作者：
Elmogy, Mohammed
中科院分区：
文献类型：
--
作者：
Abdelmaksoud, Eman;El-Sappagh, Shaker;Elmogy, Mohammed
多标签分类（MLC）被认为是计算机视觉领域的一个重要研究课题，主要是在医学图像分析中。鉴于这一优点，我们从 MLC 中受益，可以从各种彩色眼底图像，尤其是多标签 (ML) 数据集中诊断多级糖尿病视网膜病变 (DR)。因此，眼科医生可以检测 DR 的早期症状以及不同级别，以启动适当的治疗并避免 DR 并发症。在本文中，我们提出了一种基于深度学习技术的综合机器学习计算机辅助诊断（CAD）系统。该系统的主要贡献是检测和分析伴随视网膜 DR 发展的各种病理变化，而无需向患者注射染料或进行昂贵的扫描。所提出的 ML-CAD 系统可以可视化不同的病理变化，并为眼科医生诊断 DR 等级。首先，我们消除噪声、提高质量并标准化视网膜图像的尺寸。其次，我们通过计算四个不同方向的灰度游程长度矩阵平均值来区分健康情况和 DR 情况。系统利用深度学习技术（U-Net）自动提取渗出液、微动脉瘤、出血和血管四种变化。接下来，我们提取六个特征，分别是灰度共生矩阵、四种分割病理变化的面积以及血管的分叉点计数。最后，将所得特征提供给基于分类器链的 ML 支持向量机 (SVM)，以区分各种 DR 等级。我们利用八个基准数据集（其中四个被认为是机器学习）和六个不同的性能评估指标来评估所提出的系统的性能。准确度、曲线下面积、敏感性、特异性、阳性预测值和骰子相似系数分别达到 95.1%、91.9%、86.1%、86.8%、84.7% 和 86.2%。与其他系统相比，实验显示出令人鼓舞的结果。
Multi-label classification (MLC) is considered an essential research subject in the computer vision field, principally in medical image analysis. For this merit, we derive benefits from MLC to diagnose multiple grades of diabetic retinopathy (DR) from various colored fundus images, especially from multi-label (ML) datasets. Therefore, ophthalmologists can detect early signs of DR as well as various grades to initiate appropriate treatment and avoid DR complications. In this paper, we propose a comprehensive ML computer-aided diagnosis (CAD) system based on deep learning technique. The proposed system's main contribution is to detect and analyze various pathological changes accompanying DR development in the retina without injecting the patient with dye or making expensive scans. The proposed ML-CAD system visualizes the different pathological changes and diagnoses the DR grades for the ophthalmologists. First, we eliminate noise, enhance quality, and standardize the sizes of the retinal images. Second, we differentiated between the healthy and DR cases by calculating the gray level run length matrix average in four different directions. The system automatically extracts the four changes: exudates, microaneurysms, hemorrhages, and blood vessels by utilizing a deep learning technique (U-Net). Next, we extract six features, which are the gray level co-occurrence matrix, areas of the four segmenting pathology variations, and the bifurcation points count of the blood vessels. Finally, the resulting features were afforded to an ML support vector machine (SVM) based on a classifier chain to differentiate the various DR grades. We utilized eight benchmark datasets (four of them are considered ML) and six different performance evaluation metrics to evaluate the proposed system's performance. It achieved 95.1%, 91.9%, 86.1%, 86.8%, 84.7%, 86.2% for accuracy, area under the curve, sensitivity, specificity, positive predictive value, and dice similarity coefficient, respectively. The experiments show encouraging results as compared with other systems.