Ali Aqib, Qadri Salman, Khan Mashwani Wali, Kumam Wiyada, Kumam Poom, Naeem Samreen, Goktas Atila, Jamal Farrukh, Chesneau Christophe, Anam Sania, Sulaiman Muhammad
Department of Computer Science & IT, The Islamia University of Bahawalpur, Bahawalpur 61300, Pakistan.
Institute of Numerical Sciences, Kohat University of Sciences & Technology, Kohat 26000, Pakistan.
Entropy (Basel). 2020 May 19;22(5):567. doi: 10.3390/e22050567.
The object of this study was to demonstrate the ability of machine learning (ML) methods for the segmentation and classification of diabetic retinopathy (DR). Two-dimensional (2D) retinal fundus (RF) images were used. The datasets of DR-that is, the mild, moderate, non-proliferative, proliferative, and normal human eye ones-were acquired from 500 patients at Bahawal Victoria Hospital (BVH), Bahawalpur, Pakistan. Five hundred RF datasets (sized 256 × 256) for each DR stage and a total of 2500 (500 × 5) datasets of the five DR stages were acquired. This research introduces the novel clustering-based automated region growing framework. For texture analysis, four types of features-histogram (H), wavelet (W), co-occurrence matrix (COM) and run-length matrix (RLM)-were extracted, and various ML classifiers were employed, achieving 77.67%, 80%, 89.87%, and 96.33% classification accuracies, respectively. To improve classification accuracy, a fused hybrid-feature dataset was generated by applying the data fusion approach. From each image, 245 pieces of hybrid feature data (H, W, COM, and RLM) were observed, while 13 optimized features were selected after applying four different feature selection techniques, namely Fisher, correlation-based feature selection, mutual information, and probability of error plus average correlation. Five ML classifiers named sequential minimal optimization (SMO), logistic (Lg), multi-layer perceptron (MLP), logistic model tree (LMT), and simple logistic (SLg) were deployed on selected optimized features (using 10-fold cross-validation), and they showed considerably high classification accuracies of 98.53%, 99%, 99.66%, 99.73%, and 99.73%, respectively.
本研究的目的是证明机器学习（ML）方法对糖尿病视网膜病变（DR）进行分割和分类的能力。使用了二维（2D）视网膜眼底（RF）图像。DR的数据集，即轻度、中度、非增殖性、增殖性和正常人类眼睛的数据集，是从巴基斯坦巴哈瓦尔布尔的巴哈瓦尔维多利亚医院（BVH）的500名患者那里获取的。为每个DR阶段获取了500个RF数据集（大小为256×256），总共获得了五个DR阶段的2500个（500×5）数据集。本研究引入了基于聚类的新型自动区域生长框架。对于纹理分析，提取了四种类型的特征——直方图（H）、小波（W）、共生矩阵（COM）和游程长度矩阵（RLM），并采用了各种ML分类器，分类准确率分别达到了77.67%、80%、89.87%和96.33%。为了提高分类准确率，通过应用数据融合方法生成了一个融合的混合特征数据集。从每张图像中观察到245条混合特征数据（H、W、COM和RLM），而在应用了四种不同的特征选择技术，即Fisher、基于相关性的特征选择、互信息以及误差概率加平均相关性之后，选择了13个优化特征。在选定的优化特征上部署了五个名为顺序最小优化（SMO）、逻辑回归（Lg）、多层感知器（MLP）、逻辑模型树（LMT）和简单逻辑回归（SLg）的ML分类器（使用10折交叉验证），它们分别显示出相当高的分类准确率，分别为98.53%、99%、99.66%、99.73%和99.73%。
