Machine Learning Based Automated Segmentation and Hybrid Feature Analysis for Diabetic Retinopathy Classification Using Fundus Image.
Machine Learning Based Automated Segmentation and Hybrid Feature Analysis for Diabetic Retinopathy Classification Using Fundus Image.
复制标题
DOI：
10.3390/e22050567
复制
发表时间：
2020-05-19
期刊：
影响因子：
--
通讯作者：
Sulaiman M
中科院分区：
文献类型：
--
作者：
Ali A;Qadri S;Khan Mashwani W;Kumam W;Kumam P;Naeem S;Goktas A;Jamal F;Chesneau C;Anam S;Sulaiman M
本研究的目的是证明机器学习（ML）方法在糖尿病视网膜病变（DR）的分割和分类方面的能力。采用二维（2D）视网膜眼底（RF）图像。dr的数据集，即轻度、中度、非增殖性、增殖性和正常人眼的数据集，来自巴基斯坦巴哈瓦尔布尔巴哈瓦尔维多利亚医院（BVH）的500名患者。每个DR阶段获得500个RF数据集（大小为256 × 256），五个DR阶段总共获得2500个（500 × 5）数据集。本文介绍了一种新的基于聚类的自动区域生长框架。在纹理分析方面，提取了直方图(H)、小波(W)、共现矩阵（COM）和运行长度矩阵（RLM）四种类型的特征，并使用了各种ML分类器，分类准确率分别达到77.67%、80%、89.87%和96.33%。为了提高分类精度，应用数据融合方法生成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），并采用Fisher、基于相关性的特征选择、互信息和误差概率加平均相关性四种不同的特征选择技术，筛选出13个优化特征。5个ML分类器分别命名为顺序最小优化（SMO）、逻辑（Lg）、多层感知器（MLP）、逻辑模型树（LMT）和简单逻辑（SLg），在选定的优化特征上部署（使用10倍交叉验证），它们分别显示出98.53%、99%、99.66%、99.73%和99.73%的相当高的分类准确率。
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.
登录
查看更多内容
影响因子：
5.3
作者：
Nayak, Jagadish;Bhat, P. Subbanna;Kagathi, Manjunath
通讯作者：
Kagathi, Manjunath
DOI：
10.1109/jtehm.2018.2796600
发表时间：
2018
影响因子：
3.4
作者：
Garali I;Adel M;Bourennane S;Guedj E
通讯作者：
Guedj E
影响因子：
4.6
作者：
Antal, Balint;Hajdu, Andras
通讯作者：
Hajdu, Andras
影响因子：
2.7
作者：
Guo, Yanhui;Ashour, Amira S.;Smarandache, Florentin
通讯作者：
Smarandache, Florentin
影响因子：
120.7
作者：
Gulshan, Varun;Peng, Lily;Webster, R.
通讯作者：
Webster, R.