An Active Learning Classifier for Further Reducing Diabetic Retinopathy Screening System Cost.

Yinan Zhang,Mingqiang An

doi:10.1155/2016/4345936

Abstract

Diabetic retinopathy (DR) screening system raises a financial problem. For further reducing DR screening cost, an active learning classifier is proposed in this paper. Our approach identifies retinal images based on features extracted by anatomical part recognition and lesion detection algorithms. Kernel extreme learning machine (KELM) is a rapid classifier for solving classification problems in high dimensional space. Both active learning and ensemble technique elevate performance of KELM when using small training dataset. The committee only proposes necessary manual work to doctor for saving cost. On the publicly available Messidor database, our classifier is trained with 20%–35% of labeled retinal images and comparative classifiers are trained with 80% of labeled retinal images. Results show that our classifier can achieve better classification accuracy than Classification and Regression Tree, radial basis function SVM, Multilayer Perceptron SVM, Linear SVM, and K Nearest Neighbor. Empirical experiments suggest that our active learning classifier is efficient for further reducing DR screening cost.

Highlights

Diabetic retinopathy (DR) [1] is one of the most common causes of blindness in diabetic mellitus research [2]
We train Classification and Regression Tree (CART), radial basis function (RBF) SVM, Multilayer Perceptron (MLP) SVM, Linear (Lin) SVM, and K Nearest Neighbor (KNN) with 80% of database and the remaining 20% is as testing dataset
CART, RBF, MLP, Lin, KNN, active learning (AL), Kernel extreme learning machine (KELM), and Extreme learning machine (ELM) are compared in experiments

Summary

Introduction

Diabetic retinopathy (DR) [1] is one of the most common causes of blindness in diabetic mellitus research [2]. DR screening system is still useful for diabetic patients in many low income areas. This challenging problem causes a demand of a better computer-aided DR screening system [7, 8]. (1) Retinal image is easy to snap, but manually diagnosing a result is of high cost. (2) Kernel technique is suitable for classifying retinal images which is related to classification in high dimensional spaces. (4) Active learning can further reduce the size of training dataset compared to traditional machine learning method in DR screening system. This paper is organized as follows: Section 2 shows background of retinal images and related works, Section 3 presents the details of the proposed classifier, and Section 4 presents empirical experiment and results.

Retinal Images and Related Works

Experiments and Results

Conclusion