Related Experiment Video
Updated: Jul 29, 2026
07:41
Behavioral Assessment of Visual Function via Optomotor Response and Cognitive Function via Y-Maze in Diabetic Rats
Published on: October 23, 2020
7.0K
An Active Learning Classifier for Further Reducing Diabetic Retinopathy Screening System Cost.
1School of Computer Science and Technology, Beijing Institute of Technology, Beijing 100081, China; College of Computer Science and Information Engineering, Tianjin University of Science and Technology, Tianjin 300222, China.
Computational and Mathematical Methods in Medicine
|September 24, 2016
Summary
This study introduces an active learning classifier to reduce diabetic retinopathy (DR) screening costs. The method uses fewer labeled images, achieving high accuracy and saving expenses.
Area of Science:
- Ophthalmology
- Computer Science
- Machine Learning
Background:
- Diabetic retinopathy (DR) screening is crucial but costly.
- Reducing DR screening expenses is a significant challenge in healthcare.
Purpose of the Study:
- To propose an active learning classifier to decrease the financial burden of DR screening.
- To enhance the efficiency of DR screening using machine learning techniques.
Main Methods:
- Feature extraction using anatomical part recognition and lesion detection algorithms.
- Implementation of a Kernel Extreme Learning Machine (KELM) classifier.
- Integration of active learning and ensemble techniques to improve KELM performance with limited data.
Main Results:
- The proposed classifier achieved superior accuracy compared to traditional methods (CART, SVM variants, KNN) when trained on only 20%-35% of labeled retinal images.
- Comparative classifiers required 80% of labeled data to achieve lower accuracy.
- The active learning approach minimized the need for manual annotation by medical professionals.
Conclusions:
- The active learning classifier is an efficient and cost-effective solution for DR screening.
- This approach significantly reduces the financial requirements for DR screening systems.
- The method demonstrates the potential to improve accessibility to DR screening through reduced costs.
