Related Experiment Video
Updated: Jul 8, 2026
08:17
Optical Coherence Tomography: Imaging Mouse Retinal Ganglion Cells In Vivo
Published on: September 22, 2017
19.3K
CLAHE-CapsNet: Efficient retina optical coherence tomography classification using capsule networks with contrast
Michael Opoku1, Benjamin Asubam Weyori1, Adebayo Felix Adekoya1
1Department of Computer Science and Informatics, University of Energy and Natural Resource, Sunyani, Ghana.
Plos One
|November 30, 2023
Summary
This study introduces a novel CLAHE-CapsNet model for improved retina Optical Coherence Tomography (OCT) image classification. The new method enhances accuracy in detecting eye diseases, aiding ophthalmologists.
Area of Science:
- Ophthalmology
- Medical Imaging
- Computer Science
Background:
- Manual detection of eye diseases from Optical Coherence Tomography (OCT) images is laborious and error-prone.
- Existing deep learning models like Convolutional Neural Networks (CNNs) struggle with OCT image noise and resolution loss due to pooling operations.
Conclusions:
- The CLAHE-CapsNet model demonstrates significant potential for accurate and efficient detection of retina diseases from OCT images.
- The proposed model can serve as a valuable tool to assist ophthalmologists in clinical diagnosis.
- Noise reduction via CLAHE and the capsule network architecture contribute to improved classification performance.
