Multi-Scale-Denoising Residual Convolutional Network for Retinal Disease Classification Using OCT

Macular pathologies can cause significant vision loss. Optical coherence tomography (OCT) images of the retina can assist ophthalmologists in diagnosing macular diseases. Traditional deep learning networks for retinal disease classification cannot extract discriminative features under strong noise c...

Full description

Saved in:
Bibliographic Details
Published in:Sensors (Basel, Switzerland) Switzerland), 2023-12, Vol.24 (1), p.150
Main Authors: Peng, Jinbo, Lu, Jinling, Zhuo, Junjie, Li, Pengcheng
Format: Article
Language:English
Subjects:
Automation
Classification
Computational linguistics
convolutional neural network
Datasets
Deep learning
Disease
Language processing
Machine learning
Macular degeneration
Medical personnel
multi-scale-denoising residual convolutional network
Natural language interfaces
Neural networks
Ophthalmology
optical coherence tomography (OCT)
Retina
retinal disease classification
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Macular pathologies can cause significant vision loss. Optical coherence tomography (OCT) images of the retina can assist ophthalmologists in diagnosing macular diseases. Traditional deep learning networks for retinal disease classification cannot extract discriminative features under strong noise conditions in OCT images. To address this issue, we propose a multi-scale-denoising residual convolutional network (MS-DRCN) for classifying retinal diseases. Specifically, the MS-DRCN includes a soft-denoising block (SDB), a multi-scale context block (MCB), and a feature fusion block (FFB). The SDB can determine the threshold for soft thresholding automatically, which removes speckle noise features efficiently. The MCB is designed to capture multi-scale context information and strengthen extracted features. The FFB is dedicated to integrating high-resolution and low-resolution features to precisely identify variable lesion areas. Our approach achieved classification accuracies of 96.4% and 96.5% on the OCT2017 and OCT-C4 public datasets, respectively, outperforming other classification methods. To evaluate the robustness of our method, we introduced Gaussian noise and speckle noise with varying PSNRs into the test set of the OCT2017 dataset. The results of our anti-noise experiments demonstrate that our approach exhibits superior robustness compared with other methods, yielding accuracy improvements ranging from 0.6% to 2.9% when compared with ResNet under various PSNR noise conditions.
ISSN:1424-8220
1424-8220
DOI:10.3390/s24010150