Fundus-DANet: Dilated Convolution and Fusion Attention Mechanism for Multilabel Retinal Fundus Image Classification
Open Access
- 19 September 2024
- journal article
- research article
- Published by MDPI AG in Applied Sciences
- Vol. 14 (18) , 8446
Abstract
The difficulty of classifying retinal fundus images with one or more illnesses present or missing is known as fundus multi-lesion classification. The challenges faced by current approaches include the inability to extract comparable morphological features from images of different lesions and the inability to resolve the issue of the same lesion, which presents significant feature variances due to grading disparities. This paper proposes a multi-disease recognition network model, Fundus-DANet, based on the dilated convolution. It has two sub-modules to address the aforementioned issues: the interclass learning module (ILM) and the dilated-convolution convolutional block attention module (DA-CBAM). The DA-CBAM uses a convolutional block attention module (CBAM) and dilated convolution to extract and merge multiscale information from images. The ILM uses the channel attention mechanism to map the features to lower dimensions, facilitating exploring latent relationships between various categories. The results demonstrate that this model outperforms previous models in classifying fundus multilocular lesions in the OIA-ODIR dataset with 93% accuracy.Keywords
Funding Information
- Natural Science Foundation of Jilin Province (YDZJ202401350ZYTS)
This publication has 31 references indexed in Scilit:
- Cnn-trans model: A parallel dual-branch network for fundus image classificationBiomedical Signal Processing and Control, 2024
- AES-Net: An adapter and enhanced self-attention guided network for multi-stage glaucoma classification using fundus imagesImage and Vision Computing, 2024
- Attention-based deep learning framework for automatic fundus image processing to aid in diabetic retinopathy gradingComputer Methods and Programs in Biomedicine, 2024
- A deep integrative approach for diabetic retinopathy classification with synergistic channel-spatial and self-attention mechanismExpert Systems with Applications, 2024
- ResMU-Net: Residual Multi-kernel U-Net for blood vessel segmentation in retinal fundus imagesBiomedical Signal Processing and Control, 2023
- HiFuse: Hierarchical multi-scale feature fusion network for medical image classificationBiomedical Signal Processing and Control, 2023
- Hyperspectral image classification based on residual dense and dilated convolutionInfrared Physics & Technology, 2023
- Discriminative kernel convolution network for multi-label ophthalmic disease detection on imbalanced fundus image datasetComputers in Biology and Medicine, 2023
- Multi-label classification of fundus images with graph convolutional network and LightGBMComputers in Biology and Medicine, 2022
- Enhancing CNNs through the use of hand-crafted features in automated fundus image classificationBiomedical Signal Processing and Control, 2022