Deep-Ocular: Improved Transfer Learning Architecture Using Self-Attention and Dense Layers for Recognition of Ocular Diseases

Q Abbas, M Albathan, A Altameem, RS Almakki… - Diagnostics, 2023 - mdpi.com
… By hand, eye disease diagnosis is labor-intensive, prone to mistakes, … ocular diseases such
as glaucoma (GA), diabetic retinopathy (DR), cataract (CT), and normal eye-related diseases

Combining convolutional neural networks and self-attention for fundus diseases identification

K Wang, C Xu, G Li, Y Zhang, Y Zheng, C Sun - Scientific Reports, 2023 - nature.com
… & Fattah, SAAn automatic ocular disease detection scheme from enhanced fundus images
based on ensembling deep cnn networks. In Proceedings of the 2020 11th International …

Self-speculation of clinical features based on knowledge distillation for accurate ocular disease classification

J He, C Li, J Ye, Y Qiao, L Gu - Biomedical Signal Processing and Control, 2021 - Elsevier
… A strategy to self-speculate the relevant information from CFPs is necessary for the … KD
inspired activation-based attention transfer between a deeper teacher network and a shallower …

Multi-modal retinal image classification with modality-specific attention network

X He, Y Deng, L Fang, Q Peng - IEEE transactions on medical …, 2021 - ieeexplore.ieee.org
… , the goal of our ocular disease classification method is to … attention unit, we extend the
self-attention (1) to the region-guided attention module and construct the region-guided attention

An Improved Semantic Segmentation Method for Retinal OCT Images Based on High-Resolution Network and Polarized Self-Attention Mechanism

W Fan, F Wang, R Zheng, X Wang - Proceedings of the 2024 4th …, 2024 - dl.acm.org
… Various ocular diseases manifest themselves in the layered structure of the retina, such as
glaucoma, central serous chorioretinopathy, and unilateral anterior ischemic optic neuropathy…

Discriminative kernel convolution network for multi-label ophthalmic disease detection on imbalanced fundus image dataset

A Bhati, N Gour, P Khanna, A Ojha - Computers in Biology and Medicine, 2023 - Elsevier
… Deep learning-based ocular image analysis can be used in … -label fundus images whereas
self-supervising learning is … In this manuscript, a novel attention-based model is proposed …

CSAUNet: A cascade self-attention u-shaped network for precise fundus vessel segmentation

Z Huang, M Sun, Y Liu, J Wu - Biomedical Signal Processing and Control, 2022 - Elsevier
… Recent studies have verified that the ocular diseases, such as glaucoma, pathologic
myopia and maculopathy, and other related human diseases, such as high blood pressure, …

Ads-net: attention-awareness and deep supervision based network for automatic detection of retinopathy of prematurity

Y Peng, Z Chen, W Zhu, F Shi, M Wang… - Biomedical Optics …, 2022 - opg.optica.org
self-attention mechanism to take full advantage of convolution and self-attention, generating
attention-… Retinopathy of Prematurity (ROP) is an ocular disease, which frequently occurs in …

Self-supervised feature learning via exploiting multi-modal data for retinal disease diagnosis

X Li, M Jia, MT Islam, L Yu… - IEEE Transactions on …, 2020 - ieeexplore.ieee.org
… -supervised feature learning techniques receive a lot of attention, as they do not … diseases
can greatly benefit from another imaging modality, eg, FFA, this paper presents a novel self-…

Automated segmentation and feature discovery of age-related macular degeneration and Stargardt disease via self-attended neural networks

Z Wang, SR Sadda, A Lee, ZJ Hu - Scientific Reports, 2022 - nature.com
… post-hoc attention mechanisms which can only visualize CNN features, our self-attended …
mapping of the metabolically occurring fluorophores of the ocular fundus 7 . As atrophy ensues, …