Opto-Electronic Engineering, Volume. 52, Issue 4, 240273(2025)
Fusion dual-attention retinal disease grading algorithm with PVTv2 and DenseNet121
Figures & Tables(17)
Fig. 6. Comparison of multi-class confusion matrices between the reproduction experiment and the proposed model on the IDRID dataset
Fig. 7. Comparison of AUC values between the reproduction experiment and the proposed model
Fig. 8. Comparison before and after adding Gaussian noise. (a) Before adding Gaussian noise; (b) After adding Gaussian noise
Fig. 9. Multi-class confusion matrices for each group in the ablation experiment
Table 1. The class distribution characteristics of the IDRID and APTOS 2019 datasets
View tableView in ArticleTable 1. The class distribution characteristics of the IDRID and APTOS 2019 datasets
Dataset Class distribution characteristic Total LDR=0 LDR=1 LDR=2 LDR=3 LDR=4 IDRID 168 25 168 93 62 516 APTOS 2019 1805 370 999 193 295 3662
Table 2. Performance of different algorithms on the IDRID dataset
View tableView in ArticleTable 2. Performance of different algorithms on the IDRID dataset
Methods Model QWK/% Acc/% Se/% Sp/% Ref. [ 23 ]Res2Net-50+DenseNet121 88.76 81.55 94.20 97.05 Ref. [ 24 ]Efficiientnet-b5 87.63 79.06 - - Ref. [ 25 ]CNN+SVM - 79.46 82.85 76.98 Ref. [ 26 ]CMAL-Net 85.63 76.70 91.30 97.06 Ref. [ 27 ]FBSD 88.59 77.67 91.30 97.05 Ours FAPD 90.68 80.58 95.65 97.06
Table 3. Performance of different algorithms on the APTOS 2019 dataset
View tableView in ArticleTable 3. Performance of different algorithms on the APTOS 2019 dataset
Methods Model QWK/% Acc/% Se/% AUC/% Ref. [ 23 ]Res2Net-50+DenseNet121 90.29 84.42 87.40 93.60 Ref. [ 26 ]CMAL-Net 86.08 81.96 86.43 92.46 Ref. [ 27 ]FBSD 86.34 84.28 85.32 92.78 Ref. [ 28 ]LA-NSVM 75.64 84.31 66.16 - Ref. [ 29 ]DenseNet201 78.37 85.93 69.72 - Ref. [ 30 ]Ensemble voting 77.78 85.28 86.00 - Ours FAPD 90.35 84.83 87.94 93.22
Table 4. Verification results of the generalization ability of FAPD on the EyePACS dataset
View tableView in ArticleTable 4. Verification results of the generalization ability of FAPD on the EyePACS dataset
Methods Model Acc/% AUC/% Se/% Sp/% Ref. [ 23 ]Res2Net-50+DenseNet121 83.48 91.07 78.52 89.89 Ref. [ 26 ]CMAL-Net 81.41 88.30 70.21 83.21 Ref. [ 27 ]FBSD 82.25 87.08 61.27 90.21 Ours FAPD 84.81 93.06 80.22 94.20
Table 5. Performance indicators of models with different weighting factors on the IDRID dataset
View tableView in ArticleTable 5. Performance indicators of models with different weighting factors on the IDRID dataset
QWK/% Acc/% Se/% Sp/% 0 88.21 78.64 91.27 88.23 0.1 84.52 74.39 92.75 85.29 0.2 89.13 80.58 94.20 97.06 0.3 88.97 77.67 95.65 94.11 0.4 86.32 79.61 91.30 94.12 0.5 90.55 78.64 92.75 96.25 0.6 90.85 79.61 95.65 94.11 0.7 88.69 76.69 89.85 91.48 0.8 91.34 78.64 94.20 94.20 0.9 968 80.58 95.65 97.06
Table 6. Performance of the model before and after adding Gaussian noise
View tableView in ArticleTable 6. Performance of the model before and after adding Gaussian noise
Model QWK/% Acc/% Se/% Sp/% M1 89.90 79.61 94.20 94.12 M2 90.68 80.58 95.65 97.06
Table 7. Ablation results on the IDRID dataset
View tableView in ArticleTable 7. Ablation results on the IDRID dataset
Model QWK/% Acc/% Se/% Sp/% X1 88.25 76.69 92.75 94.11 X2 87.88 74.75 91.30 88.24 X3 87.75 77.67 91.30 94.12 X4 88.21 78.64 95.65 88.23 X5 89.37 79.62 92.75 97.06 X6 90.68 80.58 95.65 97.06
Tools
Get Citation
Copy Citation Text
Liming Liang, Yi Zhong, Kangquan Chen, Chengbin Wang. Fusion dual-attention retinal disease grading algorithm with PVTv2 and DenseNet121[J]. Opto-Electronic Engineering, 2025, 52(4): 240273
Paper Information
Category: Article
Received: Nov. 22, 2024
Accepted: Jan. 23, 2025
Published Online: Jun. 11, 2025
The Author Email: Yi Zhong (钟奕)
© Copyright 2018-2021 | Chinese Laser Press.
All Rights Reserved 沪ICP备15018463号-20