Enhanced Segmentation and Multiclassification of Fundus Images to detect Diabetic Retinopathy using a Modified Attention U-Net and CNN
Keywords:
Diabetic Retinopathy Segmentation, Multiclassification, Modified Attention U-Net, CNNAbstract
In this work, we present a novel method for the assessment of diabetic retinopathy (DR), emphasizing improved segmentation and multiclassification. Utilizing a Modified Attention U-Net architecture, our suggested approach uses cutting-edge Multi-Class Ground Truth Preparation strategies for the best possible model training, to preserve high-resolution features necessary for accurate segmentation, the architecture incorporates skip connections and attention techniques. The output layer of the model is specifically designed for multiclassification, which allows it to differentiate between Red Lesions, Bright Lesions, and Background. One notable addition is implementing a new Multi-Class Ground Truth Preparation technique, which improves the model's ability to identify fine-grained retinal picture features. Our solution performs better on benchmark datasets by utilizing convolutional neural networks and other advanced deep-learning techniques. The effectiveness of the model is demonstrated by important metrics including sensitivity, specificity, AUC-ROC, and F1-score, which address issues like class imbalance and dataset unpredictability. This work adds a strong framework for automated diagnosis and emphasizes the significance of precise DR assessments. The combination of an inventive Multi-Class Ground Truth Preparation with a Modified Attention U-Net creates a state-of-the-art method that has promise for improvements in DR segmentation and multiclassification.
Downloads
References
L. Qiao, Y. Zhu and H. Zhou, “Diabetic retinopathy detection using prognosis of microaneurysm and early diagnosis system for non-proliferative diabetic retinopathy based on deep learning algorithms,” IEEE Access, vol. 8, pp. 104292–104302, 2020.
K. Ogurtsova, JD. da Rocha Fernandes, Y. Huang, “IIDF Diabetes Atlas: Global estimates for the prevalence of diabetes for 2015 and 2040,” Diabetes Res. Clin. PR., vol. 128, pp. 40-50, Jun. 2017.
Dashtbozo rg, B., Zhang, J., Huang, F. et al., Retinal microaneurysms detection using local convergence index features[J]. IEEE Trans. Image Process. 24(12):1–13, 2018.
Autio, I., García, B., Carlos, J., Immonen, I. et al., A voting margin approach for the detection of retinal microaneurysms[J]. EYE Syst. 23(23):98–109, 2005
Long S, Huang X, Chen Z, Pardhan S, Zheng D. Automatic detection of hard exudates in color retinal images using dynamic threshold and SVM classification: algorithm development and evaluation. Biomed Res Int 2019;1–13
C. Kou, W. Li, Z.Yu, J. Hao, "Microaneurysms segmentation with a UNet based on recurrent residual convolutional neural network," Journal of Medical Imaging, vol. 6, no. 2, pp. 025008, Accessed on: May. 2019
R. Zheng, L. Liu, S. Zhang, C.Zheng, F. Bunyak, "Detection of exudates in fundus photographs with imbalanced learning using conditional generative adversarial network," Biomedical optics express, vol. 9, no. 10, pp. 4863- 4878, Accessed on: Oct. 2018.
Z. Zeng, W. Xie, Y. Zhang, Y. Lu, “RIC-Unet: An Improved Neural Network Based on Unet for Nuclei Segmentation in Histology Images,” IEEE Access, vol. 7, pp. 21420-21428, Feb. 2019, DOI: 10.1109/ACCESS.2019.2896920, [Online].
W. Wang, J. Shen, M. Cheng and L. Shao, "An Iterative and Cooperative Top-Down and Bottom-Up Inference Network for Salient Object Detection," in Proc. 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019, pp. 5961-5970
W. Wang, S. Zhao, J. Shen, S. C. H. Hoi and A. Borji, "Salient Object Detection With Pyramid Attention and Salient Edges," in Proc. 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019, pp. 1448-1457
W. Wang, J. Shen, X. Dong, A. Borji and R. Yang, "Inferring Salient Objects from Human Fixations," in Proc. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2019, pp. 1-1.
Kan Ren, Longdan Chang, Minjie Wan, Guohua Gu, Qian Chen,‘‘ An improved U-net based retinal vessel image segmentation method‘‘ Heliyon 8 (2022) e11187.
Jakhongir Nodirov, Akmalbek Bobomirzaevich Abdusalomov, Taeg Keun Whangbo 2,‘‘ Attention 3D U-Net with Multiple Skip Connections for Segmentation of Brain Tumor Images“, Sensors 2022, 22, 6501.
Meshal Alharbi, Deepak Gupta,‘‘ Segmentation of diabetic retinopathy images using deep feature fused residual with U-Net, Alexandria Engineering Journal 83 (2023) 307–325.
K. Simonyan, A. Zisserman, Very Deep Convolutional Networks for Large-Scale Image Recognition, 2014 arXiv preprint arXiv:1409.1556
F M Javed Mehedi Shamrat, Bonna Akter,“ An advanced deep neural network for fundus image analysis and enhancing diabetic retinopathy detection“, Healthcare Analytics 5 (2024) 100303.
AYESHA JABBAR , HANNAN BIN LIAQA,‘‘ A Lesion-Based Diabetic Retinopathy Detection Through Hybrid Deep Learning Model‘‘,2020, IEEE Access.
Hanan Farhat, George E. Sakr, Rima Kilany,‘‘ Deep learning applications in pulmonary medical imaging: recent updates and insights on COVID-19‘‘,Machine Vision and Applications (2020).
Laith Alzubaidi, Jinglan Zhang, Amjad J. Humaidi,‘‘ Review of deep learning: concepts, CNN architectures, challenges, applications, future directions“ Alzubaidi et al. J Big Data (2021) 8:53.
Mohammad Mustafa Taye,“ Theoretical Understanding of Convolutional Neural Network: Concepts, Architectures, Applications, Future Directions“ Computation 2023, 11, 52.
Jaspreet Kaur, Prabhpreet Kaur,“ UNIConv: An enhanced U-Net based InceptionV3 convolutional model for DR semantic segmentation in retinal fundus images“, Concurrency Computat Pract Exper. 2022;e7138.
Leiyu Chen, Shaobo Li, Qiang Bai,“ Review of Image Classification Algorithms Based on Convolutional Neural Networks“, Remote Sens. 2021, 13, 4712.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
