Advanced Deep Learning Models for Accurate Retinal Disease State Detection

PDF (641KB), PP.61-71

Views: 0 Downloads: 0


Hossein. Abbasi 1,* Ahmed. Alshaeeb 2 Yasin. Orouskhani 3 Behrouz. Rahimi 4 Mostafa. Shomalzadeh 5

1. Islamic Azad University, South Tehran Branch, Tehran, Iran

2. Farabi Eye Hospital, Tehran University of Medical Sciences, Iran

3. College of Computer Engineering, Sharif University of Technology, Iran

4. Department of Ophthalmology, Shahid Mohammadi Hospital, Hormozgan University of Medical Sciences, Iran

5. Department of Radiology, Shahid Beheshti University of Medical Sciences, Tehran, Iran

* Corresponding author.


Received: 4 Nov. 2023 / Revised: 10 Jan. 2024 / Accepted: 21 Feb. 2024 / Published: 8 Jun. 2024

Index Terms

Retinal Disease Detection, Deep Learning, Transfer Learning, Optical Coherence Tomography, Classification


Retinal diseases are a significant challenge in the realm of medical diagnosis, with potential complications to vision and overall ocular health. This research endeavors to address the challenge of automating the detection of retinal disease states using advanced deep learning models, including VGG-19, ResNet-50, InceptionV3, and EfficientNetV2. Each model leverages transfer learning, drawing insights from a substantial dataset comprising optical coherence tomography (OCT) images and subsequently classifying images into four distinct retinal conditions: choroidal neovascularization, drusen, diabetic macular edema and a healthy state. The training dataset, sourced from repositories that are available to the public including OCT retinal images, spanning all four disease categories. Our findings reveal that among the models tested, EfficientNetV2 demonstrates superior performance, with a remarkable classification accuracy of 98.92%, precision of 99.6%, and a recall of 99.4%, surpassing the performance of the other models.

Cite This Paper

Hossein. Abbasi, Ahmed. Alshaeeb, Yasin. Orouskhani, Behrouz. Rahimi, Mostafa. Shomalzadeh, "Advanced Deep Learning Models for Accurate Retinal Disease State Detection", International Journal of Information Technology and Computer Science(IJITCS), Vol.16, No.3, pp.61-71, 2024. DOI:10.5815/ijitcs.2024.03.06


[1]Silke. Aumann, Sabine. Donner, Jörg. Fischer, Frank. Müller, “High Resolution Imaging in Microscopy and Ophthalmology”, New Frontiers in Biomedical Optics, Springer, pp.59-85, 2019. DOI: 10.1007/978-3-030-16638-0_3
[2]Jongwoo. Kim, Loc. Tran, “Retinal Disease Classification from OCT Images Using Deep Learning Algorithms”, IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB), Melbourne, Australia, 2021, pp. 1-6, doi: 10.1109/CIBCB49929.2021.9562919.
[3]Shervin. Minaee, Yuri. Boykov, Fatih. Porikli, Antonio. Plaza, Nasser. Kehtarnavaz, Demetri. Terzopoulos. Image segmentation using deep learning: A survey. IEEE transactions on pattern analysis and machine intelligence, 44(7), 3523-3542, 2021.
[4]Firoozeh. Shomal Zadeh, Sevda. Molani, Maysam. Orouskhani, Marziyeh. Rezaei, Mehrzad. Shafiei, Hossein. Abbasi,” Generative Adversarial Networks for Brain Images Synthesis: A Review”. (2023).  arXiv preprint arXiv:2305.15421.
[5]Daniel S. Kermany, Michael. Goldbaum, Wenjia. Cai and et al., “Identifying medical diagnoses and treatable diseases by image-based deep learning,’ Cell, vol. 172, no. 5, pp. 1122–1131, 2018.
[6]Jongwoo. Kim, Loc. Tran, “Ensemble Learning based on Convolutional Neural Networks for the Classification of Retinal Diseases from Optical Coherence Tomography Images,” IEEE 33rd International Symposium on Computer-Based Medical Systems, pp 535-540, Rochester, USA, July 2020.
[7]Li, Feng et al. “Deep learning-based automated detection of retinal diseases using optical coherence tomography images.” Biomedical optics express vol. 10,12 6204-6226. 11 Nov. 2019, doi:10.1364/BOE.10.006204
[8]Li, Feng et al. “Fully automated detection of retinal disorders by image-based deep learning.” Graefe's archive for clinical and experimental ophthalmology = Albrecht von Graefes Archiv fur klinische und experimentelle Ophthalmologie vol. 257,3 (2019): 495-505. doi:10.1007/s00417-018-04224-8
[9]Lu, Wei et al. “Deep Learning-Based Automated Classification of Multi-Categorical Abnormalities from Optical Coherence Tomography Images.” Translational vision science & technology vol. 7,6 41. 28 Dec. 2018, doi:10.1167/tvst.7.6.41
[10]Karen. Simonyan, Andrew. Zisserman, very deep convolutional networks for large-scale image recognition. 2014arXiv1409.1556S.
[11]He. Kaiming, Zhang. Xiangyu, Ren. Shaoqing, Sun. Jian. Deep residual learning for image recognition. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, USA, 2016; pp. 770–778.
[12]Christian. Szegedy, Vincent. Vanhoucke, Sergey. Ioffe, Jonathon. Shlens, Zbigniew. Wojna. Rethinking the Inception Architecture for Computer Vision. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, USA, 2016; pp. 2818–2826. 
[13]Mingxing. Tan, Quoc V. Le. Efficientnetv2: Smaller models and faster training. In International conference on machine learning, pp. 10096-10106. 2021.
[14]Srinivasan, Pratul P et al. “Fully automated detection of diabetic macular edema and dry age-related macular degeneration from optical coherence tomography images.” Biomedical optics express vol. 5,10 3568-77. 12 Sep. 2014, doi:10.1364/BOE.5.003568
[15]Wei. Lu, Yan. Tong, Yue. Yu, Yiqiao. Xing, Changzheng. Chen, Yin. Shen, Deep Learning-Based Automated Classification of Multi-Categorical Abnormalities from Optical Coherence Tomography Images. Trans. Vis. Sci. Technol. 2018. doi:10.1167/tvst.7.6.41
[16]Gulshan, Varun et al. “Development and Validation of a Deep Learning Algorithm for Detection of Diabetic Retinopathy in Retinal Fundus Photographs.” JAMA vol. 316,22 (2016): 2402-2410. doi:10.1001/jama.2016.17216
[17]Karri, S P K et al. “Transfer learning-based classification of optical coherence tomography images with diabetic macular edema and dry age-related macular degeneration.” Biomedical optics express vol. 8,2 579-592. 4 Jan. 2017, doi:10.1364/BOE.8.000579.
[18]Kermany, Daniel S et al. “Identifying Medical Diagnoses and Treatable Diseases by Image-Based Deep Learning.” Cell vol. 172,5 (2018): 1122-1131.e9. doi:10.1016/j.cell.2018.02.010
[19]Burlina, Philippe M et al. “Automated Grading of Age-Related Macular Degeneration From Color Fundus Images Using Deep Convolutional Neural Networks.” JAMA ophthalmology vol. 135,11(2017): 1170-1176. doi:10.1001/jamaophthalmol.2017.3782.
[20]Heo, Tae-Young et al. “Development of a Deep-Learning-Based Artificial Intelligence Tool for Differential Diagnosis between Dry and Neovascular Age-Related Macular Degeneration.” Diagnostics (Basel, Switzerland) vol. 10,5 261. 28 Apr. 2020, doi:10.3390/diagnostics10050261
[22]Ali, Luqman et al. “Performance Evaluation of Deep CNN-Based Crack Detection and Localization Techniques for Concrete Structures.” Sensors (Basel, Switzerland) vol. 21,5 1688. 1 Mar. 2021, doi:10.3390/s21051688