Using Machine Learning to Detect Different Eye Diseases from OCT Images

Öz

Diseases or damage to the retina that cause adverse effects are one of the most common reasons people lose their sight at an early age. Today, machine learning techniques, which give high accuracy results in a short time, have been used for disease detection in the biomedical field. Optical coherence tomography, an advanced ophthalmic imaging technique to display the cross-section of retinal layers, is one of the important tools used for the determination, analysis and treatment design of retinal diseases. The aim of this study is to detect eight retinal diseases that can occur in the eye and cause permanent damage as a result, using machine learning from eye tomography images. For this purpose, hyperparameter settings were applied to six deep learning models, training was performed on the OCT-C8 dataset and performance analyzes were made. The performance of these hyperparameter-tuned models was also compared with previous eye disease detection studies in the literature, and it was seen that the classification success of the hyperparameter-tuned DenseNet121 model presented in this study was higher than the success of the other models discussed. The fine-tuned DenseNet121 classifier achieved 97.79% accuracy, 97.69% sensitivity, and 97.79% precision for the OCT-C8 dataset.

Anahtar Kelimeler

• Retinal Disease
• Optical Coherence Tomography (OCT)
• Machine Learning
• Deep Learning
• DenseNet

Kaynakça

1. [1] D. S. Kermany et al., (2018). Identifying Medical Diagnoses and Treatable Diseases by Image-Based Deep Learning. Cell, 172(5);1122-1131 doi: 10.1016/J.CELL.2018.02.010.
2. [2] K. L. Pennington and M. M. DeAngelis (2016). Epidemiology of age-related macular degeneration (AMD): associations with cardiovascular disease phenotypes and lipid factors. Eye Vis. (London, England), 3(1) doi: 10.1186/S40662-016-0063-5.
3. [3] X. Yang, T. Zhang, C. Xu, S. Yan, M. S. Hossain, and A. Ghoneim, (2016). Deep relative attributes. IEEE Trans. Multimed., 18(9);1832–1842, doi: 10.1109/TMM.2016.2582379.
4. [4] M. S. Hossain, G. Muhammad, and A. Alamri, (2019). Smart healthcare monitoring: a voice pathology detection paradigm for smart cities, Multimed. Syst., 25(5);565–575, doi: 10.1007/S00530-017-0561-X/FIGURES/9.
5. [5] I. El Naqa and M. J. Murphy, (2015). What Is Machine Learning?,” in Machine Learning in Radiation Oncology: Theory and Applications, I. El Naqa, R. Li, and M. J. Murphy, Eds. Cham: Springer International Publishing, pp. 3–11. doi: 10.1007/978-3-319-18305-3_1.
6. [6] K. Liu, J. Zhou, and D. Dong, (2021). Improving stock price prediction using the long short-term memory model combined with online social networks. J. Behav. Exp. Financ., 30; 100507, doi: 10.1016/J.JBEF.2021.100507.
7. [7] M. Sarkar, A. Roy, Y. Badr, B. Gaur, and S. Gupta, (2022). An Intelligent Music Recommendation Framework for Multimedia Big Data: A Journey of Entertainment Industry, pp. 39–67, doi: 10.1007/978-981-16-3828-2_3.
8. [8] S. Tripathi and N. Sharma, (2021). Computer-Based Segmentation of Cancerous Tissues in Biomedical Images Using Enhanced Deep Learning Model. 39(5);1208–1222, doi: 10.1080/02564602.2021.1994044.

9. [9] K. T. Islam, S. Wijewickrema, and S. O’Leary (2019). Identifying diabetic retinopathy from OCT images using deep transfer learning with artificial neural networks. Proc. - IEEE Symp. Comput. Med. Syst., 281–286, doi: 10.1109/CBMS.2019.00066.
10. [10] A. Tayal, J. Gupta, A. Solanki, K. Bisht, A. Nayyar, and M. Masud, (2022). DL-CNN-based approach with image processing techniques for diagnosis of retinal diseases. Multimed. Syst., 28(4);1417–1438, doi: 10.1007/S00530-021-00769-7/FIGURES/13.
11. [11] W. Lu, Y. Tong, Y. Yu, Y. Xing, C. Chen, and Y. Shen, (2018). Deep Learning-Based Automated Classification of Multi-Categorical Abnormalities From Optical Coherence Tomography Images. Transl. Vis. Sci. Technol., 7(6);41–41, doi: 10.1167/TVST.7.6.41.
12. [12] Retinal OCT - C8, (2022). https://www.kaggle.com/datasets/obulisainaren/retinal-oct-c8/code (accessed May 09, 2023).
13. [13] M. Subramanian, K. Shanmugavadivel, O. S. Naren, K. Premkumar, and K. Rankish, (2022). Classification of Retinal OCT Images Using Deep Learning, Int. Conf. Comput. Commun. Informatics, ICCCI , doi: 10.1109/ICCCI54379.2022.9740985.
14. [14] Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner, (1998). Gradient-based learning applied to document recognition, Proc. IEEE, 86(11);2278–2323, doi: 10.1109/5.726791.
15. [15] M. M. Islam, T. N. Poly, B. A. Walther, H. C. Yang, and Y. C. Li, (2020). Artificial Intelligence in Ophthalmology: A Meta-Analysis of Deep Learning Models for Retinal Vessels Segmentation, J. Clin. Med. 9;(4);1018, doi: 10.3390/JCM9041018.
16. [16] G. Huang, Z. Liu, L. Van Der Maaten, and K. Q. Weinberger, (2017). Densely Connected Convolutional Networks. Conf. Comput. Vis. Pattern Recognit., pp. 4700–4708, Accessed: Sep. 11, 2022. [Online].: https://github.com/liuzhuang13/DenseNet.
17. [17] M. Tan and Q. V. Le, (2019). EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks. 36th Int. Conf. Mach. Learn. ICML 2019, 2019;10691–10700, doi: 10.48550/arxiv.1905.11946.
18. [18] C. Szegedy et al., (2015). Going deeper with convolutions; Going deeper with convolutions. doi: 10.1109/CVPR.2015.7298594.
19. [19] C. Szegedy, V. Vanhoucke, S. Ioffe, and J. Shlens, (2016). Rethinking the Inception Architecture for Computer Vision; Rethinking the Inception Architecture for Computer Vision. IEEE Conf. Comput. Vis. Pattern Recognit., pp. 2818–2826, doi: 10.1109/CVPR.2016.308.
20. [20] A. G. Howard et al., (2017). MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications.
21. [21] K. Simonyan and A. Zisserman, (2015). VERY DEEP CONVOLUTIONAL NETWORKS FOR LARGE-SCALE IMAGE RECOGNITION. Comput. Vis. Pattern Recognit., 2015, Accessed: Apr. 26, 2022. [Online]. Available: http://www.robots.ox.ac.uk/
22. [22] F. Chollet, (2017). Xception: Deep Learning with Depthwise Separable Convolutions. doi: 10.1109/CVPR.2017.195.