UTILIZING DEEP LEARNING AND DATA AUGMENTATION FOR EARLY DETECTION OF EYE DISEASES IN PETS

Year 2023, , 112 - 122, 30.06.2023

Nilgün Şengöz

https://doi.org/10.47933/ijeir.1227798

Abstract

This paper presents a deep learning algorithm for the diagnosis of eye diseases, which is taken from cats and dogs, using data augmentation. The database of eye images was collected from cell phone cameras, and with data augmentation techniques were used to increase the number of samples. The performance of the algorithms was evaluated on the original dataset of 146 diseased and 255 healthy images. The results showed that the VGG16 algorithm achieved a classification accuracy of 99.25% before data augmentation, which was significantly higher than the accuracy of existing methods. Furthermore, after the data augmentation again VGG16 model has significant performance metrics that are 99.9% than other algorithms. The proposed algorithm can be used to accurately diagnose various eye diseases, which can potentially improve the quality of care for patients.

Keywords

Classification, eye disease, deep learning, data augmentation

UTILIZING DEEP LEARNING AND DATA AUGMENTATION FOR EARLY DETECTION OF EYE DISEASES IN PETS

Abstract

Bu makale, kedi ve köpeklerden veri artırma kullanılarak alınan göz hastalıklarının teşhisi için derin bir öğrenme algoritması sunmaktadır. Göz görüntülerinin veri tabanı cep telefonu kameralarından toplanmış ve veri büyütme teknikleri kullanılarak örnek sayısı artırılmıştır. Algoritmaların performansı, 146 hastalıklı ve 255 sağlıklı görüntünün orijinal veri kümesi üzerinde değerlendirildi. Sonuçlar, VGG16 algoritmasının, veri artırmadan önce %99,25'lik bir sınıflandırma doğruluğu elde ettiğini gösterdi; bu, mevcut yöntemlerin doğruluğundan önemli ölçüde daha yüksekti. Ayrıca veri artırma işleminden sonra yine VGG16 modeli diğer algoritmalara göre %99,9 oranında önemli performans ölçütlerine sahiptir. Önerilen algoritma, hastalar için bakım kalitesini potansiyel olarak artırabilen çeşitli göz hastalıklarını doğru bir şekilde teşhis etmek için kullanılabilir.

Keywords

Classification, Göz hastalıkları, derin öğrenme, veri çoğaltma

References

• [1] Kirk N. Gelatt (2013), Ocular Diseases of Companion Animals, Veterinary Ophthalmology, 5th Edition
• [2] Shan, J., Li, L. (2016). A deep learning method for microaneurysm detection in fundus images, IEEE First International Conference on Connected Health: Applications, Systems and Engineering Technologies (CHASE), Washington, DC, 357-358.
• [3] Deepa, V., Kumar, C. S., & Andrews, S. S. (2021). Fusing dualtree quaternion wavelet transform and local mesh-based features for grading of diabetic retinopathy using extreme learning machine classifier. International Journal of Imaging Systems and Technology, 31, 1625-1637
• [4] Güldemir, N.H., Alkan A., (2021), Derin Öğrenme ile Optik Koherens Tomografi Görüntülerinin Sınıflandırılması, Fırat Üniversitesi Müh. Bil. Dergisi Araştırma Makalesi 33(2), 607-615
• [5] Tasnim N, Hasan M, Islam I, (2019), Comparisonal study of Deep Learning approaches on Retinal OCT Image”, arXiv preprint arXiv:1912.07783
• [6] Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Rabinovich, A., (2015), Going deeper with convolutions, In Proceedings of the IEEE conference on computer vision and pattern recognition, 1-9
• [7] Pandiyan, Vigneashwara & Tjahjowidodo, Tegoeh & Caesarendra, Wahyu and Murugan, Pushparaja. (2019). In-process virtual verification of weld seam removal in robotic abrasive belt grinding process using deep learning,Robotics and Computer-Integrated Manufacturing. 57. 477–487, 10.1016/j.rcim.2019.01.006
• [8] He, K.; Zhang, X.; Ren, S.; Sun, J. (2016), Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA, 27–30 June; pp. 770–778
• [9] Szegedy, C.; Vanhoucke, V.; Ioffe, S.; Shlens, J.; Wojna, Z. (2016), Rethinking the inception architecture for computer vision. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA, 27–30 June; pp. 2818–2826
• [10] N. Dong, L. Zhao, C.H. Wu, J.F. Chang, (2020), Inception v3 based cervical cell classification combined with artificially extracted features, Applied Soft Computing, Volume 93, https://doi.org/10.1016/j.asoc.2020.106311
• [11] Chollet, François, (2016) Xception: Deep Learning with Depthwise Separable Convolutions, arXiv Preprint arXiv:1610.02357
• [12] Gao Huang, Zhuang Liu, Kilian Q. Weinberger, Laurens van der Maaten, and Chen Change Loy, (2016), Densely Connected Convolutional Networks, arXiv:1608.06993
• [13] Marin, Ivana, Saša Mladenović, Sven Gotovac, and Goran Zaharija. (2021), Deep-Feature-Based Approach to Marine Debris Classification, Applied Sciences 11, no. 12: 5644. https://doi.org/10.3390/app11125644
• [14] Mingxing Tan, Quoc V. Le., (2019), EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks, In International Conference on Computer Vision (ICCV)
• [15] Ahmed, T., Sabab, N.H.N., (2022), Classification and Understanding of Cloud Structures via Satellite Images with EfficientUNet. SN COMPUT. SCI. 3, 99 https://doi.org/10.1007/s42979-021-00981-2