Glokom Hastalığının Evrişimli Sinir Ağı Mimarileri ile Tespiti

Year 2021, Volume: 23 Issue: 68, 521 - 529, 24.05.2021

Murat Uçar

https://doi.org/10.21205/deufmd.2021236815

Cited By: 5

Abstract

Glokom, genellikle göz içi basıncının yükselmesi nedeniyle optik sinire zarar veren bir hastalıktır ve dünya genelinde geri döndürülemez körlüğün yaygın bir sebebidir. Ancak hastalık erken dönemde tespit edilebilirse görme kaybı önlenebilmektedir. Günümüzde glokom hastalığının tanısı, gelişmiş yapay zeka teknikleri kullanılarak bilgisayar destekli sistemler yardımıyla yapılabilmektedir. Bu çalışmada, yeni oluşturulmuş büyük ölçekli bir veri setine ait dijital fundus görüntüleri kullanılarak otomatik glokom tespiti için derin evrişimli sinir ağları yöntemi kullanılmıştır. Literatürde sınıflandırma problemlerinde en sık kullanılan mimarilerden VGG16, Inception-V3, EfficientNet, DenseNet, ResNet50 ve MobileNet mimarileri seçilmiştir. Deneysel çalışmalar sonucunda DenseNet mimarisinin %96.19 ile en yüksek başarı oranını elde ettiği görülmüştür. Elde edilen bulgular evrişimli sinir ağlarının normal ve glokomlu görüntüleri sınıflandırmada başarılı bir yöntem olduğunu kanıtlamıştır.

Keywords

Glokom, Derin öğrenme, Evrişimli sinir ağları, Transfer Öğrenimi

Diagnosis of Glaucoma Disease using Convolutional Neural Network Architectures

Abstract

Glaucoma is a disease that damages the optic nerve, often due to increased intraocular pressure, and is a common cause of irreversible blindness worldwide. However, if the disease can be detected in the early period, vision loss can be prevented. Today, the diagnosis of glaucoma disease can be made with the help of computer-aided systems using advanced artificial intelligence techniques. In this study, deep convolutional neural networks were used for automatic glaucoma detection using digital fundus images of a newly created large-scale data set. VGG16, Inception-V3, EfficientNet, DenseNet, ResNet50 and MobileNet architectures which are the most frequently used architectures in classification problems were selected. As a result of experimental studies, it was seen that the DenseNet architecture achieved the highest accuracy rate with 96.19%. The findings have proven that convolutional neural networks are a successful methods on classification of normal and glaucoma images.

Keywords

Glaucoma, Deep learning, Convolutional neural networks, Transfer Learning

References

• Tham, Y. C., Li, X., Wong, T. Y., Quigley, H. A., Aung, T., & Cheng, C. Y. 2014. Global prevalence of glaucoma and projections of glaucoma burden through 2040: a systematic review and meta-analysis, Ophthalmology, vol. 121, no. 11, pp. 2081–2090. doi:10.1016/j.ophtha.2014.05.013
• Gulshan, V., Peng, L., Coram, M., Stumpe, M. C., Wu, D., Narayanaswamy, A., ... & Kim, R. 2016. Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs, Jama, vol. 316, no. 22, pp. 2402–2410. doi:10.1001/jama.2016.17216
• Lee, C. S., Baughman, D. M., & Lee, A. Y. 2017. Deep learning is effective for classifying normal versus age-related macular degeneration OCT images, Ophthalmol. Retin., vol. 1, no. 4, pp. 322–327. doi:10.1016/j.oret.2016.12.009
• Chen, X., Xu, Y., Wong, D. W. K., Wong, T. Y., & Liu, J. 2015. Glaucoma detection based on deep convolutional neural network, in 2015 37th annual international conference of the IEEE engineering in medicine and biology society (EMBC), pp. 715–718. doi: 10.1109/EMBC.2015.7318462
• Raghavendra, U., Fujita, H., Bhandary, S. V., Gudigar, A., Tan, J. H., & Acharya, U. R. 2018. Deep convolution neural network for accurate diagnosis of glaucoma using digital fundus images, Inf. Sci. (Ny)., vol. 441, pp. 41–49. doi:10.1016/j.ins.2018.01.051
• Y. Chai, H. Liu, and J. Xu, “Glaucoma diagnosis based on both hidden features and domain knowledge through deep learning models,” Knowledge-Based Syst., vol. 161, pp. 147–156, 2018.
• Fu, H., Cheng, J., Xu, Y., Zhang, C., Wong, D. W. K., Liu, J., & Cao, X. 2018. Disc-aware ensemble network for glaucoma screening from fundus image, IEEE Trans. Med. Imaging, vol. 37, no. 11, pp. 2493–2501. doi:10.1109/TMI.2018.2837012
• Li, L., Xu, M., Wang, X., Jiang, L., & Liu, H. 2019. Attention based glaucoma detection: A large-scale database and CNN Model, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 10571–10580.
• Bisneto, T. R. V., de Carvalho Filho, A. O., & Magalhães, D. M. V. 2020. Generative adversarial network and texture features applied to automatic glaucoma detection, Appl. Soft Comput., vol. 90, p. 1061-65. doi:10.1016/j.asoc.2020.106165
• Shankaranarayana, S. M., Ram, K., Mitra, K., & Sivaprakasam, M. 2017. Joint optic disc and cup segmentation using fully convolutional and adversarial networks, in Fetal, Infant and Ophthalmic Medical Image Analysis, Springer, pp. 168–176.
• Zilly, J., Buhmann, J. M., & Mahapatra, D. 2017. Glaucoma detection using entropy sampling and ensemble learning for automatic optic cup and disc segmentation, Comput. Med. Imaging Graph., vol. 55, pp. 28–41. doi:10.1016/j.compmedimag.2016.07.012
• Simonyan, K., & Zisserman, A. 2014. Very deep convolutional networks for large-scale image recognition, arXiv Prepr. arXiv1409.1556.
• 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, pp. 2818–2826.
• Tan, M., & Le, Q. V. 2019. Efficientnet: Rethinking model scaling for convolutional neural networks, 36th Int. Conf. Mach. Learn. ICML 2019, vol. 2019-June, pp. 10691–10700.
• Huang, G., Liu, Z., Van Der Maaten, L., & Weinberger, K. Q. 2017. Densely connected convolutional networks, in Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 4700–4708.
• He, K., Zhang, X., Ren, S., & Sun, J. 2016. Deep residual learning for image recognition, Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit., vol. 2016-Decem, pp. 770–778.
• Howard, A. G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., ... & Adam, H. 2017. Mobilenets: Efficient convolutional neural networks for mobile vision applications, arXiv Prepr. arXiv1704.04861.