The second most common visually disabling disease after Diabetic Retinopathy is Retinal Vein Occlusion (RVO). There are three types of Retinal Vein Occlusions: Central Retinal Vein Occlusion (CRVO), Branch Retinal Vein Occlusion (BRVO) and Hemi-retinal Vein Occlusion (HRVO). Here, CRVO is the blockage of the center vein, BRVO is the blockage of smaller veins i.e. branches of the vein and HRVO is the blockage of sub-veins of the main vein. Branch Retinal Vein Occlusion (BRVO) is three times more prevalent than Central Retinal Vein Occlusion (CRVO). Vision loss or blurry vision, floaters are some of the common features of BRVO. The treatment of BRVO aims at avoiding further damage to the patient’s vision but it cannot heal or help regain the vision. Due to this reason, the detection of BRVO requires proper attention. Also, fundus machines for detection of BRVO are not available in remote areas. The symptoms of this disease cannot be easily detected due to very small variations in the early stages and also due to the absence of an ophthalmologist. To serve this purpose an Artificial Intelligence is developed with the aim of providing the first level of diagnosis of BRVO. For this, different preprocessing techniques and layers are used to build four Convolutional Neural Network models.

occlusion, Artificial Intelligence, Convolutional Neural Network

[1] Karia N. Retinal vein occlusion: pathophysiology and treatment options. Clin Ophthalmol. 2010 Jul 30;4:809-16.
[2] Hayreh SS. Prevalent misconceptions about acute retinal occlusive disorders. ProgRetin Eye Res 2005; 24: 493-519.
[3] A. Krizhevsky, I. Sutskever, G. E. Hinton, “ImageNet Classification with Deep Convolutional Neural Networks,” in Proceedings of Neural Information Processing Systems Conference (NIPS), 2012
[4] R. Socher, B. Huval, B. Bhat, C.D. Manning, and A.Y. Ng, “Convolutional-recursive deep learning for 3D object classification,” in Proceedings of Neural Information Processing Systems Conference (NIPS), 2012.
[5] Y. Sun, Y. Chen, X. Wang, and X. Tang, “Deep learning face representation by joint identification-verification,” in Proceedings of Neural Information Processing Systems Conference (NIPS), 2014.
[6] Daraius Shroff, Abhishek Kothari, Gagan Bhatia, Charu Gupta, “Clinical Diagnosis of Retinal Vein Occlusion”, in International Journal of Ophthalmic Research Volume 2 - No 2, 2016
[7] Juil J. Zode, Pranali C. Choudhari, “Detection of Branch Retinal Vein Occlusion using Fractal Analysis,” in International Journal of Computer Applications (0975 – 8887) Volume 162 – No 8, March 2017.
[8] Pallvi Dehariya, “An Artificial Immune System and Neural Network to Improve the Detection Rate in Intrusion Detection System”, in International Journal of Scientific Research in Network Security and Communication, Volume-4, Issue-1, Feb- 2016
[9] A.K.Gupta, S.Gupta, “Neural Network through Face Recognition”, in International Journal of Scientific Research in Research Paper. Computer Science and Engineering Vol.6, Issue.2, pp.38-40, April (2018)