Glaucoma Classification using Light Vision Transformer
Keywords:Glaucoma, CNN models, Vision Transformer Model, Optimizers, Fundus imaging
INTRODUCTION: Nowadays one of the primary causes of permanent blindness is glaucoma. Due to the trade-offs, it makes in terms of portability, size, and cost, fundus imaging is the most widely used glaucoma screening technique.
OBJECTIVES:To boost accuracy,focusing on less execution time, and less resources consumption, we have proposed a vision transformer-based model with data pre-processing techniques which fix classification problems.
METHODS: Convolution is a “local” technique used by CNNs that is restricted to a limited area around an image. Self-attention, used by Vision Transformers, is a “global” action since it gathers data from the whole image. This makes it possible for the ViT to successfully collect far-off semantic relevance in an image. Several optimizers, including Adamax, SGD, RMSprop, Adadelta, Adafactor, Nadam, and Adagrad, were studied in this paper. We have trained and tested the Vision Transformer model on the IEEE Fundus image dataset having 1750 Healthy and Glaucoma images. Additionally, the dataset was preprocessed using image resizing, auto-rotation, and auto-adjust contrast by adaptive equalization.
RESULTS: Results also show that the Nadam Optimizer increased accuracy up to 97% in adaptive equalized preprocessing dataset followed by auto rotate and image resizing operations.
CONCLUSION: The experimental findings shows that transformer based classification spurred a revolution in computer vision with reduced time in training and classification.
Weinreb R N, Aung T, Medeiros FA. The pathophysiology and treatment of glaucoma: a review. In JAMA, 311(18), 1901–1911) DOI: https://doi.org/10.1001/jama.2014.3192.
Singh PB, Singh P, Dev H. Optimized convolutional neural network for glaucoma detection with improved Optic-Cup segmentation. Advances in Engineering Software 175(2023), 1-13 (2022) DOI: https://doi.org/10.1016/j.advengsoft.2022.103328
Tham, Y.C., Li, X., Wong, T.Y., Quigley, H. A., Aung, T., Cheng, C.Y. Global prevalence of glaucoma and projections of glaucoma burden through 2040: a systematic review and meta-analysis. Ophthalmology,121(11), 2081–2090 (2014) DOI: 10.1016/j.ophtha.2014.05.013
Bajpai S, Sharma K, Chaurasia BK. Intrusion Detection Framework in IoT Networks. Springer Nature Computer Science Journal, Special Issue on Machine Learning and Smart Systems, 4(350), 1-17 (2023) DOI: https://doi.org/10.1007/s42979-023-01770-9
Courtie, E., Veenith, T., Logan, A.: Retinal blood flow in critical illness and systemic disease: A Review. Annals of Intensive Care 10(152), 1-18 (2020) DOI: https://doi.org/10.1186/s13613-020-00768-3
Bajpai S, Sharma K, Chaurasia BK. Intrusion Detection System in IoT Network using ML. In NeuroQuantology 20(13), 3597-3601 (2022) DOI: 10.14704/nq.2022.20.13.NQ88441
Qummar S, Khan FG, Shah S, Khan A,Shamshirband S, Rehman Z U, Khan IA, Jadoon W (2019) A Deep Learning Ensemble Approach for Diabetic Retinopathy Detection. In IEEE Access, 7:150530- 150539 DOI: 10.1109/ACCESS.2019.2947484
Krizhevsky A, Sutskever I, Hinton GE. ImageNet classification with deep convolutional neural networks. In Communications of the ACM, 60, 84–90 (2017) DOI:10.1145/3065386.
Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser L, Polosukhin I. Attention is all you need, In Proc. Conf. Neural Informat. Process. Syst., 6000–6010 (2017)
Nguyen MH, Quang KN. A Study of Vision Transformer for Lung Diseases Classification. In 6th International Conference on Green Technology and Sustainable Development (GTSD), 116-121 (2022) DOI: 10.1109/GTSD54989.2022.9989100
Okolo GI, Katsigiannis S. Ramzan, N. IEViT: An enhanced vision transformer architecture for chest X-ray image classification, In Computer Methods and Programs in Biomedicine, 226 (107141), 1-11 (2022). DOI:10.1016/j.cmpb.2022.107141
Han K, Wang, Y, Chen H, Chen X, Guo J, Liu Z, Tang Y, Xiao AuC, Xu Y, Yang Z, Zhang Y, Tao D. A Survey on Vision Transformer. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45 (1), 87-110 (2023) DOI: 10.1109/TPAMI.2022.3152247
Huang Z, Du Ji-X, Zhang H-Bo. A Multi-Stage Vision Transformer for Fine-grained Image Classification. In 11th International Conference on Information Technology in Medicine and Education (ITME), 191-195 (2021) DOI: 10.1109/ITME53901.2021.00047
Han X, Wang K, Tu S, Zhou W. Image Classification Based on Convolution and Lite Transformer. 4th Internati-onal Conference on Applied Machine Learning (ICAML), 3-7 (2022)DOI: 10.1109/ICAML57167.2022.00009
Mallick S, Paul J, Sengupta N, Sil J. Study of Different Transformer based Networks for Glaucoma Detection. In IEEE Region 10 Conference (TENCON), 1-6 (2022) DOI: 10.1109/TENCON55691.2022.9977730
Tripathi A, Misra A, Kumar K, Chaurasia BK.Optimized Machine Learning for classifying colorectal tissues. Springer Nature Computer Science Journal, Special Issue on Machine Learning and Smart Systems, 1-26 (2023) DOI : 10.1007/s42979-023-01882-2
Chaurasia BK, Raj H, Rathour SS,Singh PB. Transfer Learning driven Ensemble Model for Detection of Diabetic Retinopathy Disease. In Medical & Biological Engineering & Computing, Springer, 1-22 (2023) DOI : 10.1007/s11517-023-02863-6
Tripathi A, Misra A, Kumar K, Chaurasia BK. Colon Cancer classification using Machine Learning. IEEE ISCON, 1-6 (2023). DOI: 10.1109/ISCON57294.2023.10112181
Wassel M, Hamdi AM, Adly N, Torki M. Vision Transformers Based Classification for Glaucomatous Eye Condition. In 26th International Conference on Pattern Recognition (ICPR), 5082-5088 (2022) DOI: 10.1109/TENCON55691.2022.9977730
IEEE Dataset, Online Available at: https://ieee-dataport.org/documents/1450-fundus-images- 899-glaucoma-data-and-551-normal-data
How to Cite
Copyright (c) 2023 Piyush Bhushan Singh, Pawan Singh, Harsh Dev, Anil Tiwari, Devanshu Batra, Brijesh Kumar Chaurasia
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
This is an open access article distributed under the terms of the CC BY-NC-SA 4.0, which permits copying, redistributing, remixing, transformation, and building upon the material in any medium so long as the original work is properly cited.