Glaucoma Detection using Hybrid SVM+ANN Classification
##plugins.themes.bootstrap3.article.main##
Abstract
Glaucomaisaneurologicaldisease and one of the mostwell-knowncausesofvisionloss, according to the abstract. Be causenervedegenerationisanirreversible process, early detection of the conditionisessential to preventing permanent visual loss. Glaucoma is mostly caused by elevated intraocular pressure, and if it is not identified and treated promptly, it can damage vision. Glaucoma is a vision condition that gradually become sworse over time and affects theeye's optic nerve. It results from pressure accumulation inside the eye. Glaucoma frequently runs in families and may not manifest itself since later in life. One of the most crucial and difficult parts is the identification of glaucoma to us progression. Inthisstudy, we presented aunique hybrid algorithm for glaucoma diagnos is. In this study, we provide anovelhybrid approach for classification utilising Artificial Neural Networks (ANN) and supported vector machines (SVM). For segmentation, we used HMM with Cuckoo search optimization (CSO), and for classification, we employe dahybrid of SVM and ANN. When compared to other approaches already in use, the results demonstrate strong performance.
##plugins.themes.bootstrap3.article.details##
Section
Articles
References
[1]. Natarajan, V.; Thangaraj, V. (2017, June). Utilizing a support vector machine, diagnose glaucoma. 2017 saw the first-ever ICICCS (International Conference on Intelligent Computing and Control Systems) (pp. 394-399). IEEE.
[2]. Ng,E.Y.K., Eugene, L.W.J.,Noronha,K.P., Min,L.C., Nayak,K.P., and Bhandary,
S. (2015). Using the Gabor transformation, a glaucoma decision support system. 15, 18– 26, Biomedical Information Theory and Control.
[3]. Dahiya, N., Chauhan, R. P., & Kumar, B. N. (2016, January). A review of image processing methods for glaucoma detection. The 2016 MicroCom Conference on Microelectronics, Computing, and Communications (pp. 1-6). IEEE.
[4]. Bandyopadhyay, S. K. and Dey, A. (2016). Automated glaucoma detection utilising the classification techniqueof thesupportvector machine. BMMR, 11(12), 1. British Journal of Medical and Medical Research.
[5]. Juneja, M.; Thakur, N. (2020). glaucoma classification utilising hybrid features and machine learning techniques. 62, 102137; Biomedical Image Analysis and Control
[6]. Nyúl, L. G. (2009, October). Analyzing retinal images to assess glaucoma risk automatically.MedicalImaging,ParallelImageProcessing,andOptimizationTechniques in MIPPR 2009 (Vol. 7497, pp. 332-340). SPIE.
[7]. N.Kavyaand K.V.Padmaja (2017,October). Detectingglaucoma byextracting textural characteristics. The 51st Asilomar Symposium on Signals, Systems, and Computers was held in 2017. (pp. 1471-1475). IEEE.
[8]. R.Bock, J.Meier, G.Michelson, L.G.Nyl, & J.Hornegger (2007,September).glaucoma classification using fundus images as the basis. Joint Symposium on Pattern Recognition (pp. 355-364). Berlin, Heidelberg: Springer.
[9]. Michelson, G., Dörfler, A., Wärntges, S., El-Rafei, A., & Engelhorn J. (2013). categorization of glaucoma based on diffusion tensor imaging examination of the visual pathway. 1081–1091 in Magnetic Resonance Imaging, 31(7).
[10]. Liu,J., Yin,F., Wirawan,A., Cheung,C.,...&Wong, T.Y.,Zhang,Z.,Kwoh,C.K.(2011, January). For automated glaucoma diagnosis, MRMR optimised classification was used. 2011IEEE Engineering inMedical andBiologySocietyAnnualInternationalConference (pp. 6228-6231). IEEE.
[11]. N. Anantrasirichai, A. Achim, J. E. Morgan, I. Erchova, and L. Nicholson (2013, April). Classification of texture in the optical coherence tomography using SVM. IEEE's 10th Annual Symposium on Biomedical Imaging took place in 2013 (pp. 1332-1335). IEEE.
[12]. Saba,T.,S.T. F. Bokhari,M.Sharif,M.Yasmin, & M.Raza(2018). Areviewof fundus image categorization techniques for glaucoma detection. Research and techniques in microscopy, 81(10), 1105–1121.
[13]. Swindale, N. V., Mikelberg, F. S., and C. M. Parfitt (1995, September). employing a synthetic neural network to identify glaucoma. Engineering in Medical and Biology Society's 17th International Conference Proceedings (Vol. 1, pp. 847-848). IEEE.
[14]. Sunitha, R., Gayathri, & Rao, P. V. (2015). An innovative method of designing and analysing an ANN-based cup-to-disk ratio for the identification of diabetic retinopathy glaucoma. 10, 446-454, Procedia Materials Science.
[15]. Rao,P.V., Gayathri,R., and Aruna, S.(September 2014).glaucomadetectionmethodthat uses ANN and waveletenergy characteristics. ICACCI, the World Congresson Advances in Computing, Communications andInformatics, washeldin 2014. (pp.2808-2812).IEEE.
[16]. S.Pathan, P.Kumar, R.M.Pai, &S.V.Bhandary (2021). Segmentation and classification of retinal characteristics automatically for the diagnosis of glaucoma. 63, 102244. Biomedical Signal Analysis and Control.
[17]. Yaemsuk, A., Suvannachart, P., Itthipanichpong, R., Chansangpetch, S., Phasuk, S., Poopresert, P.,... & Tantibundhit, C. (2019, July). Deep learning-based automated glaucoma screening using retinal fundus images. In 2019, the IEEE Engineering in Medicine and Bioscience Society (EMBC) will hold its 41st annual international conference (pp. 904-907). IEEE.
[18]. The authors are Soltani, Badaoui, Battikh, and Jabri (2018, April). a cutting edge technique for classifying artificialneuralnetworksforthediagnosisofglaucoma.2018saw the fifth CoDIT (Control, Decision and Information Technologies) international conference (pp. 1128-1133). IEEE.
[19]. Manimegala,R., Ranjana,S., andPriya, K.(2020). UsinghiddenMarkov models, colour texture inspection of the fundus picture may be used to diagnose glaucoma. 2020, 7(09), European Society of Molecular & Clinical Medicine.
[20]. Daniel, E., and Anitha, J. 20. (2016). Enhanced random search optimization for optimal wavelet-basedmaskingagainforbackgroundsubtractionofmedicalpictures.Biologyand medical computing, 71, 149–155.
[21]. Anitha, J., Daniel, E., and (2016). Scale value optimization using cuckoo search for improvingretinalimageregistrationFifthInternationalConventiononSoftComputingfor Problem Solving, Proceedings (pp. 453-460). Singapore's Springer.
[2]. Ng,E.Y.K., Eugene, L.W.J.,Noronha,K.P., Min,L.C., Nayak,K.P., and Bhandary,
S. (2015). Using the Gabor transformation, a glaucoma decision support system. 15, 18– 26, Biomedical Information Theory and Control.
[3]. Dahiya, N., Chauhan, R. P., & Kumar, B. N. (2016, January). A review of image processing methods for glaucoma detection. The 2016 MicroCom Conference on Microelectronics, Computing, and Communications (pp. 1-6). IEEE.
[4]. Bandyopadhyay, S. K. and Dey, A. (2016). Automated glaucoma detection utilising the classification techniqueof thesupportvector machine. BMMR, 11(12), 1. British Journal of Medical and Medical Research.
[5]. Juneja, M.; Thakur, N. (2020). glaucoma classification utilising hybrid features and machine learning techniques. 62, 102137; Biomedical Image Analysis and Control
[6]. Nyúl, L. G. (2009, October). Analyzing retinal images to assess glaucoma risk automatically.MedicalImaging,ParallelImageProcessing,andOptimizationTechniques in MIPPR 2009 (Vol. 7497, pp. 332-340). SPIE.
[7]. N.Kavyaand K.V.Padmaja (2017,October). Detectingglaucoma byextracting textural characteristics. The 51st Asilomar Symposium on Signals, Systems, and Computers was held in 2017. (pp. 1471-1475). IEEE.
[8]. R.Bock, J.Meier, G.Michelson, L.G.Nyl, & J.Hornegger (2007,September).glaucoma classification using fundus images as the basis. Joint Symposium on Pattern Recognition (pp. 355-364). Berlin, Heidelberg: Springer.
[9]. Michelson, G., Dörfler, A., Wärntges, S., El-Rafei, A., & Engelhorn J. (2013). categorization of glaucoma based on diffusion tensor imaging examination of the visual pathway. 1081–1091 in Magnetic Resonance Imaging, 31(7).
[10]. Liu,J., Yin,F., Wirawan,A., Cheung,C.,...&Wong, T.Y.,Zhang,Z.,Kwoh,C.K.(2011, January). For automated glaucoma diagnosis, MRMR optimised classification was used. 2011IEEE Engineering inMedical andBiologySocietyAnnualInternationalConference (pp. 6228-6231). IEEE.
[11]. N. Anantrasirichai, A. Achim, J. E. Morgan, I. Erchova, and L. Nicholson (2013, April). Classification of texture in the optical coherence tomography using SVM. IEEE's 10th Annual Symposium on Biomedical Imaging took place in 2013 (pp. 1332-1335). IEEE.
[12]. Saba,T.,S.T. F. Bokhari,M.Sharif,M.Yasmin, & M.Raza(2018). Areviewof fundus image categorization techniques for glaucoma detection. Research and techniques in microscopy, 81(10), 1105–1121.
[13]. Swindale, N. V., Mikelberg, F. S., and C. M. Parfitt (1995, September). employing a synthetic neural network to identify glaucoma. Engineering in Medical and Biology Society's 17th International Conference Proceedings (Vol. 1, pp. 847-848). IEEE.
[14]. Sunitha, R., Gayathri, & Rao, P. V. (2015). An innovative method of designing and analysing an ANN-based cup-to-disk ratio for the identification of diabetic retinopathy glaucoma. 10, 446-454, Procedia Materials Science.
[15]. Rao,P.V., Gayathri,R., and Aruna, S.(September 2014).glaucomadetectionmethodthat uses ANN and waveletenergy characteristics. ICACCI, the World Congresson Advances in Computing, Communications andInformatics, washeldin 2014. (pp.2808-2812).IEEE.
[16]. S.Pathan, P.Kumar, R.M.Pai, &S.V.Bhandary (2021). Segmentation and classification of retinal characteristics automatically for the diagnosis of glaucoma. 63, 102244. Biomedical Signal Analysis and Control.
[17]. Yaemsuk, A., Suvannachart, P., Itthipanichpong, R., Chansangpetch, S., Phasuk, S., Poopresert, P.,... & Tantibundhit, C. (2019, July). Deep learning-based automated glaucoma screening using retinal fundus images. In 2019, the IEEE Engineering in Medicine and Bioscience Society (EMBC) will hold its 41st annual international conference (pp. 904-907). IEEE.
[18]. The authors are Soltani, Badaoui, Battikh, and Jabri (2018, April). a cutting edge technique for classifying artificialneuralnetworksforthediagnosisofglaucoma.2018saw the fifth CoDIT (Control, Decision and Information Technologies) international conference (pp. 1128-1133). IEEE.
[19]. Manimegala,R., Ranjana,S., andPriya, K.(2020). UsinghiddenMarkov models, colour texture inspection of the fundus picture may be used to diagnose glaucoma. 2020, 7(09), European Society of Molecular & Clinical Medicine.
[20]. Daniel, E., and Anitha, J. 20. (2016). Enhanced random search optimization for optimal wavelet-basedmaskingagainforbackgroundsubtractionofmedicalpictures.Biologyand medical computing, 71, 149–155.
[21]. Anitha, J., Daniel, E., and (2016). Scale value optimization using cuckoo search for improvingretinalimageregistrationFifthInternationalConventiononSoftComputingfor Problem Solving, Proceedings (pp. 453-460). Singapore's Springer.