Derin Öğrenmeye Karşı Makine Kullanarak Diyabetik Retinopati Teşhisi

Year 2023, Issue: 51, 301 - 313, 31.08.2023

Nehad Ramaha , Shuhad Imad

https://doi.org/10.31590/ejosat.1263514

Abstract

Diyabetik retinopati hastalığı dünya çapında milyonlarca insanı etkilemektedir. Diyabetik hastalığın bir komplikasyonu olarak kabul edilir ve göz görüşünü etkileyebilir. Hekimler bu hastalığı tıbbi göz muayenesi ile tespit edebilirler. Nihai kararı vermek için birçok görüntünün işlenmesi gerekir. Neyse ki, bilgisayar destekli karar destek sistemleri, doktorların daha az çaba ve zaman harcayarak doğru kararlar vermelerine yardımcı olabilir. Bu çalışmada, güncel diyabetik retinopati bilgisayar destekli sistemlerin bir derlemesi sunulmaktadır. Çalışma, diyabetik retinopati tespiti için makine öğrenimi veya derin öğrenme yaklaşımlarının kullanıldığı çalışmaları içermektedir. Bu makale, önerilen metodoloji, kullanılan veri seti, elde edilen sonuçlar ve değerlendirme açısından önceki tüm çalışmaları karşılaştırmaktadır. Çalışma ayrıca mevcut diyabetik retinopati veri setlerini de karşılaştırdı. Sonuç olarak, derin öğrenmeye dayalı yöntemlerin en iyi performansı gösterdiğini gördük. Ayrıca, diyabetik retinopati evrelerinin kategorik sınıflandırması, hastalık tespitinde ikili sınıflandırma yapmaktan daha iyiydi. Bu çalışma, araştırmacıların gelecekteki çalışmalarında en iyi metodolojileri ve veri kümelerini seçmelerine yardımcı olur.

Keywords

Diyabetik Retinopati, Makine Öğrenimi, Derin Öğrenme, Kan Damarları, Görüntü İşleme, Görüntü Sınıflandırma

Diabetic Retinopathy Diagnosis Using Machine Versus Deep Learning

Abstract

Diabetic retinopathy disease affects millions of people around the world. It is considered a complication of diabetic disease and can affect eye vision. Physicians can detect this disease by medical eye examination. Many images need to be processed in order to make the final decision. Fortunately, computer-aided decision support systems can help physicians make accurate decisions with less effort and time. In this study, a review of the current diabetic retinopathy computer-aided systems is introduced. The study includes studies using machine learning or deep learning approaches for diabetic retinopathy detection. This paper compares all those previous studies in terms of the proposed methodology, the used dataset, the acquired results, and the evaluation. The study also compared the current diabetic retinopathy datasets. As a result, we found that the methods that were based on deep learning had the best performance. Besides, the categorical classification of diabetic retinopathy stages was better than doing a binary classification of disease detection. This study helps researchers in their future work to select the best methodologies and datasets.

Keywords

Diabetic Retinopathy, Machine Learning, Deep Learning, Blood Vessels, Image Processing, Image Classification

References

• R. Taylor and D. Batey, Handbook of retinal screening in diabetes: diagnosis and management., John Wiley & Sons, 2012.
• International diabetes federation, "What is diabetes," 161 2023. [Online]. Available: https://www.idf.org/aboutdiabetes/what-is-diabetes.html. [Accessed 20 1 2023].
• diabetesatlas, "IDF Diabetes Atlas 2022 Reports," [Online]. Available: https://diabetesatlas.org/. [Accessed 20 1 2023].
• B. Mounirou, N. Adam, A. Yakoura, M. Aminou, Y. Liu and L. Tan, "Diabetic Retinopathy: An Overview of Treatments," Indian J Endocr Metab, vol. 26, no. 2, pp. 111-118, 2022.
• R. Bourne, G. A. Stevens, R. A. White, J. L. Smith, S. R. Flaxman, H. Price and J. B. Jonas, "Causes of vision loss worldwide, 1990–2010: a systematic analysis," The lancet global health , vol. 1, no. 6, pp. 339-349, 2013.
• M. D. Saleh and C. Eswaran, "An automated decision-support system for non-proliferative diabetic retinopathy disease based on MAs and HAs detection," Computer methods and programs in biomedicine, vol. 108, no. 1, pp. 186-196, 2012.
• W. L. Alyoubi, W. M. Shalash and M. F. Abulkhair, "Diabetic retinopathy detection through deep learning techniques: A review," Informatics in Medicine Unlocked, vol. 20, 2020.
• L. Guariguata, D. R. Whiting, I. Hambleton, J. Beagley, U. Linnenkamp and J. E. Shaw, "Global estimates of diabetes prevalence for 2013 and projections for 2035," Diabetes research and clinical practice , vol. 103, no. 2, pp. 137-149, 2014.
• P. H. Scanlon, A. Sallam and P. V. Wijngaarden, A practical manual of diabetic retinopathy management, John Wiley & Sons, 2017.
• A. Arrigo, M. Teussink, E. Aragona, F. Bandello and M. B. Parodi, "MultiColor imaging to detect different subtypes of retinal microaneurysms in diabetic retinopathy," Eye , vol. 1, pp. 277-281, 2021.
• M. Dubow, A. Pinhas, N. Shah, R. Cooper, A. Gan, R. Gentile and V. Hendrix, "Classification of human retinal microaneurysms using adaptive optics scanning light ophthalmoscope fluorescein angiography," Investigative ophthalmology & visual science, vol. 55, no. 3, pp. 1299-1309, 2014.
• A. Skouta, A. Elmoufidi, S. Jai-Andaloussi and O. Ouchetto, "Hemorrhage semantic segmentation in fundus images for the diagnosis of diabetic retinopathy by using a convolutional neural network," Journal of Big Data volume, vol. 9, no. 1, pp. 1-24, 2022.
• S. Guo, "LightEyes: A Lightweight Fundus Segmentation Network forMobile Edge Computing," Sensors, vol. 22, pp. 1-21, 2022.
• D. Das, S. Biswas, S. Bandyopadhyay and S. Sarkar, "Early Detection of Diabetic Retinopathy Using Machine Learning Techniques: A Survey on Recent Trends and Techniques," in Lecture Notes in Electrical Engineering book series, 2020.
• P. Porwal, S. Pachade, R. Kamble, M. Kokare, G. Deshmukh, V. Sahasrabuddhe and F. Meriaudeau, "Indian Diabetic Retinopathy Image Dataset (IDRiD): A Database for Diabetic Retinopathy Screening Research," data, vol. 3, no. 3, 2018.
• M. Chetoui, M. Akhloufi and M. Kardouchi, "Diabetic Retinopathy Detection Using Machine Learning and Texture Features," in IEEE Canadian Conference on Electrical & Computer Engineering, 2018.
• R. Senapati, "Bright lesion detection in color fundus images based on texture features," Bulletin of Electrical Engineering and Informatics , vol. 5, no. 1, pp. 92-100, 2016.
• E. Carrera, A. González and R. Carrera, "Automated detection of diabetic retinopathy using SVM," in IEEE XXIV international conference on electronics, electrical engineering and computing, Cusco, Peru, 2017.
• M. Hardas, S. Mathur, A. Bhaskar and M. Kalla, "Retinal fundus image classification for diabetic retinopathy using SVM predictions," Physical and Engineering Sciences in Medicine, vol. 45, p. 781–791, 2022.
• E. Z. Aziza, L. M. E. Amine, M. Mohamed and B. Abdelhafid, "Decision tree CART algorithm for diabetic retinopathy classification," in International Conference on Image and Signal Processing and their Applications (ISPA), Mostaganem, Algeria, 2019.
• H. Yao, S. Wu, Z. Zhan and Z. Li, "A Classification Tree Model with Optical Coherence Tomography Angiography Variables to Screen Early-Stage Diabetic Retinopathy in Diabetic Patients," Journal of Ophthalmology, no. Special Issue, 2022.
• R. Casanova, S. Saldana, E. Y. Chew, R. P. Danis, C. M. Greven and W. T. Ambrosius, "Application of Random Forests Methods to Diabetic Retinopathy Classification Analyses," PLOS one, vol. 9, no. 6, 2014.
• F. Alzami, R. Abdussalam, A. Megantara, A. Zainul and F. Purwanto, "Diabetic Retinopathy Grade Classification based on Fractal Analysis and Random Forests," in International Seminar on Application for Technology of Information and Communication (iSemantic), 2019.
• N. ZAABOUB and A. DOUIK, "Early Diagnosis of Diabetic Retinopathy using Random Forest Algorithm," in International Conference on Advanced Technologies for Signal and Image Processing (ATSIP), Sousse, Tunisia, 2020.
• Y. Kang, Y. Fang and X. Lai, "Automatic Detection of Diabetic Retinopathy with Statistical Method and Bayesian Classifier," Journal of Medical Imaging and Health Informatics, vol. 10, no. 5, pp. 1225-1233, 2020.
• R. Hadistio, H. Mawengkang and M. Zarlis, "Perbandingan Algoritma Stochastic Gradient Descent dan Naïve Bayes Pada Klasifikasi Diabetic Retinopathy," JURNAL MEDIA INFORMATIKA BUDIDARMA, vol. 6, no. 1, 2022.
• S. Roychowdhury, D. D. Koozekanani and K. K. Parhi, "DREAM: Diabetic Retinopathy Analysis Using Machine Learning," IEEE Journal of Biomedical and Health Informatics , vol. 18, no. 5, pp. 1717-1728, 2014.
• G. T. Reddy, S. Bhattacharya, S. S. Ramakrishnan, C. L. Chowdhary and S. Hakak, "An Ensemble based Machine Learning model for Diabetic Retinopathy Classification," in International Conference on Emerging Trends in Information Technology and Engineering (ic-ETITE), Vellore, India, 2020.
• N. Sikder, M. Masud, A. K. Bairagi, A. S. M. Arif, A.-A. Nahid and H. A. Alhumyani, "Severity classification of diabetic retinopathy using an ensemble learning algorithm through analyzing retinal images," Symmetry , vol. 13, no. 4, 2021.
• M. J. Pendekal and S. Gupta, "An Ensemble Classifier Based on Individual Features for Detecting Microaneurysms in Diabetic Retinopathy," Indonesian Journal of Electrical Engineering and Informatics (IJEEI), vol. 10, no. 1, pp. 60-71, 2022.
• H. Pratt, F. Coenen, D. M. Broadbent, S. P. Harding and Y. Zheng, "Convolutional neural networks for diabetic retinopathy," Procedia computer science , vol. 90, pp. 200-205, 2016.
• S. Paul and L. Singh, "Heterogeneous modular deep neural network for diabetic retinopathy detection," in IEEE Region 10 Humanitarian Technology Conference, 2016.
• R. Gargeya and T. Leng, "Automated Identification of Diabetic Retinopathy Using Deep Learning," Ophthalmology, pp. 1-8, 2017.
• C. Lam, C. Yu, L. Huang and D. Rubin, "Retinal lesion detection with deep learning using image patches," Investigative ophthalmology & visual science, vol. 59, no. 1, pp. 590-596, 2018.
• N. M. Khalifa, M. H. Taha and H. N. Mohamed, "Deep transfer learning models for medical diabetic retinopathy detection," Acta Informatica Medica, vol. 27, no. 5, 2019.
• Q. Nguyen, R. Muthuraman and L. Singh, "Diabetic Retinopathy Detection using Deep Learning," in 4th international conference on machine learning and soft computing, 2020.
• B. Tymchenko, P. Marchenko and D. Spodarets, "Deep learning approach to diabetic retinopathy detection," arXiv preprint arXiv:2003.02261 , 2020.
• A. M. Pour, H. Seyedarabi, S. Hassan, A. Jahromi and A. Javadzadeh, "Automatic detection and monitoring of diabetic retinopathy using efficient convolutional neural networks and contrast limited adaptive histogram equalization," IEEE Access, vol. 8, pp. 136668-136673, 2020.
• N. Thota and D. Reddy, "Improving the accuracy of diabetic retinopathy severity classification with transfer learning," in Proceedings of the IEEE 63rd International Midwest Symposium on Circuits and Systems (MWSCAS), Springfield, 2020.
• G. Mushtaq and F. Siddiqui, "Detection of diabetic retinopathy using deep learning methodology," in IOP Conference Series: Materials Science and Engineering, 2021.
• S. Karki and P. Kulkarni, "Diabetic Retinopathy Classification using a Combination of EfficientNets," in International Conference on Emerging Smart Computing and Informatics (ESCI), Pune, India, 2021.
• G. U. Parthasharathi, K. V. kumar, R. Premnivas and K. Jasmine, "Diabetic Retinopathy Detection Using Machine Learning," Journal of Innovative Image Processing, vol. 4, no. 1, pp. 26-33, 2022.
• N. Shaik and T. Cherukuri, "Hinge attention network: A joint model for diabetic retinopathy severity grading," Applied Intelligence, vol. 52, p. 15105–15121, 2022.
• M. Oulhadj, J. Riffi, K. Chaimae, A. M. Mahraz, B. Ahmed, A. Yahyaouy, C. Fouad, A. Meriem, B. A. Idriss and H. Tairi, "Diabetic retinopathy prediction based on deep learning and deformable registration," Multimedia Tools and Applications volume , vol. 81, p. 28709–28727 , 2022.
• C. Lahmar and A. Idri, "Deep hybrid architectures for diabetic retinopathy classification," Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization, pp. 1-19, 2022.
• N. Gundluru, D. S. Rajput, K. Lakshmanna, R. Kaluri, M. Shorfuzzaman, M. Uddin and M.-A. Rahman-Khan, "Enhancement of Detection of Diabetic Retinopathy Using Harris Hawks Optimization with Deep Learning Model," Computational Intelligence and Neuroscience, vol. 2022 , no. Computational Overhead vs. Learning Speed and Accuracy of Deep Networks, 2022.
• E. Decenciere, G. Cazugue, X. Zhang, G. Thibault, J.-C. Klein, F. Meyer and B. Marcotegui, "TeleOphta: Machine learning and image processing methods for teleophthalmology," IRBM, vol. 34, no. 2, pp. 196-203, 2013.
• T. Kauppi, V. Kalesnykiene, J.-K. Kamarainen, L. Lensu, I. Sorri, A. Raninen, R. Voutilainen, H. Uusitalo, H. Kälviäinen and J. Pietilä, "The diaretdb1 diabetic retinopathy database and evaluation protocol," BMVC, vol. 1, no. 1, 2007.
• kaggle, "Diabetic retinopathy detection," [Online].Available: https://kaggle.com/c/diabetic-retinopathy-detection.
• J. Staal, M. D. Abràmoff, M. Niemeijer, M. A. Viergever and B. V. Ginneken, "Ridge-based vessel segmentation in color images of the retina," IEEE transactions on medical imaging, vol. 23, no. 4, pp. 501-509, 2004.
• T. Li, Y. Gao, K. Wang, S. Guo, H. Liu and H. Kang, "Diagnostic assessment of deep learning algorithms for diabetic retinopathy screening," Information Sciences, vol. 501, pp. 511-522, 2019.
• figshare,[Online].Available: https://figshare.com/articles/Advancing_Bag_of_Visual_Words_Representations_for_Lesion_Classification_in_Retinal_Images/953671.
• A. Budai, R. Bock, A. Maier, J. Hornegger and G. Michelson, "Robust vessel segmentation in fundus images," International journal of biomedical imaging, 2013.
• E. Decencière, X. Zhang, G. Cazuguel, B. Lay, B. Cochener, C. Trone and P. Gain, "Feedback on a publicly distributed image database: the Messidor database," Image Analysis & Stereology, vol. 33, no. 3, pp. 231-234, 2014.
• M. D. Abramoff, "Retinopathy Online Challenge," The University of Iowa, 2007. [Online].Available: http://roc.healthcare.uiowa.edu.