Derin Öğrenme Kullanılarak Fundus Görüntülerinden Katarakt ve Diyabetik Retinopati Tespiti

Yıl 2023, , 312 - 324, 27.10.2023

Şükrü Aykat , Sibel Senan

https://doi.org/10.46387/bjesr.1332567

Öz

Diyabetik retinopati ve katarakt ciddi körlüğe ve görme kaybına neden olabilen bazı retina hastalıklarıdır. Gözde meydana gelen bu geri dönüşü olmayan hasarı önlemek için retina hastalıklarının erken teşhisi hayati önem taşımaktadır. Bu çalışmanın problem cümlesi, bu retina hastalıklarının tespiti için derin öğrenme tabanlı sonuçların sunulması olarak verilebilir. Bu amaçla ilk önce ham bir veri seti üzerinde histogram eşitleme yöntemi kullanılarak yeni bir seti oluşturulmuştur. Ardından beş geleneksel derin öğrenme modeline hiperparametre ayarı yapılarak veri setleri üzerinde eğitimler gerçekleştirilmiştir. En son olarak veri setleri üzerinde en yüksek başarıya sahip MobileNet tabanlı bir hibrit model geliştirilmiştir. Önerilen hibrit model, ön işlenmiş veri seti üzerinde %99 doğruluk oranı elde etmiştir. Hibrit modelin sınıflandırma başarısının literatürdeki derin öğrenme modellerinin başarısından daha yüksek olduğu görülmüştür. Bu çalışma diyabetik retinopati ve katarakt hastalarının teşhis sürecine katkı sağlayacaktır.

Anahtar Kelimeler

Retina Hastalıkları, Derin Öğrenme, Evrişimli Sinir Ağları, Katarakt, Diyabetik Retinopati

Detection of Cataract and Diabetic Retinopathy from Fundus Images Using Deep Learning

Öz

Diabetic retinopathy and cataract are some retinal diseases that can cause severe blindness and vision loss. Early diagnosis of retinal diseases is vital to prevent this irreversible damage to the eye. The problem statement of this study can be given as the presentation of deep learning-based results for the detection of these retinal diseases. For this purpose, firstly, a new set was created using the histogram equalization method on a raw data set. Then, hyperparameter adjustments were made to five traditional deep learning models and training was carried out on the data sets. Finally, a MobileNet-based hybrid model with the highest success on datasets has been developed. The proposed hybrid model achieved 99% accuracy on the preprocessed dataset. It has been observed that the classification success of the hybrid model is higher than the success of the deep learning models in the literature. This study will contribute to the diagnosis process of diabetic retinopathy and cataract patients.

Anahtar Kelimeler

Retinal Diseases, Deep Learning, Convolutional Neural Networks, Cataract, Diabetic Retinopathy

Kaynakça

• P.H. Scanlon, S.J. Aldington, and I.M. Stratton “Epidemiological Issues in Diabetic Retinopathy,” Middle East Afr. J. Ophthalmol, vol. 20, no. 4, pp. 293, 2013.
• R. Lee, T.Y. Wong, and C. Sabanayagam “Epidemiology of diabetic retinopathy, diabetic macular edema and related vision loss,” Eye Vis. (London, England), vol. 2, no. 1, 2015.
• H. Ahsan “Diabetic retinopathy--biomolecules and multiple pathophysiology,” Diabetes Metab. Syndr. vol. 9, no. 1, pp. 51–54, 2015.
• R. Varma, N.M. Bressler, Q.V. Doan, M. Danese, C.M. Dolan, A. Lee, and A. Turpcu “Visual Impairment and Blindness Avoided with Ranibizumab in Hispanic and Non-Hispanic Whites with Diabetic Macular Edema in the United States,” Ophthalmology, vol. 122, no. 5, pp. 982–989, 2015.
• M.S. Ola, M.I. Nawaz, M.M. Siddiquei, S. Al-Amro, and A.M. Abu El-Asrar “Recent advances in understanding the biochemical and molecular mechanism of diabetic retinopathy,” J. Diabetes Complications, vol. 26, no. 1, pp. 56–64, 2012.
• T. Behl, I. Kaur, H. Goel, and R. Pandey “Diabetic nephropathy and diabetic retinopathy as major health burdens in modern era,” World J. Pharm, vol. 3, no. 7, pp. 370–387, 2014.
• T. Kauppi, V. Kalesnykiene, J.K. Kamarainen, L. Lensu, I. Sorri, A. Raninen, R. Voutilainen, J. Pietilä, H. Kälviäinen, and H. Uusitalo “The DIARETDB1 diabetic retinopathy database and evaluation protocol.” Proc. Br. Mach. Vis. Conf. vol. 1, pp. 15.1-15.10, 2007.
• N.B.A. Mustafa, W.M.D.W. Zaki, and A. Hussain “A review on the diabetic retinopathy assessment based on retinal vascular tortuosity,” Proc. - 2015 IEEE 11th Int. Colloq. Signal Process. Its Appl. CSPA , pp. 127–130, 2015.
• S. Jones and R.T. Edwards “Diabetic retinopathy screening: a systematic review of the economic evidence,” Diabet. Med. vol. 27, no. 3, pp. 249–256, 2010.
• S. Lin, P. Ramulu, E.L. Lamoureux, and C. Sabanayagam “Addressing risk factors, screening, and preventative treatment for diabetic retinopathy in developing countries: a review,” Clin. Experiment. Ophthalmol, vol. 44, no. 4, pp. 300–320, 2016.
• R. Raman, L. Gella, S. Srinivasan, and T. Sharma “Diabetic retinopathy: An epidemic at home and around the world.” Indian J. Ophthalmol, vol. 64, no. 1, pp. 69, 2016.
• P. Porwal, S. Pachade, M. Kokare, G. Deshmukh, and V. Sahasrabuddhe “Automatic Retinal Image Analysis for the Detection of Diabetic Retinopathy.” Biomedical Signal and Image Processing in Patient Care, pp. 146–161, 2018.
• D.S.W. Ting, G.C.M. Cheung, and T.Y. Wong “Diabetic retinopathy: global prevalence, major risk factors, screening practices and public health challenges: a review.” Clin. Experiment. Ophthalmol, vol. 44, no. 4, pp. 260–277, 2016.
• T. Walter, J.C. Klein, P. Massin, and A. Erginay “A contribution of image processing to the diagnosis of diabetic retinopathy--detection of exudates in color fundus images of the human retina,” IEEE Trans. Med. Imaging, vol. 21, no. 10, pp. 1236–1243, 2002.
• D. Allen and A. Vasavada “Cataract and surgery for cataract.” BMJ, vol. 333, no. 7559, pp. 128–132, 2006.
• Y.C. Liu, M. Wilkins, T. Kim, B. Malyugin, and J.S. Mehta “Cataracts.” Lancet, vol. 390, no. 10094, pp. 600–612, 2017.
• J.J. Drinkwater, W.A. Davis, and T.M.E. Davis “A systematic review of risk factors for cataract in type 2 diabetes.” Diabetes. Metab. Res. Rev. vol. 35, no. 1, pp. e3073, 2019.
• P.A. Asbell, I. Dualan, J. Mindel, D. Brocks, M. Ahmad, and S. Epstein “Age-related cataract.” Lancet (London, England), vol. 365, no. 9459, pp. 599–609, 2005.
• H. Li, J.H. Lim, J. Liu, D.W.K. Wong, Y. Foo, Y. Sun, and T.Y. Wong “Automatic detection of posterior subcapsular cataract opacity for cataract screening.” 2010 Annu. Int. Conf. IEEE Eng. Med. Biol. Soc. EMBC’10, pp. 5359–5362, 2010.
• H. Li, J.H. Lim, J. Liu, D.W.K. Wong, N.M. Tan, S. Lu, Z. Zhang, and T.Y. Wong “An automatic diagnosis system of nuclear cataract using slit-lamp images.” Proc. 31st Annu. Int. Conf. IEEE Eng. Med. Biol. Soc. Eng. Futur. Biomed, pp. 3693–3696, 2009.
• M. Chew, P.P.C. Chiang, Y. Zheng, R. Lavanya, R. Wu, S.M. Saw, T.Y. Wong, and E.L. Lamoureux “The impact of cataract, cataract types, and cataract grades on vision-specific functioning using rasch analysis.” Am. J. Ophthalmol, vol. 154, no. 1, pp. 29-38.e2, 2012.
• C.M. Lee and N.A. Afshari “The global state of cataract blindness.” Curr. Opin. Ophthalmol, vol. 28, no. 1, pp. 98–103, 2017.
• M. Khairallah, R. Kahloun, R. Bourne, H. Limburg, S.R. Flaxman, J.B. Jonas, J. Keeffe, J. Leasher, K. Naidoo, K. Pesudovs, H. Price, R.A. White, T.Y. Wong, S. Resnikoff, and H.R. Taylor “Number of People Blind or Visually Impaired by Cataract Worldwide and in World Regions, 1990 to 2010” Invest. Ophthalmol. Vis. Sci. vol. 56, no. 11, pp. 6762–6769, 2015.
• D. Pascolini and S.P. Mariotti: “Global estimates of visual impairment: 2010.” Br. J. Ophthalmol, vol. 96, no. 5, pp. 614–618, 2012.
• S. Farsiu, S.J. Chiu, R. V. O’Connell, F.A. Folgar, E. Yuan, J.A. Izatt, and C.A. Toth “Quantitative Classification of Eyes with and without Intermediate Age-related Macular Degeneration Using Optical Coherence Tomography.” Ophthalmology, vol. 121, no. 1, pp. 162, 2014.
• Z. Yavuz, C. İkibaş, U. Şevik, and C. Köse: “Retinal Görüntülerde Optik Diskin Otomatik Olarak Çıkartılması için Bir yöntem.” 5. Uluslararası İleri Teknolojiler Sempozyumu, IATS’09, 2009.
• Y. Peng, S. Dharssi, Q. Chen, T.D. Keenan, E. Agrón, W.T. Wong, E.Y. Chew, and Z. Lu “DeepSeeNet: A deep learning model for automated classification of patient-based age-related macular degeneration severity from color fundus photographs.” Ophthalmology, vol. 126, no. 4, pp. 565, 2019.
• M. Patil “An Approach for the Detection of Vascular Abnormalities in Diabetic Retinopathy.” Int. J. Data Min. Tech. Appl. vol. 2, no. 2, pp. 55–58, 2013.
• M.D. Abràmoff, J.M. Reinhardt, S.R. Russell, J.C. Folk, V.B. Mahajan, M. Niemeijer, and G. Quellec “Automated early detection of diabetic retinopathy.” Ophthalmology, vol. 117, no. 6, pp. 1147–1154, 2010.
• M. Niemeijer, M.D. Abràmoff, and B. Van Ginneken “Information fusion for diabetic retinopathy CAD in digital color fundus photographs.” IEEE Trans. Med. Imaging, vol. 28, no. 5, pp. 775–785, 2009.
• G. Quellec, M. Lamard, P.M. Josselin, G. Cazuguel, B. Cochener, and C. Roux “Optimal wavelet transform for the detection of microaneurysms in retina photographs.” IEEE Trans. Med. Imaging, vol. 27, no. 9, pp. 1230–1241, 2008.
• A. Osareh, M. Mirmehdi, B. Thomas, and R. Markham “Automated identification of diabetic retinal exudates in digital colour images.” Br. J. Ophthalmol, vol. 87, no. 10, pp. 1220, 2003.
• N. Ghaffar Nia, E. Kaplanoglu, and A. Nasab “Evaluation of artificial intelligence techniques in disease diagnosis and prediction.” Discov. Artif. Intell. 2023 31. vol. 3, no. 1, pp. 1–14, 2023.
• H. Tariq, M. Rashid, A. Javed, E. Zafar, S.S. Alotaibi, and M.Y.I. Zia “Performance Analysis of Deep-Neural-Network-Based Automatic Diagnosis of Diabetic Retinopathy.” Sensors 2022, vol. 22, no. 1, pp. 205, 2021.
• 35. M.D. La Pava Rodriguez: “Automatic retinopathy detection using deep learning and medical findings.” 2021.
• V.D. Vinayaki and R. Kalaiselvi “Multithreshold Image Segmentation Technique Using Remora Optimization Algorithm for Diabetic Retinopathy Detection from Fundus Images.” Neural Process. Lett. vol. 54, no. 3, pp. 2363–2384, 2022.
• S. venkatesh Chilukoti, A.S. Maida, and X. Hei “Diabetic Retinopathy Detection using Transfer Learning from Pre-trained Convolutional Neural Network Models.” 2022.
• H. Nhut Huynh, M. Thanh Do, G. Thinh Huynh, A. Tu Tran, T. Nghia Tran, M. City, H. Chi Minh City, L. Trung Ward, T. Duc District, T. Truong, T. Tran, T. Nguyen, and Q. Le “Classification of Stages Diabetic Retinopathy Using MobileNetV2 Model.” Kalpa Publ. Eng. vol. 4, pp. 147–157, 2022.
• L. Zhang, J. Li, I. Zhang, H. Han, B. Liu, J. Yang, and Q. Wang: “Automatic cataract detection and grading using Deep Convolutional Neural Network.” Proc. 2017 IEEE 14th Int. Conf. Networking, Sens. Control, pp. 60–65, 2017.
• T. Pratap and P. Kokil: “Computer-aided diagnosis of cataract using deep transfer learning.” Biomed. Signal Process. Control. vol. 53, pp. 101533, 2019.
• M.R. Hossain, S. Afroze, N. Siddique, and M.M. Hoque: “Automatic Detection of Eye Cataract using Deep Convolution Neural Networks (DCNNs).” 2020 IEEE Reg. 10 Symp. TENSYMP, pp. 1333–1338, 2020.
• A. Imran, J. Li, Y. Pei, F. Akhtar, T. Mahmood, and L. Zhang “Fundus image-based cataract classification using a hybrid convolutional and recurrent neural network.” Vis. Comput , vol. 37, no. 8, pp. 2407–2417, 2021.
• J. Kant, P. Singh, Y.S. Yadav, A.P.J. Abdul, andA.P.J.A. Kalam “Computer-aided diagnosis ofcataract severity using retinal fundus images and deeplearning.” Comput. Intell. vol. 38, no. 4, pp. 1450–1473, 2022.
• Y.-H. Chen, T. Krishna, J.S. Emer, and V. Sze:“Eyeriss: An Energy-Efficient ReconfigurableAccelerator for Deep Convolutional NeuralNetworks.” IEEE J. Solid-State Circuits, vol. 52, no.1, pp. 127–138, 2017.
• J. Salamon and J.P. Bello “Deep ConvolutionalNeural Networks and Data Augmentation forEnvironmental Sound Classification.” IEEE SignalProcess. Lett. vol. 24, no. 3, pp. 279–283, 2017.
• M.A.H.A. Bakr, H.M. Al-Attar, N.K. Mahra, and S.S.Abu-Naser “Breast Cancer Prediction using JNN.”Int. J. Acad. Inf. Syst. Res. vol. 4, pp. 1–8, 2020.
• A.M. Barhoom, A.J. Khalil, B.S. Abu-Nasser, M.M.Musleh, and S.S. Abu-Naser “Predicting TitanicSurvivors using Artificial Neural Network.” Int. J.Acad. Eng. Res. vol. 3, no. 9, pp. 8–12, 2019.
• H.Z. Belbeisi, Y.S. Al-Awadi, M.M. Abbas, and S.S.Abu-Naser “Effect of Oxygen Consumption ofThylakoid Membranes (Chloroplasts) From Spinachafter Inhibition Using JNN.” Int. J. Acad. Heal. Med.Res. vol. 4, no. 11, pp. 1–7, 2020.
• M.A. Dalffa, B.S. Abu-Nasser, and S.S. Abu-Naser“International Journal of Engineering andInformation Systems (IJEAIS) Tic-Tac-Toe LearningUsing Artificial Neural Networks.” Int. J. Eng. Inf.Syst. vol. 3, no. 2, pp. 9–19, 2019.
• I.M. Dheir, Alaa Soliman Abu Mettleq, Abeer A.Elsharif, and Samy S. Abu-Naser “Classifying NutsTypes Using Convolutional Neural Network.” Int. J.Acad. Inf. Syst. Res., vol. 3, no. 12, pp. 12–18, 2019.
• K. Jamal Dawood, M. Hussam Zaqout, R.Mohammed Salem, and S.S. Abu-Naser “ArtificialNeural Network for Mushroom Prediction.” Int. J.Acad. Inf. Syst. Res. vol. 4, pp. 9–17, 2020.
• E.N. Arrofiqoh and H. Harintaka “IMPLEMENTASIMETODE CONVOLUTIONAL NEURALNETWORK UNTUK KLASIFIKASI TANAMANPADA CITRA RESOLUSI TINGGI.”GEOMATIKA. vol. 24, no. 2, pp. 61, 2018.
• K. He, X. Zhang, S. Ren, and J. Sun “Deep ResidualLearning for Image Recognition.” IEEE Conf.Comput. Vis. Pattern Recognit. pp. 770–778, 2016.
• C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D.Anguelov, D. Erhan, V. Vanhoucke, and A.Rabinovich “Going deeper with convolutions; Goingdeeper with convolutions”, 2015.
• C. Szegedy, V. Vanhoucke, S. Ioffe, and J. Shlens:“Rethinking the Inception Architecture for ComputerVision; Rethinking the Inception Architecture for Computer Vision.” 2016 IEEE Conf. Comput. Vis. Pattern Recognit. pp. 2818–2826, 2016.
• N. Dong, L. Zhao, C.H. Wu, and J.F. Chang“Inception v3 based cervical cell classificationcombined with artificially extracted features.” Appl.Soft Comput. vol. 93, pp. 106311, 2020.
• G. Hinton, L. Deng, D. Yu, G. Dahl, A. Mohamed, N.Jaitly, A. Senior, V. Vanhoucke, P. Nguyen, T.Sainath, and B. Kingsbury: “Deep Neural Networksfor Acoustic Modeling in Speech Recognition: TheShared Views of Four Research Groups.” IEEESignal Process. Mag. vol. 29, no. 6, pp. 82–97, 2012.
• S. Ghoury, C. Sungur, and A. Durdu “Real-TimeDiseases Detection of Grape and Grape Leaves usingFaster R-CNN and SSD MobileNet Architectures.”Int. Conf. Adv. Technol. Comput. Eng. Sci, 2019.
• X. Liu, Z. Jia, X. Hou, M. Fu, and L. Ma “Real-timeMarine Animal Images Classification by EmbeddedSystem Based on Mobilenet and Transfer Learning;Real-time Marine Animal Images Classification byEmbedded System Based on Mobilenet and TransferLearning.” OCEANS 2019 - Marseille (2019).
• K.D. Kadam, S. Ahirrao, and K. Kotecha “EfficientApproach towards Detection and Identification ofCopy Move and Image Splicing Forgeries UsingMask R-CNN with MobileNet V1.” Comput. Intell.Neurosci. vol. 2022, 2022.
• F. Chollet “Xception: Deep Learning with DepthwiseSeparable Convolutions.” 2017.
• Ö. Polat “Detection of Covid-19 from Chest CTImages using Xception Architecture: A DeepTransfer Learning based Approach.” Sak. Univ. J.Sci. vol. 25, no. 3, pp. 800–810, 2021.
• M. Tan and Q. V. Le “EfficientNet: RethinkingModel Scaling for Convolutional Neural Networks.”36th Int. Conf. Mach. Learn, pp. 10691–10700, 2019.
• M. Tan and Q. V. Le “EfficientNetV2: SmallerModels and Faster Training.” 2021.
• Y. Bengio “Practical recommendations for gradient-based training of deep architectures.” Lect. NotesComput. Sci. (including Subser. Lect. Notes Artif.Intell. Lect. Notes Bioinformatics), vol. 7700, pp.437–478, 2012.
• S. Haykin “Neural networks and learning machines,3/E.” Pearson Education India, 2009.
• R.J. Fante, V.D. Durairaj, and S.C.N. Oliver“Diabetic retinopathy: An update on treatment.” Am.J.Med. vol. 123, no. 3, pp. 213–216, 2010.
• M.D. Abramoff, M.K. Garvin, and M. Sonka “Retinalimaging and image analysis.” IEEE Rev. Biomed.Eng. vol. 3, pp. 169–208, 2010.
• G.V. DODDI “eye_diseases_classification | Kaggle,”https://www.kaggle.com/datasets/gunavenkatdoddi/eye-diseases-classification.