An Ensemble Learning Approach for Glaucoma Detection in Retinal Images

Majlesi Journal of Electrical Engineering

مقاله 9، دوره 16، شماره 4، اسفند 2022، صفحه 117-122   

نوع مقاله: Reseach Article

شناسه دیجیتال (DOI): 10.30486/mjee.2022.696522

نویسندگان

Marwah M. Mahdi^{* 1}؛ Mohammed Abdulkreem Mohammed²؛ Haider Al-Chalibi³؛ Bashar S. Bashar⁴؛ Hayder Adnan Sadeq⁵؛ Talib Mohammed Jawad Abbas⁶

¹Anesthesia Techniques Department, Al-Mustaqbal University College, Babylon, Iraq

²Department of Anesthesia Techniques, Al-Noor University College, Bartella, Iraq

³Medical Technical College, Al-Farahidi University, Baghdad, Iraq

⁴Al-Nisour University College, Baghdad, Iraq

⁵Al-Hadi University College, Baghdad,10011, Iraq

⁶Medical device engineering, Ashur University College, Baghdad, Iraq

چکیده

To stop vision loss from glaucoma, early identification and regular screening are crucial. Convolutional neural networks (CNN) have been effectively used in recent years to diagnose glaucoma automatically from color fundus pictures. CNNs can extract distinctive characteristics directly from the fundus pictures, as opposed to the current automatic screening techniques. In this study, a CNN-based deep learning architecture is created for the categorization of normal and glaucomatous fundus pictures. In this paper, we propose a deep learning-based framework for the detection of glaucoma based on retinal images. Our proposed approach utilizes the two CNN-based models, namely Inception and DenseNet, in order to classify the input images. We also show the impact of transfer learning on the training and the validation processes and put forward an effective pipeline with lower trainable parameters for the target task. Our experiments on a collected dataset demonstrate the efficacy of the proposed model by achieving an accuracy of 93.84%, a precision of 92.83%, and a recall of 95.00%.

کلیدواژه‌ها

Glaucoma Detection؛ Convolutional Neural Networks؛ Medical Images Analysis؛ Retinal Images؛ DenseNet؛ Inception

مراجع

• [1] Ran, An Ran, Clement C. Tham, Poemen P. Chan, Ching-Yu Cheng, Yih-Chung Tham, Tyler Hyungtaek Rim, and Carol Y. Cheung. "Deep learning in glaucoma with optical coherence tomography: a review."Eye 35, No. 1, pp. 188-201, 2021.
• [2] Thompson, Atalie C., Alessandro A. Jammal, and Felipe A. Medeiros. "A review of deep learning for screening, diagnosis, and detection of glaucoma progression."Translational Vision Science & Technology 9, No. 2, pp. 42-42, 2020.
• [3] Mirzania, Delaram, Atalie C. Thompson, and Kelly W. Muir. "Applications of deep learning in detection of glaucoma: a systematic review." European Journal of Ophthalmology31, No. 4, pp. 1618-1642,2021.
• [4] Asaoka, Ryo, Hiroshi Murata, Kazunori Hirasawa, Yuri Fujino, Masato Matsuura, Atsuya Miki, Takashi Kanamoto et al. "Using deep learning and transfer learning to accurately diagnose early-onset glaucoma from macular optical coherence tomography images."American journal of ophthalmology 198, pp. 136-145, 2019.
• [5] Serte, Sertan, and Ali Serener. "A generalized deep learning model for glaucoma detection." In 2019 3rd International symposium on multidisciplinary studies and innovative technologies (ISMSIT), pp. 1-5. IEEE, 2019.
• [6] Sreng, Syna, Noppadol Maneerat, Kazuhiko Hamamoto, and Khin Yadanar Win. "Deep learning for optic disc segmentation and glaucoma diagnosis on retinal images."Applied Sciences 10, No. 14, pp. 4916, 2020.
• [7] Lee J, Kim YK, Park KH, Jeoung JW. “Diagnosing glaucoma with spectral-domain optical coherence tomography using deep learning classifier.” Journal of glaucoma. 29(4),pp. 287-94, 2020.
• [8] Veena, H. N., A. Muruganandham, and T. Senthil Kumaran. "A novel optic disc and optic cup segmentation technique to diagnose glaucoma using deep learning convolutional neural network over retinal fundus images."Journal of King Saud University-Computer and Information Sciences (2021).
• [9] Asaoka, Ryo, Masaki Tanito, Naoto Shibata, Keita Mitsuhashi, Kenichi Nakahara, Yuri Fujino, Masato Matsuura, Hiroshi Murata, Kana Tokumo, and Yoshiaki Kiuchi. "Validation of a deep learning model to screen for glaucoma using images from different fundus cameras and data augmentation."Ophthalmology Glaucoma 2, No. 4, pp. 224-231, 2019.
• Sharghi, Elnaz, Vahid Nourani, Hessam Najafi, and Amir Molajou. "Emotional ANN (EANN) and wavelet-ANN (WANN) approaches for Markovian and seasonal based modeling of rainfall-runoff process."Water resources management 32, No. 10, pp.  3441-3456, 2018.
• Nourani, Vahid, Zahra Razzaghzadeh, Aida Hosseini Baghanam, and Amir Molajou. "ANN-based statistical downscaling of climatic parameters using decision tree predictor screening method."Theoretical and Applied Climatology 137, No. 3, pp. 1729-1746, 2019.
• Ali, Waqar, Wenhong Tian, Salah Ud Din, Desire Iradukunda, and Abdullah Aman Khan. "Classical and modern face recognition approaches: a complete review."Multimedia Tools and Applications 80, No. 3, pp. 4825-4880, 2021.
• Chen, Chun-Fu Richard, Quanfu Fan, and Rameswar Panda. "Crossvit: Cross-attention multi-scale vision transformer for image classification." In Proceedings of the IEEE/CVF international conference on computer vision, pp. 357-366. 2021.
• Zafar, Afia, Muhammad Aamir, Nazri Mohd Nawi, Sikandar Ali, Mujtaba Husnain, and Ali Samad. "A Comprehensive Convolutional Neural Network Survey to Detect Glaucoma Disease." Mobile Information Systems2022, 2022.
• Deperlioglu, Omer, Utku Kose, Deepak Gupta, Ashish Khanna, Fabio Giampaolo, and Giancarlo Fortino. "Explainable framework for Glaucoma diagnosis by image processing and convolutional neural network synergy: analysis with doctor evaluation."Future Generation Computer Systems 129, pp. 152-169, 2022.
• Babu, Ch, G. Prabaharan, and R. Pitchai. "Efficient detection of glaucoma using double tier deep convolutional neural network."Personal and Ubiquitous Computing (2022), pp. 1-11, 2022.
• RUI, CHIARA, Silvia Gazzina, Giovanni Montesano, David P. Crabb, David F. Garway-Heath, Francesco Oddone, Paolo Lanzetta et al. "Convolutional Neural Network for Glaucoma detection using Compass color fundus images."Investigative Ophthalmology & Visual Science 63, no. 7 (2022): 2039-A0480.
• Liu, Yuan, Leonard Wei Leon Yip, Yuanjin Zheng, and Lipo Wang. "Glaucoma screening using an attention-guided stereo ensemble network." Methods202 (2022), pp. 14-21.
• Gupta, Ravi Kumar, Utkarsh Sharma, and Vivek Singh. "Detection of Glaucoma using Deep Learning."International Journal of Research in Engineering, Science and Management 5, No. 5, pp. 147-150, 2022.
• Akbar, Shahzad, Syed Ale Hassan, Ayesha Shoukat, Jaber Alyami, and Saeed Ali Bahaj. "Detection of microscopic glaucoma through fundus images using deep transfer learning approach."Microscopy Research and Technique 85, No. 6, pp. 2259-2276, 2022.
• Garg, H., Gupta, N., Agrawal, R., Shivani, S. and Sharma, B., 2022. “A real time cloud-based framework for glaucoma screening using EfficientNet.”Multimedia Tools and Applications, pp.1-22.
• Kumar, S., Gupta, S. and Arora, S., 2022. “A comparative simulation of normalization methods for machine learning-based intrusion detection systems using KDD Cup’99 dataset.”Journal of Intelligent & Fuzzy Systems, (Preprint), pp.1-18.
• Izonin, Ivan, Roman Tkachenko, Nataliya Shakhovska, Bohdan Ilchyshyn, and Krishna Kant Singh. "A Two-Step Data Normalization Approach for Improving Classification Accuracy in the Medical Diagnosis Domain."Mathematics 10, No. 11 (2022): 1942.
• Yang, Haitao, Jiali Li, Kai Zhuo Lim, Chuanji Pan, Tien Van Truong, Qian Wang, Kerui Li et al. "Automatic strain sensor design via active learning and data augmentation for soft machines." Nature Machine Intelligence4, No. 1, pp. 84-94, 2022.
• Temraz, Mohammed, and Mark T. Keane. "Solving the class imbalance problem using a counterfactual method for data augmentation." Machine Learning with Applications(2022): 100375.
• Khouloud, S., Ahlem, M., Fadel, T. and Amel, S., “W-net and inception residual network for skin lesion segmentation and classification.”Applied Intelligence, 52(4), 2022, pp.3976-3994.
• Pawar, Kamlesh, Zhaolin Chen, N. Jon Shah, and Gary F. Egan. "Suppressing motion artefacts in MRI using an Inception‐ResNet network with motion simulation augmentation."NMR in Biomedicine 35, no. 4 (2022): e4225.
• Mujahid, Muhammad, Furqan Rustam, Roberto Álvarez, Juan Luis Vidal Mazón, Isabel de la Torre Díez, and Imran Ashraf. "Pneumonia Classification from X-ray Images with Inception-V3 and Convolutional Neural Network."Diagnostics 12, No. 5 (2022): 1280.
• Bhat, Sachin S., Alaka Ananth, Rajashree Nambiar, and Nagaraj Bhat. "Building Dataset and Deep Learning-Based Inception Model for the Character Classification of Tigalari Script." In Recent Advances in Artificial Intelligence and Data Engineering, pp. 239-252. Springer, Singapore, 2022.
• Vakharia, Vinay, Jay Vora, Sakshum Khanna, Rakesh Chaudhari, Milind Shah, Danil Yu Pimenov, Khaled Giasin, Parth Prajapati, and Szymon Wojciechowski. "Experimental investigations and prediction of WEDMed surface of Nitinol SMA using SinGAN and DenseNet deep learning model."journal of materials research and technology 18 (2022), pp. 325-337.
• Bohmrah, Maneet Kaur, and Harjot Kaur. "Classification of Covid-19 patients using efficient fine-tuned deep learning DenseNet model."Global Transitions Proceedings 2, No. 2 (2021), pp. 476-483.
• Lu, Tao, Baokun Han, Lipin Chen, Fanqianhui Yu, and Changhu Xue. "A generic intelligent tomato classification system for practical applications using DenseNet-201 with transfer learning."Scientific Reports 11, No. 1, pp. 1-8, 2021.
• Kim, Yongtae, Youngsoo Kim, Charles Yang, Kundo Park, Grace X. Gu, and Seunghwa Ryu. "Deep learning framework for material design space exploration using active transfer learning and data augmentation." Computational Materials7, No. 1, pp. 1-7, 2021.