An Intelligent Ensembling of Fine-Tuned Transfer Learning-Based Model for Cataract Diagnosis from Fundus Images
An Intelligent Ensembling of Fine-Tuned Transfer Learning-Based Model for Cataract Diagnosis from Fundus Images |
||
 |
 |
|
| © 2024 by IJETT Journal | ||
| Volume-72 Issue-5 |
||
| Year of Publication : 2024 | ||
| Author : Mahdi Falah Mahdi Alyami, Meenu Garg, Vatsala Anand, Sheifali Gupta, Mana Saleh Al Reshan, Saleh Hamad Sajaan Almansour, Shoug Salem Hasan Alyami, Asadullah Shaikh |
||
| DOI : 10.14445/22315381/IJETT-V72I5P113 | ||
How to Cite?
Mahdi Falah Mahdi Alyami, Meenu Garg, Vatsala Anand, Sheifali Gupta, Mana Saleh Al Reshan, Saleh Hamad Sajaan Almansour, Shoug Salem Hasan Alyami, Asadullah Shaikh, "An Intelligent Ensembling of Fine-Tuned Transfer Learning-Based Model for Cataract Diagnosis from Fundus Images," International Journal of Engineering Trends and Technology, vol. 72, no. 5, pp. 120-130, 2024. Crossref, https://doi.org/10.14445/22315381/IJETT-V72I5P113
Abstract
Blindness and Visual Impairment are serious and pervasive health issues in the current situation. Although new innovative technologies are developing quickly, vision impairment continues to be a significant issue for global healthcare systems. Cataracts are among the most common causes of vision impairment. Accurate and rapid diagnosis of cataracts is the greatest way to prevent or treat it in its early stages. In this research, a weighted ensemble transfer learning based model is proposed for the prediction of cataracts from the fundus images. The weighted average ensemble is performed using three transfer learning models i.e. VGG16, VGG19 and ResNet50 model. Here, weight1, weight2 and weight3 are evaluated through optimisation for VGG16, VGG19 and ResNet50 models, respectively, to take the weighted average of three models. Different experiments based on different optimisers, different batch sizes and different numbers of epochs have been performed for the proposed ensemble model. Different transfer learning models, i.e. VGG16, VGG19 and ResNet50, are used individually also for training of the datasets and their performance is compared with the proposed ensemble model. The proposed weighted ensemble model is performing better as compared to the three transfer learning models with 99% sensitivity, 100% specificity, 100% precision, 64.5% recall and 99.37% accuracy.
Keywords
Artificial Intelligence, Cataract, Ensemble Mode, Ocular Disease Intelligent Recognition (ODIR), Transfer Learning (TF), Validation (Val).
References
[1] Dishant Padalia, Abhishek Mazumdar, and Bharati Singh, “A CNN-LSTM Combination Network for Cataract Detection Using Eye Fundus Images,” Arxiv, pp. 1-8, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[2] Seth R. Flaxman et al., “Global Causes of Blindness and Distance Vision Impairment 1990-2020: A Systematic Review and Meta-Analysis,” The Lancet Global Health, vol. 5, no. 12, pp. e1221-e1234, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[3] A. Foster, “Vision 2020: The Cataract Challenge,” Community Eye Health, vol. 13, no. 34, pp. 17-19, 2000. [Google Scholar] [Publisher Link] [4] Euna Koo et al., “Ten-Year Incidence Rates of Age-Related Cataract in the Age-Related Eye Disease Study (AREDS): AREDS Report No. 33,” Ophthalmic Epidemiology, vol. 20, no. 2, pp. 71-81, 2013.
[Google Scholar] [Publisher Link]
[5] David Allen, and Abhay Vasavada, “Cataract and Surgery for Cataract,” Bmj Journals, vol. 333, pp. 128-132, 2006. [CrossRef] [Google Scholar] [Publisher Link] [6] Md Kamrul Hasan et al., “Cataract Disease Detection by Using Transfer Learning-Based Intelligent Methods,” Computational and Mathematical Methods in Medicine, vol. 2021, pp. 1-12, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[7] Ji-Jiang Yang et al., “Exploiting Ensemble Learning For Automatic Cataract Detection and Grading,” Computer Methods and Programs in Biomedicine, vol. 124, pp. 45-57, 2016.
[CrossRef] [Google Scholar] [Publisher Link]
[8] Huiqi Li et al., “A Computer-Aided Diagnosis System of Nuclear Cataract,” IEEE Transactions on Biomedical Engineering, vol. 57, no. 7, pp. 1690-1698, 2010.
[CrossRef] [Google Scholar] [Publisher Link]
[9] Miguel Caixinha et al., “New Approach for Objective Cataract Classification Based on Ultrasound Techniques Using Multiclass SVM Classifiers,” 2014 IEEE International Ultrasonics Symposium, Chicago, IL, USA, pp. 2402-2405, 2014.
[CrossRef] [Google Scholar] [Publisher Link]
[10] Linglin Zhang et al., “Automatic Cataract Detection and Grading Using Deep Convolutional Neural Network,” 2017 IEEE 14th International Conference on Networking, Sensing and Control (ICNSC), Calabria, pp. 60-65, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[11] Weiming Fan et al., “Principal Component Analysis Based Cataract Grading and Classification,” 2015 17th International Conference on E-Health Networking, Application & Services (HealthCom), Boston, MA, pp. 459-462, 2015.
[CrossRef] [Google Scholar] [Publisher Link]
[12] Liye Guo et al., “A Computer-Aided Healthcare System for Cataract Classification and Grading Based on Fundus Image Analysis,” Computers in Industry, vol. 69, pp. 72-80, 2015.
[CrossRef] [Google Scholar] [Publisher Link]
[13] Xingzhi Qian et al., “Machine Learning on Cataracts Classification using SqueezeNet,” 2018 4th International Conference on Universal Village (UV), Boston, MA, USA, pp. 1-3, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[14] Yanyan Dong et al., “Classification of Cataract Fundus Image Based on Deep Learning,” 2017 IEEE International Conference on Imaging Systems and Techniques (IST), Beijing, China, pp. 1-5, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[15] Divya, and C. Senbagavalli, “Blood Vessel Segmentation and Classification Based On ANFIS Method for Retinal Images,” International Journal of Computer Science Trends and Technology, vol. 6, no. 4, pp. 123-130, 2018.
[Google Scholar] [Publisher Link]
[16] Mehmet Emre Sertkaya, Burhan Ergen, and Mesut Togacar, “Diagnosis of Eye Retinal Diseases Based on Convolutional Neural Networks Using Optical Coherence Images,” 2019 23rd International Conference Electronics, Palanga, Lithuania, pp. 1-5, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[17] Chandra Lekha Dondapati, Ashutosh Ghosh, and TYJ. Naga Malleswari, “Classification of Eye Disorders Based on Deep Convolutional Neural Network,” International Journal of Innovative Technology and Exploring Engineering, vol. 9, no. 6, pp. 1388-1393, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[18] Meimei Yang et al., “Classification of Retinal Image for Automatic Cataract Detection,” 2013 IEEE 15th International Conference on E-Health Networking, Applications and Services (Healthcom 2013), Lisbon, pp. 674-679, 2013.
[CrossRef] [Google Scholar] [Publisher Link]
[19] Rajib Hossain et al., “Automatic Detection of Eye Cataract Using Deep Convolution Neural Networks (DCNNs),” 2020 IEEE Region 10 Symposium (TENSYMP), Dhaka, Bangladesh, pp. 1333-1338, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[20] Yue Zhou, Guoqi Li, and Huiqi Li, “Automatic Cataract Classification Using Deep Neural Network with Discrete State Transition,” IEEE Transactions on Medical Imaging, vol. 39, no. 2, pp. 436-446, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[21] Li Xiong, Huiqi Li, and Liang Xu, “An Approach to Evaluate Blurriness in Retinal Images with Vitreous Opacity for Cataract Diagnosis,” Journal of Healthcare Engineering, vol. 2017, pp. 1-17, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[22] T.R Soumya et al., “Profile Similarity Recognition in Online Social Network using Machine Learning Approach,” 2022 4th International Conference on Inventive Research in Computing Applications (ICIRCA), Coimbatore, India, pp. 805-809, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[23] Sanjay Singh et al., “COVID 19: Identification of Masked Face Using CNN Architecture,” 2022 3rd International Conference on Electronics and Sustainable Communication Systems (ICESC), Coimbatore, India, pp. 1045-1051, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[24] Tanima Bhattacharya et al., “Applications of Phyto-Nanotechnology for the Treatment of Neurodegenerative Disorders,” Materials, vol. 15, no. 3, pp. 1-32, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[25] Bhisham Sharma, and Deepika Koundal, “Cattle Health Monitoring System Using Wireless Sensor Network: A Survey From Innovation Perspective,” IET Wireless Sensor Systems, vol. 8, no. 4, pp.143-151, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[26] Alifia Revan Prananda et al., “Retinal Nerve Fiber Layer Analysis Using Deep Learning to Improve Glaucoma Detection in Eye Disease Assessment,” Applied Sciences, vol. 13, no. 1, pp. 1-21, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[27] Rohit Thanki, “A Deep Neural Network and Machine Learning Approach for Retinal Fundus Image Classification,” Healthcare Analytics, vol. 3, pp. 1-9, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[28] K. Susheel Kumar, and Nagendra Pratap Singh, “Retinal Disease Prediction through Blood Vessel Segmentation and Classification Using Ensemble-Based Deep Learning Approaches,” Neural Computing and Applications, vol. 35, pp. 12495-12511, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[29] Ahmed Al Marouf et al., “An Efficient Approach to Predict Eye Diseases from Symptoms Using Machine Learning and Ranker-Based Feature Selection Methods,” Bioengineering, vol. 10, no. 1, pp. 1-20, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[30] P. Saranya, R. Pranati, and Sneha Shruti Patro, “Detection and Classification of Red Lesions from Retinal Images for Diabetic Retinopathy Detection Using Deep Learning Models,” Multimedia Tools and Applications, vol. 82, pp. 39327-39347, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[31] Yogesh Kumar, and Bharat Gupta, “Retinal Image Blood Vessel Classification using Hybrid Deep Learning in Cataract Diseased Fundus Images,” Biomedical Signal Processing and Control, vol. 84, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[32] Ahlam Shamsan, Ebrahim Mohammed Senan, and Hamzeh Salameh Ahmad Shatnawi, “Automatic Classification of Colour Fundus Images for Prediction Eye Disease Types Based on Hybrid Features,” Diagnostics, vol. 13, no. 10, pp. 1-23, 2023.
[CrossRef] [Google Scholar] [Publisher Link]