![11. References
[1]M. K. Hasan et al., "Cataract Disease Detection by Using Transfer Learning-Based
Intelligent Methods," Computational and Mathematical Methods in Medicine, vol.
2021, p. 7666365, 2021/12/08 2021, doi: 10.1155/2021/7666365.
[2] I. Weni, P. E. P. Utomo, B. F. Hutabarat, and M. Alfalah, "Detection of Cataract
Based on Image Features Using Convolutional Neural Networks," Indonesian Journal of
Computing and Cybernetics Systems), vol. 15, no. 1, pp. 75-86, 2021.
[3] D. Kim, T. J. Jun, D. Kim, and Y. Eom, "Tournament Based Ranking CNN for the
Cataract grading," 2019 41st Annual International Conference of the IEEE Engineering
in Medicine and Biology Society (EMBC), pp. 1630-1636, 2019.
[4] X. Xu, L. Zhang, J. Li, Y. Guan, and L. Zhang, "A Hybrid GlobalLocal
Representation CNN Model for Automatic Cataract Grading," IEEE Journal of
Biomedical and Health Informatics, vol. 24, no. 2, pp. 556-567, 2020, doi:
10.1109/JBHI.2019.2914690.
[5] T. M. o. H. Indonesia. "Data Center and Information Technology."
www.pusdatin.kemkes.go.id (accessed Aug, 31, 2022).
[6] X. Qian, E. W. Patton, J. Swaney, Q. Xing, and T. Zeng, "Machine Learning on
Cataracts Classification Using SqueezeNet," in 2018 4th International Conference on
Universal Village (UV), 21-24 Oct. 2018 2018, pp. 1-3, doi: 10.1109/UV.2018.8642133.
[7] K. Y. Son et al., "Deep Learning-Based Cataract Detection and Grading from Slit-
Lamp and Retro-Illumination Photographs: Model Development and Validation Study,"
Ophthalmology Science, vol. 2, no. 2, p. 100147, 2022/06/01/ 2022, doi:
https://doi.org/10.1016/j.xops.2022.100147](https://image.slidesharecdn.com/cataractdiseasedetectionppt-240926125313-a4264ffc/85/eye-abnormality-detection-using-machine-learning-20-320.jpg)
eye abnormality detection using machine learning
- 1. DETECTION AND CLASSIFICATION OF CATARACT DISEASE USING RESNET Done by – GROUP 9 Name Exam No : Name : Exam No : Name : Exam No Under the guidance of – Prof. Department of Electronics and Telecommunications Engineering Bharati Vidyapeeth’s College of Engineering for Women, Pune
- 2. •Outline 1. Introduction 2 . Literature Survey 3. Problem Statement 4. Objectives 5. Specifications 6. Block Diagram 7. Methodology 8. Flowchart 9. Future Scope 10. References
- 3. 1. Introduction • One of the most significant issues with world health is vision impairment. One of the most common reasons for impairment and even blindness is a cataract. • The existing technique for diagnosing and treating cataracts is excessively time-consuming and expensive. • Even when cataracts have not yet damaged a person's eyesight, it might be challenging to detect them at an early stage. • When the cataract blocks the lens, this can sometimes result in partial or even full blindness. Another technique used by ophthalmologists to identify cataracts is a retinal examination. The rear of the eye is the primary focus of the retinal examination. It is also called as a funduscopy or ophthalmoscopy. • Using fundus pictures, the retina, choroid, and optic disc are investigated.
- 4. • The development of tools and software for identifying and diagnosing illnesses is now simpler than ever before because to the intense focus on the use of artificial intelligence in medical applications. The • the residual network(Resnet) which is used for pattern recognition (including images) which can help automate image classification, in this case, the retinal fundus data image. Among several methods of machine learning, the (Resnet) is a very popular method because of its ability to solve problems in computer vision domains, namely among others in detection systems, classification systems, and other computer vision and video analysis applications
- 5. 2. Literature Survey Sr No Author Paper Name Proposed Model 1 Yadav, S., & Yadav, J. K. P. S Automatic Cataract Severity Detection and Grading Using Deep Learning image acquisition (dataset construction), image quality selection, preprocessing and data augmentation, feature extraction, and classification and CNN were used for classification 2 T.Pratap and Kokil Computer-aided diagnosis of cataract using deep transfer learning support vector machine (SVM) classifier 3 Sasha Targ, Diogo Almeida, Kevin Lyman Resnet in Resnet Generalizing Residual Architectures 4 T. Pratap and P. Kokil Automatic cataract detection in fundus retinal images using singular value decomposition SVM is used 5 Nihal Bhandary1, Anish Adnani2 Eye Disease Detection using RESNET, (IRJET) Generalizing Resnet Architectures 6 N. Hnoohom and A. Jitpattanakul Comparison of Ensemble Learning Algorithms for Cataract Detection from Fundus Images DT, BPNN and sequential minimal optimization 7 Sahana M, Gowrishankar S Identification and Classification of Cataract Stages in Old Age People Using Deep Learning Algorithm, (IJITEE) Inception V3 architecture trained on image net. 8 Sucheta Kolhe, Shanthi K. Guru Remote Automated Cataract Detection System Based on Binary SVM is implemented to classify the fundus image and for grading
- 6. 3. Problem Statement • To Design and Implement Detection and Classification of cataract using ResNet • Overcome the Performance of classification of Cataract images (front eye or Fundus) • Developing new approach with different algorithm than CNN for image classification used to commonly found eye disease, Cataract…
- 7. 4.objectives • To collect dataset from Kaggle. • To detect cataracts at an early stage when they are easier to treat. • To improve the accuracy of algorithm. • To compare the accuracy of the Resnet50 algorithm with the existing algorithm
- 8. Software Tool • Pycharm IDE – Python Development tool • Windows 10 – 64 bit OS • Python Libraries • Python ML packages • Front End HTML and Streamlit API
- 9. Hardware and Equipment • System PC / Laptop • Intel CoreI5 • 300GB HDD • 6GB RAM
- 10. 6. Block diagram
- 11. • Dataset: The dataset employed in this suggested system consists of 1088 fundus pictures. Shanggong Medical Technology Co., Ltd. collected the pictures from various hospitals and medical institutions around China. The Ocular Disease Intelligent Recognition (ODIR) database is a structured ophthalmic database including 5000 patients’ ages, color fundus images of their right and left eyes, and diagnostic keywords given by doctors. The dataset is made up of actual patient data. From the previously mentioned datasets, we solely utilized cataracts and ordinary fundus pictures for our purposes. • Preprocessing: The proposed system dataset combines photographs of normal, diabetes, glaucoma, cataract, pathological myopia, hypertension, age-related macular degeneration, and other diseases/abnormalities. Labels were used to filter the data. Because they were obtained with different cameras, experimental fundus pictures had varying image sizes. As a result, we used OpenCV to resize the picture to 224 × 224 pixels. The dataset is next loaded and converted into an array format for training purposes using the NumPy library. 7.Methodology
- 12. • Data Augmentation: The key data augmentation processes, including rotation, flipping (horizontal), zooming are performed on images. • • Feature Extraction:. • Detecting and classifying cataracts using Resnet is a valuable application of deep learning in healthcare. • • Classification: • Resnet50 excel at image classification tasks, making them a suitable choice for identifying and classifying cataracts in medical images into severity of cataract. • • Output: • The obtained result is detected and classified as cataract and non cataract images.
- 13. The proposed cataract detection framework is depicted in Fig, it contains three main steps: data pre-processing, Segmentation, and Resnet-Based classification. First, image transformations like resizing, conversion, normalization, and augmentation were employed in the preprocessing step. Second, K-means clustering was utilized to recharacterized the pre-processed RGB images into segmented images. Finally, the segmented images were then fed to train the Resnet50-based classifier.
- 15. 7.Flowchart
- 16. ●8. Future Scope • In near future this module of prediction can be integrate with the module of automated processing system. • The system is trained on old training dataset so future software can be made such that new testing data should also take part in training data after some fixed time. • More advanced self trained AI model or bots can be designed to give More precise and accurate output
- 17. ● 9. Results
- 20. 11. References [1]M. K. Hasan et al., "Cataract Disease Detection by Using Transfer Learning-Based Intelligent Methods," Computational and Mathematical Methods in Medicine, vol. 2021, p. 7666365, 2021/12/08 2021, doi: 10.1155/2021/7666365. [2] I. Weni, P. E. P. Utomo, B. F. Hutabarat, and M. Alfalah, "Detection of Cataract Based on Image Features Using Convolutional Neural Networks," Indonesian Journal of Computing and Cybernetics Systems), vol. 15, no. 1, pp. 75-86, 2021. [3] D. Kim, T. J. Jun, D. Kim, and Y. Eom, "Tournament Based Ranking CNN for the Cataract grading," 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), pp. 1630-1636, 2019. [4] X. Xu, L. Zhang, J. Li, Y. Guan, and L. Zhang, "A Hybrid GlobalLocal Representation CNN Model for Automatic Cataract Grading," IEEE Journal of Biomedical and Health Informatics, vol. 24, no. 2, pp. 556-567, 2020, doi: 10.1109/JBHI.2019.2914690. [5] T. M. o. H. Indonesia. "Data Center and Information Technology." www.pusdatin.kemkes.go.id (accessed Aug, 31, 2022). [6] X. Qian, E. W. Patton, J. Swaney, Q. Xing, and T. Zeng, "Machine Learning on Cataracts Classification Using SqueezeNet," in 2018 4th International Conference on Universal Village (UV), 21-24 Oct. 2018 2018, pp. 1-3, doi: 10.1109/UV.2018.8642133. [7] K. Y. Son et al., "Deep Learning-Based Cataract Detection and Grading from Slit- Lamp and Retro-Illumination Photographs: Model Development and Validation Study," Ophthalmology Science, vol. 2, no. 2, p. 100147, 2022/06/01/ 2022, doi: https://doi.org/10.1016/j.xops.2022.100147
- 21. THANK YOU