Diabetic Retinopathy Prediction using Modified Inception V3 Model Structure

Authors

  • Shwetha G. K. NMAM Institute of Technology , Affiliated to NITTE (Deemed to be University) , India
  • Udaya Kumar Reddy K. R. School of Engineering, Dayananda Sagar University , Bengaluru, India Alva’s Institute of Engineering & Technology , Moodubidire , India
  • Jayantkumar A. Rathod School of Electronics and Communication Engineering,REVA University,Bengaluru,India
  • Sathyaprakash B. P. Alva’s Institute of Engineering & Technology , Moodubidire , India
  • Lolakshi P. K. Alva’s Institute of Engineering & Technology , Moodubidire , India

Keywords:

Diabetic Retinopathy (DR), Retinal Fundus Images, Histogram Equalization, Contrast Enhancement, Optic disc, Morphological Techniques

Abstract

The analysis of clinical findings revealed that more than 10% of diabetic individuals have an elevated risk of eye issues. Diabetic Retinopathy (DR) is a type of eye illness that impacts 80-85% of persons suffering for more than 10 years from diabetes. In hospitals, retinal fundus images are commonly employed for the identification and study of diabetic retinopathy. The unprocessed retinal fundus images are difficult for machine learning approaches to analyze. Original retinal fundus images are pre-processed utilizing green channel separation, histogram equalization, contrast enhancement, and scaling procedures. For statistical analysis, 14 attributes are additionally collected from preprocessed images. Technique for the detection of retinal lesions can aid in the earlier identification and treatment of a frequently found condition, diabetic retinopathy. We introduce a new criterion for the identification of the optic disc in which we initially identify the significant blood vessels and then utilize their intersection to estimate the position of the optic disc. Future localized utilizing color characteristics. We also demonstrate that a set of attributes, including blood vessels, mucus, micro aneurysms, and hemorrhages, may be recognized with high precision utilizing different morphological techniques applied suitably.

 

Downloads

Download data is not yet available.

References

Alyoubi, W. L., Shalash, W. M., & Abulkhair, M. F. (2020). Diabetic retinopathy detection through deep learning techniques: A review. Informatics in Medicine Unlocked, 20, 100377. https://doi.org/10.1016/j.imu.2020.100377

Arenas-Cavalli, J. T., Ríos, S. A., Pola, M., & Donoso, R. (2015). A Web- based Platform for Automated Diabetic Retinopathy Screening. Procedia Computer Science, 60, 557–563. https://doi.org/10.1016/j.procs.2015.08.179

Behera, M. K., & Chakravarty, S. (2020). Diabetic Retinopathy Image Classification Using Support Vector Machine. 2020 International Conference on Computer Science, Engineering and Applications (ICCSEA). https://doi.org/10.1109/iccsea49143.2020.9132875

Cloudinary. (n.d.). Node.js SDK – Cloudinary. https://cloudinary.com/documentation/node_integration

darkmode.js. (n.d.). Darkmodejs. https://darkmodejs.learn.uno/

EJS. (n.d.). EJS -- Embedded JavaScript templates. https://ejs.co/#docs

Express 4.x - API Reference. (n.d.). ExpressJS. https://expressjs.com/en/4x/api.html

Flask Documentation (2.1.x). (n.d.). Flask. https://flask.palletsprojects.com/en/2.1.x/

GeeksforGeeks.(2020, February 27). VGG-16 | CNN model. https://www.geeksforgeeks.org/vgg-16-cnn-model/

GeeksforGeeks. (2020, July 17). CNN - Image data pre-processing with generators. https://www.geeksforgeeks.org/cnn-image-data-pre-processing-with- generators/

Gunicorn. (n.d.). Gunicorn - WSGI server — Gunicorn 20.1.0 documentation. https://docs.gunicorn.org/en/stable/index.html

Habib Raj, M. A., Mamun, M. A., & Faruk, M. F. (2020). CNN Based Diabetic Retinopathy Status Prediction Using Fundus Images. 2020 IEEE Region 10 Symposium (TENSYMP). https://doi.org/10.1109/tensymp50017.2020.9230974

Heroku. (n.d.). Documentation | Heroku Dev Center. https://devcenter.heroku.com/categories/reference

Huda, S. M. A., Ila, I. J., Sarder, S., Shamsujjoha, M., & Ali, M. N. Y. (2019). An Improved Approach for Detection of Diabetic Retinopathy Using Feature Importance and Machine Learning Algorithms. 2019 7th International Conference on Smart Computing & Communications (ICSCC). https://doi.org/10.1109/icscc.2019.8843676

Inception V3 Model. (2017, June 30). Kaggle. https://www.kaggle.com/google-brain/inception-v3

MongooseJS. (n.d.). Mongoose v6.3.4: Schemas. https://mongoosejs.com/docs/guide.html

Npm: Body-parser. (2022, April 3). Npm. https://www.npmjs.com/package/body-parser

Ravishankar, S., Jain, A., & Mittal, A. (2009). Automated feature extraction for early detection of diabetic retinopathy in fundus images. 2009 IEEE Conference on Computer Vision and Pattern Recognition. https://doi.org/10.1109/cvpr.2009.5206763

Singh Sisodia, D., Nair, S., & Khobragade, P. (2017). Diabetic Retinal Fundus Images: Preprocessing and Feature Extraction For Early Detection of Diabetic Retinopathy. Biomedical and Pharmacology Journal, 10(02), 615–626. https://doi.org/10.13005/bpj/1148

VGG 16 Structure

Downloads

Published

16.01.2023

How to Cite

G. K., S. ., Reddy K. R., U. K. ., A. Rathod, J. ., B. P., S. ., & P. K., L. . (2023). Diabetic Retinopathy Prediction using Modified Inception V3 Model Structure. International Journal of Intelligent Systems and Applications in Engineering, 11(1), 261–268. Retrieved from https://www.ijisae.org/index.php/IJISAE/article/view/2466

Issue

Vol. 11 No. 1 (2023)

Section

Research Article

License

Copyright (c) 2023 Shwetha G. K., Udaya Kumar Reddy K. R., Jayantkumar A. Rathod, Sathyaprakash B. P., Lolakshi P. K.

Creative Commons License

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.

IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.