FORMATION AND NORMALIZATION METHODS OF MEDICAL IMAGE DATABASES RELATED TO EYE DISEASES

Authors

  • Musayeva Muxtasar Zayirjon kizi x

Keywords:

eye diseases, medical imaging, retina, database, normalization, deep learning, artificial intelligence, data preparation.

Abstract

This article discusses the processes of creating and normalizing a medical image database to improve the effectiveness of artificial intelligence (AI) technologies in the early diagnosis of eye diseases. It analyzes errors caused by image inconsistency, the need for data standardization, and the practical application of various normalization methods. The results show that applying normalization techniques can improve the accuracy of deep learning models by 10–15%.

Downloads

Download data is not yet available.

References

Abramoff M.D., Lavin P.T., et al. “Pivotal trial of an autonomous AI-based diagnostic system for detection of diabetic retinopathy.” NPJ Digital Medicine, 2018.

Pratt H., Coenen F., Broadbent D. “Convolutional Neural Networks for Diabetic Retinopathy.” Procedia Computer Science, 2016.

ODIR-5K Dataset – https://odir2019.grand-challenge.org/

Tan N.M., Acharya U.R., et al. “Automated diagnosis of diabetic retinopathy using digital fundus images.” Journal of Medical Systems, 2018.

Nguyen Q., et al. “Deep learning in ophthalmology: A review.” Eye and Vision, 2020.

Gonzalez R., Woods R. “Digital Image Processing.” Prentice Hall, 2018.

Downloads

Published

2025-11-01

How to Cite

Musayeva Muxtasar Zayirjon kizi. (2025). FORMATION AND NORMALIZATION METHODS OF MEDICAL IMAGE DATABASES RELATED TO EYE DISEASES. Journal of Applied Science and Social Science, 15(10), 1624–1626. Retrieved from https://www.internationaljournal.co.in/index.php/jasass/article/view/2289

Issue

Vol. 15 No. 10 (2025): Volume 15 Issue 10

Section

Articles

License

Creative Commons License

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

All content published in the Journal of Applied Science and Social Science (JASSS) is protected by copyright. Authors retain the copyright to their work, and grant JASSS the right to publish the work under a Creative Commons Attribution License (CC BY). This license allows others to distribute, remix, adapt, and build upon the work, even commercially, as long as they credit the author(s) for the original creation.