International Journal on Science and Technology

E-ISSN: 2229-7677   •   Impact Factor: 9.88

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Bi-monthly Scholarly International Journal

Call for Paper Volume 16 Issue 3 July-September 2025 Submit your research before last 3 days of September to publish your research paper in the issue of July-September.
Submit Research Paper Join as a Reviewer

Plagiarism is checked by the leading plagiarism checker TurnItIn

Call for Paper

Volume 16 Issue 3
July-September 2025

Submit your research paper

Indexing Partners
Academia Advanced Sciences Index Bielefeld Academic Search Engine CiteSeer DRJI Google Scholar Independent Search Engine & Directory Network ISI (International Scientific Indexing) Issuu Mendeley Research Networks
RefSeek ResearcherId - Thomson Reuters ResearchGate Scirus Scribd Semantic Scholar UTeM - Universiti Teknikal Malaysia Melaka Wiki for Call for Papers WorldCat Zenodo

A Framework for Building a Balanced Corneal Image Dataset from Public Repositories for AI-Based Diagnosis

Author(s) Ms. Amanda Grace Ndebele, Mr. Munyaradzi Charles Rushambwa, Prof. Dr. Rajkumar Palaniappan
Country Zimbabwe
Abstract Deep learning models' performance in medical imaging highly depends on the availability of well-balanced, high-quality annotated datasets, [1]. Nevertheless, several ophthalmic diseases, such as keratitis, do not have the public databases readily available. This paper provides a systematic approach to creating well-balanced corneal image datasets from scattered public databases such as Kaggle and GitHub. The proposed system is capable of tackling problems such as image heterogeneity, class imbalance, and format discrepancies. The manual provides step-by-step guidance on image selection, quality control, class redistribution, data pre-processing, and data augmentation. A pilot dataset of 400 images from the four classes, Bacterial Keratitis (BK), Fungal Keratitis (FK), Herpes Simplex Keratitis (HSK), and Normal Eyes, each class with 100 images, was generated using this framework, and experiments were conducted in MATLAB. The results show that the dataset can be used to train baseline convolutional neural networks (CNNs) with reproducible accuracy. This framework is a cost-effective, scalable approach to enable an AI-based diagnostics system for underserved medical domains.
Keywords class balancing, corneal image datasets, data augmentation, dataset construction, deep learning, keratitis, low-resource AI, medical image curation
Field Engineering
Published In Volume 16, Issue 3, July-September 2025
Published On 2025-07-08
DOI https://doi.org/10.71097/IJSAT.v16.i3.6855
Short DOI https://doi.org/g9sx6b
View / Download PDF File

Share this


CrossRef

CrossRef DOI is assigned to each research paper published in our journal.

IJSAT DOI prefix is
10.71097/IJSAT

Downloads
Research Paper Format Copyright Permission Form and Undertaking Form Cover Page Vol 16 Isu 3Cover Page Vol 16 Isu 2Cover Page Vol 16 Isu 1

All research papers published on this website are licensed under Creative Commons Attribution-ShareAlike 4.0 International License, and all rights belong to their respective authors/researchers.

CC-BY-SA Open Access

About IJSAT
Fees & Payment
Current Issue
Publication Archive 		Submit Research Paper
Track Submission Status
Publication Guidelines
Publication Ethics
Peer Review & Plagiarism 		Join as a Reviewer
Editors & Reviewers
Reviewer Referral Program
Get Reviewer Membership Certi. 		Website/Journal Policies
Usage Policy
Content Policies
Privacy Policy
Contact Us Message on WhatsApp +91-9687-182-185 editor@ijsat.org