Resource-Efficient Conjunctivitis Screening Using MOGONET and VGG-Based Transfer Learning

Pranto Halder; Anurag Sinha; Md. Khalid Hasan; Amit Kumar; Jibran Gulzar; Anmol Chauhan; Divyank Sharma; Pratyush Singh; Sagar Singh; Kshitij Tandon; Kshitij Ranjan; Aditya Pandey

doi:10.5455/EJCSI.20251213060931

Eu J Comp Sci Informatics. 2026; 3(2): 67-82

doi: 10.5455/EJCSI.20251213060931

Resource-Efficient Conjunctivitis Screening Using MOGONET and VGG-Based Transfer Learning

Pranto Halder, Anurag Sinha, Md. Khalid Hasan, Amit Kumar, Jibran Gulzar, Anmol Chauhan, Divyank Sharma, Pratyush Singh, Sagar Singh, Kshitij Tandon, Kshitij Ranjan, Aditya Pandey.

Abstract
Background/Aim: Conjunctivitis, commonly known as pink eye, poses a significant diagnostic challenge due to overlapping presentations across viral, bacterial, and allergic subtypes. This study presents MOGONET, a multi-objective generalized normal distribution optimization framework built upon VGGNet, specifically designed to address conjunctivitis identification through resource-aware deep learning optimization.
Methods: The proposed pipeline integrates contrast-limited adaptive histogram equalization-based image enhancement, data augmentation, and multi-level Otsu thresholding segmentation with transfer learning using a VGG16 backbone. A MOGNDO-based outer-loop search simultaneously maximizes classification accuracy, minimizes binary cross-entropy loss, and minimizes computational cost (FLOPs) using Pareto-front-based non-dominated sorting. Experiments were conducted on 1,230 conjunctival eye images sourced from Kaggle and Shutterstock, with a stratified 72%/18%/10% train/validation/test split.
Results: MOGONET achieves 98.32% test accuracy, 97.54% precision, 96.92% recall, and 96.22% F1-score. Compared with the unoptimized Visual Geometry Group-based baseline, MOGONET reduces FLOPs by 79.18% (from 238.06M to 49.56M), and model parameters by 77.78% (from approximately 9M to 2M).
Conclusion: MOGONET demonstrates that multi-objective optimization can substantially reduce computational complexity in conjunctivitis classification without sacrificing diagnostic performance, offering a promising framework for deployment on resource-constrained clinical screening platforms.

Key words: Conjunctivitis, Generalized Normal Distribution Optimization, multi-thresholding, deep learning

	ARTICLE TOOLS
	Abstract
	PDF Fulltext
	How to cite this article
	Citation Tools
	Related Records
	Articles by Pranto Halder Articles by Anurag Sinha Articles by Md. Khalid Hasan Articles by Amit Kumar Articles by Jibran Gulzar Articles by Anmol Chauhan Articles by Divyank Sharma Articles by Pratyush Singh Articles by Sagar Singh Articles by Kshitij Tandon Articles by Kshitij Ranjan Articles by Aditya Pandey
	on Google
	on Google Scholar

How to Cite this Article

Pubmed Style

Halder P, Sinha A, Hasan MK, Kumar A, Gulzar J, Chauhan A, Sharma D, Singh P, Singh S, Tandon K, Ranjan K, Pandey A. Resource-Efficient Conjunctivitis Screening Using MOGONET and VGG-Based Transfer Learning. Eu J Comp Sci Informatics. 2026; 3(2): 67-82. doi:10.5455/EJCSI.20251213060931

Web Style

Halder P, Sinha A, Hasan MK, Kumar A, Gulzar J, Chauhan A, Sharma D, Singh P, Singh S, Tandon K, Ranjan K, Pandey A. Resource-Efficient Conjunctivitis Screening Using MOGONET and VGG-Based Transfer Learning. https://www.wisdomgale.com/ejcsi/?mno=303056 [Access: June 07, 2026]. doi:10.5455/EJCSI.20251213060931

AMA (American Medical Association) Style

Halder P, Sinha A, Hasan MK, Kumar A, Gulzar J, Chauhan A, Sharma D, Singh P, Singh S, Tandon K, Ranjan K, Pandey A. Resource-Efficient Conjunctivitis Screening Using MOGONET and VGG-Based Transfer Learning. Eu J Comp Sci Informatics. 2026; 3(2): 67-82. doi:10.5455/EJCSI.20251213060931

Vancouver/ICMJE Style

Halder P, Sinha A, Hasan MK, Kumar A, Gulzar J, Chauhan A, Sharma D, Singh P, Singh S, Tandon K, Ranjan K, Pandey A. Resource-Efficient Conjunctivitis Screening Using MOGONET and VGG-Based Transfer Learning. Eu J Comp Sci Informatics. (2026), [cited June 07, 2026]; 3(2): 67-82. doi:10.5455/EJCSI.20251213060931

Harvard Style

Halder, P., Sinha, . A., Hasan, . M. K., Kumar, . A., Gulzar, . J., Chauhan, . A., Sharma, . D., Singh, . P., Singh, . S., Tandon, . K., Ranjan, . K. & Pandey, . A. (2026) Resource-Efficient Conjunctivitis Screening Using MOGONET and VGG-Based Transfer Learning. Eu J Comp Sci Informatics, 3 (2), 67-82. doi:10.5455/EJCSI.20251213060931

Turabian Style

Halder, Pranto, Anurag Sinha, Md. Khalid Hasan, Amit Kumar, Jibran Gulzar, Anmol Chauhan, Divyank Sharma, Pratyush Singh, Sagar Singh, Kshitij Tandon, Kshitij Ranjan, and Aditya Pandey. 2026. Resource-Efficient Conjunctivitis Screening Using MOGONET and VGG-Based Transfer Learning. European Journal of Computer Sciences and Informatics, 3 (2), 67-82. doi:10.5455/EJCSI.20251213060931

Chicago Style

Halder, Pranto, Anurag Sinha, Md. Khalid Hasan, Amit Kumar, Jibran Gulzar, Anmol Chauhan, Divyank Sharma, Pratyush Singh, Sagar Singh, Kshitij Tandon, Kshitij Ranjan, and Aditya Pandey. "Resource-Efficient Conjunctivitis Screening Using MOGONET and VGG-Based Transfer Learning." European Journal of Computer Sciences and Informatics 3 (2026), 67-82. doi:10.5455/EJCSI.20251213060931

MLA (The Modern Language Association) Style

Halder, Pranto, Anurag Sinha, Md. Khalid Hasan, Amit Kumar, Jibran Gulzar, Anmol Chauhan, Divyank Sharma, Pratyush Singh, Sagar Singh, Kshitij Tandon, Kshitij Ranjan, and Aditya Pandey. "Resource-Efficient Conjunctivitis Screening Using MOGONET and VGG-Based Transfer Learning." European Journal of Computer Sciences and Informatics 3.2 (2026), 67-82. Print. doi:10.5455/EJCSI.20251213060931

APA (American Psychological Association) Style

Halder, P., Sinha, . A., Hasan, . M. K., Kumar, . A., Gulzar, . J., Chauhan, . A., Sharma, . D., Singh, . P., Singh, . S., Tandon, . K., Ranjan, . K. & Pandey, . A. (2026) Resource-Efficient Conjunctivitis Screening Using MOGONET and VGG-Based Transfer Learning. European Journal of Computer Sciences and Informatics, 3 (2), 67-82. doi:10.5455/EJCSI.20251213060931