Next Article in Journal
AI-Powered Cybersecurity Mesh for Financial Transactions: A Generative-Intelligence Paradigm for Payment Security
Previous Article in Journal
LSTM-Based News Article Category Classification
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
Computer Sciences & Mathematics Forum
Volume 12
Issue 1
10.3390/cmsf2025012009
csmf-logo
Submit to this Journal
► Article Menu

Article Menu

share Share announcement Help format_quote Cite question_answer Discuss in SciProfiles
first_page
settings
Order Article Reprints
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
Proceeding Paper

Self-Supervised Learning for Complex Pattern Interpretation in Vitiligo Skin Imaging †

by
Priyanka Pawar
1,*,
Anagha Kulkarni
1,
Bhavana Pansare
1,
Prajakta Pawar
2,
Prachi Bahekar
3 and
Madhavi Kapre
3
1
Dr. D. Y. Patil School of Science and Technology, Dr. D. Y. Patil Vidyapeeth, Pimpri, Pune 411033, India
2
Department of Mechanical Engineering, Dr. D. Y. Patil Institute of Technology, Pimpri, Pune 411018, India
3
Department of Computer Engineering, Pimpri Chinchwad College of Engineering and Research, Pune 412101, India
*
Author to whom correspondence should be addressed.
†
Presented at the First International Conference on Computational Intelligence and Soft Computing (CISCom 2025), Melaka, Malaysia, 26–27 November 2025.
Comput. Sci. Math. Forum 2025, 12(1), 9; https://doi.org/10.3390/cmsf2025012009
Published: 18 December 2025
(This article belongs to the Proceedings of First International Conference on Computational Intelligence and Soft Computing (CISCom 2025))
Browse Figures
Versions Notes

Abstract

Depigmented patches are the result of vitiligo, a skin condition brought on by the slow breakdown of melanocytes. High variability, complex lesion morphology, and subtle differences between affected and unaffected skin make accurate diagnosis difficult. In these situations, conventional supervised image analysis techniques have trouble generalizing. By allowing models to acquire significant representations from unlabeled data, self-supervised learning (SSL) presents a viable substitute. The new SSL-based framework for vitiligo skin image analysis proposed in this study uses contrastive learning with augmentation-based pretext tasks to capture complex visual patterns such as patch distribution, texture loss, and border irregularity. The SSL-enhanced model achieved a validation accuracy of 0.83 after fine-tuning on a small, labeled subset. This suggests that SSL could support accurate and labeled efficient vitiligo assessment in clinical and research settings. Direct comparisons with existing supervised model were not performed and were left for future research.
Keywords: deep learning; self-supervised learning; vitiligo; dermatology; skin disease; ResNet 18 deep learning; self-supervised learning; vitiligo; dermatology; skin disease; ResNet 18

Share and Cite

MDPI and ACS Style

Pawar, P.; Kulkarni, A.; Pansare, B.; Pawar, P.; Bahekar, P.; Kapre, M. Self-Supervised Learning for Complex Pattern Interpretation in Vitiligo Skin Imaging. Comput. Sci. Math. Forum 2025, 12, 9. https://doi.org/10.3390/cmsf2025012009

AMA Style

Pawar P, Kulkarni A, Pansare B, Pawar P, Bahekar P, Kapre M. Self-Supervised Learning for Complex Pattern Interpretation in Vitiligo Skin Imaging. Computer Sciences & Mathematics Forum. 2025; 12(1):9. https://doi.org/10.3390/cmsf2025012009

Chicago/Turabian Style

Pawar, Priyanka, Anagha Kulkarni, Bhavana Pansare, Prajakta Pawar, Prachi Bahekar, and Madhavi Kapre. 2025. "Self-Supervised Learning for Complex Pattern Interpretation in Vitiligo Skin Imaging" Computer Sciences & Mathematics Forum 12, no. 1: 9. https://doi.org/10.3390/cmsf2025012009

APA Style

Pawar, P., Kulkarni, A., Pansare, B., Pawar, P., Bahekar, P., & Kapre, M. (2025). Self-Supervised Learning for Complex Pattern Interpretation in Vitiligo Skin Imaging. Computer Sciences & Mathematics Forum, 12(1), 9. https://doi.org/10.3390/cmsf2025012009

Article Metrics

Back to TopTop