Robust Hybrid Model for Vitiligo Skin Lesion Detection: Integrating Grey Wolf and Particle Swarm Optimization for Enhanced Feature Extraction and Classification
DOI:
https://doi.org/10.32350.umt-air.52.03Keywords:
Vitiligo Classification, Deep learning, PSO, Grey Wolf Optimizer, Medical Image AnalysisAbstract
The study and diagnosis of numerous skin disorders, including benign and malignant ones, have emerged as one of the central areas of research in the sphere of medical imaging. The advanced deep learning system known as Linear Sequential Convolutional Neural Networks (CNNs) has shown impressive abilities in automating image-related processes, including dermatological conditions and so on. This study explores how CNNs could be used to detect and classify the various skin disorders, including vitiligo, using the skin lesions dataset provided by Kaggle. This processing of images and data augmentation, and the use of ready-made models are the key elements of enhancing the system performance and generalization. This study proposes a robust Hybrid Model, designated as HGWO-GBPSO, which combines the exploratory power of the Grey Wolf Optimizer (GWO) with the refinement efficiency of Global Best Particle Swarm Optimization (GBPSO). The HGWO-GBPSO model exhibits an impressive accuracy and loss of 95.26, and 0.14 respectively. However, the average precision, recall, F1 score, and support.
Downloads
References
[1] S. Yu, Z. Chen, J. He, and H. Wang,
“Comparative study of dermatologists
and deep learning model on
diagnosing childhood vitiligo,”
Photodiagn. Photodyn. Ther., vol. 54,
Aug. 2025, Art. no. 104727, doi:
10.1016/j.pdpdt.2025.104727.
[2] M. Böhm, R. Sommer, U. Gieler, P.
Staubach, A. Zink, C. Apfelbacher, et
al., “Vitiligo–a disease: A position
paper on stigmatization, life quality
impairment and psychosocial
comorbidity,” JDDG: J. der
Deutschen Dermatol. Gesells., vol.
22, pp. 1327–1335, 2024, doi:
https://doi.org/10.1111/ddg.15503.
[3] I. H. Hamzavi, K. Bibeau, P. Grimes,
J. E. Harris, N. van Geel, D. Parsad, et
al., “Exploring the natural and
treatment history of vitiligo:
Perceptions of patients and healthcare
professionals from the global
VALIANT study,” Br. J. Dermatol.,
vol. 189, pp. 569–577, Nov. 2023,
doi:
https://doi.org/10.1093/bjd/ljad245.
[4] S. Hayes, “Dermoscopy: the
dermatologist’s stethoscope,” Clin.
Experiment. Dermatol., vol. 49, no. 9,
June 2024, Art. no. 955, doi:
https://doi.org/10.1093/ced/llae241.
[5] S. Ye and M. Chen, “The emerging
role of artificial intelligence in
diagnosis and clinical analysis of
dermatology,” Dermatol. Sin., vol. 41,
pp. 145–152, 2023, doi:
https://doi.org/ 10.4103/ds.DS-D-23-
00025.
[6] A. Kallipolitis et al., “Skin image
analysis for detection and quantitative
assessment of dermatitis, vitiligo and
alopecia areata lesions: A systematic
literature review,” BMC Med. Inform.
Decis. Mak., vol. 25, Jan. 2025, doi:
https://doi.org/10.1186/s12911-024-
02843-2.
[7] J. A. Godínez-Chaparro, R. Roldán-
Marín, H. Vidaurri-de la Cruz, L. A.
Soto-Mota, and K. Férez,
“Dermatoscopic patterns in vitiligo,”
Dermatol. Pract. Concept., vol. 13,
Oct. 2023, Art. no. 2023197, doi:
https://doi.org/10.5826/dpc.1304a197.
[8] P. Abdi et al., “Non-invasive skin
measurement methods and diagnostics
for vitiligo: A systematic review,”
Front. Med., vol. 10, July 2023, Art.
no. 1200963, doi: https://doi.org/
10.3389/fmed.2023.1200963.
[9] M. M. Hasan, J. Phu, A. Sowmya, E.
Meijering, and M. Kalloniatis,
“Artificial intelligence in the
diagnosis of glaucoma and
neurodegenerative diseases,” Clin.
Exp. Optom., vol. 107, pp. 130–146,
2024, doi:
https://doi.org/10.1080/08164622.202
3.2235346.
[10] J. Zhang, F. Zhong, K. He, M. Ji, S.
Li, and C. Li, “Recent advancements
and perspectives in the diagnosis of
skin diseases using machine learning
and deep learning: A review,”
Diagnostics, vol. 13, Nov. 2023, Art.
no. 3506, doi:
https://doi.org/10.3390/diagnostics132
33506.
[11] S. Sharma, K. Guleria, S. Kumar, and
S. Tiwari, “Deep learning-based
model for detection of vitiligo skin
disease using pre-trained Inception
Internal, Robust Hybrid Model for Vitiligo…
20 UMT Artificial Intelligence Review
Volume 5 Issue 2, Fall 2025
V3,” Int. J. Math. Eng. Manag. Sci.,
vol. 8, 2023, Art. no. 1024, doi:
/10.33889/IJMEMS.2023.8.5.059.
[12] M. Usman, M. Y. Iqbal, K. Zafar, and
S. Basharat, “A novel approach to
vitiligo diagnosis using artificial
neural networks and dermatological
image analysis,” J. Comput. Biomed.
Inform., vol. 8, no. 1, 2024, Art. no.
736-0801/2024.
[13] H. Huang et al., “Intelligent diagnosis
of hypopigmented dermatoses and
intelligent evaluation of vitiligo
severity on the basis of deep
learning,” Dermatol. Ther., vol. 14,
pp. 3307–3320, Nov. 2024, doi:
https://doi.org/ 10.1007/s13555-024-
01296-9.
[14] Y. Li, S. T. G. Thng, and A. W.-K.
Kong, “Bridging the gap between
vitiligo segmentation and clinical
scores,” IEEE J. Biomed. Health
Inform., vol. 28, pp. 1623–1634,
2023,
doi:https://doi.org/10.1109/JBHI.2023
.3342069.
[15] J. Wu, M. Sun, Z. Wei, Q. Jiang, H.
Chen, and L. Chen, “Sensitivity and
specificity analysis of different lesion
areas of vitiligo by reflectance
confocal microscopy,” J. Cosmet.
Dermatol., vol. 24, 2025, Art. no.
70006, doi: https://doi.org/
10.1111/jocd.70006.
[16] M. Parikh, G. Fang, F. Poon, M.
Kyeremeh, D. Cruz, K. Ki, et al.,
“Technological advances in vitiligo
management: Perspectives on AI,
mobile tools, and clinical utility,”
Front. Med., vol. 12, 2025, doi:
https://doi.org/10.3389/fmed.2025.16
61554.
[17] M. Z. Hussain, M. Z. Hasan, M. M.
Baig, T. Khan, S. Nosheen, A. M.
Bhatti, et al., “Malware/ransomware
analysis and detection,” in Proc.
WorldS4 Conf., 2023, pp. 339–352,
doi: https://doi.org/10.1007/978-981-
99-8031-4_30.
[18] Q. Shi-fan, T. Jun-kun, Z. Yong-gang,
W. Li-jun, Z. Ming-fei, T. Jun, et al.,
“Settlement prediction of foundation
pit excavation based on the GWO-
ELM model,” Adv. Civ. Eng., vol.
2021, 2021, doi: https://doi.org
/10.1155/2021/8896210.
[19] L. Guo, Y. Yang, H. Ding, H. Zheng,
H. Yang, J. Xie, et al., “A deep
learning-based hybrid artificial
intelligence model for vitiligo
detection and severity assessment,”
Ann. Transl. Med., vol. 10, May 2022,
Art. no. 590, doi: https://doi.org
/10.21037/atm-22-1738.
[20] M. Parikh, G. Fang, F. Poon, M.
Kyeremeh, D. Cruz, K. Ki, et al.,
“Technological advances in vitiligo
management: Perspectives on AI,
mobile tools, and clinical utility,”
Front. Med., vol. 12, Oct. 2025, doi:
https://doi.org/10.3389/fmed.2025.16
61554.
[21] F. Zhong, “Optimizing vitiligo
diagnosis with ResNet and Swin
transformer deep learning models,”
Sci. Rep., vol. 14, 2024, Art. no. 9127,
doi: https://doi.org/10.1038/s41598-
024-59436-2.
[22] R. Mazzetto, A. Sernicola, J.
Tartaglia, C. Ciolfi, and M. Alaibac,
“Potential of automated image
analysis for the measurement of
vitiligo lesions,” Front. Med., vol. 12,
2025, doi:
https://doi.org/10.3389/fmed.2025.16
Nand et al.
21
Department of Information System
Volume 5 Issue 2, Fall 2025
23408.
[23] A. Al Abdulwahid, S. S. Alqahtany,
D. Syed, M. S. Al Reshan, K. Rajab,
and A. Shaikh, “A hybrid improved
binary GWO-PSO with random
forest-based intrusion detection
model,” Sci. Rep., 2026, doi:
https://doi.org/ 10.1038/s41598-025-
33242-w.
[24] M. Xu, S. Yoon, A. Fuentes, and D. S.
Park, “A comprehensive survey of
image augmentation techniques for
deep learning,” Pattern Recognit., vol.
137, Art. no. 109347, 2023.
[25] L. Kumar, M. Pandey, and M. K.
Ahirwal, “Parallel global best-worst
particle swarm optimization
algorithm,” Appl. Soft Comput., vol.
142, July 2023, Art. no. 110329, doi:
https://doi.org/10.1016/j.asoc.2023.11
0329.
[26] F. Chen, X. Sun, D. Wei, and Y.
Tang, “Tradeoff strategy between
exploration and exploitation for PSO,”
in Proc. Int. Conf. Nat. Comput.,
2011, pp. 1216–1222.
[27] Z. Xu, H. Yang, J. Li, X. Zhang, B.
Lu, and S. Gao, “Comparative study
on chaotic grey wolf optimization
algorithms,” IEEE Access, vol. 9, pp.
77416–77437, 2021, doi: https://doi.
org/10.1109/ACCESS.2021.3083220.
[28] L. Alzubaidi et al., “Review of deep
learning: concepts, CNN
architectures, challenges, applications,
future directions,” J. Big Data, vol. 8,
pp. 1–74, Mar. 2021, doi:
https://doi.org /10.1186/s40537-021-
00444-8.
[29] P. Das and D. H. Mazumder,
“MLCNNF: A multi-label CNN
framework for predicting adverse
COVID drug reactions,” IEEE Trans.
Comput. Biol. Bioinform., 2025, doi:
https://doi.org/10.1109/TCBBIO.2024
.3515480.
[30] G. Averkov, C. Hojny, and M.
Merkert, “On the expressiveness of
rational ReLU neural networks,”
arXiv, 2025. [Online]. Available:
https://doi.org/10.48550/arXiv.2502.0
6283.
[31] Y. Zhao, X. Deng, J. Zhang, and P.
Wang, “Spatio-temporal regularized
stochastic configuration network,”
IEEE Trans. Autom. Sci. Eng., vol. 22,
Jan. 2025, doi: https://doi.org/
10.1109/TASE.2025.3531850.
[32] Y. Guo, G. Chen, T. Zeng, Q. Jin, and
M. K.-P. Ng, “Quaternion nuclear
norm minus Frobenius norm
minimization,” Pattern Recognit., vol.
158, Feb. 2025, Art. no. 110986, doi:
https://doi.org/10.1016/j.patcog.2024.
110986.
[33] G. Ekambaram and T. Rakkiannan,
“Transfer learning-based deep
learning model for facial expression,”
in Proc. IEEE IDCIoT, 2025, pp.
2030–2037, doi:
IDCIOT64235.2025.10915054.
[34] D. Yu and F. Cao, “Construction and
approximation rate for feedforward
neural network operators,” J. Comput.
Appl. Math., vol. 453, Jan. 2025, Art.
no. 116150, doi: https://doi.org/
10.1016/j.cam.2024.116150.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Shardha Nand, Asif Raza , Usman Amjad, Nancy Alias Shivani Kumari
This work is licensed under a Creative Commons Attribution 4.0 International License.
UMT-AIR follow an open-access publishing policy and full text of all published articles is available free, immediately upon publication of an issue. The journal’s contents are published and distributed under the terms of the Creative Commons Attribution 4.0 International (CC-BY 4.0) license. Thus, the work submitted to the journal implies that it is original, unpublished work of the authors (neither published previously nor accepted/under consideration for publication elsewhere). On acceptance of a manuscript for publication, a corresponding author on the behalf of all co-authors of the manuscript will sign and submit a completed the Copyright and Author Consent Form.
