Authors : Ali Layth Mokhles Al-Darraji; Samer Mohanad Ali; Yasir Shalash Ammash; Mahmood Ezuldin Atateya Arabe

Volume/Issue : Volume 10 - 2025, Issue 4 - April

Google Scholar : https://tinyurl.com/37kzatj9

Scribd : https://tinyurl.com/w82bknae

DOI : https://doi.org/10.38124/ijisrt/25apr1943

Google Scholar

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Note : Google Scholar may take 15 to 20 days to display the article.

Abstract : Melasma is a common dermatological condition involving a common form of hyperpigmentation, the dermatological diagnosis of which is plagued by the variable presentation and overlap with other skin conditions. Unfortunately, most of the current diagnostic methods are not very precise or reliable, which results in inadequate patient outcome. According to these challenges, this research develops a Windows based application for detection of melasma using advanced image processing techniques and machine learning algorithms. To detect melasma accurately and efficiently, the proposed system is based on the set of 300 high resolution images from DermNet NZ that is preprocessed, segmented, feature extracted, and classified. The application using C# in Visual Studio achieved 97 % detection accuracy in the application that can be used to enhance patient care and clinical decision making. In this paper, each step of the methodology, system design and results are further described and future directions for the research of melasma detection are provided.

Keywords : Melasma Detection, Image Processing, Machine Learning, Medical Imaging, Dermatological Diagnosis

References :

1. Gao R, Peng J, Nguyen L, Liang Y, Thng S, Lin Z. Classification of non-tumorous facial pigmentation disorders using deep learning and SMOTE. 2019 IEEE International Symposium on Circuits and Systems (ISCAS), IEEE; 2019, p. 1–5.
2. Ding H, Zhang E, Fang F, Liu X, Zheng H, Yang H, et al. Automatic identification of benign pigmented skin lesions from clinical images using deep convolutional neural network. BMC Biotechnol 2022;22:28.
3. Vingan NR, Panton JA, Barillas J, Lazzarini A, Hoopman J, Kenkel JM, et al. Investigating the efficacy of a fractionated 1927 nm laser for diffuse dyspigmentation and actinic changes. Lasers Surg Med 2023;55:344–58.
4. Ardigo M, Cameli N, Berardesca E, Gonzalez S. Characterization and evaluation of pigment distribution and response to therapy in melasma using in vivo reflectance confocal microscopy: a preliminary study. Journal of the European Academy of Dermatology and Venereology 2010;24:1296–303.
5. Ardigo M, Cameli N, Berardesca E, Gonzalez S. Characterization and evaluation of pigment distribution and response to therapy in melasma using in vivo reflectance confocal microscopy: a preliminary study. Journal of the European Academy of Dermatology and Venereology 2010;24:1296–303.
6. JEONG S-Y, CHANG S-E, Bak H, CHOI J-H, Kim I-H. New melasma treatment by collimated low fluence Q-switched Nd: YAG laser. Korean Journal of Dermatology 2008:1163–70.
7. Jung G, Lee J, Kim S. Integrated deep learning approach for generating cross-polarized images and analyzing skin melanin and hemoglobin distributions. Biomed Eng Lett 2024:1–10.
8. Lu J, Tong X, Wu H, Liu Y, Ouyang H, Zeng Q. Image classification and auxiliary diagnosis system for hyperpigmented skin diseases based on deep learning. Heliyon 2023;9.
9. Yang T, Ma C, Jhou J, Chen Y, Lan CE. Response predictor for pigment reduction after one session of photo‐based therapy using convolutional neural network: a proof of concept study. Photodermatol Photoimmunol Photomed 2023;39:498–505.
10. Tsai A-C, Huang P-H, Wu Z-C, Wang J-F. Advanced pigmented facial skin analysis using conditional generative adversarial networks. IEEE Access 2024.
11. Tay EY, Gan EY, Tan VWD, Lin Z, Liang Y, Lin F, et al. Pilot study of an automated method to determine Melasma Area and Severity Index. British Journal of Dermatology 2015;172:1535–40.
12. Kang WH, Yoon KH, Lee E, Kim J, Lee KB, Yim H, et al. Melasma: histopathological characteristics in 56 Korean patients. British Journal of Dermatology 2002;146:228–37.
13. Tannous ZS, Astner S. Utilizing fractional resurfacing in the treatment of therapy‐resistant melasma. Journal of Cosmetic and Laser Therapy 2005;7:39–43.
14. Zhang J, Zhong F, He K, Ji M, Li S, Li C. Recent Advancements and Perspectives in the Diagnosis of Skin Diseases Using Machine Learning and Deep Learning: A Review. Diagnostics 2023;13. https://doi.org/10.3390/diagnostics13233506.