Next Article in Journal
Bone Mineral Density (BMD) Assessment Using Dual-Energy CT with Different Base Material Pairs (BMPs)
Previous Article in Journal
Implantation of an Artificial Intelligence Denoising Algorithm Using SubtlePET™ with Various Radiotracers: 18F-FDG, 68Ga PSMA-11 and 18F-FDOPA, Impact on the Technologist Radiation Doses
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
J. Imaging
Volume 11
Issue 7
10.3390/jimaging11070235
jimaging-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite
first_page
settings
Order Article Reprints
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Article

MST-AI: Skin Color Estimation in Skin Cancer Datasets

by
Vahid Khalkhali
1,
Hayan Lee
2,3,4,*,
Joseph Nguyen
2,
Sergio Zamora-Erazo
2,
Camille Ragin
5,
Abhishek Aphale
6,
Alfonso Bellacosa
2,
Ellis P Monk
7 and
Saroj K. Biswas
1
1
Electrical and Computer Engineering Department, Temple University, Philadelphia, PA 19122, USA
2
Cancer Epigenetics Institute, Nuclear Dynamics and Cancer Program, Fox Chase Cancer Center, Philadelphia, PA 19111, USA
3
Department of Medical Genetics and Molecular Biochemistry, Lewis Katz School of Medicine (LKSOM), Temple University Health System, Philadelphia, PA 19140, USA
4
4 Department of Cancer and Cellular Biology, Lewis Katz School of Medicine (LKSOM), Temple University Health System, Philadelphia, PA 19140, USA
5
Cancer Prevention and Control Program, Fox Chase Cancer Center, Philadelphia, PA 19111, USA
6
Division of Dermatology, Melanoma and Skin Cancer Program, Fox Chase Cancer Center, Philadelphia, PA 19111, USA
7
Department of Sociology, Harvard University, Cambridge, MA 02138, USA
*
Author to whom correspondence should be addressed.
J. Imaging 2025, 11(7), 235; https://doi.org/10.3390/jimaging11070235 (registering DOI)
Submission received: 28 May 2025 / Revised: 4 July 2025 / Accepted: 9 July 2025 / Published: 13 July 2025
(This article belongs to the Section AI in Imaging)
Versions Notes

Abstract

The absence of skin color information in skin cancer datasets poses a significant challenge for accurate diagnosis using artificial intelligence models, particularly for non-white populations. In this paper, based on the Monk Skin Tone (MST) scale, which is less biased than the Fitzpatrick scale, we propose MST-AI, a novel method for detecting skin color in images of large datasets, such as the International Skin Imaging Collaboration (ISIC) archive. The approach includes automatic frame, lesion removal, and lesion segmentation using convolutional neural networks, and modeling normal skin tones with a Variational Bayesian Gaussian Mixture Model (VB-GMM). The distribution of skin color predictions was compared with MST scale probability distribution functions (PDFs) using the Kullback-Leibler Divergence (KLD) metric. Validation against manual annotations and comparison with K-means clustering of image and skin mean RGBs demonstrated the superior performance of the MST-AI, with Kendall’s Tau, Spearman’s Rho, and Normalized Discounted Cumulative Gain (NDGC) of 0.68, 0.69, and 1.00, respectively. This research lays the groundwork for developing unbiased AI models for early skin cancer diagnosis by addressing skin color imbalances in large datasets.
Keywords: skin color detection; skin cancer detection; bias reduction; artificial intelligence (AI); Monk skin tone (MST) scale skin color detection; skin cancer detection; bias reduction; artificial intelligence (AI); Monk skin tone (MST) scale

Share and Cite

MDPI and ACS Style

Khalkhali, V.; Lee, H.; Nguyen, J.; Zamora-Erazo, S.; Ragin, C.; Aphale, A.; Bellacosa, A.; Monk, E.P.; Biswas, S.K. MST-AI: Skin Color Estimation in Skin Cancer Datasets. J. Imaging 2025, 11, 235. https://doi.org/10.3390/jimaging11070235

AMA Style

Khalkhali V, Lee H, Nguyen J, Zamora-Erazo S, Ragin C, Aphale A, Bellacosa A, Monk EP, Biswas SK. MST-AI: Skin Color Estimation in Skin Cancer Datasets. Journal of Imaging. 2025; 11(7):235. https://doi.org/10.3390/jimaging11070235

Chicago/Turabian Style

Khalkhali, Vahid, Hayan Lee, Joseph Nguyen, Sergio Zamora-Erazo, Camille Ragin, Abhishek Aphale, Alfonso Bellacosa, Ellis P Monk, and Saroj K. Biswas. 2025. "MST-AI: Skin Color Estimation in Skin Cancer Datasets" Journal of Imaging 11, no. 7: 235. https://doi.org/10.3390/jimaging11070235

APA Style

Khalkhali, V., Lee, H., Nguyen, J., Zamora-Erazo, S., Ragin, C., Aphale, A., Bellacosa, A., Monk, E. P., & Biswas, S. K. (2025). MST-AI: Skin Color Estimation in Skin Cancer Datasets. Journal of Imaging, 11(7), 235. https://doi.org/10.3390/jimaging11070235

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Article metric data becomes available approximately 24 hours after publication online.
Back to TopTop