EUVIMEDOpdag EUVIMED
Open access

Quantitative CRFF ‐ OCT Imaging Features for Characterization of Disease Activity in Non‐Segmental Vitiligo: A Machine Learning–Assisted Study

Chau Yee Ng iD, I-Ling Chen, Yi-Ting Chen, Feng-Ling Tsai, Hsing Cheng, Ling Huang, Yen-Lin Huang, Tsung-Fu Tsai iD, Sheng-Ni Chen iD, Yi-Ching Lai iD

Experimental Dermatology · 2026-07 · 35 (7)

DOI: 10.1111/exd.70309 ↗

At a glance

Journal article in Experimental Dermatology, published online on 2026-07-21. Written by Chau Yee Ng and 9 co-authors. Institution: Department of Dermatology, Chang Gung Memorial Hospital, Linkou Main Branch, Taoyuan, Taiwan. Major MEDLINE topics: Vitiligo, Tomography, Optical Coherence, Machine Learning. 13 references. The full text is freely available in PubMed Central. Funded by: Research Grant.

AbstractSubjectsBibliografiske oplysningerCiteRelated studies

Abstract (original language)

Vitiligo is an autoimmune pigmentary disorder characterized by progressive melanocyte loss and unpredictable activity. Objective of disease activity remains challenging, particularly in lesions with subtle clinical changes Cellular‐resolution full‐field optical coherence tomography (CRFF‐OCT) enables non‐invasive, high‐resolution, histology‐like visualization of skin microstructure. This study evaluated the feasibility of integrating CRFF‐OCT with machine learning‐assisted quantitative analysis for imaging‐based characterization of active and stable vitiligo lesions. Fifty patients with non‐segmental vitiligo were prospectively enrolled (2021–2022). CRFF‐OCT imaging was performed on lesional, perilesional, and normal‐appearing skin within the same anatomical region. Quantitative features describing epidermal structure, dermal–epidermal junction (DEJ) morphology, and pigment‐associated reflectivity were extracted. A machine learning‐assisted computer‐aided detection (CADe) framework incorporating 13 features was developed for image‐level classification of lesion activity. CRFF‐OCT imaging demonstrated distinct microstructural patterns between active and stable lesions. Basal epidermal pigment‐associated reflectivity was significantly lower in stable lesions compared with active lesions (9.94% ± 10.06% vs. 21.84% ± 11.08%), with corresponding differences in lesion‐to‐normal reflectivity ratios (0.21 vs. 0.56). Quantitative analysis revealed significant differences in epidermal thickness, DEJ associated reflectivity, inter‐layer contrast, and reflectivity heterogeneity. Among the 13 extracted features, 9 differed significantly between groups and were incorporated into classification models. The CADe framework achieved a maximum image‐level classification accuracy of 80.6% using a support vector machine model. These findings demonstrate the feasibility of CRFF‐OCT‐based quantitative imaging for objective characterization of vitiligo lesion status and support its potential role in disease activity assessment and longitudinal monitoring.

Subjects

MeSH terms (MEDLINE)

VitiligoTomography, Optical CoherenceMachine LearningHumansFemaleAdultMaleAdolescentYoung AdultProspective StudiesMiddle AgedEpidermisFeasibility Studies

Author keywords

machine learningoptical coherence tomographyvitiligo

Authors and institutions

  • Department of Dermatology, Chang Gung Memorial Hospital, Linkou Main Branch, Taoyuan, Taiwan.
  • Department of Dermatology and Aesthetic Medicine Center, Jen-Ai Hospital, Taichung, Taiwan.
  • College of Medicine, Chang Gung University, Taoyuan, Taiwan.
  • Vitiligo Clinic and Pigment Research Center, Chang Gung Memorial Hospital, Linkou, Taiwan.
  • Apollo Medical Optics, Ltd., Taipei, Taiwan.
  • Department of Pathology, Chang Gung Memorial Hospital, Linkou Main Branch, Taoyuan, Taiwan.

ORCID profiles: Chau Yee Ng, Tsung-Fu Tsai, Sheng-Ni Chen, Yi-Ching Lai

Funding

  • Research Grant

Cite

APA

Ng, C. Y., Chen, I. L., Chen, Y. T., Tsai, F. L., Cheng, H., Huang, L., Huang, Y. L., Tsai, T. F., Chen, S. N., & Lai, Y. C. (2026). Quantitative CRFF ‐ OCT Imaging Features for Characterization of Disease Activity in Non‐Segmental Vitiligo: A Machine Learning–Assisted Study. Experimental Dermatology, 35(7). https://doi.org/10.1111/exd.70309

Vancouver

Ng CY, Chen IL, Chen YT, Tsai FL, Cheng H, Huang L, et al. Quantitative CRFF ‐ OCT Imaging Features for Characterization of Disease Activity in Non‐Segmental Vitiligo: A Machine Learning–Assisted Study. Experimental Dermatology. 2026;35(7). doi:10.1111/exd.70309

BibTeX
@article{Ng2026,
  author = {Ng, Chau Yee and Chen, I-Ling and Chen, Yi-Ting and Tsai, Feng-Ling and Cheng, Hsing and Huang, Ling and Huang, Yen-Lin and Tsai, Tsung-Fu and Chen, Sheng-Ni and Lai, Yi-Ching},
  title = {Quantitative CRFF ‐ OCT Imaging Features for Characterization of Disease Activity in Non‐Segmental Vitiligo: A Machine Learning–Assisted Study},
  journal = {Experimental Dermatology},
  year = {2026},
  volume = {35},
  number = {7},
  doi = {10.1111/exd.70309}
}
Start for free →