Imaging and machine learning reveal pigment ring spatial characteristics in vitiligo progression

Clinical Snapshot

Key Findings

• P Value: Not reported

• Effect Size: Progressive-stage patients showed denser clustering of absent/depressed rings; stable-stage patients had higher clustering coefficients for complete rings

• Primary Outcome: Spatial clustering patterns of pigment rings differed significantly between progressive and stable vitiligo stages

• Nnt Or Sensitivity: Classification accuracy: AUC 0.99, precision-recall score 0.95

• Confidence Interval: Not reported

Clinical Application

Limited by requirement for specialized RCM equipment and computational expertise Could complement existing dermatological assessment tools; RCM available in major Australian dermatology centers; may inform PBS-subsidized treatment decisions for vitiligo therapies Vitiligo patients requiring disease activity assessment and staging

Abstract

BACKGROUND: Vitiligo is a chronic autoimmune disorder causing skin depigmentation due to melanocyte loss, with pigment ring dynamics being key to understanding and managing the disease. METHODS: Data from 105 vitiligo patients were collected using reflectance confocal microscopy (RCM) imaging to analyze pigment ring patterns across progressive and stable stages. A multi-task self-supervised learning framework was used to identify and classify pigment ring types (complete, depressed, incomplete, and absent). Graph-based structural analysis was applied to characterize the spatial and network dynamics of pigment rings, incorporating metrics such as clustering coefficients, centrality measures, and Ripley's statistics. RESULTS: Progressive-stage patients exhibited denser clustering and spatial propagation of absent and depressed pigment rings, which played dominant roles in the network. Stable-stage patients showed higher clustering coefficients for complete rings, indicating restored structural stability. The learning framework demonstrated high accuracy in identifying pigment ring types, with an AUC of 0.99 and PR score of 0.95. Ripley's K-function analysis highlighted significant clustering of absent and depressed rings in the progression stage, correlating with active disease. CONCLUSION: Integrating imaging, machine learning, and graph-based analysis offers key insights into vitiligo progression, enabling better staging and personalized treatments, with future research needed for broader validation and model refinement.

References

1. 1.Wang, Z., Hu, H., Wen, Y., Nie, Z., Wang, C., Fu, H., Zeng, Q., & Zhang, J. (2026). Imaging and machine learning reveal pigment ring spatial characteristics in vitiligo progression. Computers in Biology and Medicine. https://doi.org/10.1016/j.compbiomed.2026.111666