Objective and Quantitative Assessment of Facial Vitiligo via AI-powered 3D Analysis for Diagnostic Support

Traditional vitiligo assessment methods rely on subjective evaluation and 2D photographic analysis, limiting consistency and accuracy in clinical practice.

To develop and validate an AI-assisted, 3D reconstruction-based system for accurate and objective quantification of facial vitiligo lesions.

In this diagnostic study, standardized 3-view clinical facial photographs from patients with facial vitiligo at a tertiary referral center between 2022 and 2024 were retrospectively analyzed. After excluding incomplete or poor-quality images, 329 patients were included. A deep learning segmentation model was trained to detect depigmented lesions and applied to 3D reconstruction with surface mapping for facial curvature. Performance was compared with manual assessments by board-certified dermatologists, with and without AI guidance, across two sessions.

The AI segmentation model achieved consistently high boundary delineation (F1 score > 0.98) and robust lesion identification accuracy (median Dice ≈ 0.85). When integrated into dermatologists' evaluations, AI assistance markedly reduced mean absolute error in lesion quantification (3.13 vs 6.71) compared with manual assessment alone. Correlation with reference lesion areas also improved Pearson correlation coefficient (r = 0.92 vs 0.84), demonstrating enhanced reliability. Bland-Altman analysis further revealed a reduction in systematic bias and narrower limits of agreement, supporting the reproducibility of AI-assisted quantification. Collectively, these findings indicate that AI guidance not only improves segmentation performance but also augments clinical interpretation accuracy and consistency.

This study demonstrates the potential clinical impact of AI-assisted 3D reconstruction. The system provides precise and standardized quantification of facial vitiligo lesions by incorporating surface curvature into lesion mapping. Compared with manual assessments, AI support improved diagnostic accuracy, reduced interobserver variability, and offered consistent measurements across sessions. These findings highlight the promise of integrating AI-driven 3D tools into routine dermatological practice to enhance patient monitoring and optimize treatment planning.