Multi-Illumination Nail Analysis With Uncertainty-Aware Deep Learning: A Comprehensive Approach to Automated Fungal Detection
IEEE Access · 2026 · 14 · 63834-63846
DOI: 10.1109/access.2026.3686347 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Access, 2026. Verfasst von Zenab Bosheah und 8 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 21 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: projects Visionail 2.0, Visionail 1.0, Incubation Projects of the Life Sciences Cluster of the Centre of Excellence for Interdisciplinary Research.
Abstract (Originalsprache)
This study presents a comprehensive approach to nail condition classification using multi-illumination imaging and uncertainty-aware deep learning.We developed a diagnostic system capturing nail images under ten lighting conditions (normal and polarized versions of white, UV, red, green, and blue light) and classifying them into three categories: normal, fungal infections, and other pathologies. Our Conv-NeXt-based neural network architecture demonstrated exceptional performance for fungal detection, achieving accuracies ranging from 93.63% to 96.31% across the various illumination modes. Multi-illumination analysis revealed distinctive signatures, with white light channels demonstrating highest importance (32–33% of attention weights) and red light showing specific utility for fungal detection (11.1% vs. 5–7% for other conditions). Spatial analysis through Gradient-weighted Class Activation Mapping (Grad-CAM) identified that models focus primarily on nail edges when detecting fungal infections, with quantitative grid analysis showing edge regions contributing approximately 3 times more to classification decisions than central regions. Bayesian ensembles provided reliable uncertainty: predictive entropy discriminates correct vs. incorrect decisions (AUROC 0.9429), with strong calibration for the fungus classifier (Brier 0.040, ECE 0.032). t-SNE visualization demonstrated clear feature space separation, with fungal infections showing the most cohesive clustering corresponding to their distinctive illumination-spatial patterns. These convergent findings support clinical examination optimization: prioritizing nail edges under white light, with supplementary red light for suspected fungal cases, represents a promising strategy for future clinical validation.
Förderung
- projects Visionail 2.0
- Visionail 1.0
- Incubation Projects of the Life Sciences Cluster of the Centre of Excellence for Interdisciplinary Research
- University of Szeged Open Access Fund
Zitieren
APA
Bosheah, Z., Keresztes, D., Lődár, P., Gaszner, P., Szebényi, J., Marx, E., Jánki, Z. R., Gyulai, R., & Bilicki, V. (2026). Multi-Illumination Nail Analysis With Uncertainty-Aware Deep Learning: A Comprehensive Approach to Automated Fungal Detection. IEEE Access, 14, 63834-63846. https://doi.org/10.1109/access.2026.3686347
Vancouver
Bosheah Z, Keresztes D, Lődár P, Gaszner P, Szebényi J, Marx E, et al. Multi-Illumination Nail Analysis With Uncertainty-Aware Deep Learning: A Comprehensive Approach to Automated Fungal Detection. IEEE Access. 2026;14:63834-63846. doi:10.1109/access.2026.3686347
BibTeX
@article{Bosheah2026,
author = {Bosheah, Zenab and Keresztes, Dorottya and Lődár, Péter and Gaszner, Péter and Szebényi, Júlia and Marx, Eszter and Jánki, Zoltán Richárd and Gyulai, Rolland and Bilicki, Vilmos},
title = {Multi-Illumination Nail Analysis With Uncertainty-Aware Deep Learning: A Comprehensive Approach to Automated Fungal Detection},
journal = {IEEE Access},
year = {2026},
volume = {14},
pages = {63834--63846},
doi = {10.1109/access.2026.3686347}
}
EUVIMED