EUVIMEDEUVIMED entdecken
Crossref

Deep learning based hair removal on ultraviolet-induced fluorescence dermatoscopy images

Aleksander Kempski, Natalia Salwowska, Anna Slian, Katarzyna Korecka, Paweł Pietkiewicz, Adriana Polańska, Damian Borys, Joanna Czajkowska

Computer Methods and Programs in Biomedicine · 2026-10 · 285 · 109501

DOI: 10.1016/j.cmpb.2026.109501 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Computer Methods and Programs in Biomedicine, 2026-10. Verfasst von Aleksander Kempski und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Systems Biology and Engineering, Faculty of Automatic Control, Electronics and Computer Science, Silesian University of Technology, Gli…. Hauptthemen laut MEDLINE: Deep Learning, Ultraviolet Rays, Dermoscopy, Hair Removal. Die Arbeit nennt 49 Literaturangaben. Gefördert von: Silesian University of Technology.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

BACKGROUND AND OBJECTIVE: Ultraviolet-induced fluorescence dermatoscopy (UVFD) is a novel technique utilizing ultraviolet light to produce visible fluorescence. Many skin conditions reveal specific features during UVFD, guiding early detection and diagnosis. Although there are many methods for computer processing of dermatoscopic images, there are no methods targeting UVFD images. This work identifies newly encountered challenges and proposes a preprocessing pipeline for preparing obtained data for further statistical analysis. METHODS: The study discusses the challenges and the applicability of methods developed for regular dermatoscopic images. Finally, the universal pipeline for preprocessing is presented. The study used a collection of 2027 background images, manually selected by an expert from hairless regions, which were later used for hair generation. Additionally, 120 images were manually annotated for dark and light hair, resulting in a set of ground truth masks. The study evaluated a number of algorithmic methods and a deep neural networks: UNet, ChimeraNet and TransUNet. RESULTS: The results clearly showed the superiority of deep learning over algorithmic methods in the task of hair segmentation in UVFD images. For dark hair segmentation, the UNet and TransUNet reported Dice scores ranging 0.95-0.98 on synthetic data. On real-life light hair UNet achieved the higher result, with Dice score of 0.557, while on dark hair all models ranged 0.61-0.65. CONCLUSIONS: The study used a synthetic dataset to train the UNET neural network, which yielded results superior to analytical approaches known from dermatological images. The presented preprocessing pipeline is freely available and can be found on our GitHub repository https://github.com/aKempski01/UVFD-data-preprocessing.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningUltraviolet RaysDermoscopyHair RemovalImage Processing, Computer-AssistedHumansAlgorithmsFluorescenceHairNeural Networks, Computer

Stichwörter der Autor:innen

Automatic hair removalDermatoscopyHair detectionUNETUltraviolet-induced fluorescence

Autor:innen und Institutionen

  • Department of Systems Biology and Engineering, Faculty of Automatic Control, Electronics and Computer Science, Silesian University of Technology, Gliwice, Poland.
  • Department of Dermatology, Medical University of Silesia, Katowice, Poland.
  • Department of Medical Informatics and Artificial Intelligence, Faculty of Biomedical Engineering, Silesian University of Technology, Gliwice, Poland. Electronic address: anna.slian@polsl.pl.
  • Department of Dermatology, Poznan University of Medical Sciences, Poznan, Poland.
  • Prisca Sapientia Intitute, Zürich, Switzerland; Zwierzyniecka Medical Center, Poznan, Poland.
  • Department of Systems Biology and Engineering, Faculty of Automatic Control, Electronics and Computer Science, Silesian University of Technology, Gliwice, Poland; Biotechnology Centre, Silesian University of Technology,…

Förderung

  • Silesian University of Technology

Zitieren

APA

Kempski, A., Salwowska, N., Slian, A., Korecka, K., Pietkiewicz, P., Polańska, A., Borys, D., & Czajkowska, J. (2026). Deep learning based hair removal on ultraviolet-induced fluorescence dermatoscopy images. Computer Methods and Programs in Biomedicine, 285, 109501. https://doi.org/10.1016/j.cmpb.2026.109501

Vancouver

Kempski A, Salwowska N, Slian A, Korecka K, Pietkiewicz P, Polańska A, et al. Deep learning based hair removal on ultraviolet-induced fluorescence dermatoscopy images. Computer Methods and Programs in Biomedicine. 2026;285:109501. doi:10.1016/j.cmpb.2026.109501

BibTeX
@article{Kempski2026,
  author = {Kempski, Aleksander and Salwowska, Natalia and Slian, Anna and Korecka, Katarzyna and Pietkiewicz, Paweł and Polańska, Adriana and Borys, Damian and Czajkowska, Joanna},
  title = {Deep learning based hair removal on ultraviolet-induced fluorescence dermatoscopy images},
  journal = {Computer Methods and Programs in Biomedicine},
  year = {2026},
  volume = {285},
  pages = {109501},
  doi = {10.1016/j.cmpb.2026.109501}
}
Kostenlos starten →