EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A U-Net model for epidermal segmentation in optical coherence tomography images of actinic keratosis

Theofanis Angelis iD, Peter A Philipsen iD, Vinzent K Ortner, Gabriella Fredman, Merete Haedersdal, Gavrielle R Untracht iD

PLOS One · 05.06.2026 · 21 (6) · e0346059

DOI: 10.1371/journal.pone.0346059 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, online erschienen am 05.06.2026. Verfasst von Theofanis Angelis und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Dermatology, Copenhagen University Hospital, Bispebjerg and Frederiksberg, Copenhagen, Denmark. Hauptthemen laut MEDLINE: Tomography, Optical Coherence, Keratosis, Actinic, Epidermis, Image Processing, Computer-Assisted. Die Arbeit nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Greater Copenhagen Health Science Partners.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Actinic keratosis (AK) is a pre-cancerous skin lesion typically caused by excessive exposure to ultraviolet light. Optical coherence tomography (OCT) can provide sub-surface information relevant for lesion classification, but manual analysis of images is time-consuming and subject to inter-observer variability; automated segmentation based on deep learning models can provide faster and more consistent results. However, structural changes, such as thickening and hyperkeratosis, complicate epidermal segmentation tasks. For this reason, we aimed to develop and optimize a U-Net model for the automated epidermal segmentation of AK lesions in OCT images, combining both accuracy and computational efficiency. Multiple configurations were evaluated by varying hyperparameters, including image sizes (256 × 256, 512 × 512, 1024 × 1024, and 464 × 1356 pixels), batch sizes (2, 4, 8, and 16), and training durations (50, 100, and 150 epochs). Model performance was evaluated quantitatively using several metrics including the Dice coefficient and Jaccard index, comparing automated epidermal segmentations against expert annotations. The optimal configuration, with an image resolution of 256 × 256 pixels and a batch size of 2 over 50 epochs, had a Dice score of 0.86 and a Jaccard index of 0.76. Higher resolutions and longer training increased computation without significantly enhancing the accuracy values and sometimes caused overfitting. These findings show that a simple U-Net architecture could achieve efficient and accurate epidermal segmentation in AK lesions, provided it is fine-tuned to enhance performance.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Tomography, Optical CoherenceKeratosis, ActinicEpidermisImage Processing, Computer-AssistedHumansDeep Learning

Autor:innen und Institutionen

  • Department of Dermatology, Copenhagen University Hospital, Bispebjerg and Frederiksberg, Copenhagen, Denmark.
  • Department of Health Technology, Technical University of Denmark, Kongens Lyngby, Denmark.
  • Department of Clinical Medicine, Faculty of Health and Medical Science, University of Copenhagen, Copenhagen, Denmark.

ORCID-Profile: Theofanis Angelis, Peter A Philipsen, Gavrielle R Untracht

Förderung

  • Greater Copenhagen Health Science Partners

Zitieren

APA

Angelis, T., Philipsen, P. A., Ortner, V. K., Fredman, G., Haedersdal, M., & Untracht, G. R. (2026). A U-Net model for epidermal segmentation in optical coherence tomography images of actinic keratosis. PLOS One, 21(6), e0346059. https://doi.org/10.1371/journal.pone.0346059

Vancouver

Angelis T, Philipsen PA, Ortner VK, Fredman G, Haedersdal M, Untracht GR. A U-Net model for epidermal segmentation in optical coherence tomography images of actinic keratosis. PLOS One. 2026;21(6):e0346059. doi:10.1371/journal.pone.0346059

BibTeX
@article{Angelis2026,
  author = {Angelis, Theofanis and Philipsen, Peter A and Ortner, Vinzent K and Fredman, Gabriella and Haedersdal, Merete and Untracht, Gavrielle R},
  title = {A U-Net model for epidermal segmentation in optical coherence tomography images of actinic keratosis},
  journal = {PLOS One},
  year = {2026},
  volume = {21},
  number = {6},
  pages = {e0346059},
  doi = {10.1371/journal.pone.0346059}
}
Kostenlos starten →