Research
Print page Print page
Switch language
The Capital Region of Denmark - a part of Copenhagen University Hospital
Published

Automatic Segmentation of Epidermis and Hair Follicles in Optical Coherence Tomography Images of Normal Skin by Convolutional Neural Networks

Research output: Contribution to journalJournal articleResearchpeer-review

DOI

  1. Magnetic Resonance Imaging of Enthesitis in Spondyloarthritis, Including Psoriatic Arthritis-Status and Recent Advances

    Research output: Contribution to journalReviewResearchpeer-review

  2. Intradermal Tests With Drugs: An Approach to Standardization

    Research output: Contribution to journalJournal articleResearchpeer-review

  3. Clinical Utility of Measuring Inspiratory Neural Drive During Cardiopulmonary Exercise Testing (CPET)

    Research output: Contribution to journalReviewResearchpeer-review

  1. Tocilizumab in systemic sclerosis: a randomised, double-blind, placebo-controlled, phase 3 trial

    Research output: Contribution to journalJournal articleResearchpeer-review

  2. In Vivo Reflectance Confocal Microscopy of Gold Microparticles Deposited in the Skin. A Case Report on Cutaneous Chrysiasis

    Research output: Contribution to journalJournal articleResearchpeer-review

  • Rocío Del Amor
  • Sandra Morales
  • Adrián Colomer
  • Mette Mogensen
  • Mikkel Jensen
  • Niels M Israelsen
  • Ole Bang
  • Valery Naranjo
View graph of relations

Optical coherence tomography (OCT) is a well-established bedside imaging modality that allows analysis of skin structures in a non-invasive way. Automated OCT analysis of skin layers is of great relevance to study dermatological diseases. In this paper, an approach to detect the epidermal layer along with the follicular structures in healthy human OCT images is presented. To the best of the authors' knowledge, the approach presented in this paper is the only epidermis detection algorithm that segments the pilosebaceous unit, which is of importance in the progression of several skin disorders such as folliculitis, acne, lupus erythematosus, and basal cell carcinoma. The proposed approach is composed of two main stages. The first stage is a Convolutional Neural Network based on U-Net architecture. The second stage is a robust post-processing composed by a Savitzky-Golay filter and Fourier Domain Filtering to fully define the borders belonging to the hair follicles. After validation, an average Dice of 0.83 ± 0.06 and a thickness error of 10.25 μm is obtained on 270 human skin OCT images. Based on these results, the proposed method outperforms other state-of-the-art methods for epidermis segmentation. It demonstrates that the proposed image segmentation method successfully detects the epidermal region in a fully automatic way in addition to defining the follicular skin structures as main novelty.

Original languageEnglish
Article number220
JournalFrontiers in Medicine
Volume7
ISSN2296-858X
DOIs
Publication statusPublished - 2020

    Research areas

  • convolutional neural networks, epidermis, follicular structures, layer segmentation, pilosebaceous unit, skin OCT

ID: 61824520