Three-dimensional conditional random field for the dermal–epidermal junction segmentation

Julie Robic, Benjamin Perret, Alex Nkengne, Michel Couprie, Hugues TalbotJournal of Medical Imaging 2019 · DOI

Abstract

The segmentation of the dermal-epidermal junction (DEJ) in <i>in vivo</i> confocal images represents a challenging task due to uncertainty in visual labeling and complex dependencies between skin layers. We propose a method to segment the DEJ surface, which combines random forest classification with spatial regularization based on a three-dimensional conditional random field (CRF) to improve the classification robustness. The CRF regularization introduces spatial constraints consistent with skin anatomy and its biological behavior. We propose to specify the interaction potentials between pixels according to their depth and their relative position to each other to model skin biological properties. The proposed approach adds regularity to the classification by prohibiting inconsistent transitions between skin layers. As a result, it improves the sensitivity and specificity of the classification results.
BibTeX
@article{robic2019three,
  author = {Julie Robic and Benjamin Perret and Alex Nkengne and Michel Couprie and Hugues Talbot},
  title = {{Three-dimensional conditional random field for the dermal–epidermal junction segmentation}},
  journal = {Journal of Medical Imaging},
  year = {2019},
  doi = {10.1117/1.jmi.6.2.024003},
}

Loading related content...

Figure