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

Publikation: Bidrag til tidsskriftTidsskriftartikelfagfællebedømt

Standard

Automatic Segmentation of Epidermis and Hair Follicles in Optical Coherence Tomography Images of Normal Skin by Convolutional Neural Networks. / Del Amor, Rocío; Morales, Sandra; Colomer, Adrián; Mogensen, Mette; Jensen, Mikkel; Israelsen, Niels M; Bang, Ole; Naranjo, Valery.

I: Frontiers in Medicine, Bind 7, 220, 2020.

Publikation: Bidrag til tidsskriftTidsskriftartikelfagfællebedømt

Harvard

Del Amor, R, Morales, S, Colomer, A, Mogensen, M, Jensen, M, Israelsen, NM, Bang, O & Naranjo, V 2020, 'Automatic Segmentation of Epidermis and Hair Follicles in Optical Coherence Tomography Images of Normal Skin by Convolutional Neural Networks', Frontiers in Medicine, bind 7, 220. https://doi.org/10.3389/fmed.2020.00220

APA

Del Amor, R., Morales, S., Colomer, A., Mogensen, M., Jensen, M., Israelsen, N. M., Bang, O., & Naranjo, V. (2020). Automatic Segmentation of Epidermis and Hair Follicles in Optical Coherence Tomography Images of Normal Skin by Convolutional Neural Networks. Frontiers in Medicine, 7, [220]. https://doi.org/10.3389/fmed.2020.00220

Vancouver

Del Amor R, Morales S, Colomer A, Mogensen M, Jensen M, Israelsen NM o.a. Automatic Segmentation of Epidermis and Hair Follicles in Optical Coherence Tomography Images of Normal Skin by Convolutional Neural Networks. Frontiers in Medicine. 2020;7. 220. https://doi.org/10.3389/fmed.2020.00220

Author

Del Amor, Rocío ; Morales, Sandra ; Colomer, Adrián ; Mogensen, Mette ; Jensen, Mikkel ; Israelsen, Niels M ; Bang, Ole ; Naranjo, Valery. / Automatic Segmentation of Epidermis and Hair Follicles in Optical Coherence Tomography Images of Normal Skin by Convolutional Neural Networks. I: Frontiers in Medicine. 2020 ; Bind 7.

Bibtex

@article{2eeeefe2bd76420586355dda7c547493,
title = "Automatic Segmentation of Epidermis and Hair Follicles in Optical Coherence Tomography Images of Normal Skin by Convolutional Neural Networks",
abstract = "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.",
author = "{Del Amor}, Roc{\'i}o and Sandra Morales and Adri{\'a}n Colomer and Mette Mogensen and Mikkel Jensen and Israelsen, {Niels M} and Ole Bang and Valery Naranjo",
note = "Copyright {\textcopyright} 2020 del Amor, Morales, Colomer, Mogensen, Jensen, Israelsen, Bang and Naranjo.",
year = "2020",
doi = "10.3389/fmed.2020.00220",
language = "English",
volume = "7",
journal = "Frontiers in Medicine",
issn = "2296-858X",
publisher = "Frontiers Media S.A.",

}

RIS

TY - JOUR

T1 - Automatic Segmentation of Epidermis and Hair Follicles in Optical Coherence Tomography Images of Normal Skin by Convolutional Neural Networks

AU - Del Amor, Rocío

AU - Morales, Sandra

AU - Colomer, Adrián

AU - Mogensen, Mette

AU - Jensen, Mikkel

AU - Israelsen, Niels M

AU - Bang, Ole

AU - Naranjo, Valery

N1 - Copyright © 2020 del Amor, Morales, Colomer, Mogensen, Jensen, Israelsen, Bang and Naranjo.

PY - 2020

Y1 - 2020

N2 - 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.

AB - 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.

U2 - 10.3389/fmed.2020.00220

DO - 10.3389/fmed.2020.00220

M3 - Journal article

C2 - 32582729

VL - 7

JO - Frontiers in Medicine

JF - Frontiers in Medicine

SN - 2296-858X

M1 - 220

ER -

ID: 262913467