Textural analysis of optical coherence tomography skin images: Quantitative differentiation between healthy and cancerous tissues

Saba Adabi; Silvia Conforto; Matin Hosseinzadeh; Shahryar Noe; Steven Daveluy; Darius Mehregan; Mohammadreza Nasiriavanaki

doi:10.1117/12.2254869

Textural analysis of optical coherence tomography skin images: Quantitative differentiation between healthy and cancerous tissues

Saba Adabi
, Silvia Conforto
, Matin Hosseinzadeh
, Shahryar Noe
, Steven Daveluy
, Darius Mehregan
, Mohammadreza Nasiriavanaki

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

5 Scopus citations

Abstract

Optical Coherence Tomography (OCT) offers real-time high-resolution three-dimensional images of tissue microstructures. In this study, we used OCT skin images acquired from ten volunteers, neither of whom had any skin conditions addressing the features of their anatomic location. OCT segmented images are analyzed based on their optical properties (attenuation coefficient) and textural image features e.g., contrast, correlation, homogeneity, energy, entropy, etc. Utilizing the information and referring to their clinical insight, we aim to make a comprehensive computational model for the healthy skin. The derived parameters represent the OCT microstructural morphology and might provide biological information for generating an atlas of normal skin from different anatomic sites of human skin and may allow for identification of cell microstructural changes in cancer patients. We then compared the parameters of healthy samples with those of abnormal skin and classified them using a linear Support Vector Machines (SVM) with 82% accuracy.

Original language	English
Title of host publication	Optical Coherence Tomography and Coherence Domain Optical Methods in Biomedicine XXI
Editors	Valery V. Tuchin, Joseph A. Izatt, James G. Fujimoto, Valery V. Tuchin
Publisher	SPIE
ISBN (Electronic)	9781510605473
DOIs	https://doi.org/10.1117/12.2254869
State	Published - 2017
Externally published	Yes
Event	Optical Coherence Tomography and Coherence Domain Optical Methods in Biomedicine XXI - San Francisco, United States Duration: 29 Jan 2017 → 1 Feb 2017

Publication series

Name	Progress in Biomedical Optics and Imaging - Proceedings of SPIE
Volume	10053
ISSN (Print)	1605-7422

Conference

Conference	Optical Coherence Tomography and Coherence Domain Optical Methods in Biomedicine XXI
Country/Territory	United States
City	San Francisco
Period	29/01/17 → 1/02/17

Keywords

Classification
OCT
Skin
Texture analysis

Access to Document

10.1117/12.2254869

Cite this

Adabi, S., Conforto, S., Hosseinzadeh, M., Noe, S., Daveluy, S., Mehregan, D., & Nasiriavanaki, M. (2017). Textural analysis of optical coherence tomography skin images: Quantitative differentiation between healthy and cancerous tissues. In V. V. Tuchin, J. A. Izatt, J. G. Fujimoto, & V. V. Tuchin (Eds.), Optical Coherence Tomography and Coherence Domain Optical Methods in Biomedicine XXI Article 100533F (Progress in Biomedical Optics and Imaging - Proceedings of SPIE; Vol. 10053). SPIE. https://doi.org/10.1117/12.2254869

Adabi, Saba ; Conforto, Silvia ; Hosseinzadeh, Matin et al. / Textural analysis of optical coherence tomography skin images : Quantitative differentiation between healthy and cancerous tissues. Optical Coherence Tomography and Coherence Domain Optical Methods in Biomedicine XXI. editor / Valery V. Tuchin ; Joseph A. Izatt ; James G. Fujimoto ; Valery V. Tuchin. SPIE, 2017. (Progress in Biomedical Optics and Imaging - Proceedings of SPIE).

@inproceedings{0d69a8cb527247898ab7aaabb9f7e43b,

title = "Textural analysis of optical coherence tomography skin images: Quantitative differentiation between healthy and cancerous tissues",

abstract = "Optical Coherence Tomography (OCT) offers real-time high-resolution three-dimensional images of tissue microstructures. In this study, we used OCT skin images acquired from ten volunteers, neither of whom had any skin conditions addressing the features of their anatomic location. OCT segmented images are analyzed based on their optical properties (attenuation coefficient) and textural image features e.g., contrast, correlation, homogeneity, energy, entropy, etc. Utilizing the information and referring to their clinical insight, we aim to make a comprehensive computational model for the healthy skin. The derived parameters represent the OCT microstructural morphology and might provide biological information for generating an atlas of normal skin from different anatomic sites of human skin and may allow for identification of cell microstructural changes in cancer patients. We then compared the parameters of healthy samples with those of abnormal skin and classified them using a linear Support Vector Machines (SVM) with 82\% accuracy.",

keywords = "Classification, OCT, Skin, Texture analysis",

author = "Saba Adabi and Silvia Conforto and Matin Hosseinzadeh and Shahryar Noe and Steven Daveluy and Darius Mehregan and Mohammadreza Nasiriavanaki",

note = "Publisher Copyright: {\textcopyright} 2017 SPIE.; Optical Coherence Tomography and Coherence Domain Optical Methods in Biomedicine XXI ; Conference date: 29-01-2017 Through 01-02-2017",

year = "2017",

doi = "10.1117/12.2254869",

language = "English",

series = "Progress in Biomedical Optics and Imaging - Proceedings of SPIE",

publisher = "SPIE",

editor = "Tuchin, \{Valery V.\} and Izatt, \{Joseph A.\} and Fujimoto, \{James G.\} and Tuchin, \{Valery V.\}",

booktitle = "Optical Coherence Tomography and Coherence Domain Optical Methods in Biomedicine XXI",

address = "United States",

}

Adabi, S, Conforto, S, Hosseinzadeh, M, Noe, S, Daveluy, S, Mehregan, D & Nasiriavanaki, M 2017, Textural analysis of optical coherence tomography skin images: Quantitative differentiation between healthy and cancerous tissues. in VV Tuchin, JA Izatt, JG Fujimoto & VV Tuchin (eds), Optical Coherence Tomography and Coherence Domain Optical Methods in Biomedicine XXI., 100533F, Progress in Biomedical Optics and Imaging - Proceedings of SPIE, vol. 10053, SPIE, Optical Coherence Tomography and Coherence Domain Optical Methods in Biomedicine XXI, San Francisco, United States, 29/01/17. https://doi.org/10.1117/12.2254869

Textural analysis of optical coherence tomography skin images: Quantitative differentiation between healthy and cancerous tissues. / Adabi, Saba; Conforto, Silvia; Hosseinzadeh, Matin et al.
Optical Coherence Tomography and Coherence Domain Optical Methods in Biomedicine XXI. ed. / Valery V. Tuchin; Joseph A. Izatt; James G. Fujimoto; Valery V. Tuchin. SPIE, 2017. 100533F (Progress in Biomedical Optics and Imaging - Proceedings of SPIE; Vol. 10053).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Textural analysis of optical coherence tomography skin images

T2 - Optical Coherence Tomography and Coherence Domain Optical Methods in Biomedicine XXI

AU - Adabi, Saba

AU - Conforto, Silvia

AU - Hosseinzadeh, Matin

AU - Noe, Shahryar

AU - Daveluy, Steven

AU - Mehregan, Darius

AU - Nasiriavanaki, Mohammadreza

PY - 2017

Y1 - 2017

N2 - Optical Coherence Tomography (OCT) offers real-time high-resolution three-dimensional images of tissue microstructures. In this study, we used OCT skin images acquired from ten volunteers, neither of whom had any skin conditions addressing the features of their anatomic location. OCT segmented images are analyzed based on their optical properties (attenuation coefficient) and textural image features e.g., contrast, correlation, homogeneity, energy, entropy, etc. Utilizing the information and referring to their clinical insight, we aim to make a comprehensive computational model for the healthy skin. The derived parameters represent the OCT microstructural morphology and might provide biological information for generating an atlas of normal skin from different anatomic sites of human skin and may allow for identification of cell microstructural changes in cancer patients. We then compared the parameters of healthy samples with those of abnormal skin and classified them using a linear Support Vector Machines (SVM) with 82% accuracy.

AB - Optical Coherence Tomography (OCT) offers real-time high-resolution three-dimensional images of tissue microstructures. In this study, we used OCT skin images acquired from ten volunteers, neither of whom had any skin conditions addressing the features of their anatomic location. OCT segmented images are analyzed based on their optical properties (attenuation coefficient) and textural image features e.g., contrast, correlation, homogeneity, energy, entropy, etc. Utilizing the information and referring to their clinical insight, we aim to make a comprehensive computational model for the healthy skin. The derived parameters represent the OCT microstructural morphology and might provide biological information for generating an atlas of normal skin from different anatomic sites of human skin and may allow for identification of cell microstructural changes in cancer patients. We then compared the parameters of healthy samples with those of abnormal skin and classified them using a linear Support Vector Machines (SVM) with 82% accuracy.

KW - Classification

KW - OCT

KW - Skin

KW - Texture analysis

UR - https://www.scopus.com/pages/publications/85019218797

U2 - 10.1117/12.2254869

DO - 10.1117/12.2254869

M3 - Conference contribution

AN - SCOPUS:85019218797

T3 - Progress in Biomedical Optics and Imaging - Proceedings of SPIE

BT - Optical Coherence Tomography and Coherence Domain Optical Methods in Biomedicine XXI

A2 - Tuchin, Valery V.

A2 - Izatt, Joseph A.

A2 - Fujimoto, James G.

A2 - Tuchin, Valery V.

PB - SPIE

Y2 - 29 January 2017 through 1 February 2017

ER -

Adabi S, Conforto S, Hosseinzadeh M, Noe S, Daveluy S, Mehregan D et al. Textural analysis of optical coherence tomography skin images: Quantitative differentiation between healthy and cancerous tissues. In Tuchin VV, Izatt JA, Fujimoto JG, Tuchin VV, editors, Optical Coherence Tomography and Coherence Domain Optical Methods in Biomedicine XXI. SPIE. 2017. 100533F. (Progress in Biomedical Optics and Imaging - Proceedings of SPIE). doi: 10.1117/12.2254869

Textural analysis of optical coherence tomography skin images: Quantitative differentiation between healthy and cancerous tissues

Abstract

Publication series

Conference

Keywords

Access to Document

Fingerprint

Cite this