Application of principal component analysis to multispectral imaging data for evaluation of pigmented skin lesions

Dainis Jakovels; Ilze Lihacova; Ilona Kuzmina; Janis Spigulis

doi:10.1117/12.2044383

Application of principal component analysis to multispectral imaging data for evaluation of pigmented skin lesions

Dainis Jakovels
, Ilze Lihacova
, Ilona Kuzmina
, Janis Spigulis

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

5 Citations (Scopus)

Abstract

Non-invasive and fast primary diagnostics of pigmented skin lesions is required due to frequent incidence of skin cancer - melanoma. Diagnostic potential of principal component analysis (PCA) for distant skin melanoma recognition is discussed. Processing of the measured clinical multi-spectral images (31 melanomas and 94 nonmalignant pigmented lesions) in the wavelength range of 450-950 nm by means of PCA resulted in 87 % sensitivity and 78 % specificity for separation between malignant melanomas and pigmented nevi.

Original language	English
Title of host publication	Biophotonics - Riga 2013
DOIs	https://doi.org/10.1117/12.2044383
Publication status	Published - 2013
Event	1st International Conference on Biophotonics - Riga 2013, BPR 2013 - Riga, Latvia Duration: 26 Aug 2013 → 31 Aug 2013

Publication series

Name	Progress in Biomedical Optics and Imaging - Proceedings of SPIE
Volume	9032
ISSN (Print)	1605-7422

Conference

Conference	1st International Conference on Biophotonics - Riga 2013, BPR 2013
Country/Territory	Latvia
City	Riga
Period	26/08/13 → 31/08/13

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Keywords

Melanoma
Multispectral imaging
Principal component analysis
Skin

Access to Document

10.1117/12.2044383

Cite this

@inproceedings{ed298f91c26443fc8cb8ae80bd3b40c2,

title = "Application of principal component analysis to multispectral imaging data for evaluation of pigmented skin lesions",

abstract = "Non-invasive and fast primary diagnostics of pigmented skin lesions is required due to frequent incidence of skin cancer - melanoma. Diagnostic potential of principal component analysis (PCA) for distant skin melanoma recognition is discussed. Processing of the measured clinical multi-spectral images (31 melanomas and 94 nonmalignant pigmented lesions) in the wavelength range of 450-950 nm by means of PCA resulted in 87 \% sensitivity and 78 \% specificity for separation between malignant melanomas and pigmented nevi.",

keywords = "Melanoma, Multispectral imaging, Principal component analysis, Skin",

author = "Dainis Jakovels and Ilze Lihacova and Ilona Kuzmina and Janis Spigulis",

year = "2013",

doi = "10.1117/12.2044383",

language = "English",

isbn = "9780819499806",

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

booktitle = "Biophotonics - Riga 2013",

note = "1st International Conference on Biophotonics - Riga 2013, BPR 2013 ; Conference date: 26-08-2013 Through 31-08-2013",

}

Jakovels, D, Lihacova, I, Kuzmina, I & Spigulis, J 2013, Application of principal component analysis to multispectral imaging data for evaluation of pigmented skin lesions. in Biophotonics - Riga 2013., 903204, Progress in Biomedical Optics and Imaging - Proceedings of SPIE, vol. 9032, 1st International Conference on Biophotonics - Riga 2013, BPR 2013, Riga, Latvia, 26/08/13. https://doi.org/10.1117/12.2044383

Application of principal component analysis to multispectral imaging data for evaluation of pigmented skin lesions. / Jakovels, Dainis; Lihacova, Ilze; Kuzmina, Ilona et al.
Biophotonics - Riga 2013. 2013. 903204 (Progress in Biomedical Optics and Imaging - Proceedings of SPIE; Vol. 9032).

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

TY - GEN

T1 - Application of principal component analysis to multispectral imaging data for evaluation of pigmented skin lesions

AU - Jakovels, Dainis

AU - Lihacova, Ilze

AU - Kuzmina, Ilona

AU - Spigulis, Janis

PY - 2013

Y1 - 2013

N2 - Non-invasive and fast primary diagnostics of pigmented skin lesions is required due to frequent incidence of skin cancer - melanoma. Diagnostic potential of principal component analysis (PCA) for distant skin melanoma recognition is discussed. Processing of the measured clinical multi-spectral images (31 melanomas and 94 nonmalignant pigmented lesions) in the wavelength range of 450-950 nm by means of PCA resulted in 87 % sensitivity and 78 % specificity for separation between malignant melanomas and pigmented nevi.

AB - Non-invasive and fast primary diagnostics of pigmented skin lesions is required due to frequent incidence of skin cancer - melanoma. Diagnostic potential of principal component analysis (PCA) for distant skin melanoma recognition is discussed. Processing of the measured clinical multi-spectral images (31 melanomas and 94 nonmalignant pigmented lesions) in the wavelength range of 450-950 nm by means of PCA resulted in 87 % sensitivity and 78 % specificity for separation between malignant melanomas and pigmented nevi.

KW - Melanoma

KW - Multispectral imaging

KW - Principal component analysis

KW - Skin

UR - https://www.scopus.com/pages/publications/84891335691

U2 - 10.1117/12.2044383

DO - 10.1117/12.2044383

M3 - Conference paper

AN - SCOPUS:84891335691

SN - 9780819499806

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

BT - Biophotonics - Riga 2013

T2 - 1st International Conference on Biophotonics - Riga 2013, BPR 2013

Y2 - 26 August 2013 through 31 August 2013

ER -

Application of principal component analysis to multispectral imaging data for evaluation of pigmented skin lesions

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this