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

18 November 2013 Application of principal component analysis to multispectral imaging data for evaluation of pigmented skin lesions

Dainis Jakovels, Ilze Lihacova, Ilona Kuzmina, Janis Spigulis

Author Affiliations +

Proceedings Volume 9032, Biophotonics—Riga 2013; 903204 (2013) https://doi.org/10.1117/12.2044383
Event: 1st International Conference "Biophotonics Riga 2013", 2013, Riga, Latvia

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.

Citation Download Citation

Dainis Jakovels, Ilze Lihacova, Ilona Kuzmina, and Janis Spigulis "Application of principal component analysis to multispectral imaging data for evaluation of pigmented skin lesions", Proc. SPIE 9032, Biophotonics—Riga 2013, 903204 (18 November 2013); https://doi.org/10.1117/12.2044383

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available