Dependent component analysis based approach to robust demarcation of skin tumors

Ivica Kopriva; Antun Peršin; Neira Puizina-Ivić; Lina Mirić M.D.

doi:10.1117/12.806404

27 March 2009 Dependent component analysis based approach to robust demarcation of skin tumors

Ivica Kopriva, Antun Peršin, Neira Puizina-Ivić, Lina Mirić M.D.

Proceedings Volume 7259, Medical Imaging 2009: Image Processing; 72594Q (2009) https://doi.org/10.1117/12.806404
Event: SPIE Medical Imaging, 2009, Lake Buena Vista (Orlando Area), Florida, United States

Abstract

Method for robust demarcation of the basal cell carcinoma (BCC) is presented employing novel dependent component analysis (DCA)-based approach to unsupervised segmentation of the red-green-blue (RGB) fluorescent image of the BCC. It exploits spectral diversity between the BCC and the surrounding tissue. DCA represents an extension of the independent component analysis (ICA) and is necessary to account for statistical dependence induced by spectral similarity between the BCC and surrounding tissue. Robustness to intensity fluctuation is due to the scale invariance property of DCA algorithms. By comparative performance analysis with state-of-the-art image segmentation methods such as active contours (level set), K-means clustering, non-negative matrix factorization and ICA we experimentally demonstrate good performance of DCA-based BCC demarcation in demanding scenario where intensity of the fluorescent image has been varied almost two-orders of magnitude.

Citation Download Citation

Ivica Kopriva, Antun Peršin, Neira Puizina-Ivić, and Lina Mirić M.D. "Dependent component analysis based approach to robust demarcation of skin tumors", Proc. SPIE 7259, Medical Imaging 2009: Image Processing, 72594Q (27 March 2009); https://doi.org/10.1117/12.806404

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