Enhancement of spectral change from change of cell nucleus size distribution in epithelium using multiclass linear discriminant

Kazuhiro Gono; Makoto Igarashi; Takashi Obi; Masahiro Yamaguchi; Nagaaki Ohyama

doi:10.1117/12.528902

13 July 2004 Enhancement of spectral change from change of cell nucleus size distribution in epithelium using multiclass linear discriminant

Kazuhiro Gono, Makoto Igarashi, Takashi Obi, Masahiro Yamaguchi, Nagaaki Ohyama

Author Affiliations +

Proceedings Volume 5326, Optical Biopsy V; (2004) https://doi.org/10.1117/12.528902
Event: Biomedical Optics 2004, 2004, San Jose, CA, United States

Abstract

Here, we propose a new method to enhance the sensitivity of the reflectance spectrum to the scattering feature of the superficial tissue layer. This method is based on multiple discriminant analysis (MDA) in the eigen subspace of the spectrum. Considering the application of scattering imaging, we evaluated this method by performing multispectral imaging of two-layered tissue phantoms. A color map converted from the spectral reflectance well corresponds to variations in the size of the scatter in the first layer. In order to confirm our proposed method works well under more realistic conditions, we performed the computational simulations of the light propagation in the tissue. We used the simulation model combined with the Monte Carlo and the Mie scattering. Its conditions like the slab geometry and the particle distribution of the cell nucleus were estimated by the image measuring of pathological slices. Results on simulations show the possibility of enhancing the sensitivity of the reflectance spectrum to the scattering feature of the superficial tissue layer.

Citation Download Citation

Kazuhiro Gono, Makoto Igarashi, Takashi Obi, Masahiro Yamaguchi, and Nagaaki Ohyama "Enhancement of spectral change from change of cell nucleus size distribution in epithelium using multiclass linear discriminant", Proc. SPIE 5326, Optical Biopsy V, (13 July 2004); https://doi.org/10.1117/12.528902

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