Share Email Print

Proceedings Paper

Automated microscopy for lymph node cancer diagnosis
Author(s): Lawrence M. Firestone
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

A Coulter diff3/50 research microscope under computer control was used to digitize biopsy slides at differing resolutions and in full color. Then, a broad set of candidate features were extracted using color analysis, template matching, statistical texture analysis, frequency domain techniques, and surface modeling by both cellular logic filters and relative extrema analysis. In all, over 600 candidate features were measured for selection and classifier design. Standard pattern recognition techniques for classifier design assume that objects cluster into distinct classes. For the lymphoma problem, where the classes (subtypes) form a continuum based on the percentage of large cells, this discrete class assumption does not apply. Estimation theoretic techniques were combined with pattern recognition for this project to design classifiers that exploit the continuous nature of lymphoma subtyping.

Paper Details

Date Published: 17 September 1993
PDF: 6 pages
Proc. SPIE 1894, Clinical Applications of Modern Imaging Technology, (17 September 1993); doi: 10.1117/12.154951
Show Author Affiliations
Lawrence M. Firestone, GDE Systems Inc. (United States)

Published in SPIE Proceedings Vol. 1894:
Clinical Applications of Modern Imaging Technology
Abund Ottokar Wist, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?