Share Email Print

Proceedings Paper

Localization of tissues in high-resolution digital anatomic pathology images
Author(s): Raja S. Alomari; Ron Allen; Bikash Sabata; Vipin Chaudhary
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

High resolution digital pathology images have a wide range of variability in color, shape, size, number, appearance, location, and texture. The segmentation problem is challenging in this environment. We introduce a hybrid method that combines parametric machine learning with heuristic methods for feature extraction as well as pre- and post-processing steps for localizing diverse tissues in slide images. The method uses features such as color, intensity, texture, and spatial distribution. We use principal component analysis for feature reduction and train a two layer back propagation neural network (with one hidden layer). We perform image labeling at pixel-level and achieve higher than 96% automatic localization accuracy on 294 test images.

Paper Details

Date Published: 3 March 2009
PDF: 10 pages
Proc. SPIE 7260, Medical Imaging 2009: Computer-Aided Diagnosis, 726016 (3 March 2009); doi: 10.1117/12.811430
Show Author Affiliations
Raja S. Alomari, Univ. at Buffalo, SUNY (United States)
Ron Allen, Bioimagene, Inc. (United States)
Bikash Sabata, Bioimagene, Inc. (United States)
Vipin Chaudhary, Univ. at Buffalo, SUNY (United States)

Published in SPIE Proceedings Vol. 7260:
Medical Imaging 2009: Computer-Aided Diagnosis
Nico Karssemeijer; Maryellen L. Giger, 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?