A pixel classification system for segmenting biomedical images using intensity neighborhoods and dimension reduction

We present an intensity neighborhood-based system for segmenting arbitrary biomedical image datasets using supervised learning. Because neighborhood methods are often associated with high-dimensional feature vectors, we explore a Principal Component Analysis (PCA) based method to reduce the dimensio...

Full description

Saved in:
Bibliographic Details
Published in2011 IEEE International Symposium on Biomedical Imaging: From Nano to Macro pp. 1649 - 1652
Main Authors Cheng Chen, Ozolek, J A, Wei Wang, Rohde, G K
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.03.2011
Subjects
Biomedical imaging
dimension reduction
Image segmentation
intensity neighborhood
Pixel
pixel classification
Principal component analysis
Support vector machines
Testing
Training
Online AccessGet full text
ISBN1424441277
9781424441273
ISSN1945-7928
DOI10.1109/ISBI.2011.5872720

Cover

More Information
Summary:We present an intensity neighborhood-based system for segmenting arbitrary biomedical image datasets using supervised learning. Because neighborhood methods are often associated with high-dimensional feature vectors, we explore a Principal Component Analysis (PCA) based method to reduce the dimensionality (and provide computational savings) of each neighborhood. Our results show that the system can accurately segment data in three applications: tissue segmentation from brain MR data, and histopathological images, and nuclei segmentation from fluorescence images. Our results also show that the dimension reduction method we described improves computational efficiency while maintaining similar accuracy.
ISBN:1424441277
9781424441273
ISSN:1945-7928
DOI:10.1109/ISBI.2011.5872720