These publications are provided on the
LIVE website for research purposes ONLY. No part of these documents
may be distributed for commercial purposes
Feature normalization via expectation maximization and unsupervised nonparametric classification for M-FISH chromosome images
H. Choi, A.C. Bovik and K.R. Castleman
IEEE Transactions on Medical Imaging
Abstract
Multicolor fluorescence in situ hybridization
(M-FISH) techniques provide color karyotyping that allows
simultaneous analysis of numerical and structural abnormalities
of whole human chromosomes. Chromosomes are stained combinatorially
in M-FISH. By analyzing the intensity combinations of
each pixel, all chromosome pixels in an image are classified. Often,
the intensity distributions between different images are found to
be considerably different and the difference becomes the source
of misclassifications of the pixels. Improved pixel classification
accuracy is the most important task to ensure the success of the
M-FISH technique. In this paper, we introduce a new feature normalization
method for M-FISH images that reduces the difference
in the feature distributions among different images using the expectation
maximization (EM) algorithm. We also introduce a new
unsupervised, nonparametric classification method for M-FISH
images. The performance of the classifier is as accurate as the
maximum-likelihood classifier, whose accuracy also significantly
improved after the EM normalization. We would expect that any
classifier will likely produce an improved classification accuracy
following the EM normalization. Since the developed classification
method does not require training data, it is highly convenient
when ground truth does not exist. A significant improvement was
achieved on the pixel classification accuracy after the new feature
normalization. Indeed, the overall pixel classification accuracy
improved by 20% after EM normalization.
[Download PDF]
