Mahdieh Khalilinezhad and Silvana Dellepiane and Gianni Vernazza
Detecting HCC Tumor in Three Phasic CT Liver Images with Optimization of Neural Network
277 - 282
2015
9
3
International Journal of Computer and Information Engineering
https://publications.waset.org/pdf/10000812
https://publications.waset.org/vol/99
World Academy of Science, Engineering and Technology
The aim of this work is to build a model based on
tissue characterization that is able to discriminate pathological and
nonpathological regions from threephasic CT images. With our
research and based on a feature selection in different phases, we are
trying to design a neural network system with an optimal neuron
number in a hidden layer. Our approach consists of three steps
feature selection, feature reduction, and classification. For each
region of interest (ROI), 6 distinct sets of texture features are
extracted such as first order histogram parameters, absolute gradient,
runlength matrix, cooccurrence matrix, autoregressive model, and
wavelet, for a total of 270 texture features. When analyzing more
phases, we show that the injection of liquid cause changes to the high
relevant features in each region. Our results demonstrate that for
detecting HCC tumor phase 3 is the best one in most of the features
that we apply to the classification algorithm. The percentage of
detection between pathology and healthy classes, according to our
method, relates to first order histogram parameters with accuracy of
85 in phase 1, 95 in phase 2, and 95 in phase 3.
Open Science Index 99, 2015