Medical Image Recognition of Heart Regions by Deep Multi-Layered GMDH-Type Neural Network Using Principal Component-Regression Analysis
Authors
Tadashi Kondo, Junji Ueno, Shoichiro Takao
Corresponding Author
Tadashi Kondo
Available Online 1 December 2015.
DOI
https://doi.org/10.2991/jrnal.2015.2.3.7
Keywords
Deep neural networks, GMDH, Medical image recognition, Evolutionary computation
Abstract
In this study, a deep Group Method of Data Handling (GMDH)-type neural
network using principal component-regression is applied to the medical
image recognition of the heart regions. The deep GMDH-type neural network
algorithm can organize the neural network architecture with many hidden
layers fitting the complexity of the nonlinear systems so as to minimize
the prediction error criterion defined as AIC (Akaike’s Information Criterion)
or PSS (Prediction Sum of Squares). This algorithm is applied to the medical
image recognition of the heart regions and it is shown that this algorithm
is useful for the medical image recognition of the heart regions because
deep neural network architecture is automatically organized using the principal
component-regression analysis from the medical images of the heart regions.
Copyright
© 2013, the Authors. Published by ALife Robotics Corp. Ltd.
Open Access
This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).