Title :
Use of neural networks in detecting cardiac diseases from echocardiographic images
Author :
Cios, K.J. ; Chen, K. ; Langenderfer, R.A.
Author_Institution :
Dept. of Electr. Eng., Toledo Univ., OH, USA
Abstract :
The usefulness of backpropagation neural networks in the analysis of two-dimensional echocardiographic (2DE) images has been evaluated. The gray-scale levels from 2DE images directly correspond to the intensity of echo signal from cardiac tissue, providing visual texture and allowing qualitative and quantitative analysis of myocardial tissue. A subject population consisting of 11 normal, 7 hypertrophic cardiomyopathy, and 11 myocardial infarction patients was studied. Two types of backpropagational neural networks were used: fully connected, and patterned. In the fully connected network, the outputs of neurodes in each layer are connected to the inputs of all neurodes in the following layer. In the patterned network, only neurodes within a defined neighborhood are connected. The results suggest that the fully connected network provides better classifying performance than the patterned network.<>
Keywords :
acoustic imaging; biomedical ultrasonics; cardiology; computerised picture processing; medical diagnostic computing; neural nets; backpropagation neural networks; cardiac diseases; cardiac tissue; defined neighborhood; echo signal; fully connected network; gray-scale levels; hypertrophic cardiomyopathy patients; inputs; myocardial infarction patients; myocardial tissue; neurodes; normal patients; outputs; patterned network; quantitative analysis; subject population; two dimensional echocardiographic images; visual texture; Backpropagation; Cardiac disease; Cardiac tissue; Cardiology; Gray-scale; Image analysis; Image texture analysis; Myocardium; Neural networks; Signal analysis;
Journal_Title :
Engineering in Medicine and Biology Magazine, IEEE
