DocumentCode :
2821394
Title :
Application of intelligent processing and 4-D deformation modeling to the detection of abnormal motion patterns
Author :
Stalidis, G. ; Maglaveras, N. ; Dimitriadis, A. ; Pappas, C.
Author_Institution :
Lab. of Med. Inf., Aristotelian Univ. of Thessaloniki, Greece
fYear :
2000
fDate :
2000
Firstpage :
699
Lastpage :
702
Abstract :
The study of cardiac motion through CINE MRI is an important non-invasive diagnostic tool for cardiac abnormalities. In this paper, a method for automatic detection of abnormal motion patterns is proposed to be used as a computerized diagnostic tool for pathologic cardiac function. A multi-scale modeling method, based on a Generating-Shrinking neural network and a 4-D surface parametric model were used to extract the deformation of the myocardium from multi slice-multi phase MRI examinations. A feature extraction procedure then calculated myocardial thickening and radial deformation of the left ventricle and produced a set of motion parameters from the surface model. Input patterns consisting of the above features were fed into a feedforward neural network, which was trained to capture the normal cardiac function and to distinguish certain pathologic motion patterns
Keywords :
biomechanics; biomedical MRI; cardiology; feature extraction; feedforward neural nets; image motion analysis; medical image processing; physiological models; 4-D deformation modeling; 4-D surface parametric model; CINE MRI; abnormal motion patterns detection; cardiac abnormalities; computerized diagnostic tool; feature extraction procedure; generating-shrinking neural network; input patterns; intelligent processing; left ventricle; magnetic resonance imaging; medical diagnostic imaging; motion parameters set; multiscale modeling method; multislice-multiphase MRI examinations; myocardial thickening; noninvasive diagnostic tool; normal cardiac function; pathologic cardiac function; pathologic motion patterns; radial deformation; surface model; Biomedical informatics; Data mining; Deformable models; Magnetic resonance imaging; Motion detection; Myocardium; Neural networks; Shape; Solid modeling; Thickness measurement;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Computers in Cardiology 2000
Conference_Location :
Cambridge, MA
ISSN :
0276-6547
Print_ISBN :
0-7803-6557-7
Type :
conf
DOI :
10.1109/CIC.2000.898620
Filename :
898620
Link To Document :
بازگشت