DocumentCode :
3175052
Title :
Contour detection using artificial neuronal network pre-segmentation
Author :
Süssner, M. ; Budil, M. ; Strohmer, Th. ; Greher, M. ; Porenta, G. ; Binder, Th.
Author_Institution :
Div. of Neuronal Electron., Tech. Univ. Wien, Austria
fYear :
1995
fDate :
10-13 Sept. 1995
Firstpage :
737
Lastpage :
740
Abstract :
Visual analysis of two-dimensional echocardiograms is based on detection of the endocardial border to assess global and regional wall motion. Human experts rely on information from the spatial and time domain. The purpose of this study was to apply artificial neuronal networks (ANN) and to compute the endocardial border by using time domain information. The first processing step of this semiautomatic detection system is the segmentation by extracting the tissue region, which is computed by the ANN using local texture information. A human operator must interactively define the left ventricular (LV) center and a rectangular region of interest surrounding the LV-wall. Starting at the LV-center the algorithm searches for a transition from a "blood filled" to a "tissue" region in the segmented image and decides then the position of the contour point. Since lateral tissue information is sparse between end-systole and end-diastole the detected contour points can be transformed to intermediate images by applying correlation techniques. Thus sufficient endocardial contour points can be extracted to facilitate an efficient contour linking.
Keywords :
correlation methods; echocardiography; edge detection; image segmentation; image texture; medical image processing; neural nets; smoothing methods; time-domain analysis; ANN; LV wall; artificial neuronal network pre-segmentation; blood filled region; contour detection; contour point; correlation techniques; end-diastole; end-systole; endocardial border detection; endocardial contour points; global wall motion; human operator; lateral tissue information; left ventricular center; local texture information; rectangular region; regional wall motion; segmented image; semiautomatic detection system; spatial domain; time domain; tissue region; tissue region extraction; two-dimensional echocardiograms; visual analysis; Biological neural networks; Blood; Cardiology; Data mining; Humans; Image quality; Image segmentation; Joining processes; Myocardium; Ultrasonic imaging;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Computers in Cardiology 1995
Conference_Location :
Vienna, Austria
Print_ISBN :
0-7803-3053-6
Type :
conf
DOI :
10.1109/CIC.1995.482770
Filename :
482770
Link To Document :
بازگشت