DocumentCode :
409578
Title :
Vertical coherence applied to SPECT imagery in the 3D reconstruction of the left ventricle
Author :
Garcia-Panyella, O. ; Susin, A.
Author_Institution :
La Salle Sch. of Eng., Barcelona, Spain
fYear :
2003
fDate :
21-24 Sept. 2003
Firstpage :
753
Lastpage :
756
Abstract :
As we already presented in the previous edition of the conference, our algorithm uses SPECT data to automatically recover the three-dimensional shape of the human´s left ventricle. The reconstruction of both the internal and external surfaces, allowed us to present the synthetic cardiac cycle for an actual patient and derive its associated ejection fraction estimation. The segmentation module has been improved in order to provide a better and robust border detection and classification. Now the filtering process is based on the maximum-likelihood classification approach (MLC), which rewards an edge depending on its probability to be a part of the left ventricle. The algorithm also takes into account vertical coherence between slices that improves the inputs adding information on the 3D shape. In terms of practical results, we test all these new features against several left-ventricle reconstructions applied to actual pathological hearts.
Keywords :
cardiovascular system; edge detection; filtering theory; image classification; image reconstruction; image segmentation; maximum likelihood detection; maximum likelihood estimation; medical image processing; single photon emission computed tomography; SPECT imagery; ejection fraction estimation; filtering process; left ventricle 3D reconstruction; maximum-likelihood classification approach; pathological hearts; robust border detection; segmentation module; synthetic cardiac cycle; vertical coherence; Filtering; Heart; Image reconstruction; Maximum likelihood detection; Maximum likelihood estimation; Pathology; Robustness; Shape; Surface reconstruction; Testing;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Computers in Cardiology, 2003
ISSN :
0276-6547
Print_ISBN :
0-7803-8170-X
Type :
conf
DOI :
10.1109/CIC.2003.1291265
Filename :
1291265
Link To Document :
بازگشت