Abstract
We evaluate in this paper different strategies for the construction of a statistical shape model (SSM) of the left ventricle (LV) to be used for segmentation in cardiac magnetic resonance (CMR) images. From a large database of LV surfaces obtained throughout the cardiac cycle from 3D echocardiographic (3DE) LV images, different LV shape models were built by varying the considered phase in the cardiac cycle and the registration procedure employed for surface alignment. Principal component analysis was computed to describe the statistical variability of the SSMs, which were then deformed by applying an active shape model (ASM) approach to segment the LV endocardium in CMR images of 45 patients. Segmentation performance was evaluated by comparing LV volumes derived by ASM segmentation with different SSMs and those obtained by manual tracing, considered as a reference. A high correlation (r2 >0.92) was found in all cases, with better results when using the SSM models comprising more than one frame of the cardiac cycle.
| Original language | English |
|---|---|
| Journal | Journal of Electrocardiology |
| DOIs | |
| Publication status | Accepted/In press - 2016 |
Fingerprint
Keywords
- Cardiac MRI
- Image segmentation
- Left ventricular volume
- Statistical shape model
ASJC Scopus subject areas
- Cardiology and Cardiovascular Medicine
Cite this
Segmentation of the left ventricular endocardium from magnetic resonance images by using different statistical shape models. / Piazzese, Concetta; Carminati, M. Chiara; Colombo, Andrea; Krause, Rolf; Potse, Mark; Auricchio, Angelo; Weinert, Lynn; Tamborini, Gloria; Pepi, Mauro; Lang, Roberto M.; Caiani, Enrico G.
In: Journal of Electrocardiology, 2016.Research output: Contribution to journal › Article
}
TY - JOUR
T1 - Segmentation of the left ventricular endocardium from magnetic resonance images by using different statistical shape models
AU - Piazzese, Concetta
AU - Carminati, M. Chiara
AU - Colombo, Andrea
AU - Krause, Rolf
AU - Potse, Mark
AU - Auricchio, Angelo
AU - Weinert, Lynn
AU - Tamborini, Gloria
AU - Pepi, Mauro
AU - Lang, Roberto M.
AU - Caiani, Enrico G.
PY - 2016
Y1 - 2016
N2 - We evaluate in this paper different strategies for the construction of a statistical shape model (SSM) of the left ventricle (LV) to be used for segmentation in cardiac magnetic resonance (CMR) images. From a large database of LV surfaces obtained throughout the cardiac cycle from 3D echocardiographic (3DE) LV images, different LV shape models were built by varying the considered phase in the cardiac cycle and the registration procedure employed for surface alignment. Principal component analysis was computed to describe the statistical variability of the SSMs, which were then deformed by applying an active shape model (ASM) approach to segment the LV endocardium in CMR images of 45 patients. Segmentation performance was evaluated by comparing LV volumes derived by ASM segmentation with different SSMs and those obtained by manual tracing, considered as a reference. A high correlation (r2 >0.92) was found in all cases, with better results when using the SSM models comprising more than one frame of the cardiac cycle.
AB - We evaluate in this paper different strategies for the construction of a statistical shape model (SSM) of the left ventricle (LV) to be used for segmentation in cardiac magnetic resonance (CMR) images. From a large database of LV surfaces obtained throughout the cardiac cycle from 3D echocardiographic (3DE) LV images, different LV shape models were built by varying the considered phase in the cardiac cycle and the registration procedure employed for surface alignment. Principal component analysis was computed to describe the statistical variability of the SSMs, which were then deformed by applying an active shape model (ASM) approach to segment the LV endocardium in CMR images of 45 patients. Segmentation performance was evaluated by comparing LV volumes derived by ASM segmentation with different SSMs and those obtained by manual tracing, considered as a reference. A high correlation (r2 >0.92) was found in all cases, with better results when using the SSM models comprising more than one frame of the cardiac cycle.
KW - Cardiac MRI
KW - Image segmentation
KW - Left ventricular volume
KW - Statistical shape model
UR - http://www.scopus.com/inward/record.url?scp=84961910437&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84961910437&partnerID=8YFLogxK
U2 - 10.1016/j.jelectrocard.2016.03.017
DO - 10.1016/j.jelectrocard.2016.03.017
M3 - Article
AN - SCOPUS:84961910437
JO - Journal of Electrocardiology
JF - Journal of Electrocardiology
SN - 0022-0736
ER -