Efficient and generalizable statistical models of shape and appearance for analysis of cardiac MRI Export

@article{citeulike:3544962, abstract = {We present a framework for the analysis of short axis cardiac MRI, using statistical models of shape and appearance. The framework integrates temporal and structural constraints and avoids common optimization problems inherent in such high dimensional models. The first contribution is the introduction of an algorithm for fitting 3D active appearance models (AAMs) on short axis cardiac MRI. We observe a 44-fold increase in fitting speed and a segmentation accuracy that is on par with Gauss\&\#x2013;Newton optimization, one of the most widely used optimization algorithms for such problems. The second contribution involves an investigation on hierarchical 2D\ +\ time active shape models (ASMs), that integrate temporal constraints and simultaneously improve the 3D AAM based segmentation. We obtain encouraging results (endocardial/epicardial error 1.43\ \&\#xb1;\ 0.49\ mm/1.51\ \&\#xb1;\ 0.48\ mm) on 7980 short axis cardiac MR images acquired from 33 subjects. We have placed our dataset online, for the community to use and build upon.}, author = {Andreopoulos, A. and Tsotsos, J.}, citeulike-article-id = {3544962}, citeulike-linkout-0 = {http://dx.doi.org/10.1016/j.media.2007.12.003}, citeulike-linkout-1 = {http://linkinghub.elsevier.com/retrieve/pii/S1361841508000029}, doi = {10.1016/j.media.2007.12.003}, issn = {13618415}, journal = {Medical Image Analysis}, keywords = {aam, asm, cardiac, mri, registration, segmentation}, month = {June}, number = {3}, pages = {335--357}, posted-at = {2008-11-16 23:07:49}, priority = {5}, title = {Efficient and generalizable statistical models of shape and appearance for analysis of cardiac MRI}, url = {http://dx.doi.org/10.1016/j.media.2007.12.003}, volume = {12}, year = {2008} }

TY - JOUR ID - citeulike:3544962 L3 - citeulike-article-id:3544962 N2 - We present a framework for the analysis of short axis cardiac MRI, using statistical models of shape and appearance. The framework integrates temporal and structural constraints and avoids common optimization problems inherent in such high dimensional models. The first contribution is the introduction of an algorithm for fitting 3D active appearance models (AAMs) on short axis cardiac MRI. We observe a 44-fold increase in fitting speed and a segmentation accuracy that is on par with Gauss–Newton optimization, one of the most widely used optimization algorithms for such problems. The second contribution involves an investigation on hierarchical 2D + time active shape models (ASMs), that integrate temporal constraints and simultaneously improve the 3D AAM based segmentation. We obtain encouraging results (endocardial/epicardial error 1.43 ± 0.49 mm/1.51 ± 0.48 mm) on 7980 short axis cardiac MR images acquired from 33 subjects. We have placed our dataset online, for the community to use and build upon. IS - 3 JF - Medical Image Analysis SN - 13618415 EP - 357 TI - Efficient and generalizable statistical models of shape and appearance for analysis of cardiac MRI VL - 12 SP - 335 KW - aam KW - asm KW - cardiac KW - mri KW - registration KW - segmentation AU - Andreopoulos, A AU - Tsotsos, J PY - 2008/06// UR - http://dx.doi.org/10.1016/j.media.2007.12.003 ER -