SPASM: A 3D-ASM for segmentation of sparse and arbitrarily oriented cardiac MRI data Export

@article{citeulike:504049, abstract = {A new technique (SPASM) based on a 3D-ASM is presented for automatic segmentation of cardiac MRI image data sets consisting of multiple planes with arbitrary orientations, and with large undersampled regions. Model landmark positions are updated in a two-stage iterative process. First, landmark positions close to intersections with images are updated. Second, the update information is propagated to the regions without image information, such that new locations for the whole set of the model landmarks are obtained. Feature point detection is performed by a fuzzy inference system, based on fuzzy C-means clustering. Model parameters were optimized on a computer cluster and the computational load distributed by grid computing. SPASM was applied to image data sets with an increasing sparsity (from 2 to 11 slices) comprising images with different orientations and stemming from different MRI acquisition protocols.Segmentation outcomes and calculated volumes were compared to manual segmentation on a dense short-axis data configuration in a 3D manner. For all data configurations, (sub-)pixel accuracy was achieved. Performance differences between data configurations were significantly different (p < 0.05) for SA data sets with less than 6 slices, but not clinically relevant (volume differences < 4 ml). Comparison to results from other 3D model-based methods showed that SPASM performs comparable to or better than these other methods, but SPASM uses considerably less image data. Sensitivity to initial model placement proved to be limited within a range of position perturbations of approximately 20 mm in all directions.}, author = {van Assen, Hans C. and Danilouchkine, Mikhail G. and Frangi, Alejandro F. and Ordas, Sebastian and Westenberg, Jos J. and Reiber, Johan H. and Lelieveldt, Boudewijn P.}, citeulike-article-id = {504049}, citeulike-linkout-0 = {http://dx.doi.org/10.1016/j.media.2005.12.001}, citeulike-linkout-1 = {http://www.sciencedirect.com/science/article/B6W6Y-4J3WSNT-1/2/c37d802d83d1908bed5535c7faab5086}, doi = {10.1016/j.media.2005.12.001}, journal = {Medical Image Analysis}, keywords = {asm, cardiac, data, mri, segmentation, sparse}, month = {April}, number = {2}, pages = {286--303}, posted-at = {2006-02-18 02:58:47}, priority = {5}, title = {SPASM: A 3D-ASM for segmentation of sparse and arbitrarily oriented cardiac MRI data}, url = {http://dx.doi.org/10.1016/j.media.2005.12.001}, volume = {10}, year = {2006} }

TY - JOUR ID - citeulike:504049 L3 - citeulike-article-id:504049 N2 - A new technique (SPASM) based on a 3D-ASM is presented for automatic segmentation of cardiac MRI image data sets consisting of multiple planes with arbitrary orientations, and with large undersampled regions. Model landmark positions are updated in a two-stage iterative process. First, landmark positions close to intersections with images are updated. Second, the update information is propagated to the regions without image information, such that new locations for the whole set of the model landmarks are obtained. Feature point detection is performed by a fuzzy inference system, based on fuzzy C-means clustering. Model parameters were optimized on a computer cluster and the computational load distributed by grid computing. SPASM was applied to image data sets with an increasing sparsity (from 2 to 11 slices) comprising images with different orientations and stemming from different MRI acquisition protocols.Segmentation outcomes and calculated volumes were compared to manual segmentation on a dense short-axis data configuration in a 3D manner. For all data configurations, (sub-)pixel accuracy was achieved. Performance differences between data configurations were significantly different (p < 0.05) for SA data sets with less than 6 slices, but not clinically relevant (volume differences < 4 ml). Comparison to results from other 3D model-based methods showed that SPASM performs comparable to or better than these other methods, but SPASM uses considerably less image data. Sensitivity to initial model placement proved to be limited within a range of position perturbations of approximately 20 mm in all directions. IS - 2 JF - Medical Image Analysis EP - 303 TI - SPASM: A 3D-ASM for segmentation of sparse and arbitrarily oriented cardiac MRI data VL - 10 SP - 286 KW - asm KW - cardiac KW - data KW - mri KW - segmentation KW - sparse AU - van Assen, Hans AU - Danilouchkine, Mikhail AU - Frangi, Alejandro AU - Ordas, Sebastian AU - Westenberg, Jos AU - Reiber, Johan AU - Lelieveldt, Boudewijn PY - 2006/04// UR - http://dx.doi.org/10.1016/j.media.2005.12.001 ER -