Shape-based MRI data segmentation in the presence of intensity inhomogeneities using level sets Export

@article{citeulike:373250, abstract = {Magnetic resonance imaging (MRI) intensity inhomogeneities can be attributed to imperfections in the RF coils or some problems associated with the acquisition sequences. The result is a slowly varying shading artifact over the image that can produce errors with conventional intensity-based classification. The removal of the spatial intensity inhomogeneities from MR images is difficult because the inhomogeneities could change with different MRI acquisition parameters from patient to patient and from slice to slice. We propose a shape-based classification technique to overcome this problem using the level set approach. A signed distance function is dedicated to describe the model of the tissue of interest. Then, a partial differential equation (PDE) is derived to describe the evolution of an observed structure. At each iteration, the observed structure is registered with the prior shape model. The algorithm is used at different levels of noise and intensity inhomogeneities showing a good accuracy.}, author = {Hassan, Hossam and Farag, Aly A.}, citeulike-article-id = {373250}, citeulike-linkout-0 = {http://dx.doi.org/10.1016/j.ics.2004.03.291}, citeulike-linkout-1 = {http://www.sciencedirect.com/science/article/B7581-4CHRSVD-1J/2/79a6ae357e91f133c4a79dc18377e2e7}, doi = {10.1016/j.ics.2004.03.291}, journal = {International Congress Series}, keywords = {artifacts, level-sets, medical-imaging, mri, segmentation}, month = {June}, pages = {213--218}, posted-at = {2005-10-31 13:04:20}, priority = {2}, title = {Shape-based MRI data segmentation in the presence of intensity inhomogeneities using level sets}, url = {http://dx.doi.org/10.1016/j.ics.2004.03.291}, volume = {1268}, year = {2004} }

TY - JOUR ID - citeulike:373250 L3 - citeulike-article-id:373250 N2 - Magnetic resonance imaging (MRI) intensity inhomogeneities can be attributed to imperfections in the RF coils or some problems associated with the acquisition sequences. The result is a slowly varying shading artifact over the image that can produce errors with conventional intensity-based classification. The removal of the spatial intensity inhomogeneities from MR images is difficult because the inhomogeneities could change with different MRI acquisition parameters from patient to patient and from slice to slice. We propose a shape-based classification technique to overcome this problem using the level set approach. A signed distance function is dedicated to describe the model of the tissue of interest. Then, a partial differential equation (PDE) is derived to describe the evolution of an observed structure. At each iteration, the observed structure is registered with the prior shape model. The algorithm is used at different levels of noise and intensity inhomogeneities showing a good accuracy. JF - International Congress Series EP - 218 TI - Shape-based MRI data segmentation in the presence of intensity inhomogeneities using level sets VL - 1268 SP - 213 KW - artifacts KW - level-sets KW - medical-imaging KW - mri KW - segmentation AU - Hassan, Hossam AU - Farag, Aly PY - 2004/06// UR - http://dx.doi.org/10.1016/j.ics.2004.03.291 ER -