Medical image analysis
-
Medical image analysis · Dec 2007
Correction of susceptibility artifacts in diffusion tensor data using non-linear registration.
Diffusion tensor imaging can be used to localize major white matter tracts within the human brain. For surgery of tumors near eloquent brain areas such as the pyramidal tract this information is of importance to achieve an optimal resection while avoiding post-operative neurological deficits. However, due to the small bandwidth of echo planar imaging, diffusion tensor images suffer from susceptibility artifacts resulting in positional shifts and distortion. ⋯ The effect of the correction on the pyramidal tract was then quantified by measuring the position of the tract before and after registration. As a result, the distortions observed in phase encoding direction were most prominent at the cortex and the brainstem. The presented approach allows correcting fiber tract distortions which is an important prerequisite when tractography data are integrated into a stereotactic setup for intra-operative guidance.
-
Medical image analysis · Dec 2007
Boundary element method-based regularization for recovering of LV deformation.
The quantification of left ventricular (LV) deformation from noninvasive image sequences is an important clinical problem. To date, feature information from either magnetic resonance (MR), computed tomographic (CT) or echocardiographic image data have been assembled with the help of different regularization models to estimate LV deformation. The currently available regularization models have tradeoffs related to accuracy, lattice density, physical plausibility and computation time. ⋯ The approach is evaluated on in vivo cardiac magnetic resonance image sequences. All results are compared to displacements found using implanted markers, taken to be a gold standard. The approach is also evaluated on the 4D real time echocardiographic image sequences and the results demonstrate that the approach is capable of tracking the LV deformation for echocardiography.
-
Medical image analysis · Oct 2007
Motion-compensated MR valve imaging with COMB tag tracking and super-resolution enhancement.
Understanding the morphology and function of heart valves is important to the study of underlying causes of heart failure. Existing techniques such as those based on echocardiography are limited by the relatively low signal-to-noise ratio (SNR), attenuation artefacts, and restricted access. The alternative of cardiovascular MR imaging offers versatility and accuracy in 3D localisation, but is hampered by large movements of the valves throughout the cardiac cycle. ⋯ In vivo results demonstrate the effectiveness of the proposed motion-compensation and super-resolution schemes for depicting the structure of the valve leaflets throughout the cardiac cycle. The proposed method fundamentally changes the way MR imaging is performed by transforming it from a spatially to materially localised imaging method. This also has important implications for quantifying blood flow and myocardial perfusion, as well as tracking anatomy and function of the heart.
-
Medical image analysis · Feb 2007
Hidden Markov multiple event sequence models: A paradigm for the spatio-temporal analysis of fMRI data.
This paper presents a novel, completely unsupervised fMRI brain mapping method that addresses the three problems of hemodynamic response function (HRF) variability, hemodynamic event timing, and fMRI response non-linearity. Spatial and temporal information are directly taken into account into the core of the activation detection process. ⋯ The multiple event sequence alignment problem is solved within the probabilistic framework of hidden Markov multiple event sequence models (HMMESMs), a new class of hidden Markov models. Results obtained on real and synthetic data significantly outperform those obtained with the popular statistical parametric mapping (SPM2) method without requiring any prior definition of the expected activation patterns, the HMMESM mapping approach being completely unsupervised.
-
Medical image analysis · Oct 2006
Adaptive Markov modeling for mutual-information-based, unsupervised MRI brain-tissue classification.
This paper presents a novel method for brain-tissue classification in magnetic resonance (MR) images that relies on a very general, adaptive statistical model of image neighborhoods. The method models MR-tissue intensities as derived from stationary random fields. It models the associated Markov statistics nonparametrically via a data-driven strategy. ⋯ It automatically tunes its important internal parameters based on the information content of the data. Combined with an atlas-based initialization, it is completely automatic. Experiments on real, simulated, and multimodal data demonstrate the advantages of the method over the current state-of-the-art.