Magnetic resonance in medicine : official journal of the Society of Magnetic Resonance in Medicine
-
Eddy-current (EC) and motion effects in diffusion-tensor imaging (DTI) bias the estimation of quantitative diffusion indices, such as the fractional anisotropy. Both effects can be retrospectively corrected by registering the strongly distorted diffusion-weighted images to less-distorted T2-weighted images acquired without diffusion weighting. Two different affine spatial transformations are usually employed for this correction: slicewise and whole-brain transformations. ⋯ Using this model, it is demonstrated that a more distinct evaluation of the whole-brain EC effects is possible if the through-plane distortion was considered in addition to the well-known in-plane distortions. Moreover, a comparison of different whole-brain registrations relative to a slicewise approach is performed, in terms of the relative tensor error. Our findings suggest that for appropriate intersubject comparison of DTI data, a whole-brain registration containing nine affine parameters provides comparable performance (between 0 and 3%) to slicewise methods and can be performed in a fraction of the time.
-
Dynamic susceptibility contrast magnetic resonance perfusion imaging (DSC-MRI) is a useful method to characterize gliomas. Recently, support vector machines (SVMs) have been introduced as means to prospectively characterize new patients based on information from previous patients. Based on features derived from automatically segmented tumor volumes from 101 DSC-MR examinations, four different SVM models were compared. ⋯ A correct prediction of low-grade glioma was obtained at 83% (true positive rate) and for high-grade glioma at 91% (true negative rate) on the independent test data set. In conclusion, the combination of automated tumor segmentation followed by SVM classification is feasible. Thereby, a powerful tool is available to characterize glioma presurgically in patients.