Meeting Banner
Abstract #0695

Optimal Enhancement of Brain Structures by Combining Different MR Contrasts: Demonstration of Venous Vessel Enhancement in Multi-Echo Gradient-Echo MRI

Andreas Deistung1, Ferdinand Schweser2, Jrgen R. Reichenbach2

1Medical Physics Group, Institute of Diagnostic and Interventional Radiology I, Jena University Hospital - Friedrich Schiller University Jena, Jena, Germany; 2Medical Physics Group, Institute of Diagnostic and Interventional Radiology I, Jena University Hospital - Friedrich Schiller University, Jena, Germany

We present a supervised approach for creating image contrast that enhances specific structures of interest. To this end, we apply linear discriminant analysis (LDA) to optimally combine multiple image contrasts generated from complex-valued multi-echo GRE information (magnetic susceptibility, R2*, and S0) to create a novel contrast with increased cerebral venous vessel contrast. This approach can easily be adjusted to emphasize other tissue properties by changing the definition of classes in the training step.

Keywords

according accurate accurately acquisition additional adjusted allowed although ambiguous apparent applied approaches around arrow arrows arteries assigned audience axis background black blue brain central cerebral characterized class classes classifier combination combined combining complex composite computing considerable considered content contours contrast contrasts contributions cortical creating decay decreased deep delineation dependence depends derived deviation deviations diagnostic diffusion dimensional dipole discriminant discrimination displayed distance distribution drawback dual ease eliminated employed enhance enhancement established evaluated evaluation exponential features field filtering fissure fluid frontal generated generation gradient gray healthy hemispheric heuristic immediately improved incorporating incremental indicate intensity inter inversion inverted john just lesions linear magnitude majority maps neural noise novel optimal particular plotted processing projects quantitative radiology recalled recognition reduce reflected remaining respect respectively scanner segmentation separation sets sharp sinus slight sons space step structures subject subjects subscripts susceptibilities susceptibility target throughout tissue today training transverse vectors vein veins venous vessel visualization volunteers white yield yielded