Sphere Extraction in MR Images with Application to Whole-Body MRI

Recent technological advances in magnetic resonance imaging (MRI) lead to shorter acquisition times and consequently make it an interesting whole-body imaging modality. The acquisition time can further be reduced by acquiring images with a large field-of-view (FOV), making less scan stations necessary. Images with a large FOV are however disrupted by severe geometric distortion artifacts, which become more pronounced closer to the boundaries. Also the current trend in MRI, towards shorter and wider bore magnets, makes the images more prone to geometric distortion. In a previous work, 4 we proposed a method to correct for those artifacts using simultaneous deformable registration. In the future, we would like to integrate previous knowledge about the distortion field into the process. For this purpose we scan a specifically designed phantom consisting of small spheres arranged in a cube. In this article, we focus on the automatic extraction of the centers of the spheres, wherein we are particularly interested, for the calculation of the distortion field. The extraction is not trivial because of the significant intensity inhomogeneity within the images. We propose to use the local phase for the extraction purposes. The phase has the advantage that it provides structural information invariant to intensity. We use the monogenic signal to calculate the phase. Subsequently, we once apply a Hough transform and once a direct maxima search, to detect the centers. Moreover, we use a gradient and variance based approach for the radius estimation. We performed our extraction on several phantom scans and obtained good results.