3D non-linear invisible boundary detection filters

Abstract

The human vision system can discriminate regions which differ up to the second order statistics only. A lot of malignant tumours have boundaries which are not visible to the human eye. We present an algorithm designed to reveal "hidden" boundaries in grey level images, by computing gradients in higher order statistics of the data. We demonstrate it by applying it to the identification of possible "hidden" boundaries of gliomas as manifest themselves in MRI 3D scans.