Automatic image contrast enhancement method for liver vasculature detection

This paper presents an automatic method for image contrast enhancement necessary as a preprocessing step during vasculature detection in medical images. The method takes as input two volumetric images: one containing the original data from a computed tomography (CT) study and the other one containing segmented liver as a binary mask. The aim of the method is to enhance the contrast in the original image based on blood vessels intensities found in the organ defined by the provided mask. The methodology employs Frangi's vesselness filter and the analysis of maximal intensity projection (MIP) images to calculate the parameters of contrast enhancing function. The algorithm has been evaluated on 40 CT datasets containing liver studies in the portal phase and is being tested as a preprocessing step for automatic liver vasculature detection method being developed for a minimally-invasive liver surgery planning computer system.