Title: Renal DMSA scan morphology analysis using undecimated wavelet transform and isocontours

Authors: Ana Gavrovska; Milorad Paskaš; Vladimir Kovačević; Irini Reljin

Addresses: Department of Telecommunications, Faculty of Electrical Engineering, University of Belgrade, Serbia ' Department of Telecommunications, Faculty of Electrical Engineering, University of Belgrade, Serbia ' Department of Telecommunications, Faculty of Electrical Engineering, University of Belgrade, Serbia ' Department of Telecommunications, Faculty of Electrical Engineering, University of Belgrade, Serbia

Abstract: Signal and image processing tools open up opportunities to develop modules that can be interesting for supporting clinical decisions. In this paper, the aim is to develop an algorithm for providing better insight into renal scintigraphy scans using sparse transform such as discrete wavelet transform and isocontours. Renal 99mTc-DMSA scintigraphy scans are widely accepted as the most sensitive method for evaluating renal lesions and parenchymal damage like renal scars. An approach for improving DMSA scan analysis and regions of interest is presented from the aspect of visual inspection and relevant morphology information retrieval. For the purpose of testing archived scans are considered.

Keywords: DMSA scans; renal scintigraphy scans; UTIs; urinary tract infections; lesions; discrete wavelet transform; DWT; starlet transform; isocontours; boundaries; enhancement; watersheds; renal scans; kidneys; kidney morphology; renal lesions; parenchymal damage; renal scars; signal processing; image processing.

DOI: 10.1504/IJRIS.2013.055123

International Journal of Reasoning-based Intelligent Systems, 2013 Vol.5 No.1, pp.12 - 21

Published online: 17 Jul 2013 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article