Pyramidal multiresolution image segmentation in SPECT

Author

Erdi, Y. ; Loew, M. ; Erdi, A. ; Wessels, B.

Author_Institution

George Washington Univ., Washington, DC, USA

fYear

1994

fDate

3-6 Nov 1994

Firstpage

694

Abstract

A median filtered pyramidal multiresolution (MFPM) image segmentation method for detecting and delineating compact objects was applied to single-photon emission computed tomography (SPECT) images. These SPECT images were obtained by scanning spheres from 1 to 54 ml in size and from 50% to 100% contrast settings. The algorithm performed accurately for large sphere (20 and 54 ml) and high contrast (90% and 100%) cases. As the size and contrast decrease, the accuracy of the method also decreases. Comparison of the MFPM method with adaptive thresholding with edge-preserving smoothing (ATEPS) indicated superior performance of the MFPM method

Keywords

image segmentation; medical image processing; object detection; single photon emission computed tomography; SPECT; edge-preserving smoothing; image contrast; medical diagnostic imaging; method accuracy; nuclear medicine; pyramidal multiresolution image segmentation; spheres; Biological systems; Biomedical imaging; Computed tomography; Image edge detection; Image resolution; Image segmentation; Imaging phantoms; Large-scale systems; Low pass filters; Object detection; Smoothing methods;

fLanguage

English

Publisher

ieee

Conference_Titel

Engineering in Medicine and Biology Society, 1994. Engineering Advances: New Opportunities for Biomedical Engineers. Proceedings of the 16th Annual International Conference of the IEEE

Conference_Location

Baltimore, MD

Print_ISBN

0-7803-2050-6

Type

conf

DOI

10.1109/IEMBS.1994.411866

Filename

411866