Segmentation of Liver Region based on Multifractal Analysis

Authors

  • K. Bartnykas Vilnius Gediminas Technical University

Abstract

Multifractal analysis is suggested to solve the liver region segmentation problem from CT scans. It is claimed that image contrast enhancement should be taken as a preprocessing step. It is shown that this ensures more exact reproduction of multifractal spectrum. According to the dice similarity coefficient the liver region segmentation results evaluated are limited in range with the start value 75.8 % and the end value 97.5 %. These results coincide with achievements in this research area published by the other scientists. This suggests that multifractal analysis can be valuable tool to segment the liver region from CT scans. Ill. 4, bibl. 8 (in English; summaries in English, Russian and Lithuanian).

Downloads

Published

2010-01-26

How to Cite

Bartnykas, K. (2010). Segmentation of Liver Region based on Multifractal Analysis. Elektronika Ir Elektrotechnika, 98(2), 79-82. Retrieved from https://eejournal.ktu.lt/index.php/elt/article/view/9932

Issue

Section

T 125 AUTOMATION, ROBOTICS