Decision fusion for temporal prediction of respiratory liver motion

C. Tanner, K. Eppenhof, J. Gelderblom, G. Székely

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

5 Citations (Scopus)
3 Downloads (Pure)

Abstract

Temporal prediction of respiratory motion is required due to the latencies in image-guided therapy systems. In this study we propose to combine the outcome of four temporal prediction methods, which have different strength and weaknesses, by taking their median. Based on 25 motion traces from ultrasound liver tracking, this decision fusion provided statistically significantly better results than the individual outcomes for latencies from 150 to 1000ms. On average, RMS errors reduced by at least 50% in comparison to assuming no motion for all latencies. Furthermore it was shown that time-intensive optimization of the methods parameters to individual cases was not required, as performance from using the median parameters from the population was not significantly worse when using decision fusion.

Original languageEnglish
Title of host publication2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014, April 29-May 2, 2014, Beijing, China
Place of PublicationPiscataway
PublisherInstitute of Electrical and Electronics Engineers
Pages698-701
Number of pages4
ISBN (Print)978-1-4673-1959-1
DOIs
Publication statusPublished - 29 Jul 2014
Event11th IEEE International Symposium on Biomedical Imaging (ISBI 2014) - Renaissance Beijing Capital Hotel, Beijing, China
Duration: 29 Apr 20142 May 2014
Conference number: 11
http://biomedicalimaging.org/2014/

Conference

Conference11th IEEE International Symposium on Biomedical Imaging (ISBI 2014)
Abbreviated titleISBI 2014
CountryChina
CityBeijing
Period29/04/142/05/14
Internet address

Keywords

  • Decision fusion
  • Image-guided therapy
  • Liver
  • Respiratory motion
  • Temporal prediction

Fingerprint Dive into the research topics of 'Decision fusion for temporal prediction of respiratory liver motion'. Together they form a unique fingerprint.

Cite this