Decision fusion for temporal prediction of respiratory liver motion

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

doi:10.1109/ISBI.2014.6867966

Decision fusion for temporal prediction of respiratory liver motion

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

Biomedical Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-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 language	English
Title of host publication	2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014, April 29-May 2, 2014, Beijing, China
Place of Publication	Piscataway
Publisher	Institute of Electrical and Electronics Engineers
Pages	698-701
Number of pages	4
ISBN (Print)	978-1-4673-1959-1
DOIs	https://doi.org/10.1109/ISBI.2014.6867966
Publication status	Published - 29 Jul 2014
Event	11th IEEE International Symposium on Biomedical Imaging (ISBI 2014) - Renaissance Beijing Capital Hotel, Beijing, China Duration: 29 Apr 2014 → 2 May 2014 Conference number: 11 http://biomedicalimaging.org/2014/

Conference

Conference	11th IEEE International Symposium on Biomedical Imaging (ISBI 2014)
Abbreviated title	ISBI 2014
Country	China
City	Beijing
Period	29/04/14 → 2/05/14
Internet address	http://biomedicalimaging.org/2014/

Keywords

Decision fusion
Image-guided therapy
Liver
Respiratory motion
Temporal prediction

Access to Document

10.1109/ISBI.2014.6867966

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

Cite this

@inproceedings{4fd00871d4c944e79aa041b8f1d80b77,

title = "Decision fusion for temporal prediction of respiratory liver motion",

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.",

keywords = "Decision fusion, Image-guided therapy, Liver, Respiratory motion, Temporal prediction",

author = "C. Tanner and K. Eppenhof and J. Gelderblom and G. Sz{\'e}kely",

year = "2014",

month = jul,

day = "29",

doi = "10.1109/ISBI.2014.6867966",

language = "English",

isbn = "978-1-4673-1959-1",

pages = "698--701",

booktitle = "2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014, April 29-May 2, 2014, Beijing, China",

publisher = "Institute of Electrical and Electronics Engineers",

address = "United States",

note = "11th IEEE International Symposium on Biomedical Imaging (ISBI 2014), ISBI 2014 ; Conference date: 29-04-2014 Through 02-05-2014",

url = "http://biomedicalimaging.org/2014/",

}

Tanner, C, Eppenhof, K, Gelderblom, J & Székely, G 2014, Decision fusion for temporal prediction of respiratory liver motion. in 2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014, April 29-May 2, 2014, Beijing, China., 6867966, Institute of Electrical and Electronics Engineers, Piscataway, pp. 698-701, 11th IEEE International Symposium on Biomedical Imaging (ISBI 2014), Beijing, China, 29/04/14. https://doi.org/10.1109/ISBI.2014.6867966

Decision fusion for temporal prediction of respiratory liver motion. / Tanner, C.; Eppenhof, K.; Gelderblom, J.; Székely, G.

2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014, April 29-May 2, 2014, Beijing, China. Piscataway : Institute of Electrical and Electronics Engineers, 2014. p. 698-701 6867966.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Decision fusion for temporal prediction of respiratory liver motion

AU - Tanner, C.

AU - Eppenhof, K.

AU - Gelderblom, J.

AU - Székely, G.

N1 - Conference code: 11

PY - 2014/7/29

Y1 - 2014/7/29

N2 - 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.

AB - 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.

KW - Decision fusion

KW - Image-guided therapy

KW - Liver

KW - Respiratory motion

KW - Temporal prediction

UR - http://www.scopus.com/inward/record.url?scp=84927939265&partnerID=8YFLogxK

U2 - 10.1109/ISBI.2014.6867966

DO - 10.1109/ISBI.2014.6867966

M3 - Conference contribution

AN - SCOPUS:84927939265

SN - 978-1-4673-1959-1

SP - 698

EP - 701

BT - 2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014, April 29-May 2, 2014, Beijing, China

PB - Institute of Electrical and Electronics Engineers

CY - Piscataway

T2 - 11th IEEE International Symposium on Biomedical Imaging (ISBI 2014)

Y2 - 29 April 2014 through 2 May 2014

ER -

Decision fusion for temporal prediction of respiratory liver motion

Abstract

Conference

Keywords

Access to Document

Other files and links

Cite this