Correlating chest surface motion to motion of the liver using ε-SVR - A porcine study

Floris Ernst; Volker Martens; Stefan Schlichting; Armin Beširević; Markus Kleemann; Christoph Koch; Dirk Petersen; Achim Schweikard

doi:10.1007/978-3-642-04271-3_44

Correlating chest surface motion to motion of the liver using ε-SVR - A porcine study

Floris Ernst, Volker Martens, Stefan Schlichting, Armin Beširević, Markus Kleemann, Christoph Koch, Dirk Petersen, Achim Schweikard

Abstract

In robotic radiosurgery, the compensation of motion of internal organs is vital. This is currently done in two phases: an external surrogate signal (usually active optical markers placed on the patient's chest) is recorded and subsequently correlated to an internal motion signal obtained using stereoscopic X-ray imaging. This internal signal is sampled very infrequently to minimise the patient's exposure to radiation. We have investigated the correlation of the external signal to the motion of the liver in a porcine study using ε-support vector regression. IR LEDs were placed on the swines' chest. Gold fiducials were placed in the swines' livers and were recorded using a two-plane X-ray system. The results show that a very good correlation model can be built using ε-SVR, in this test clearly outperforming traditional polynomial models by at least 45 and as much as 74 %. Using multiple markers simultaneously can increase the new model's accuracy.

Original language	English
Title of host publication	MICCAI 2009: Medical Image Computing and Computer-Assisted Intervention – MICCAI 2009
Number of pages	9
Volume	5762 LNCS
Place of Publication	Berlin, Heidelberg
Publisher	Springer Verlag
Publication date	01.12.2009
Pages	356-364
ISBN (Print)	978-3-642-04270-6
ISBN (Electronic)	978-3-642-04271-3
DOIs	https://doi.org/10.1007/978-3-642-04271-3_44
Publication status	Published - 01.12.2009
Event	12th International Conference on Medical Image Computing and Computer-Assisted Intervention - London, United Kingdom Duration: 20.09.2009 → 24.09.2009 Conference number: 77822

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1007/978-3-642-04271-3_44

Cite this

Ernst, F., Martens, V., Schlichting, S., Beširević, A., Kleemann, M., Koch, C., Petersen, D., & Schweikard, A. (2009). Correlating chest surface motion to motion of the liver using ε-SVR - A porcine study. In MICCAI 2009: Medical Image Computing and Computer-Assisted Intervention – MICCAI 2009 (Vol. 5762 LNCS, pp. 356-364). (Lecture Notes in Computer Science; Vol. 5762 LNCS). Springer Verlag. https://doi.org/10.1007/978-3-642-04271-3_44

@inproceedings{8754d4975feb4708a3b0c80127245645,

title = "Correlating chest surface motion to motion of the liver using ε-SVR - A porcine study",

abstract = "In robotic radiosurgery, the compensation of motion of internal organs is vital. This is currently done in two phases: an external surrogate signal (usually active optical markers placed on the patient's chest) is recorded and subsequently correlated to an internal motion signal obtained using stereoscopic X-ray imaging. This internal signal is sampled very infrequently to minimise the patient's exposure to radiation. We have investigated the correlation of the external signal to the motion of the liver in a porcine study using ε-support vector regression. IR LEDs were placed on the swines' chest. Gold fiducials were placed in the swines' livers and were recorded using a two-plane X-ray system. The results show that a very good correlation model can be built using ε-SVR, in this test clearly outperforming traditional polynomial models by at least 45 and as much as 74 %. Using multiple markers simultaneously can increase the new model's accuracy.",

author = "Floris Ernst and Volker Martens and Stefan Schlichting and Armin Be{\v s}irevi{\'c} and Markus Kleemann and Christoph Koch and Dirk Petersen and Achim Schweikard",

year = "2009",

month = dec,

day = "1",

doi = "10.1007/978-3-642-04271-3_44",

language = "English",

isbn = "978-3-642-04270-6",

volume = "5762 LNCS",

series = "Lecture Notes in Computer Science",

publisher = "Springer Verlag",

pages = "356--364",

booktitle = "MICCAI 2009: Medical Image Computing and Computer-Assisted Intervention – MICCAI 2009",

note = "12th International Conference on Medical Image Computing and Computer-Assisted Intervention, MICCAI 2009 ; Conference date: 20-09-2009 Through 24-09-2009",

}

Ernst, F, Martens, V, Schlichting, S, Beširević, A, Kleemann, M, Koch, C, Petersen, D & Schweikard, A 2009, Correlating chest surface motion to motion of the liver using ε-SVR - A porcine study. in MICCAI 2009: Medical Image Computing and Computer-Assisted Intervention – MICCAI 2009 . vol. 5762 LNCS, Lecture Notes in Computer Science, vol. 5762 LNCS, Springer Verlag, Berlin, Heidelberg, pp. 356-364, 12th International Conference on Medical Image Computing and Computer-Assisted Intervention, London, United Kingdom, 20.09.09. https://doi.org/10.1007/978-3-642-04271-3_44

Correlating chest surface motion to motion of the liver using ε-SVR - A porcine study. / Ernst, Floris; Martens, Volker; Schlichting, Stefan et al.
MICCAI 2009: Medical Image Computing and Computer-Assisted Intervention – MICCAI 2009 . Vol. 5762 LNCS Berlin, Heidelberg: Springer Verlag, 2009. p. 356-364 (Lecture Notes in Computer Science; Vol. 5762 LNCS).

Research output: Chapters in Books/Reports/Conference Proceedings › Conference contribution › peer-review

TY - GEN

T1 - Correlating chest surface motion to motion of the liver using ε-SVR - A porcine study

AU - Ernst, Floris

AU - Martens, Volker

AU - Schlichting, Stefan

AU - Beširević, Armin

AU - Kleemann, Markus

AU - Koch, Christoph

AU - Petersen, Dirk

AU - Schweikard, Achim

N1 - Conference code: 77822

PY - 2009/12/1

Y1 - 2009/12/1

N2 - In robotic radiosurgery, the compensation of motion of internal organs is vital. This is currently done in two phases: an external surrogate signal (usually active optical markers placed on the patient's chest) is recorded and subsequently correlated to an internal motion signal obtained using stereoscopic X-ray imaging. This internal signal is sampled very infrequently to minimise the patient's exposure to radiation. We have investigated the correlation of the external signal to the motion of the liver in a porcine study using ε-support vector regression. IR LEDs were placed on the swines' chest. Gold fiducials were placed in the swines' livers and were recorded using a two-plane X-ray system. The results show that a very good correlation model can be built using ε-SVR, in this test clearly outperforming traditional polynomial models by at least 45 and as much as 74 %. Using multiple markers simultaneously can increase the new model's accuracy.

AB - In robotic radiosurgery, the compensation of motion of internal organs is vital. This is currently done in two phases: an external surrogate signal (usually active optical markers placed on the patient's chest) is recorded and subsequently correlated to an internal motion signal obtained using stereoscopic X-ray imaging. This internal signal is sampled very infrequently to minimise the patient's exposure to radiation. We have investigated the correlation of the external signal to the motion of the liver in a porcine study using ε-support vector regression. IR LEDs were placed on the swines' chest. Gold fiducials were placed in the swines' livers and were recorded using a two-plane X-ray system. The results show that a very good correlation model can be built using ε-SVR, in this test clearly outperforming traditional polynomial models by at least 45 and as much as 74 %. Using multiple markers simultaneously can increase the new model's accuracy.

UR - https://www.scopus.com/record/display.uri?eid=2-s2.0-77952277796&origin=inward&txGid=e48aa087f677f2489024c25cdf0d8c6f

U2 - 10.1007/978-3-642-04271-3_44

DO - 10.1007/978-3-642-04271-3_44

M3 - Conference contribution

SN - 978-3-642-04270-6

VL - 5762 LNCS

T3 - Lecture Notes in Computer Science

SP - 356

EP - 364

BT - MICCAI 2009: Medical Image Computing and Computer-Assisted Intervention – MICCAI 2009

PB - Springer Verlag

CY - Berlin, Heidelberg

T2 - 12th International Conference on Medical Image Computing and Computer-Assisted Intervention

Y2 - 20 September 2009 through 24 September 2009

ER -

Ernst F, Martens V, Schlichting S, Beširević A, Kleemann M, Koch C et al. Correlating chest surface motion to motion of the liver using ε-SVR - A porcine study. In MICCAI 2009: Medical Image Computing and Computer-Assisted Intervention – MICCAI 2009 . Vol. 5762 LNCS. Berlin, Heidelberg: Springer Verlag. 2009. p. 356-364. (Lecture Notes in Computer Science). doi: 10.1007/978-3-642-04271-3_44

Correlating chest surface motion to motion of the liver using ε-SVR - A porcine study

Abstract

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this