Image-based navigation for a robotized flexible endoscope

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

4 Citations (Scopus)

Abstract

Robotizing flexible endoscopy enables image-based control of endoscopes. Especially during high-throughput procedures, such as a colonoscopy, navigation support algorithms could improve procedure turnaround and ergonomics for the endoscopist. In this study, we have developed and implemented a navigation algorithm that is based on image classification followed by dark region segmentation. Robustness and accuracy were evaluated on real images obtained from human colonoscopy exams. Comparison was done using manual annotation as a reference. Intraclass correlation (ICC) was employed as a measure for similarity between automated and manual results. The discrimination of the developed classifier was 6.8, making it a reliable classifier. In the experiments, the developed algorithm gave an ICC of 93 % (range 84.7–98.8 %) over the test image sequences on average. If images were classified as ‘uninformative’, which led to re-initialization of the algorithm, this was predictive for the result of dark region segmentation accuracy. In conclusion, the developed target detection algorithm provided accurate results and is thought to provide reliable assistance in the clinic. The clinical relevance of this kind of navigation and control is currently being investigated.
Original languageUndefined
Title of host publicationFirst International Workshop on Computer-Assisted and Robotic Endoscopy, CARE 2014
EditorsXiongbiao Luo, Tobias Reichl, Daniel Mirota, Timothy Soper
Place of PublicationSwitzerland
PublisherSpringer
Pages77-87
Number of pages11
ISBN (Print)978-3-319-13409-3
DOIs
Publication statusPublished - 1 Dec 2014

Publication series

NameLecture Notes in Computer Science
PublisherSpringer International Publishing
Volume8899
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Keywords

  • robotized endoscopy
  • EWI-25304
  • image classification
  • METIS-309661
  • Flexible endoscopy
  • Image-based navigation
  • IR-93014

Cite this

van der Stap, N., Slump, C. H., Broeders, I. A. M. J., & van der Heijden, F. (2014). Image-based navigation for a robotized flexible endoscope. In X. Luo, T. Reichl, D. Mirota, & T. Soper (Eds.), First International Workshop on Computer-Assisted and Robotic Endoscopy, CARE 2014 (pp. 77-87). (Lecture Notes in Computer Science; Vol. 8899). Switzerland: Springer. https://doi.org/10.1007/978-3-319-13410-9_8
van der Stap, N. ; Slump, Cornelis H. ; Broeders, Ivo Adriaan Maria Johannes ; van der Heijden, Ferdinand. / Image-based navigation for a robotized flexible endoscope. First International Workshop on Computer-Assisted and Robotic Endoscopy, CARE 2014. editor / Xiongbiao Luo ; Tobias Reichl ; Daniel Mirota ; Timothy Soper. Switzerland : Springer, 2014. pp. 77-87 (Lecture Notes in Computer Science).
@inproceedings{9e793f11df624c87b65e99a1c8e9aaa0,
title = "Image-based navigation for a robotized flexible endoscope",
abstract = "Robotizing flexible endoscopy enables image-based control of endoscopes. Especially during high-throughput procedures, such as a colonoscopy, navigation support algorithms could improve procedure turnaround and ergonomics for the endoscopist. In this study, we have developed and implemented a navigation algorithm that is based on image classification followed by dark region segmentation. Robustness and accuracy were evaluated on real images obtained from human colonoscopy exams. Comparison was done using manual annotation as a reference. Intraclass correlation (ICC) was employed as a measure for similarity between automated and manual results. The discrimination of the developed classifier was 6.8, making it a reliable classifier. In the experiments, the developed algorithm gave an ICC of 93 {\%} (range 84.7–98.8 {\%}) over the test image sequences on average. If images were classified as ‘uninformative’, which led to re-initialization of the algorithm, this was predictive for the result of dark region segmentation accuracy. In conclusion, the developed target detection algorithm provided accurate results and is thought to provide reliable assistance in the clinic. The clinical relevance of this kind of navigation and control is currently being investigated.",
keywords = "robotized endoscopy, EWI-25304, image classification, METIS-309661, Flexible endoscopy, Image-based navigation, IR-93014",
author = "{van der Stap}, N. and Slump, {Cornelis H.} and Broeders, {Ivo Adriaan Maria Johannes} and {van der Heijden}, Ferdinand",
note = "10.1007/978-3-319-13410-9_8",
year = "2014",
month = "12",
day = "1",
doi = "10.1007/978-3-319-13410-9_8",
language = "Undefined",
isbn = "978-3-319-13409-3",
series = "Lecture Notes in Computer Science",
publisher = "Springer",
pages = "77--87",
editor = "Xiongbiao Luo and Tobias Reichl and Daniel Mirota and Timothy Soper",
booktitle = "First International Workshop on Computer-Assisted and Robotic Endoscopy, CARE 2014",

}

van der Stap, N, Slump, CH, Broeders, IAMJ & van der Heijden, F 2014, Image-based navigation for a robotized flexible endoscope. in X Luo, T Reichl, D Mirota & T Soper (eds), First International Workshop on Computer-Assisted and Robotic Endoscopy, CARE 2014. Lecture Notes in Computer Science, vol. 8899, Springer, Switzerland, pp. 77-87. https://doi.org/10.1007/978-3-319-13410-9_8

Image-based navigation for a robotized flexible endoscope. / van der Stap, N.; Slump, Cornelis H.; Broeders, Ivo Adriaan Maria Johannes; van der Heijden, Ferdinand.

First International Workshop on Computer-Assisted and Robotic Endoscopy, CARE 2014. ed. / Xiongbiao Luo; Tobias Reichl; Daniel Mirota; Timothy Soper. Switzerland : Springer, 2014. p. 77-87 (Lecture Notes in Computer Science; Vol. 8899).

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

TY - GEN

T1 - Image-based navigation for a robotized flexible endoscope

AU - van der Stap, N.

AU - Slump, Cornelis H.

AU - Broeders, Ivo Adriaan Maria Johannes

AU - van der Heijden, Ferdinand

N1 - 10.1007/978-3-319-13410-9_8

PY - 2014/12/1

Y1 - 2014/12/1

N2 - Robotizing flexible endoscopy enables image-based control of endoscopes. Especially during high-throughput procedures, such as a colonoscopy, navigation support algorithms could improve procedure turnaround and ergonomics for the endoscopist. In this study, we have developed and implemented a navigation algorithm that is based on image classification followed by dark region segmentation. Robustness and accuracy were evaluated on real images obtained from human colonoscopy exams. Comparison was done using manual annotation as a reference. Intraclass correlation (ICC) was employed as a measure for similarity between automated and manual results. The discrimination of the developed classifier was 6.8, making it a reliable classifier. In the experiments, the developed algorithm gave an ICC of 93 % (range 84.7–98.8 %) over the test image sequences on average. If images were classified as ‘uninformative’, which led to re-initialization of the algorithm, this was predictive for the result of dark region segmentation accuracy. In conclusion, the developed target detection algorithm provided accurate results and is thought to provide reliable assistance in the clinic. The clinical relevance of this kind of navigation and control is currently being investigated.

AB - Robotizing flexible endoscopy enables image-based control of endoscopes. Especially during high-throughput procedures, such as a colonoscopy, navigation support algorithms could improve procedure turnaround and ergonomics for the endoscopist. In this study, we have developed and implemented a navigation algorithm that is based on image classification followed by dark region segmentation. Robustness and accuracy were evaluated on real images obtained from human colonoscopy exams. Comparison was done using manual annotation as a reference. Intraclass correlation (ICC) was employed as a measure for similarity between automated and manual results. The discrimination of the developed classifier was 6.8, making it a reliable classifier. In the experiments, the developed algorithm gave an ICC of 93 % (range 84.7–98.8 %) over the test image sequences on average. If images were classified as ‘uninformative’, which led to re-initialization of the algorithm, this was predictive for the result of dark region segmentation accuracy. In conclusion, the developed target detection algorithm provided accurate results and is thought to provide reliable assistance in the clinic. The clinical relevance of this kind of navigation and control is currently being investigated.

KW - robotized endoscopy

KW - EWI-25304

KW - image classification

KW - METIS-309661

KW - Flexible endoscopy

KW - Image-based navigation

KW - IR-93014

U2 - 10.1007/978-3-319-13410-9_8

DO - 10.1007/978-3-319-13410-9_8

M3 - Conference contribution

SN - 978-3-319-13409-3

T3 - Lecture Notes in Computer Science

SP - 77

EP - 87

BT - First International Workshop on Computer-Assisted and Robotic Endoscopy, CARE 2014

A2 - Luo, Xiongbiao

A2 - Reichl, Tobias

A2 - Mirota, Daniel

A2 - Soper, Timothy

PB - Springer

CY - Switzerland

ER -

van der Stap N, Slump CH, Broeders IAMJ, van der Heijden F. Image-based navigation for a robotized flexible endoscope. In Luo X, Reichl T, Mirota D, Soper T, editors, First International Workshop on Computer-Assisted and Robotic Endoscopy, CARE 2014. Switzerland: Springer. 2014. p. 77-87. (Lecture Notes in Computer Science). https://doi.org/10.1007/978-3-319-13410-9_8