Display options
Share it on

Sensors (Basel). 2016 Aug 13;16(8). doi: 10.3390/s16081288.

Hyperspectral Imaging Using Flexible Endoscopy for Laryngeal Cancer Detection.

Sensors (Basel, Switzerland)

Bianca Regeling, Boris Thies, Andreas O H Gerstner, Stephan Westermann, Nina A Müller, Jörg Bendix, Wiebke Laffers

Affiliations

  1. Laboratory for Climatology and Remote Sensing, Faculty of Geography, University of Marburg, Deutschhausstr. 12, Marburg 35032, Germany. [email protected].
  2. Laboratory for Climatology and Remote Sensing, Faculty of Geography, University of Marburg, Deutschhausstr. 12, Marburg 35032, Germany. [email protected].
  3. Klinikum Braunschweig, ENT-Clinic, Holwedestr. 16, Braunschweig 38118, Germany. [email protected].
  4. Department of Otorhinolaryngology/Head and Neck Surgery, University of Bonn, Sigmund-Freud-Str. 25, Bonn 53127, Germany. [email protected].
  5. Department of Otorhinolaryngology/Head and Neck Surgery, University of Bonn, Sigmund-Freud-Str. 25, Bonn 53127, Germany. [email protected].
  6. Laboratory for Climatology and Remote Sensing, Faculty of Geography, University of Marburg, Deutschhausstr. 12, Marburg 35032, Germany. [email protected].
  7. Department of Otorhinolaryngology/Head and Neck Surgery, University of Bonn, Sigmund-Freud-Str. 25, Bonn 53127, Germany. [email protected].

PMID: 27529255 PMCID: PMC5017453 DOI: 10.3390/s16081288

Abstract

Hyperspectral imaging (HSI) is increasingly gaining acceptance in the medical field. Up until now, HSI has been used in conjunction with rigid endoscopy to detect cancer in vivo. The logical next step is to pair HSI with flexible endoscopy, since it improves access to hard-to-reach areas. While the flexible endoscope's fiber optic cables provide the advantage of flexibility, they also introduce an interfering honeycomb-like pattern onto images. Due to the substantial impact this pattern has on locating cancerous tissue, it must be removed before the HS data can be further processed. Thereby, the loss of information is to minimize avoiding the suppression of small-area variations of pixel values. We have developed a system that uses flexible endoscopy to record HS cubes of the larynx and designed a special filtering technique to remove the honeycomb-like pattern with minimal loss of information. We have confirmed its feasibility by comparing it to conventional filtering techniques using an objective metric and by applying unsupervised and supervised classifications to raw and pre-processed HS cubes. Compared to conventional techniques, our method successfully removes the honeycomb-like pattern and considerably improves classification performance, while preserving image details.

Keywords: classification; flexible endoscopy; honeycomb-like pattern removal; laryngeal cancer detection

References

  1. Int J Comput Assist Radiol Surg. 2014 Nov;9(6):1059-72 - PubMed
  2. J Biophotonics. 2016 Mar;9(3):235-45 - PubMed
  3. Burns. 2015 Feb;41(1):118-24 - PubMed
  4. J Biophotonics. 2011 Aug;4(7-8):565-76 - PubMed
  5. J Biomed Opt. 2013 Feb;18(2):26010 - PubMed
  6. CA Cancer J Clin. 2005 Mar-Apr;55(2):74-108 - PubMed
  7. Eur Arch Otorhinolaryngol. 2009 Jul;266(7):1017-23 - PubMed
  8. Cancer Sci. 2011 Apr;102(4):852-7 - PubMed
  9. Opt Express. 2006 Sep 18;14(19):8675-84 - PubMed
  10. Nat Methods. 2012 Jul;9(7):671-5 - PubMed
  11. Int J Health Geogr. 2012 Jun 21;11:21 - PubMed
  12. Sensors (Basel). 2012;12(1):162-74 - PubMed
  13. J Biophotonics. 2012 Mar;5(3):255-62 - PubMed
  14. J Biomed Opt. 2014 Jan;19(1):10901 - PubMed
  15. Comput Biol Med. 2015 Feb;57:173-81 - PubMed
  16. IEEE Trans Biomed Eng. 2006 Oct;53(10):2035-46 - PubMed

MeSH terms

Publication Types