Automated spectroscopic tissue classification in colorectal surgery

Rutger M. Schols, Lejla Alic, Geerard L. Beets, Stéphanie O. Breukink, Fokko P. Wieringa, Laurents P.S. Stassen

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

Background. In colorectal surgery, detecting ureters and mesenteric arteries is of utmost importance to prevent iatrogenic injury and to facilitate intraoperative decision making. A tool enabling ureter- and artery-specific image enhancement within (and possibly through) surrounding adipose tissue would facilitate this need, especially during laparoscopy. To evaluate the potential of hyperspectral imaging in colorectal surgery, we explored spectral tissue signatures using single-spot diffuse reflectance spectroscopy (DRS). As hyperspectral cameras with silicon (Si) and indium gallium arsenide (InGaAs) sensor chips are becoming available, we investigated spectral distinctive features for both sensor ranges. Methods. In vivo wide-band (wavelength range 350-1830 nm) DRS was performed during open colorectal surgery. From the recorded spectra, 36 features were extracted at predefined wavelengths: 18 gradients and 18 amplitude differences. For classification of respectively ureter and artery in relation to surrounding adipose tissue, the best distinctive feature was selected using binary logistic regression for Si- and InGaAs-sensor spectral ranges separately. Classification performance was evaluated by leave-one-out cross-validation. Results. In 10 consecutive patients, 253 spectra were recorded on 53 tissue sites (including colon, adipose tissue, muscle, artery, vein, ureter). Classification of ureter versus adipose tissue revealed accuracy of 100% for both Si range and InGaAs range. Classification of artery versus surrounding adipose tissue revealed accuracies of 95% (Si) and 89% (InGaAs). Conclusions. Intraoperative DRS showed that Si and InGaAs sensors are equally suited for automated classification of ureter versus surrounding adipose tissue. Si sensors seem better suited for classifying artery versus mesenteric adipose tissue. Progress toward hyperspectral imaging within this field is promising.

Original languageEnglish
Pages (from-to)557-567
Number of pages11
JournalSurgical Innovation
Volume22
Issue number6
DOIs
Publication statusPublished - 1 Jan 2015
Externally publishedYes

Fingerprint

Colorectal Surgery
Silicon
Ureter
Adipose Tissue
Arteries
Spectrum Analysis
Mesenteric Arteries
Image Enhancement
Laparoscopy
Veins
Decision Making
Colon
Logistic Models
gallium arsenide
indium arsenide
Muscles
Wounds and Injuries

Keywords

  • adipose tissue
  • artery
  • automated tissue classification
  • colorectal surgery
  • diffuse reflectance spectroscopy
  • tissue spectral analysis
  • ureter

ASJC Scopus subject areas

  • Surgery

Cite this

Schols, R. M., Alic, L., Beets, G. L., Breukink, S. O., Wieringa, F. P., & Stassen, L. P. S. (2015). Automated spectroscopic tissue classification in colorectal surgery. Surgical Innovation, 22(6), 557-567. https://doi.org/10.1177/1553350615569076

Automated spectroscopic tissue classification in colorectal surgery. / Schols, Rutger M.; Alic, Lejla; Beets, Geerard L.; Breukink, Stéphanie O.; Wieringa, Fokko P.; Stassen, Laurents P.S.

In: Surgical Innovation, Vol. 22, No. 6, 01.01.2015, p. 557-567.

Research output: Contribution to journalArticle

Schols, RM, Alic, L, Beets, GL, Breukink, SO, Wieringa, FP & Stassen, LPS 2015, 'Automated spectroscopic tissue classification in colorectal surgery', Surgical Innovation, vol. 22, no. 6, pp. 557-567. https://doi.org/10.1177/1553350615569076
Schols RM, Alic L, Beets GL, Breukink SO, Wieringa FP, Stassen LPS. Automated spectroscopic tissue classification in colorectal surgery. Surgical Innovation. 2015 Jan 1;22(6):557-567. https://doi.org/10.1177/1553350615569076
Schols, Rutger M. ; Alic, Lejla ; Beets, Geerard L. ; Breukink, Stéphanie O. ; Wieringa, Fokko P. ; Stassen, Laurents P.S. / Automated spectroscopic tissue classification in colorectal surgery. In: Surgical Innovation. 2015 ; Vol. 22, No. 6. pp. 557-567.
@article{da86b7990b6246fbab0e1579b7d7c990,
title = "Automated spectroscopic tissue classification in colorectal surgery",
abstract = "Background. In colorectal surgery, detecting ureters and mesenteric arteries is of utmost importance to prevent iatrogenic injury and to facilitate intraoperative decision making. A tool enabling ureter- and artery-specific image enhancement within (and possibly through) surrounding adipose tissue would facilitate this need, especially during laparoscopy. To evaluate the potential of hyperspectral imaging in colorectal surgery, we explored spectral tissue signatures using single-spot diffuse reflectance spectroscopy (DRS). As hyperspectral cameras with silicon (Si) and indium gallium arsenide (InGaAs) sensor chips are becoming available, we investigated spectral distinctive features for both sensor ranges. Methods. In vivo wide-band (wavelength range 350-1830 nm) DRS was performed during open colorectal surgery. From the recorded spectra, 36 features were extracted at predefined wavelengths: 18 gradients and 18 amplitude differences. For classification of respectively ureter and artery in relation to surrounding adipose tissue, the best distinctive feature was selected using binary logistic regression for Si- and InGaAs-sensor spectral ranges separately. Classification performance was evaluated by leave-one-out cross-validation. Results. In 10 consecutive patients, 253 spectra were recorded on 53 tissue sites (including colon, adipose tissue, muscle, artery, vein, ureter). Classification of ureter versus adipose tissue revealed accuracy of 100{\%} for both Si range and InGaAs range. Classification of artery versus surrounding adipose tissue revealed accuracies of 95{\%} (Si) and 89{\%} (InGaAs). Conclusions. Intraoperative DRS showed that Si and InGaAs sensors are equally suited for automated classification of ureter versus surrounding adipose tissue. Si sensors seem better suited for classifying artery versus mesenteric adipose tissue. Progress toward hyperspectral imaging within this field is promising.",
keywords = "adipose tissue, artery, automated tissue classification, colorectal surgery, diffuse reflectance spectroscopy, tissue spectral analysis, ureter",
author = "Schols, {Rutger M.} and Lejla Alic and Beets, {Geerard L.} and Breukink, {St{\'e}phanie O.} and Wieringa, {Fokko P.} and Stassen, {Laurents P.S.}",
year = "2015",
month = "1",
day = "1",
doi = "10.1177/1553350615569076",
language = "English",
volume = "22",
pages = "557--567",
journal = "Surgical Innovation",
issn = "1553-3506",
publisher = "SAGE Publications Inc.",
number = "6",

}

TY - JOUR

T1 - Automated spectroscopic tissue classification in colorectal surgery

AU - Schols, Rutger M.

AU - Alic, Lejla

AU - Beets, Geerard L.

AU - Breukink, Stéphanie O.

AU - Wieringa, Fokko P.

AU - Stassen, Laurents P.S.

PY - 2015/1/1

Y1 - 2015/1/1

N2 - Background. In colorectal surgery, detecting ureters and mesenteric arteries is of utmost importance to prevent iatrogenic injury and to facilitate intraoperative decision making. A tool enabling ureter- and artery-specific image enhancement within (and possibly through) surrounding adipose tissue would facilitate this need, especially during laparoscopy. To evaluate the potential of hyperspectral imaging in colorectal surgery, we explored spectral tissue signatures using single-spot diffuse reflectance spectroscopy (DRS). As hyperspectral cameras with silicon (Si) and indium gallium arsenide (InGaAs) sensor chips are becoming available, we investigated spectral distinctive features for both sensor ranges. Methods. In vivo wide-band (wavelength range 350-1830 nm) DRS was performed during open colorectal surgery. From the recorded spectra, 36 features were extracted at predefined wavelengths: 18 gradients and 18 amplitude differences. For classification of respectively ureter and artery in relation to surrounding adipose tissue, the best distinctive feature was selected using binary logistic regression for Si- and InGaAs-sensor spectral ranges separately. Classification performance was evaluated by leave-one-out cross-validation. Results. In 10 consecutive patients, 253 spectra were recorded on 53 tissue sites (including colon, adipose tissue, muscle, artery, vein, ureter). Classification of ureter versus adipose tissue revealed accuracy of 100% for both Si range and InGaAs range. Classification of artery versus surrounding adipose tissue revealed accuracies of 95% (Si) and 89% (InGaAs). Conclusions. Intraoperative DRS showed that Si and InGaAs sensors are equally suited for automated classification of ureter versus surrounding adipose tissue. Si sensors seem better suited for classifying artery versus mesenteric adipose tissue. Progress toward hyperspectral imaging within this field is promising.

AB - Background. In colorectal surgery, detecting ureters and mesenteric arteries is of utmost importance to prevent iatrogenic injury and to facilitate intraoperative decision making. A tool enabling ureter- and artery-specific image enhancement within (and possibly through) surrounding adipose tissue would facilitate this need, especially during laparoscopy. To evaluate the potential of hyperspectral imaging in colorectal surgery, we explored spectral tissue signatures using single-spot diffuse reflectance spectroscopy (DRS). As hyperspectral cameras with silicon (Si) and indium gallium arsenide (InGaAs) sensor chips are becoming available, we investigated spectral distinctive features for both sensor ranges. Methods. In vivo wide-band (wavelength range 350-1830 nm) DRS was performed during open colorectal surgery. From the recorded spectra, 36 features were extracted at predefined wavelengths: 18 gradients and 18 amplitude differences. For classification of respectively ureter and artery in relation to surrounding adipose tissue, the best distinctive feature was selected using binary logistic regression for Si- and InGaAs-sensor spectral ranges separately. Classification performance was evaluated by leave-one-out cross-validation. Results. In 10 consecutive patients, 253 spectra were recorded on 53 tissue sites (including colon, adipose tissue, muscle, artery, vein, ureter). Classification of ureter versus adipose tissue revealed accuracy of 100% for both Si range and InGaAs range. Classification of artery versus surrounding adipose tissue revealed accuracies of 95% (Si) and 89% (InGaAs). Conclusions. Intraoperative DRS showed that Si and InGaAs sensors are equally suited for automated classification of ureter versus surrounding adipose tissue. Si sensors seem better suited for classifying artery versus mesenteric adipose tissue. Progress toward hyperspectral imaging within this field is promising.

KW - adipose tissue

KW - artery

KW - automated tissue classification

KW - colorectal surgery

KW - diffuse reflectance spectroscopy

KW - tissue spectral analysis

KW - ureter

UR - http://www.scopus.com/inward/record.url?scp=84925405212&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84925405212&partnerID=8YFLogxK

U2 - 10.1177/1553350615569076

DO - 10.1177/1553350615569076

M3 - Article

C2 - 25652527

AN - SCOPUS:84925405212

VL - 22

SP - 557

EP - 567

JO - Surgical Innovation

JF - Surgical Innovation

SN - 1553-3506

IS - 6

ER -