Towards automated spectroscopic tissue classification in thyroid and parathyroid surgery

Rutger M. Schols, Lejla Alic, Fokko P. Wieringa, Nicole D. Bouvy, Laurents P.S. Stassen

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Background: In (para-)thyroid surgery iatrogenic parathyroid injury should be prevented. To aid the surgeons’ eye, a camera system enabling parathyroid-specific image enhancement would be useful. Hyperspectral camera technology might work, provided that the spectral signature of parathyroid tissue offers enough specific features to be reliably and automatically distinguished from surrounding tissues. As a first step to investigate this, we examined the feasibility of wide band diffuse reflectance spectroscopy (DRS) for automated spectroscopic tissue classification, using silicon (Si) and indium-gallium-arsenide (InGaAs) sensors. Methods: DRS (350–1830 nm) was performed during (para-)thyroid resections. From the acquired spectra 36 features at predefined wavelengths were extracted. The best features for classification of parathyroid from adipose or thyroid were assessed by binary logistic regression for Si- and InGaAs-sensor ranges. Classification performance was evaluated by leave-one-out cross-validation. Results: In 19 patients 299 spectra were recorded (62 tissue sites: thyroid = 23, parathyroid = 21, adipose = 18). Classification accuracy of parathyroid–adipose was, respectively, 79% (Si), 82% (InGaAs) and 97% (Si/InGaAs combined). Parathyroid–thyroid classification accuracies were 80% (Si), 75% (InGaAs), 82% (Si/InGaAs combined). Conclusions: Si and InGaAs sensors are fairly accurate for automated spectroscopic classification of parathyroid, adipose and thyroid tissues. Combination of both sensor technologies improves accuracy. Follow-up research, aimed towards hyperspectral imaging seems justified.

Original languageEnglish
Article numbere1748
JournalInternational Journal of Medical Robotics and Computer Assisted Surgery
Volume13
Issue number1
DOIs
Publication statusPublished - 1 Mar 2017
Externally publishedYes

Fingerprint

Gallium arsenide
Silicon
Indium
Surgery
Thyroid Gland
Tissue
Sensors
Spectrum Analysis
Cameras
Spectroscopy
Image Enhancement
Technology
Image enhancement
indium arsenide
gallium arsenide
Logistics
Adipose Tissue
Logistic Models
Wavelength
Wounds and Injuries

Keywords

  • adipose tissue
  • automated tissue classification
  • diffuse reflectance spectroscopy
  • parathyroid
  • thyroid
  • thyroid and parathyroid surgery

ASJC Scopus subject areas

  • Surgery
  • Biophysics
  • Computer Science Applications

Cite this

Towards automated spectroscopic tissue classification in thyroid and parathyroid surgery. / Schols, Rutger M.; Alic, Lejla; Wieringa, Fokko P.; Bouvy, Nicole D.; Stassen, Laurents P.S.

In: International Journal of Medical Robotics and Computer Assisted Surgery, Vol. 13, No. 1, e1748, 01.03.2017.

Research output: Contribution to journalArticle

@article{1353a9da2d4a4657baa3b813a99f4929,
title = "Towards automated spectroscopic tissue classification in thyroid and parathyroid surgery",
abstract = "Background: In (para-)thyroid surgery iatrogenic parathyroid injury should be prevented. To aid the surgeons’ eye, a camera system enabling parathyroid-specific image enhancement would be useful. Hyperspectral camera technology might work, provided that the spectral signature of parathyroid tissue offers enough specific features to be reliably and automatically distinguished from surrounding tissues. As a first step to investigate this, we examined the feasibility of wide band diffuse reflectance spectroscopy (DRS) for automated spectroscopic tissue classification, using silicon (Si) and indium-gallium-arsenide (InGaAs) sensors. Methods: DRS (350–1830 nm) was performed during (para-)thyroid resections. From the acquired spectra 36 features at predefined wavelengths were extracted. The best features for classification of parathyroid from adipose or thyroid were assessed by binary logistic regression for Si- and InGaAs-sensor ranges. Classification performance was evaluated by leave-one-out cross-validation. Results: In 19 patients 299 spectra were recorded (62 tissue sites: thyroid = 23, parathyroid = 21, adipose = 18). Classification accuracy of parathyroid–adipose was, respectively, 79{\%} (Si), 82{\%} (InGaAs) and 97{\%} (Si/InGaAs combined). Parathyroid–thyroid classification accuracies were 80{\%} (Si), 75{\%} (InGaAs), 82{\%} (Si/InGaAs combined). Conclusions: Si and InGaAs sensors are fairly accurate for automated spectroscopic classification of parathyroid, adipose and thyroid tissues. Combination of both sensor technologies improves accuracy. Follow-up research, aimed towards hyperspectral imaging seems justified.",
keywords = "adipose tissue, automated tissue classification, diffuse reflectance spectroscopy, parathyroid, thyroid, thyroid and parathyroid surgery",
author = "Schols, {Rutger M.} and Lejla Alic and Wieringa, {Fokko P.} and Bouvy, {Nicole D.} and Stassen, {Laurents P.S.}",
year = "2017",
month = "3",
day = "1",
doi = "10.1002/rcs.1748",
language = "English",
volume = "13",
journal = "International Journal of Medical Robotics and Computer Assisted Surgery",
issn = "1478-596X",
publisher = "John Wiley and Sons Ltd",
number = "1",

}

TY - JOUR

T1 - Towards automated spectroscopic tissue classification in thyroid and parathyroid surgery

AU - Schols, Rutger M.

AU - Alic, Lejla

AU - Wieringa, Fokko P.

AU - Bouvy, Nicole D.

AU - Stassen, Laurents P.S.

PY - 2017/3/1

Y1 - 2017/3/1

N2 - Background: In (para-)thyroid surgery iatrogenic parathyroid injury should be prevented. To aid the surgeons’ eye, a camera system enabling parathyroid-specific image enhancement would be useful. Hyperspectral camera technology might work, provided that the spectral signature of parathyroid tissue offers enough specific features to be reliably and automatically distinguished from surrounding tissues. As a first step to investigate this, we examined the feasibility of wide band diffuse reflectance spectroscopy (DRS) for automated spectroscopic tissue classification, using silicon (Si) and indium-gallium-arsenide (InGaAs) sensors. Methods: DRS (350–1830 nm) was performed during (para-)thyroid resections. From the acquired spectra 36 features at predefined wavelengths were extracted. The best features for classification of parathyroid from adipose or thyroid were assessed by binary logistic regression for Si- and InGaAs-sensor ranges. Classification performance was evaluated by leave-one-out cross-validation. Results: In 19 patients 299 spectra were recorded (62 tissue sites: thyroid = 23, parathyroid = 21, adipose = 18). Classification accuracy of parathyroid–adipose was, respectively, 79% (Si), 82% (InGaAs) and 97% (Si/InGaAs combined). Parathyroid–thyroid classification accuracies were 80% (Si), 75% (InGaAs), 82% (Si/InGaAs combined). Conclusions: Si and InGaAs sensors are fairly accurate for automated spectroscopic classification of parathyroid, adipose and thyroid tissues. Combination of both sensor technologies improves accuracy. Follow-up research, aimed towards hyperspectral imaging seems justified.

AB - Background: In (para-)thyroid surgery iatrogenic parathyroid injury should be prevented. To aid the surgeons’ eye, a camera system enabling parathyroid-specific image enhancement would be useful. Hyperspectral camera technology might work, provided that the spectral signature of parathyroid tissue offers enough specific features to be reliably and automatically distinguished from surrounding tissues. As a first step to investigate this, we examined the feasibility of wide band diffuse reflectance spectroscopy (DRS) for automated spectroscopic tissue classification, using silicon (Si) and indium-gallium-arsenide (InGaAs) sensors. Methods: DRS (350–1830 nm) was performed during (para-)thyroid resections. From the acquired spectra 36 features at predefined wavelengths were extracted. The best features for classification of parathyroid from adipose or thyroid were assessed by binary logistic regression for Si- and InGaAs-sensor ranges. Classification performance was evaluated by leave-one-out cross-validation. Results: In 19 patients 299 spectra were recorded (62 tissue sites: thyroid = 23, parathyroid = 21, adipose = 18). Classification accuracy of parathyroid–adipose was, respectively, 79% (Si), 82% (InGaAs) and 97% (Si/InGaAs combined). Parathyroid–thyroid classification accuracies were 80% (Si), 75% (InGaAs), 82% (Si/InGaAs combined). Conclusions: Si and InGaAs sensors are fairly accurate for automated spectroscopic classification of parathyroid, adipose and thyroid tissues. Combination of both sensor technologies improves accuracy. Follow-up research, aimed towards hyperspectral imaging seems justified.

KW - adipose tissue

KW - automated tissue classification

KW - diffuse reflectance spectroscopy

KW - parathyroid

KW - thyroid

KW - thyroid and parathyroid surgery

UR - http://www.scopus.com/inward/record.url?scp=84971003198&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84971003198&partnerID=8YFLogxK

U2 - 10.1002/rcs.1748

DO - 10.1002/rcs.1748

M3 - Article

VL - 13

JO - International Journal of Medical Robotics and Computer Assisted Surgery

JF - International Journal of Medical Robotics and Computer Assisted Surgery

SN - 1478-596X

IS - 1

M1 - e1748

ER -