Toward Assessment of Resection Margins Using Hyperspectral Diffuse Reflection Imaging (400–1,700 nm) During Tongue Cancer Surgery

Susan G. Brouwer de Koning, Pim Weijtmans, M. Baris Karakullukcu, Caifeng Shan, Elisabeth J.M. Baltussen, Laura A. Smit, Robert L.P. van Veen, Benno H.W. Hendriks, Henricus J.C.M. Sterenborg, Theo J.M. Ruers

Research output: Contribution to journalArticleAcademicpeer-review

Abstract

Background and Objectives: There is a clinical need to assess the resection margins of tongue cancer specimens, intraoperatively. In the current ex vivo study, we evaluated the feasibility of hyperspectral diffuse reflectance imaging (HSI) for distinguishing tumor from the healthy tongue tissue. Study Design/Materials and Methods: Fresh surgical specimens (n = 14) of squamous cell carcinoma of the tongue were scanned with two hyperspectral cameras that cover the visible and near-infrared spectrum (400–1,700 nm). Each pixel of the hyperspectral image represents a measure of the diffuse optical reflectance. A neural network was used for tissue-type prediction of the hyperspectral images of the visual and near-infrared data sets separately as well as both data sets combined. Results: HSI was able to distinguish tumor from muscle with a good accuracy. The diagnostic performance of both wavelength ranges (sensitivity/specificity of visual and near-infrared were 84%/80% and 77%/77%, respectively) appears to be comparable and there is no additional benefit of combining the two wavelength ranges (sensitivity and specificity were 83%/76%). Conclusions: HSI has a strong potential for intra-operative assessment of tumor resection margins of squamous cell carcinoma of the tongue. This may optimize surgery, as the entire resection surface can be scanned in a single run and the results can be readily available. Lasers Surg. Med.

Original languageEnglish
JournalLasers in surgery and medicine
DOIs
Publication statusE-pub ahead of print/First online - 15 Sep 2019

Fingerprint

Tongue Neoplasms
Tongue
Squamous Cell Carcinoma
Sensitivity and Specificity
Neoplasms
Feasibility Studies
Lasers
Muscles
Margins of Excision
Datasets

Keywords

  • deep learning
  • hyperspectral imaging
  • resection margin assessment
  • tissue recognition
  • tongue cancer

Cite this

Brouwer de Koning, Susan G. ; Weijtmans, Pim ; Karakullukcu, M. Baris ; Shan, Caifeng ; Baltussen, Elisabeth J.M. ; Smit, Laura A. ; van Veen, Robert L.P. ; Hendriks, Benno H.W. ; Sterenborg, Henricus J.C.M. ; Ruers, Theo J.M. / Toward Assessment of Resection Margins Using Hyperspectral Diffuse Reflection Imaging (400–1,700 nm) During Tongue Cancer Surgery. In: Lasers in surgery and medicine. 2019.
@article{bf164187fe21479e9d23559367d56596,
title = "Toward Assessment of Resection Margins Using Hyperspectral Diffuse Reflection Imaging (400–1,700 nm) During Tongue Cancer Surgery",
abstract = "Background and Objectives: There is a clinical need to assess the resection margins of tongue cancer specimens, intraoperatively. In the current ex vivo study, we evaluated the feasibility of hyperspectral diffuse reflectance imaging (HSI) for distinguishing tumor from the healthy tongue tissue. Study Design/Materials and Methods: Fresh surgical specimens (n = 14) of squamous cell carcinoma of the tongue were scanned with two hyperspectral cameras that cover the visible and near-infrared spectrum (400–1,700 nm). Each pixel of the hyperspectral image represents a measure of the diffuse optical reflectance. A neural network was used for tissue-type prediction of the hyperspectral images of the visual and near-infrared data sets separately as well as both data sets combined. Results: HSI was able to distinguish tumor from muscle with a good accuracy. The diagnostic performance of both wavelength ranges (sensitivity/specificity of visual and near-infrared were 84{\%}/80{\%} and 77{\%}/77{\%}, respectively) appears to be comparable and there is no additional benefit of combining the two wavelength ranges (sensitivity and specificity were 83{\%}/76{\%}). Conclusions: HSI has a strong potential for intra-operative assessment of tumor resection margins of squamous cell carcinoma of the tongue. This may optimize surgery, as the entire resection surface can be scanned in a single run and the results can be readily available. Lasers Surg. Med.",
keywords = "deep learning, hyperspectral imaging, resection margin assessment, tissue recognition, tongue cancer",
author = "{Brouwer de Koning}, {Susan G.} and Pim Weijtmans and Karakullukcu, {M. Baris} and Caifeng Shan and Baltussen, {Elisabeth J.M.} and Smit, {Laura A.} and {van Veen}, {Robert L.P.} and Hendriks, {Benno H.W.} and Sterenborg, {Henricus J.C.M.} and Ruers, {Theo J.M.}",
year = "2019",
month = "9",
day = "15",
doi = "10.1002/lsm.23161",
language = "English",
journal = "Lasers in surgery and medicine",
issn = "0196-8092",
publisher = "Wiley-Liss Inc.",

}

Toward Assessment of Resection Margins Using Hyperspectral Diffuse Reflection Imaging (400–1,700 nm) During Tongue Cancer Surgery. / Brouwer de Koning, Susan G.; Weijtmans, Pim; Karakullukcu, M. Baris; Shan, Caifeng; Baltussen, Elisabeth J.M.; Smit, Laura A.; van Veen, Robert L.P.; Hendriks, Benno H.W.; Sterenborg, Henricus J.C.M.; Ruers, Theo J.M.

In: Lasers in surgery and medicine, 15.09.2019.

Research output: Contribution to journalArticleAcademicpeer-review

TY - JOUR

T1 - Toward Assessment of Resection Margins Using Hyperspectral Diffuse Reflection Imaging (400–1,700 nm) During Tongue Cancer Surgery

AU - Brouwer de Koning, Susan G.

AU - Weijtmans, Pim

AU - Karakullukcu, M. Baris

AU - Shan, Caifeng

AU - Baltussen, Elisabeth J.M.

AU - Smit, Laura A.

AU - van Veen, Robert L.P.

AU - Hendriks, Benno H.W.

AU - Sterenborg, Henricus J.C.M.

AU - Ruers, Theo J.M.

PY - 2019/9/15

Y1 - 2019/9/15

N2 - Background and Objectives: There is a clinical need to assess the resection margins of tongue cancer specimens, intraoperatively. In the current ex vivo study, we evaluated the feasibility of hyperspectral diffuse reflectance imaging (HSI) for distinguishing tumor from the healthy tongue tissue. Study Design/Materials and Methods: Fresh surgical specimens (n = 14) of squamous cell carcinoma of the tongue were scanned with two hyperspectral cameras that cover the visible and near-infrared spectrum (400–1,700 nm). Each pixel of the hyperspectral image represents a measure of the diffuse optical reflectance. A neural network was used for tissue-type prediction of the hyperspectral images of the visual and near-infrared data sets separately as well as both data sets combined. Results: HSI was able to distinguish tumor from muscle with a good accuracy. The diagnostic performance of both wavelength ranges (sensitivity/specificity of visual and near-infrared were 84%/80% and 77%/77%, respectively) appears to be comparable and there is no additional benefit of combining the two wavelength ranges (sensitivity and specificity were 83%/76%). Conclusions: HSI has a strong potential for intra-operative assessment of tumor resection margins of squamous cell carcinoma of the tongue. This may optimize surgery, as the entire resection surface can be scanned in a single run and the results can be readily available. Lasers Surg. Med.

AB - Background and Objectives: There is a clinical need to assess the resection margins of tongue cancer specimens, intraoperatively. In the current ex vivo study, we evaluated the feasibility of hyperspectral diffuse reflectance imaging (HSI) for distinguishing tumor from the healthy tongue tissue. Study Design/Materials and Methods: Fresh surgical specimens (n = 14) of squamous cell carcinoma of the tongue were scanned with two hyperspectral cameras that cover the visible and near-infrared spectrum (400–1,700 nm). Each pixel of the hyperspectral image represents a measure of the diffuse optical reflectance. A neural network was used for tissue-type prediction of the hyperspectral images of the visual and near-infrared data sets separately as well as both data sets combined. Results: HSI was able to distinguish tumor from muscle with a good accuracy. The diagnostic performance of both wavelength ranges (sensitivity/specificity of visual and near-infrared were 84%/80% and 77%/77%, respectively) appears to be comparable and there is no additional benefit of combining the two wavelength ranges (sensitivity and specificity were 83%/76%). Conclusions: HSI has a strong potential for intra-operative assessment of tumor resection margins of squamous cell carcinoma of the tongue. This may optimize surgery, as the entire resection surface can be scanned in a single run and the results can be readily available. Lasers Surg. Med.

KW - deep learning

KW - hyperspectral imaging

KW - resection margin assessment

KW - tissue recognition

KW - tongue cancer

UR - http://www.scopus.com/inward/record.url?scp=85073919914&partnerID=8YFLogxK

U2 - 10.1002/lsm.23161

DO - 10.1002/lsm.23161

M3 - Article

JO - Lasers in surgery and medicine

JF - Lasers in surgery and medicine

SN - 0196-8092

ER -