Detection of brain tumor margins using optical coherence tomography

Ronald M. Juarez-Chambi, Carmen Kut, Jesus Rico-Jimenez, Daniel U. Campos-Delgado, Alfredo Quinones-Hinojosa, Xingde Li, Javier Jo

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In brain cancer surgery, it is critical to achieve extensive resection without compromising adjacent healthy, noncancerous regions. Various technological advances have made major contributions in imaging, including intraoperative magnetic imaging (MRI) and computed tomography (CT). However, these technologies have pros and cons in providing quantitative, real-time and three-dimensional (3D) continuous guidance in brain cancer detection. Optical Coherence Tomography (OCT) is a non-invasive, label-free, cost-effective technique capable of imaging tissue in three dimensions and real time. The purpose of this study is to reliably and efficiently discriminate between non-cancer and cancerinfiltrated brain regions using OCT images. To this end, a mathematical model for quantitative evaluation known as the Blind End-Member and Abundances Extraction method (BEAE). This BEAE method is a constrained optimization technique which extracts spatial information from volumetric OCT images. Using this novel method, we are able to discriminate between cancerous and non-cancerous tissues and using logistic regression as a classifier for automatic brain tumor margin detection. Using this technique, we are able to achieve excellent performance using an extensive cross-validation of the training dataset (sensitivity 92.91% and specificity 98.15%) and again using an independent, blinded validation dataset (sensitivity 92.91% and specificity 86.36%). In summary, BEAE is well-suited to differentiate brain tissue which could support the guiding surgery process for tissue resection.

Original languageEnglish (US)
Title of host publicationOptical Coherence Tomography and Coherence Domain Optical Methods in Biomedicine XXII
PublisherSPIE
Volume10483
ISBN (Electronic)9781510614512
DOIs
StatePublished - Jan 1 2018
EventOptical Coherence Tomography and Coherence Domain Optical Methods in Biomedicine XXII 2018 - San Francisco, United States
Duration: Jan 29 2018Jan 31 2018

Other

OtherOptical Coherence Tomography and Coherence Domain Optical Methods in Biomedicine XXII 2018
CountryUnited States
CitySan Francisco
Period1/29/181/31/18

Fingerprint

Optical tomography
Optical Coherence Tomography
Brain Neoplasms
brain
Tumors
margins
Brain
tumors
tomography
Tissue
Imaging techniques
surgery
Surgery
cancer
Sensitivity and Specificity
sensitivity
logistics
Constrained optimization
classifiers
Magnetic resonance imaging

Keywords

  • Brain Cancer
  • Image-guided surgery
  • Machine Learning
  • Optical Coherence Tomography
  • Quadratic Optimization

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Atomic and Molecular Physics, and Optics
  • Biomaterials
  • Radiology Nuclear Medicine and imaging

Cite this

Juarez-Chambi, R. M., Kut, C., Rico-Jimenez, J., Campos-Delgado, D. U., Quinones-Hinojosa, A., Li, X., & Jo, J. (2018). Detection of brain tumor margins using optical coherence tomography. In Optical Coherence Tomography and Coherence Domain Optical Methods in Biomedicine XXII (Vol. 10483). [104832Y] SPIE. https://doi.org/10.1117/12.2292136

Detection of brain tumor margins using optical coherence tomography. / Juarez-Chambi, Ronald M.; Kut, Carmen; Rico-Jimenez, Jesus; Campos-Delgado, Daniel U.; Quinones-Hinojosa, Alfredo; Li, Xingde; Jo, Javier.

Optical Coherence Tomography and Coherence Domain Optical Methods in Biomedicine XXII. Vol. 10483 SPIE, 2018. 104832Y.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Juarez-Chambi, RM, Kut, C, Rico-Jimenez, J, Campos-Delgado, DU, Quinones-Hinojosa, A, Li, X & Jo, J 2018, Detection of brain tumor margins using optical coherence tomography. in Optical Coherence Tomography and Coherence Domain Optical Methods in Biomedicine XXII. vol. 10483, 104832Y, SPIE, Optical Coherence Tomography and Coherence Domain Optical Methods in Biomedicine XXII 2018, San Francisco, United States, 1/29/18. https://doi.org/10.1117/12.2292136
Juarez-Chambi RM, Kut C, Rico-Jimenez J, Campos-Delgado DU, Quinones-Hinojosa A, Li X et al. Detection of brain tumor margins using optical coherence tomography. In Optical Coherence Tomography and Coherence Domain Optical Methods in Biomedicine XXII. Vol. 10483. SPIE. 2018. 104832Y https://doi.org/10.1117/12.2292136
Juarez-Chambi, Ronald M. ; Kut, Carmen ; Rico-Jimenez, Jesus ; Campos-Delgado, Daniel U. ; Quinones-Hinojosa, Alfredo ; Li, Xingde ; Jo, Javier. / Detection of brain tumor margins using optical coherence tomography. Optical Coherence Tomography and Coherence Domain Optical Methods in Biomedicine XXII. Vol. 10483 SPIE, 2018.
@inproceedings{a6696f239d0f47ebb966345320d6aa06,
title = "Detection of brain tumor margins using optical coherence tomography",
abstract = "In brain cancer surgery, it is critical to achieve extensive resection without compromising adjacent healthy, noncancerous regions. Various technological advances have made major contributions in imaging, including intraoperative magnetic imaging (MRI) and computed tomography (CT). However, these technologies have pros and cons in providing quantitative, real-time and three-dimensional (3D) continuous guidance in brain cancer detection. Optical Coherence Tomography (OCT) is a non-invasive, label-free, cost-effective technique capable of imaging tissue in three dimensions and real time. The purpose of this study is to reliably and efficiently discriminate between non-cancer and cancerinfiltrated brain regions using OCT images. To this end, a mathematical model for quantitative evaluation known as the Blind End-Member and Abundances Extraction method (BEAE). This BEAE method is a constrained optimization technique which extracts spatial information from volumetric OCT images. Using this novel method, we are able to discriminate between cancerous and non-cancerous tissues and using logistic regression as a classifier for automatic brain tumor margin detection. Using this technique, we are able to achieve excellent performance using an extensive cross-validation of the training dataset (sensitivity 92.91{\%} and specificity 98.15{\%}) and again using an independent, blinded validation dataset (sensitivity 92.91{\%} and specificity 86.36{\%}). In summary, BEAE is well-suited to differentiate brain tissue which could support the guiding surgery process for tissue resection.",
keywords = "Brain Cancer, Image-guided surgery, Machine Learning, Optical Coherence Tomography, Quadratic Optimization",
author = "Juarez-Chambi, {Ronald M.} and Carmen Kut and Jesus Rico-Jimenez and Campos-Delgado, {Daniel U.} and Alfredo Quinones-Hinojosa and Xingde Li and Javier Jo",
year = "2018",
month = "1",
day = "1",
doi = "10.1117/12.2292136",
language = "English (US)",
volume = "10483",
booktitle = "Optical Coherence Tomography and Coherence Domain Optical Methods in Biomedicine XXII",
publisher = "SPIE",

}

TY - GEN

T1 - Detection of brain tumor margins using optical coherence tomography

AU - Juarez-Chambi, Ronald M.

AU - Kut, Carmen

AU - Rico-Jimenez, Jesus

AU - Campos-Delgado, Daniel U.

AU - Quinones-Hinojosa, Alfredo

AU - Li, Xingde

AU - Jo, Javier

PY - 2018/1/1

Y1 - 2018/1/1

N2 - In brain cancer surgery, it is critical to achieve extensive resection without compromising adjacent healthy, noncancerous regions. Various technological advances have made major contributions in imaging, including intraoperative magnetic imaging (MRI) and computed tomography (CT). However, these technologies have pros and cons in providing quantitative, real-time and three-dimensional (3D) continuous guidance in brain cancer detection. Optical Coherence Tomography (OCT) is a non-invasive, label-free, cost-effective technique capable of imaging tissue in three dimensions and real time. The purpose of this study is to reliably and efficiently discriminate between non-cancer and cancerinfiltrated brain regions using OCT images. To this end, a mathematical model for quantitative evaluation known as the Blind End-Member and Abundances Extraction method (BEAE). This BEAE method is a constrained optimization technique which extracts spatial information from volumetric OCT images. Using this novel method, we are able to discriminate between cancerous and non-cancerous tissues and using logistic regression as a classifier for automatic brain tumor margin detection. Using this technique, we are able to achieve excellent performance using an extensive cross-validation of the training dataset (sensitivity 92.91% and specificity 98.15%) and again using an independent, blinded validation dataset (sensitivity 92.91% and specificity 86.36%). In summary, BEAE is well-suited to differentiate brain tissue which could support the guiding surgery process for tissue resection.

AB - In brain cancer surgery, it is critical to achieve extensive resection without compromising adjacent healthy, noncancerous regions. Various technological advances have made major contributions in imaging, including intraoperative magnetic imaging (MRI) and computed tomography (CT). However, these technologies have pros and cons in providing quantitative, real-time and three-dimensional (3D) continuous guidance in brain cancer detection. Optical Coherence Tomography (OCT) is a non-invasive, label-free, cost-effective technique capable of imaging tissue in three dimensions and real time. The purpose of this study is to reliably and efficiently discriminate between non-cancer and cancerinfiltrated brain regions using OCT images. To this end, a mathematical model for quantitative evaluation known as the Blind End-Member and Abundances Extraction method (BEAE). This BEAE method is a constrained optimization technique which extracts spatial information from volumetric OCT images. Using this novel method, we are able to discriminate between cancerous and non-cancerous tissues and using logistic regression as a classifier for automatic brain tumor margin detection. Using this technique, we are able to achieve excellent performance using an extensive cross-validation of the training dataset (sensitivity 92.91% and specificity 98.15%) and again using an independent, blinded validation dataset (sensitivity 92.91% and specificity 86.36%). In summary, BEAE is well-suited to differentiate brain tissue which could support the guiding surgery process for tissue resection.

KW - Brain Cancer

KW - Image-guided surgery

KW - Machine Learning

KW - Optical Coherence Tomography

KW - Quadratic Optimization

UR - http://www.scopus.com/inward/record.url?scp=85045644273&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85045644273&partnerID=8YFLogxK

U2 - 10.1117/12.2292136

DO - 10.1117/12.2292136

M3 - Conference contribution

VL - 10483

BT - Optical Coherence Tomography and Coherence Domain Optical Methods in Biomedicine XXII

PB - SPIE

ER -