AI-assisted in situ detection of human glioma infiltration using a novel computational method for optical coherence tomography

Ronald M. Juarez-Chambi, Carmen Kut, Jose J. Rico-Jimenez, Kaisorn L. Chaichana, Jiefeng Xi, Daniel U. Campos-Delgado, Fausto J. Rodriguez, Alfredo Quinones-Hinojosa, Xingde Li, Javier A. Jo

Research output: Contribution to journalArticle

Abstract

Purpose: In glioma surgery, it is critical to maximize tumor resection without compromising adjacent noncancerous brain tissue. Optical coherence tomography (OCT) is a noninvasive, label-free, real-time, high-resolution imaging modality that has been explored for glioma infiltration detection. Here, we report a novel artificial intelligence (AI)-assisted method for automated, real-time, in situ detection of glioma infiltration at high spatial resolution. Experimental Design: Volumetric OCT datasets were intraoperatively obtained from resected brain tissue specimens of 21 patients with glioma tumors of different stages and labeled as either noncancerous or glioma-infiltrated on the basis of histopathology evaluation of the tissue specimens (gold standard). Labeled OCT images from 12 patients were used as the training dataset to develop the AI-assisted OCTbased method for automated detection of glioma-infiltrated brain tissue. Unlabeled OCT images from the other 9 patients were used as the validation dataset to quantify the method detection performance. Results: Our method achieved excellent levels of sensitivity (∼100%) and specificity (∼85%) for detecting gliomainfiltrated tissue with high spatial resolution (16 mmlaterally) and processing speed (∼100,020 OCT A-lines/second). Conclusions: Previous methods for OCT-based detection of glioma-infiltrated brain tissue rely on estimating the tissue optical attenuation coefficient from the OCT signal, which requires sacrificing spatial resolution to increase signal quality, and performing systematic calibration procedures using tissue phantoms. By overcoming these major challenges, our AI-assisted method will enable implementing practical OCT-guided surgical tools for continuous, real-time, and accurate intraoperative detection of glioma-infiltrated brain tissue, facilitating maximal glioma resection and superior surgical outcomes for patients with glioma.

Original languageEnglish (US)
Pages (from-to)6329-6338
Number of pages10
JournalClinical Cancer Research
Volume25
Issue number21
DOIs
StatePublished - Nov 1 2019

Fingerprint

Artificial Intelligence
Optical Coherence Tomography
Glioma
Brain
Calibration
Neoplasms
Research Design
Sensitivity and Specificity

ASJC Scopus subject areas

  • Oncology
  • Cancer Research

Cite this

Juarez-Chambi, R. M., Kut, C., Rico-Jimenez, J. J., Chaichana, K. L., Xi, J., Campos-Delgado, D. U., ... Jo, J. A. (2019). AI-assisted in situ detection of human glioma infiltration using a novel computational method for optical coherence tomography. Clinical Cancer Research, 25(21), 6329-6338. https://doi.org/10.1158/1078-0432.CCR-19-0854

AI-assisted in situ detection of human glioma infiltration using a novel computational method for optical coherence tomography. / Juarez-Chambi, Ronald M.; Kut, Carmen; Rico-Jimenez, Jose J.; Chaichana, Kaisorn L.; Xi, Jiefeng; Campos-Delgado, Daniel U.; Rodriguez, Fausto J.; Quinones-Hinojosa, Alfredo; Li, Xingde; Jo, Javier A.

In: Clinical Cancer Research, Vol. 25, No. 21, 01.11.2019, p. 6329-6338.

Research output: Contribution to journalArticle

Juarez-Chambi, RM, Kut, C, Rico-Jimenez, JJ, Chaichana, KL, Xi, J, Campos-Delgado, DU, Rodriguez, FJ, Quinones-Hinojosa, A, Li, X & Jo, JA 2019, 'AI-assisted in situ detection of human glioma infiltration using a novel computational method for optical coherence tomography', Clinical Cancer Research, vol. 25, no. 21, pp. 6329-6338. https://doi.org/10.1158/1078-0432.CCR-19-0854
Juarez-Chambi, Ronald M. ; Kut, Carmen ; Rico-Jimenez, Jose J. ; Chaichana, Kaisorn L. ; Xi, Jiefeng ; Campos-Delgado, Daniel U. ; Rodriguez, Fausto J. ; Quinones-Hinojosa, Alfredo ; Li, Xingde ; Jo, Javier A. / AI-assisted in situ detection of human glioma infiltration using a novel computational method for optical coherence tomography. In: Clinical Cancer Research. 2019 ; Vol. 25, No. 21. pp. 6329-6338.
@article{091c8a19b00640c48ba6f317711e0e3f,
title = "AI-assisted in situ detection of human glioma infiltration using a novel computational method for optical coherence tomography",
abstract = "Purpose: In glioma surgery, it is critical to maximize tumor resection without compromising adjacent noncancerous brain tissue. Optical coherence tomography (OCT) is a noninvasive, label-free, real-time, high-resolution imaging modality that has been explored for glioma infiltration detection. Here, we report a novel artificial intelligence (AI)-assisted method for automated, real-time, in situ detection of glioma infiltration at high spatial resolution. Experimental Design: Volumetric OCT datasets were intraoperatively obtained from resected brain tissue specimens of 21 patients with glioma tumors of different stages and labeled as either noncancerous or glioma-infiltrated on the basis of histopathology evaluation of the tissue specimens (gold standard). Labeled OCT images from 12 patients were used as the training dataset to develop the AI-assisted OCTbased method for automated detection of glioma-infiltrated brain tissue. Unlabeled OCT images from the other 9 patients were used as the validation dataset to quantify the method detection performance. Results: Our method achieved excellent levels of sensitivity (∼100{\%}) and specificity (∼85{\%}) for detecting gliomainfiltrated tissue with high spatial resolution (16 mmlaterally) and processing speed (∼100,020 OCT A-lines/second). Conclusions: Previous methods for OCT-based detection of glioma-infiltrated brain tissue rely on estimating the tissue optical attenuation coefficient from the OCT signal, which requires sacrificing spatial resolution to increase signal quality, and performing systematic calibration procedures using tissue phantoms. By overcoming these major challenges, our AI-assisted method will enable implementing practical OCT-guided surgical tools for continuous, real-time, and accurate intraoperative detection of glioma-infiltrated brain tissue, facilitating maximal glioma resection and superior surgical outcomes for patients with glioma.",
author = "Juarez-Chambi, {Ronald M.} and Carmen Kut and Rico-Jimenez, {Jose J.} and Chaichana, {Kaisorn L.} and Jiefeng Xi and Campos-Delgado, {Daniel U.} and Rodriguez, {Fausto J.} and Alfredo Quinones-Hinojosa and Xingde Li and Jo, {Javier A.}",
year = "2019",
month = "11",
day = "1",
doi = "10.1158/1078-0432.CCR-19-0854",
language = "English (US)",
volume = "25",
pages = "6329--6338",
journal = "Clinical Cancer Research",
issn = "1078-0432",
publisher = "American Association for Cancer Research Inc.",
number = "21",

}

TY - JOUR

T1 - AI-assisted in situ detection of human glioma infiltration using a novel computational method for optical coherence tomography

AU - Juarez-Chambi, Ronald M.

AU - Kut, Carmen

AU - Rico-Jimenez, Jose J.

AU - Chaichana, Kaisorn L.

AU - Xi, Jiefeng

AU - Campos-Delgado, Daniel U.

AU - Rodriguez, Fausto J.

AU - Quinones-Hinojosa, Alfredo

AU - Li, Xingde

AU - Jo, Javier A.

PY - 2019/11/1

Y1 - 2019/11/1

N2 - Purpose: In glioma surgery, it is critical to maximize tumor resection without compromising adjacent noncancerous brain tissue. Optical coherence tomography (OCT) is a noninvasive, label-free, real-time, high-resolution imaging modality that has been explored for glioma infiltration detection. Here, we report a novel artificial intelligence (AI)-assisted method for automated, real-time, in situ detection of glioma infiltration at high spatial resolution. Experimental Design: Volumetric OCT datasets were intraoperatively obtained from resected brain tissue specimens of 21 patients with glioma tumors of different stages and labeled as either noncancerous or glioma-infiltrated on the basis of histopathology evaluation of the tissue specimens (gold standard). Labeled OCT images from 12 patients were used as the training dataset to develop the AI-assisted OCTbased method for automated detection of glioma-infiltrated brain tissue. Unlabeled OCT images from the other 9 patients were used as the validation dataset to quantify the method detection performance. Results: Our method achieved excellent levels of sensitivity (∼100%) and specificity (∼85%) for detecting gliomainfiltrated tissue with high spatial resolution (16 mmlaterally) and processing speed (∼100,020 OCT A-lines/second). Conclusions: Previous methods for OCT-based detection of glioma-infiltrated brain tissue rely on estimating the tissue optical attenuation coefficient from the OCT signal, which requires sacrificing spatial resolution to increase signal quality, and performing systematic calibration procedures using tissue phantoms. By overcoming these major challenges, our AI-assisted method will enable implementing practical OCT-guided surgical tools for continuous, real-time, and accurate intraoperative detection of glioma-infiltrated brain tissue, facilitating maximal glioma resection and superior surgical outcomes for patients with glioma.

AB - Purpose: In glioma surgery, it is critical to maximize tumor resection without compromising adjacent noncancerous brain tissue. Optical coherence tomography (OCT) is a noninvasive, label-free, real-time, high-resolution imaging modality that has been explored for glioma infiltration detection. Here, we report a novel artificial intelligence (AI)-assisted method for automated, real-time, in situ detection of glioma infiltration at high spatial resolution. Experimental Design: Volumetric OCT datasets were intraoperatively obtained from resected brain tissue specimens of 21 patients with glioma tumors of different stages and labeled as either noncancerous or glioma-infiltrated on the basis of histopathology evaluation of the tissue specimens (gold standard). Labeled OCT images from 12 patients were used as the training dataset to develop the AI-assisted OCTbased method for automated detection of glioma-infiltrated brain tissue. Unlabeled OCT images from the other 9 patients were used as the validation dataset to quantify the method detection performance. Results: Our method achieved excellent levels of sensitivity (∼100%) and specificity (∼85%) for detecting gliomainfiltrated tissue with high spatial resolution (16 mmlaterally) and processing speed (∼100,020 OCT A-lines/second). Conclusions: Previous methods for OCT-based detection of glioma-infiltrated brain tissue rely on estimating the tissue optical attenuation coefficient from the OCT signal, which requires sacrificing spatial resolution to increase signal quality, and performing systematic calibration procedures using tissue phantoms. By overcoming these major challenges, our AI-assisted method will enable implementing practical OCT-guided surgical tools for continuous, real-time, and accurate intraoperative detection of glioma-infiltrated brain tissue, facilitating maximal glioma resection and superior surgical outcomes for patients with glioma.

UR - http://www.scopus.com/inward/record.url?scp=85074445179&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85074445179&partnerID=8YFLogxK

U2 - 10.1158/1078-0432.CCR-19-0854

DO - 10.1158/1078-0432.CCR-19-0854

M3 - Article

C2 - 31315883

AN - SCOPUS:85074445179

VL - 25

SP - 6329

EP - 6338

JO - Clinical Cancer Research

JF - Clinical Cancer Research

SN - 1078-0432

IS - 21

ER -