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.
N1 - Funding Information:
This research was partially supported by grants from the NIH (grants R01CA218739, R01CA200399), the Cancer Prevention and Research Institute of Texas (grant RP180588), the Coulter H. Wallace Foundation, NSF-NCSA XSEDE ASC170017, FONDECYT-CONCYTEC Fellowship. A. Quinones-Hinojosa acknowledged the support by the William J. and Charles H. Mayo Professorship and a Mayo Clinician Investigator award. K.L. Chaichana acknowledged the support by the Mayo RACER award.
Publisher Copyright:
© 2019 American Association for Cancer Research.
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
SN - 1078-0432
VL - 25
SP - 6329
EP - 6338
JO - Clinical Cancer Research
JF - Clinical Cancer Research
IS - 21
ER -