AI-Assisted In Situ Detection of Human Glioma Infiltration Using a Novel Computational Method for Optical Coherence Tomography

被引：48
作者：
Juarez-Chambi, Ronald M. [1 ]
Kut, Carmen [2 ]
Rico-Jimenez, Jose J. [1 ]
Chaichana, Kaisorn L. [3 ]
Xi, Jiefeng [2 ]
Campos-Delgado, Daniel U. [4 ]
Rodriguez, Fausto J. [5 ]
Quinones-Hinojosa, Alfredo [3 ]
Li, Xingde [2 ]
Jo, Javier A. [6 ]
机构：
[1] Texas A&M Univ, Dept Biomed Engn, College Stn, TX USA
[2] Johns Hopkins Univ, Dept Biomed Engn, Baltimore, MD USA
[3] Mayo Clin, Dept Neurol Surg, Jacksonville, FL 32224 USA
[4] Univ Autonoma San Luis De Potosi, Fac Ciencias, San Luis Potosi, Mexico
[5] Johns Hopkins Univ, Div Neuropathol, Dept Neurosurg, Baltimore, MD USA
[6] Univ Oklahoma, Sch Elect & Comp Engn, Norman, OK 73019 USA
来源：
CLINICAL CANCER RESEARCH | 2019年 / 25卷 / 21期
关键词：
LOW-GRADE GLIOMAS; BRAIN-TUMOR; GLIOBLASTOMA-MULTIFORME; 5-AMINOLEVULINIC ACID; RAMAN-SPECTROSCOPY; MOUSE-BRAIN; GREY-MATTER; RESECTION; SURVIVAL; TISSUE;
D O I：
10.1158/1078-0432.CCR-19-0854
中图分类号：
R73 [肿瘤学];
学科分类号：
100214 ;
摘要：
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 OCT based 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 (similar to 100%) and specificity (similar to 85%) for detecting glioma-infiltrated tissue with high spatial resolution (16 mu m laterally) and processing speed (similar to 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.
引用
收藏
页码：6329 / 6338
页数：10
相关论文
共 49 条
[1]   The Value of Extent of Resection of Glioblastomas: Clinical Evidence and Current Approach [J].
Almeida, Joao Paulo ;
Chaichana, Kaisorn L. ;
Rincon-Torroella, Jordina ;
Quinones-Hinojosa, Alfredo .
CURRENT NEUROLOGY AND NEUROSCIENCE REPORTS, 2015, 15 (02)
[2]   Precise comparison of protoporphyrin IX fluorescence spectra with pathological results for brain tumor tissue identification [J].
Ando, Takehiro ;
Kobayashi, Etsuko ;
Liao, Hongen ;
Maruyama, Takashi ;
Muragaki, Yoshihiro ;
Iseki, Hiroshi ;
Kubo, Osami ;
Sakuma, Ichiro .
BRAIN TUMOR PATHOLOGY, 2011, 28 (01) :43-51
[3]   Imaging ex vivo healthy and pathological human brain tissue with ultra-high-resolution optical coherence tomography -: art. no. 011006 [J].
Bizheva, K ;
Unterhuber, A ;
Hermann, B ;
Povazay, B ;
Sattmann, H ;
Fercher, AF ;
Drexler, W ;
Preusser, M ;
Budka, H ;
Stingl, A ;
Le, T .
JOURNAL OF BIOMEDICAL OPTICS, 2005, 10 (01)
[4]   Time-domain and spectral-domain optical coherence tomography in the analysis of brain tumor tissue [J].
Boehringer, H. J. ;
Boller, D. ;
Leppert, J. ;
Knopp, U. ;
Lankenau, E. ;
Reusche, E. ;
Huettmann, G. ;
Giese, A. .
LASERS IN SURGERY AND MEDICINE, 2006, 38 (06) :588-597
[5]   Imaging of human brain tumor tissue by near-infrared laser coherence tomography [J].
Boehringer, H. J. ;
Lankenau, E. ;
Stellmacher, F. ;
Reusche, E. ;
Huettmann, G. ;
Giese, A. .
ACTA NEUROCHIRURGICA, 2009, 151 (05) :507-517
[6]   Optical coherence tomography for neurosurgical imaging of human intracortical melanoma [J].
Boppart, SA ;
Brezinski, ME ;
Pitris, C ;
Fujimoto, JG .
NEUROSURGERY, 1998, 43 (04) :834-841
[7]   A COMPUTATIONAL APPROACH TO EDGE-DETECTION [J].
CANNY, J .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1986, 8 (06) :679-698
[8]   The butterfly effect on glioblastoma: is volumetric extent of resection more effective than biopsy for these tumors? [J].
Chaichana, Kaisorn L. ;
Jusue-Torres, Ignacio ;
Lemos, Ana Maria ;
Gokaslan, Aaron ;
Cabrera-Aldana, Eibar Ernesto ;
Ashary, Ahmed ;
Olivi, Alessandro ;
Quinones-Hinojosa, Alfredo .
JOURNAL OF NEURO-ONCOLOGY, 2014, 120 (03) :625-634
[9]   When Gross Total Resection of a Glioblastoma Is Possible, How Much Resection Should Be Achieved? [J].
Chaichana, Kaisorn L. ;
Cabrera-Aldana, Eibar Ernesto ;
Jusue-Torres, Ignacio ;
Wijesekera, Olindi ;
Olivi, Alessandro ;
Rahman, Maryam ;
Quinones-Hinojosa, Alfredo .
WORLD NEUROSURGERY, 2014, 82 (1-2) :E257-E265
[10]   Establishing percent resection and residual volume thresholds affecting survival and recurrence for patients with newly diagnosed intracranial glioblastoma [J].
Chaichana, Kaisorn L. ;
Jusue-Torres, Ignacio ;
Navarro-Ramirez, Rodrigo ;
Raza, Shaan M. ;
Pascual-Gallego, Maria ;
Ibrahim, Aly ;
Hernandez-Hermann, Marta ;
Gomez, Luis ;
Ye, Xiaobu ;
Weingart, Jon D. ;
Olivi, Alessandro ;
Blakeley, Jaishri ;
Gallia, Gary L. ;
Lim, Michael ;
Brem, Henry ;
Quinones-Hinojosa, Alfredo .
NEURO-ONCOLOGY, 2014, 16 (01) :113-122
12345