Deep Learning-Based Framework for In Vivo Identification of Glioblastoma Tumor using Hyperspectral Images of Human Brain

被引:116
作者
Fabelo, Himar [1 ,2 ]
Halicek, Martin [1 ,3 ,4 ]
Ortega, Samuel [2 ]
Shahedi, Maysam [1 ]
Szolna, Adam [5 ]
Pineiro, Juan F. [5 ]
Sosa, Coralia [5 ]
O'Shanahan, Aruma J. [5 ]
Bisshopp, Sara [5 ]
Espino, Carlos [5 ]
Marquez, Mariano [5 ]
Hernandez, Maria [5 ]
Carrera, David [5 ]
Morera, Jesus [5 ]
Callico, Gustavo M. [2 ]
Sarmiento, Roberto [2 ]
Fei, Baowei [1 ,6 ,7 ]
机构
[1] Univ Texas Dallas, Dept Bioengn, 800 W Campbell Rd, Richardson, TX 75080 USA
[2] ULPGC, Inst Appl Microelect IUMA, Las Palmas Gran Canaria 35017, Spain
[3] Emory Univ, Dept Biomed Engn, 1841 Clifton Rd NE, Atlanta, GA 30329 USA
[4] Georgia Inst Technol, 1841 Clifton Rd NE, Atlanta, GA 30329 USA
[5] Univ Hosp Doctor Negrin Gran Canaria, Dept Neurosurg, Barranco Ballena S-N, Las Palmas Gran Canaria 35010, Spain
[6] Univ Texas Southwestern Med Ctr Dallas, Adv Imaging Res Ctr, 5323 Harry Hine Blvd, Dallas, TX 75390 USA
[7] Univ Texas Southwestern Med Ctr Dallas, Dept Radiol, 5323 Harry Hine Blvd, Dallas, TX 75390 USA
基金
美国国家卫生研究院;
关键词
brain tumor; cancer surgery; hyperspectral imaging; bioinformatics; intraoperative imaging; deep learning; precision medicine; image-guided surgery; RESECTION; TISSUE; EXTENT; DISCRIMINATION; HEMOGLOBIN; LESIONS; CANCER; GLIOMA; SHIFT;
D O I
10.3390/s19040920
中图分类号
O65 [分析化学];
学科分类号
070302 ; 081704 ;
摘要
The main goal of brain cancer surgery is to perform an accurate resection of the tumor, preserving as much normal brain tissue as possible for the patient. The development of a non-contact and label-free method to provide reliable support for tumor resection in real-time during neurosurgical procedures is a current clinical need. Hyperspectral imaging is a non-contact, non-ionizing, and label-free imaging modality that can assist surgeons during this challenging task without using any contrast agent. In this work, we present a deep learning-based framework for processing hyperspectral images of in vivo human brain tissue. The proposed framework was evaluated by our human image database, which includes 26 in vivo hyperspectral cubes from 16 different patients, among which 258,810 pixels were labeled. The proposed framework is able to generate a thematic map where the parenchymal area of the brain is delineated and the location of the tumor is identified, providing guidance to the operating surgeon for a successful and precise tumor resection. The deep learning pipeline achieves an overall accuracy of 80% for multiclass classification, improving the results obtained with traditional support vector machine (SVM)-based approaches. In addition, an aid visualization system is presented, where the final thematic map can be adjusted by the operating surgeon to find the optimal classification threshold for the current situation during the surgical procedure.
引用
收藏
页数:25
相关论文
共 59 条
[1]  
Abadi Martin, 2016, arXiv
[2]   Hyperspectral imaging and quantitative analysis for prostate cancer detection [J].
Akbari, Hamed ;
Halig, Luma V. ;
Schuster, David M. ;
Osunkoya, Adeboye ;
Master, Viraj ;
Nieh, Peter T. ;
Chen, Georgia Z. ;
Fei, Baowei .
JOURNAL OF BIOMEDICAL OPTICS, 2012, 17 (07)
[3]   Detection and Analysis of the Intestinal Ischemia Using Visible and Invisible Hyperspectral Imaging [J].
Akbari, Hamed ;
Kosugi, Yukio ;
Kojima, Kazuyuki ;
Tanaka, Naofumi .
IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, 2010, 57 (08) :2011-2017
[4]   Discrimination between Oral Cancer and Healthy Tissue Based on Water Content Determined by Raman Spectroscopy [J].
Barroso, E. M. ;
Smits, R. W. H. ;
Schut, T. C. Bakker ;
ten Hove, I. ;
Hardillo, J. A. ;
Wolvius, E. B. ;
de Jong, R. J. Baatenburg ;
Koljenovic, S. ;
Puppels, G. J. .
ANALYTICAL CHEMISTRY, 2015, 87 (04) :2419-2426
[5]   Hyperspectral Imaging in the Medical Field: Present and Future [J].
Calin, Mihaela Antonina ;
Parasca, Sorin Viorel ;
Savastru, Dan ;
Manea, Dragos .
APPLIED SPECTROSCOPY REVIEWS, 2014, 49 (06) :435-447
[6]   Automatic selection of molecular descriptors using random forest: Application to drug discovery [J].
Cano, Gaspar ;
Garcia-Rodriguez, Jose ;
Garcia-Garcia, Alberto ;
Perez-Sanchez, Horacio ;
Benediktsson, Jon Atli ;
Thapa, Anil ;
Barr, Alastair .
EXPERT SYSTEMS WITH APPLICATIONS, 2017, 72 :151-159
[7]   LIBSVM: A Library for Support Vector Machines [J].
Chang, Chih-Chung ;
Lin, Chih-Jen .
ACM TRANSACTIONS ON INTELLIGENT SYSTEMS AND TECHNOLOGY, 2011, 2 (03)
[8]   Glioblastoma: Overview of Disease and Treatment [J].
Davis, Mary Elizabeth .
CLINICAL JOURNAL OF ONCOLOGY NURSING, 2016, 20 (05) :2-8
[9]   New hyperspectral discrimination measure for spectral characterization [J].
Du, YZ ;
Chang, CI ;
Ren, H ;
Chang, CC ;
Jensen, JO ;
D'Amico, FM .
OPTICAL ENGINEERING, 2004, 43 (08) :1777-1786
[10]   Spatio-spectral classification of hyperspectral images for brain cancer detection during surgical operations [J].
Fabelo, Himar ;
Ortega, Samuel ;
Ravi, Daniele ;
Kiran, B. Ravi ;
Sosa, Coralia ;
Bulters, Diederik ;
Callico, Gustavo M. ;
Bulstrode, Harry ;
Szolna, Adam ;
Pineiro, Juan F. ;
Kabwama, Silvester ;
Madronal, Daniel ;
Lazcano, Raquel ;
J-O'Shanahan, Aruma ;
Bisshopp, Sara ;
Hernandez, Maria ;
Baez, Abelardo ;
Yang, Guang-Zhong ;
Stanciulescu, Bogdan ;
Salvador, Ruben ;
Juarez, Eduardo ;
Sarmiento, Roberto .
PLOS ONE, 2018, 13 (03)