Deep learning-based framework for In Vivo identification of glioblastoma tumor using hyperspectral images of human brain

Himar Fabelo, Martin Halicek, Samuel Ortega, Maysam Shahedi, Adam Szolna, Juan F. Piñeiro, Coralia Sosa, Aruma J. O’Shanahan, Sara Bisshopp, Carlos Espino, Mariano Márquez, María Hernández, David Carrera, Jesús Morera, Gustavo M. Callico, Roberto Sarmiento, Baowei Fei

Research output: Contribution to journalArticle

7 Citations (Scopus)

Abstract

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.

Original languageEnglish (US)
Article number920
JournalSensors (Switzerland)
Volume19
Issue number4
DOIs
StatePublished - Feb 2 2019

Fingerprint

Glioblastoma
surgeons
learning
brain
Tumors
Brain
tumors
Learning
Labels
Neoplasms
Tissue
Neurosurgical Procedures
surgery
Brain Neoplasms
Surgery
preserving
Contrast Media
Support vector machines
image processing
Visualization

Keywords

  • Bioinformatics
  • Brain tumor
  • Cancer surgery
  • Deep learning
  • Hyperspectral imaging
  • Image-guided surgery
  • Intraoperative imaging
  • Precision medicine

ASJC Scopus subject areas

  • Analytical Chemistry
  • Atomic and Molecular Physics, and Optics
  • Biochemistry
  • Instrumentation
  • Electrical and Electronic Engineering

Cite this

Deep learning-based framework for In Vivo identification of glioblastoma tumor using hyperspectral images of human brain. / Fabelo, Himar; Halicek, Martin; Ortega, Samuel; Shahedi, Maysam; Szolna, Adam; Piñeiro, Juan F.; Sosa, Coralia; O’Shanahan, Aruma J.; Bisshopp, Sara; Espino, Carlos; Márquez, Mariano; Hernández, María; Carrera, David; Morera, Jesús; Callico, Gustavo M.; Sarmiento, Roberto; Fei, Baowei.

In: Sensors (Switzerland), Vol. 19, No. 4, 920, 02.02.2019.

Research output: Contribution to journalArticle

Fabelo, H, Halicek, M, Ortega, S, Shahedi, M, Szolna, A, Piñeiro, JF, Sosa, C, O’Shanahan, AJ, Bisshopp, S, Espino, C, Márquez, M, Hernández, M, Carrera, D, Morera, J, Callico, GM, Sarmiento, R & Fei, B 2019, 'Deep learning-based framework for In Vivo identification of glioblastoma tumor using hyperspectral images of human brain', Sensors (Switzerland), vol. 19, no. 4, 920. https://doi.org/10.3390/s19040920
Fabelo, Himar ; Halicek, Martin ; Ortega, Samuel ; Shahedi, Maysam ; Szolna, Adam ; Piñeiro, Juan F. ; Sosa, Coralia ; O’Shanahan, Aruma J. ; Bisshopp, Sara ; Espino, Carlos ; Márquez, Mariano ; Hernández, María ; Carrera, David ; Morera, Jesús ; Callico, Gustavo M. ; Sarmiento, Roberto ; Fei, Baowei. / Deep learning-based framework for In Vivo identification of glioblastoma tumor using hyperspectral images of human brain. In: Sensors (Switzerland). 2019 ; Vol. 19, No. 4.
@article{350e928fa3e64329af599915145ac30a,
title = "Deep learning-based framework for In Vivo identification of glioblastoma tumor using hyperspectral images of human brain",
abstract = "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.",
keywords = "Bioinformatics, Brain tumor, Cancer surgery, Deep learning, Hyperspectral imaging, Image-guided surgery, Intraoperative imaging, Precision medicine",
author = "Himar Fabelo and Martin Halicek and Samuel Ortega and Maysam Shahedi and Adam Szolna and Pi{\~n}eiro, {Juan F.} and Coralia Sosa and O’Shanahan, {Aruma J.} and Sara Bisshopp and Carlos Espino and Mariano M{\'a}rquez and Mar{\'i}a Hern{\'a}ndez and David Carrera and Jes{\'u}s Morera and Callico, {Gustavo M.} and Roberto Sarmiento and Baowei Fei",
year = "2019",
month = "2",
day = "2",
doi = "10.3390/s19040920",
language = "English (US)",
volume = "19",
journal = "Sensors",
issn = "1424-3210",
publisher = "Multidisciplinary Digital Publishing Institute (MDPI)",
number = "4",

}

TY - JOUR

T1 - Deep learning-based framework for In Vivo identification of glioblastoma tumor using hyperspectral images of human brain

AU - Fabelo, Himar

AU - Halicek, Martin

AU - Ortega, Samuel

AU - Shahedi, Maysam

AU - Szolna, Adam

AU - Piñeiro, Juan F.

AU - Sosa, Coralia

AU - O’Shanahan, Aruma J.

AU - Bisshopp, Sara

AU - Espino, Carlos

AU - Márquez, Mariano

AU - Hernández, María

AU - Carrera, David

AU - Morera, Jesús

AU - Callico, Gustavo M.

AU - Sarmiento, Roberto

AU - Fei, Baowei

PY - 2019/2/2

Y1 - 2019/2/2

N2 - 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.

AB - 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.

KW - Bioinformatics

KW - Brain tumor

KW - Cancer surgery

KW - Deep learning

KW - Hyperspectral imaging

KW - Image-guided surgery

KW - Intraoperative imaging

KW - Precision medicine

UR - http://www.scopus.com/inward/record.url?scp=85064944216&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85064944216&partnerID=8YFLogxK

U2 - 10.3390/s19040920

DO - 10.3390/s19040920

M3 - Article

C2 - 30813245

AN - SCOPUS:85064944216

VL - 19

JO - Sensors

JF - Sensors

SN - 1424-3210

IS - 4

M1 - 920

ER -