Towards Real-Time Computing of Intraoperative Hyperspectral Imaging for Brain Cancer Detection Using Multi-GPU Platforms

Towards Real-Time Computing of Intraoperative Hyperspectral Imaging for Brain Cancer Detection Using Multi-GPU Platforms

Several causes make brain cancer identification a challenging task for neurosurgeons during the surgical procedure. The surgeons' naked eye sometimes is not enough to accurately delineate the brain tumor location and extension due to its diffuse nature that infiltrates in the surrounding health...

Full description

Bibliographic Details
Main Authors: Giordana Florimbi, Himar Fabelo, Emanuele Torti, Samuel Ortega, Margarita Marrero-Martin, Gustavo M. Callico, Giovanni Danese, Francesco Leporati
Format: Article
Language:English
Published: IEEE 2020-01-01
Series:IEEE Access
Subjects:
Hyperspectral imaging
high performance computing
graphic processing unit
parallel processing
parallel architectures
image processing
Online Access:https://ieeexplore.ieee.org/document/8949497/
id doaj-3f5e3e80b3f14f7c8df919cf92db7001
record_format Article
spelling doaj-3f5e3e80b3f14f7c8df919cf92db70012021-03-30T01:18:24ZengIEEEIEEE Access2169-35362020-01-0188485850110.1109/ACCESS.2020.29639398949497Towards Real-Time Computing of Intraoperative Hyperspectral Imaging for Brain Cancer Detection Using Multi-GPU PlatformsGiordana Florimbi0https://orcid.org/0000-0003-1062-3044Himar Fabelo1https://orcid.org/0000-0002-9794-490XEmanuele Torti2https://orcid.org/0000-0001-8437-8227Samuel Ortega3https://orcid.org/0000-0002-7519-954XMargarita Marrero-Martin4https://orcid.org/0000-0002-0861-9954Gustavo M. Callico5https://orcid.org/0000-0002-3784-5504Giovanni Danese6https://orcid.org/0000-0002-4411-681XFrancesco Leporati7https://orcid.org/0000-0003-2901-4935Department of Electrical, Computer and Biomedical Engineering, University of Pavia, Pavia, ItalyInstitute for Applied Microelectronics (IUMA), University of Las Palmas de Gran Canaria (ULPGC), Las Palmas de Gran Canaria, SpainDepartment of Electrical, Computer and Biomedical Engineering, University of Pavia, Pavia, ItalyInstitute for Applied Microelectronics (IUMA), University of Las Palmas de Gran Canaria (ULPGC), Las Palmas de Gran Canaria, SpainInstitute for Applied Microelectronics (IUMA), University of Las Palmas de Gran Canaria (ULPGC), Las Palmas de Gran Canaria, SpainInstitute for Applied Microelectronics (IUMA), University of Las Palmas de Gran Canaria (ULPGC), Las Palmas de Gran Canaria, SpainDepartment of Electrical, Computer and Biomedical Engineering, University of Pavia, Pavia, ItalyDepartment of Electrical, Computer and Biomedical Engineering, University of Pavia, Pavia, ItalySeveral causes make brain cancer identification a challenging task for neurosurgeons during the surgical procedure. The surgeons' naked eye sometimes is not enough to accurately delineate the brain tumor location and extension due to its diffuse nature that infiltrates in the surrounding healthy tissue. For this reason, a support system that provides accurate cancer delimitation is essential in order to improve the surgery outcomes and hence the patient's quality of life. The brain cancer detection system developed as part of the “HypErspectraL Imaging Cancer Detection” (HELICoiD) European project meets this requirement exploiting a non-invasive technique suitable for medical diagnosis: the hyperspectral imaging (HSI). A crucial constraint that this system has to satisfy is providing a real-time response in order to not prolong the surgery. The large amount of data that characterizes the hyperspectral images, and the complex elaborations performed by the classification system make the High Performance Computing (HPC) systems essential to provide real-time processing. The most efficient implementation developed in this work, which exploits the Graphic Processing Unit (GPU) technology, is able to classify the biggest image of the database (worst case) in less than three seconds, largely satisfying the real-time constraint set to 1 minute for surgical procedures, becoming a potential solution to implement hyperspectral video processing in the near future.https://ieeexplore.ieee.org/document/8949497/Hyperspectral imaginghigh performance computinggraphic processing unitparallel processingparallel architecturesimage processing
collection DOAJ
language English
format Article
sources DOAJ
author Giordana Florimbi
Himar Fabelo
Emanuele Torti
Samuel Ortega
Margarita Marrero-Martin
Gustavo M. Callico
Giovanni Danese
Francesco Leporati
spellingShingle Giordana Florimbi
Himar Fabelo
Emanuele Torti
Samuel Ortega
Margarita Marrero-Martin
Gustavo M. Callico
Giovanni Danese
Francesco Leporati
Towards Real-Time Computing of Intraoperative Hyperspectral Imaging for Brain Cancer Detection Using Multi-GPU Platforms
IEEE Access
Hyperspectral imaging
high performance computing
graphic processing unit
parallel processing
parallel architectures
image processing
author_facet Giordana Florimbi
Himar Fabelo
Emanuele Torti
Samuel Ortega
Margarita Marrero-Martin
Gustavo M. Callico
Giovanni Danese
Francesco Leporati
author_sort Giordana Florimbi
title Towards Real-Time Computing of Intraoperative Hyperspectral Imaging for Brain Cancer Detection Using Multi-GPU Platforms
title_short Towards Real-Time Computing of Intraoperative Hyperspectral Imaging for Brain Cancer Detection Using Multi-GPU Platforms
title_full Towards Real-Time Computing of Intraoperative Hyperspectral Imaging for Brain Cancer Detection Using Multi-GPU Platforms
title_fullStr Towards Real-Time Computing of Intraoperative Hyperspectral Imaging for Brain Cancer Detection Using Multi-GPU Platforms
title_full_unstemmed Towards Real-Time Computing of Intraoperative Hyperspectral Imaging for Brain Cancer Detection Using Multi-GPU Platforms
title_sort towards real-time computing of intraoperative hyperspectral imaging for brain cancer detection using multi-gpu platforms
publisher IEEE
series IEEE Access
issn 2169-3536
publishDate 2020-01-01
description Several causes make brain cancer identification a challenging task for neurosurgeons during the surgical procedure. The surgeons' naked eye sometimes is not enough to accurately delineate the brain tumor location and extension due to its diffuse nature that infiltrates in the surrounding healthy tissue. For this reason, a support system that provides accurate cancer delimitation is essential in order to improve the surgery outcomes and hence the patient's quality of life. The brain cancer detection system developed as part of the “HypErspectraL Imaging Cancer Detection” (HELICoiD) European project meets this requirement exploiting a non-invasive technique suitable for medical diagnosis: the hyperspectral imaging (HSI). A crucial constraint that this system has to satisfy is providing a real-time response in order to not prolong the surgery. The large amount of data that characterizes the hyperspectral images, and the complex elaborations performed by the classification system make the High Performance Computing (HPC) systems essential to provide real-time processing. The most efficient implementation developed in this work, which exploits the Graphic Processing Unit (GPU) technology, is able to classify the biggest image of the database (worst case) in less than three seconds, largely satisfying the real-time constraint set to 1 minute for surgical procedures, becoming a potential solution to implement hyperspectral video processing in the near future.
topic Hyperspectral imaging
high performance computing
graphic processing unit
parallel processing
parallel architectures
image processing
url https://ieeexplore.ieee.org/document/8949497/
work_keys_str_mv AT giordanaflorimbi towardsrealtimecomputingofintraoperativehyperspectralimagingforbraincancerdetectionusingmultigpuplatforms
AT himarfabelo towardsrealtimecomputingofintraoperativehyperspectralimagingforbraincancerdetectionusingmultigpuplatforms
AT emanueletorti towardsrealtimecomputingofintraoperativehyperspectralimagingforbraincancerdetectionusingmultigpuplatforms
AT samuelortega towardsrealtimecomputingofintraoperativehyperspectralimagingforbraincancerdetectionusingmultigpuplatforms
AT margaritamarreromartin towardsrealtimecomputingofintraoperativehyperspectralimagingforbraincancerdetectionusingmultigpuplatforms
AT gustavomcallico towardsrealtimecomputingofintraoperativehyperspectralimagingforbraincancerdetectionusingmultigpuplatforms
AT giovannidanese towardsrealtimecomputingofintraoperativehyperspectralimagingforbraincancerdetectionusingmultigpuplatforms
AT francescoleporati towardsrealtimecomputingofintraoperativehyperspectralimagingforbraincancerdetectionusingmultigpuplatforms
_version_ 1724187234618310656

Similar Items