<italic>In-Vivo</italic> Hyperspectral Human Brain Image Database for Brain Cancer Detection
The use of hyperspectral imaging for medical applications is becoming more common in recent years. One of the main obstacles that researchers find when developing hyperspectral algorithms for medical applications is the lack of specific, publicly available, and hyperspectral medical data. The work d...
Main Authors: | , , , , , , , , , , , , , , , , , , , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2019-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/8667294/ |
id |
doaj-217d6dff322d472a81253ca6dd596240 |
---|---|
record_format |
Article |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Himar Fabelo Samuel Ortega Adam Szolna Diederik Bulters Juan F. Pineiro Silvester Kabwama Aruma J-O'Shanahan Harry Bulstrode Sara Bisshopp B. Ravi Kiran Daniele Ravi Raquel Lazcano Daniel Madronal Coralia Sosa Carlos Espino Mariano Marquez Maria De La Luz Plaza Rafael Camacho David Carrera Maria Hernandez Gustavo M. Callico Jesus Morera Molina Bogdan Stanciulescu Guang-Zhong Yang Ruben Salvador Perea Eduardo Juarez Cesar Sanz Roberto Sarmiento |
spellingShingle |
Himar Fabelo Samuel Ortega Adam Szolna Diederik Bulters Juan F. Pineiro Silvester Kabwama Aruma J-O'Shanahan Harry Bulstrode Sara Bisshopp B. Ravi Kiran Daniele Ravi Raquel Lazcano Daniel Madronal Coralia Sosa Carlos Espino Mariano Marquez Maria De La Luz Plaza Rafael Camacho David Carrera Maria Hernandez Gustavo M. Callico Jesus Morera Molina Bogdan Stanciulescu Guang-Zhong Yang Ruben Salvador Perea Eduardo Juarez Cesar Sanz Roberto Sarmiento <italic>In-Vivo</italic> Hyperspectral Human Brain Image Database for Brain Cancer Detection IEEE Access Hyperspectral imaging cancer detection biomedical imaging medical diagnostic imaging image databases |
author_facet |
Himar Fabelo Samuel Ortega Adam Szolna Diederik Bulters Juan F. Pineiro Silvester Kabwama Aruma J-O'Shanahan Harry Bulstrode Sara Bisshopp B. Ravi Kiran Daniele Ravi Raquel Lazcano Daniel Madronal Coralia Sosa Carlos Espino Mariano Marquez Maria De La Luz Plaza Rafael Camacho David Carrera Maria Hernandez Gustavo M. Callico Jesus Morera Molina Bogdan Stanciulescu Guang-Zhong Yang Ruben Salvador Perea Eduardo Juarez Cesar Sanz Roberto Sarmiento |
author_sort |
Himar Fabelo |
title |
<italic>In-Vivo</italic> Hyperspectral Human Brain Image Database for Brain Cancer Detection |
title_short |
<italic>In-Vivo</italic> Hyperspectral Human Brain Image Database for Brain Cancer Detection |
title_full |
<italic>In-Vivo</italic> Hyperspectral Human Brain Image Database for Brain Cancer Detection |
title_fullStr |
<italic>In-Vivo</italic> Hyperspectral Human Brain Image Database for Brain Cancer Detection |
title_full_unstemmed |
<italic>In-Vivo</italic> Hyperspectral Human Brain Image Database for Brain Cancer Detection |
title_sort |
<italic>in-vivo</italic> hyperspectral human brain image database for brain cancer detection |
publisher |
IEEE |
series |
IEEE Access |
issn |
2169-3536 |
publishDate |
2019-01-01 |
description |
The use of hyperspectral imaging for medical applications is becoming more common in recent years. One of the main obstacles that researchers find when developing hyperspectral algorithms for medical applications is the lack of specific, publicly available, and hyperspectral medical data. The work described in this paper was developed within the framework of the European project HELICoiD (HypErspectraL Imaging Cancer Detection), which had as a main goal the application of hyperspectral imaging to the delineation of brain tumors in real-time during neurosurgical operations. In this paper, the methodology followed to generate the first hyperspectral database of in-vivo human brain tissues is presented. Data was acquired employing a customized hyperspectral acquisition system capable of capturing information in the Visual and Near InfraRed (VNIR) range from 400 to 1000 nm. Repeatability was assessed for the cases where two images of the same scene were captured consecutively. The analysis reveals that the system works more efficiently in the spectral range between 450 and 900 nm. A total of 36 hyperspectral images from 22 different patients were obtained. From these data, more than 300 000 spectral signatures were labeled employing a semi-automatic methodology based on the spectral angle mapper algorithm. Four different classes were defined: normal tissue, tumor tissue, blood vessel, and background elements. All the hyperspectral data has been made available in a public repository. |
topic |
Hyperspectral imaging cancer detection biomedical imaging medical diagnostic imaging image databases |
url |
https://ieeexplore.ieee.org/document/8667294/ |
work_keys_str_mv |
AT himarfabelo italicinvivoitalichyperspectralhumanbrainimagedatabaseforbraincancerdetection AT samuelortega italicinvivoitalichyperspectralhumanbrainimagedatabaseforbraincancerdetection AT adamszolna italicinvivoitalichyperspectralhumanbrainimagedatabaseforbraincancerdetection AT diederikbulters italicinvivoitalichyperspectralhumanbrainimagedatabaseforbraincancerdetection AT juanfpineiro italicinvivoitalichyperspectralhumanbrainimagedatabaseforbraincancerdetection AT silvesterkabwama italicinvivoitalichyperspectralhumanbrainimagedatabaseforbraincancerdetection AT arumajoshanahan italicinvivoitalichyperspectralhumanbrainimagedatabaseforbraincancerdetection AT harrybulstrode italicinvivoitalichyperspectralhumanbrainimagedatabaseforbraincancerdetection AT sarabisshopp italicinvivoitalichyperspectralhumanbrainimagedatabaseforbraincancerdetection AT bravikiran italicinvivoitalichyperspectralhumanbrainimagedatabaseforbraincancerdetection AT danieleravi italicinvivoitalichyperspectralhumanbrainimagedatabaseforbraincancerdetection AT raquellazcano italicinvivoitalichyperspectralhumanbrainimagedatabaseforbraincancerdetection AT danielmadronal italicinvivoitalichyperspectralhumanbrainimagedatabaseforbraincancerdetection AT coraliasosa italicinvivoitalichyperspectralhumanbrainimagedatabaseforbraincancerdetection AT carlosespino italicinvivoitalichyperspectralhumanbrainimagedatabaseforbraincancerdetection AT marianomarquez italicinvivoitalichyperspectralhumanbrainimagedatabaseforbraincancerdetection AT mariadelaluzplaza italicinvivoitalichyperspectralhumanbrainimagedatabaseforbraincancerdetection AT rafaelcamacho italicinvivoitalichyperspectralhumanbrainimagedatabaseforbraincancerdetection AT davidcarrera italicinvivoitalichyperspectralhumanbrainimagedatabaseforbraincancerdetection AT mariahernandez italicinvivoitalichyperspectralhumanbrainimagedatabaseforbraincancerdetection AT gustavomcallico italicinvivoitalichyperspectralhumanbrainimagedatabaseforbraincancerdetection AT jesusmoreramolina italicinvivoitalichyperspectralhumanbrainimagedatabaseforbraincancerdetection AT bogdanstanciulescu italicinvivoitalichyperspectralhumanbrainimagedatabaseforbraincancerdetection AT guangzhongyang italicinvivoitalichyperspectralhumanbrainimagedatabaseforbraincancerdetection AT rubensalvadorperea italicinvivoitalichyperspectralhumanbrainimagedatabaseforbraincancerdetection AT eduardojuarez italicinvivoitalichyperspectralhumanbrainimagedatabaseforbraincancerdetection AT cesarsanz italicinvivoitalichyperspectralhumanbrainimagedatabaseforbraincancerdetection AT robertosarmiento italicinvivoitalichyperspectralhumanbrainimagedatabaseforbraincancerdetection |
_version_ |
1721540449576943616 |
spelling |
doaj-217d6dff322d472a81253ca6dd5962402021-04-05T17:00:38ZengIEEEIEEE Access2169-35362019-01-017390983911610.1109/ACCESS.2019.29047888667294<italic>In-Vivo</italic> Hyperspectral Human Brain Image Database for Brain Cancer DetectionHimar Fabelo0https://orcid.org/0000-0002-9794-490XSamuel Ortega1https://orcid.org/0000-0002-7519-954XAdam Szolna2Diederik Bulters3Juan F. Pineiro4Silvester Kabwama5Aruma J-O'Shanahan6Harry Bulstrode7Sara Bisshopp8B. Ravi Kiran9Daniele Ravi10Raquel Lazcano11Daniel Madronal12Coralia Sosa13Carlos Espino14Mariano Marquez15Maria De La Luz Plaza16Rafael Camacho17David Carrera18Maria Hernandez19Gustavo M. Callico20https://orcid.org/0000-0002-3784-5504Jesus Morera Molina21Bogdan Stanciulescu22Guang-Zhong Yang23Ruben Salvador Perea24https://orcid.org/0000-0002-0021-5808Eduardo Juarez25Cesar Sanz26Roberto Sarmiento27Institute for Applied Microelectronics, University of Las Palmas de Gran Canaria, Las Palmas de Gran Canaria, SpainInstitute for Applied Microelectronics, University of Las Palmas de Gran Canaria, Las Palmas de Gran Canaria, SpainDepartment of Neurosurgery, University Hospital Doctor Negrin, Las Palmas de Gran Canaria, SpainWessex Neurological Centre, University Hospital Southampton, Southampton, U.K.Department of Neurosurgery, University Hospital Doctor Negrin, Las Palmas de Gran Canaria, SpainWessex Neurological Centre, University Hospital Southampton, Southampton, U.K.Department of Neurosurgery, University Hospital Doctor Negrin, Las Palmas de Gran Canaria, SpainDepartment of Neurosurgery, Addenbrookes Hospital, University of Cambridge, Cambridge, U.K.Department of Neurosurgery, University Hospital Doctor Negrin, Las Palmas de Gran Canaria, SpainAutonomous Systems, AKKA Technologies, Paris, FranceThe Hamlyn Centre, Imperial College London, London, U.K.Centre of Software Technologies and Multimedia Systems, Universidad Politécnica de Madrid, Madrid, SpainCentre of Software Technologies and Multimedia Systems, Universidad Politécnica de Madrid, Madrid, SpainDepartment of Neurosurgery, University Hospital Doctor Negrin, Las Palmas de Gran Canaria, SpainDepartment of Neurosurgery, University Hospital Doctor Negrin, Las Palmas de Gran Canaria, SpainDepartment of Neurosurgery, University Hospital Doctor Negrin, Las Palmas de Gran Canaria, SpainDepartment of Pathological Anatomy, University Hospital Doctor Negrin, Las Palmas de Gran Canaria, SpainDepartment of Pathological Anatomy, University Hospital Doctor Negrin, Las Palmas de Gran Canaria, SpainDepartment of Neurosurgery, University Hospital Doctor Negrin, Las Palmas de Gran Canaria, SpainDepartment of Neurosurgery, University Hospital Doctor Negrin, Las Palmas de Gran Canaria, SpainInstitute for Applied Microelectronics, University of Las Palmas de Gran Canaria, Las Palmas de Gran Canaria, SpainDepartment of Neurosurgery, University Hospital Doctor Negrin, Las Palmas de Gran Canaria, SpainEcole Nationale Supérieure des Mines de Paris, MINES ParisTech, Paris, FranceThe Hamlyn Centre, Imperial College London, London, U.K.Centre of Software Technologies and Multimedia Systems, Universidad Politécnica de Madrid, Madrid, SpainCentre of Software Technologies and Multimedia Systems, Universidad Politécnica de Madrid, Madrid, SpainCentre of Software Technologies and Multimedia Systems, Universidad Politécnica de Madrid, Madrid, SpainInstitute for Applied Microelectronics, University of Las Palmas de Gran Canaria, Las Palmas de Gran Canaria, SpainThe use of hyperspectral imaging for medical applications is becoming more common in recent years. One of the main obstacles that researchers find when developing hyperspectral algorithms for medical applications is the lack of specific, publicly available, and hyperspectral medical data. The work described in this paper was developed within the framework of the European project HELICoiD (HypErspectraL Imaging Cancer Detection), which had as a main goal the application of hyperspectral imaging to the delineation of brain tumors in real-time during neurosurgical operations. In this paper, the methodology followed to generate the first hyperspectral database of in-vivo human brain tissues is presented. Data was acquired employing a customized hyperspectral acquisition system capable of capturing information in the Visual and Near InfraRed (VNIR) range from 400 to 1000 nm. Repeatability was assessed for the cases where two images of the same scene were captured consecutively. The analysis reveals that the system works more efficiently in the spectral range between 450 and 900 nm. A total of 36 hyperspectral images from 22 different patients were obtained. From these data, more than 300 000 spectral signatures were labeled employing a semi-automatic methodology based on the spectral angle mapper algorithm. Four different classes were defined: normal tissue, tumor tissue, blood vessel, and background elements. All the hyperspectral data has been made available in a public repository.https://ieeexplore.ieee.org/document/8667294/Hyperspectral imagingcancer detectionbiomedical imagingmedical diagnostic imagingimage databases |