Please use this identifier to cite or link to this item: http://hdl.handle.net/10553/52534
Title: Hyperspectral database of pathological in-vitro human brain samples to detect carcinogenic tissues
Authors: Ortega, S. 
Callico, G. M. 
Plaza, M.L. 
Camacho, R
Fabelo, H. 
Sarmiento, R. 
UNESCO Clasification: 3314 Tecnología médica
Keywords: Artificial neural network
Brain cancer detection
Data mining
Hyperspectral imaging
Support vector machine
Issue Date: 2016
Journal: Proceedings - International Symposium on Biomedical Imaging
Conference: 13th IEEE International Symposium on Biomedical Imaging (ISBI) 
2016 IEEE 13th International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2016 
Abstract: Hyperspectral imaging is an emerging technology for medical diagnosis. Some previous studies have used this type of images to detect cancer diseases. In this research work, a multidisciplinary team conformed by pathologists and engineers has created a diagnosed hyperspectral database of in-vitro human brain tissues. In order to capture the hyperspectral information from histological slides, an acquisition system based on a microscope coupled with a hyperspectral camera has been developed. Preliminary results of applying two different supervised classification algorithms (Support Vector Machines and Artificial Neural Networks) to the hyperspectral database show that an automatic discrimination between healthy and tumour brain tissues from in-vitro samples is possible using exclusively their spectral information. The sensitivity and the specificity are over 92% in all the cases.
URI: http://hdl.handle.net/10553/52534
ISBN: 9781479923502
ISSN: 1945-7928
DOI: 10.1109/ISBI.2016.7493285
Source: Proceedings - International Symposium on Biomedical Imaging[ISSN 1945-7928],v. 2016-June (7493285), p. 369-372
Appears in Collections:Actas de congresos
Show full item record

SCOPUSTM   
Citations

9
checked on Feb 21, 2021

WEB OF SCIENCETM
Citations

5
checked on Feb 21, 2021

Page view(s)

9
checked on Feb 21, 2021

Google ScholarTM

Check

Altmetric


Share



Export metadata



Items in accedaCRIS are protected by copyright, with all rights reserved, unless otherwise indicated.