Please use this identifier to cite or link to this item:
Title: Hyperspectral Imaging for Major Neurocognitive Disorder Detection in Plasma Samples
Authors: León Martín, Sonia Raquel 
Martínez Vega, Beatriz 
Fabelo Gómez, Himar Antonio 
Ortega Sarmiento, Samuel 
Marrero Callicó, Gustavo Iván 
Balea Fernández, Francisco Javier 
Bilbao Sieyro, Cristina 
UNESCO Clasification: 32 Ciencias médicas
320507 Neurología
320711 Neuropatología
Keywords: Hyperspectral Imaging
K-Nearest Neighborhood
Neurocognitive Disorders
Random Forest
Supervised Learning, et al
Issue Date: 2020
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Conference: 35th Conference on Design of Circuits and Integrated Systems - DCIS 2020
Abstract: Neurocognitive disorders (NCD) affect over 50 million people globally. The detection biomarkers using brain imaging or cerebrospinal fluid are expensive procedures. Blood-based biomarkers such as plasma or serum present a cost-effective alternative. The work presented in this paper is focused on the use of hyperspectral (HS) imaging (HSI) to classify plasma samples in order to discriminate between patients with major NCD and healthy control subjects. HS images of plasma samples were obtained using a SWIR (Short-Wave Infrared) camera able to capture 273 bands within the 900-2,500 nm spectral range. A preliminary HSI database was obtained with 20 major NCD samples and 20 control samples. This data was segmented and classified using pixel-wise supervised classification algorithms, achieving 75% sensitivity and 100% specificity results with the best classifier in the test set.
ISBN: 9781728191324
DOI: 10.1109/DCIS51330.2020.9268625
Source: 2020 XXXV Conference on Design of Circuits and Integrated Systems (DCIS)
Appears in Collections:Actas de congresos
Show full item record

Google ScholarTM




Export metadata

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