Please use this identifier to cite or link to this item: http://hdl.handle.net/10553/77331
Title: Curve‐based classification approach for hyperspectral dermatologic data processing
Authors: Uteng, Stig
Quevedo Gutiérrez, Eduardo Gregorio 
Marrero Callicó, Gustavo Iván 
Castaño González, Irene
Carretero Hernández, Gregorio
Almeida Martín, Pablo
Garcia del Toro, Aday
Hernández Santana, Javier A.
Godtliebsen, Fred
UNESCO Clasification: 3314 Tecnología médica
320106 Dermatología
Keywords: Hyperspectral
Curve fit
Statistical discrimination
Melanoma
Benign, et al
Issue Date: 2021
Journal: Sensors (Switzerland) 
Abstract: This paper shows new contributions in the detection of skin cancer, where we present the use of a customized hyperspectral system that captures images in the spectral range from 450 to 950 nm. By choosing a 7 × 7 sub-image of each channel in the hyperspectral image (HSI) and then taking the mean and standard deviation of these sub-images, we were able to make fits of the resulting curves. These fitted curves had certain characteristics, which then served as a basis of classification. The most distinct fit was for the melanoma pigmented skin lesions (PSLs), which is also the most aggressive malignant cancer. Furthermore, we were able to classify the other PSLs in malignant and benign classes. This gives us a rather complete classification method for PSLs with a novel perspective of the classification procedure by exploiting the variability of each channel in the HSI.
URI: http://hdl.handle.net/10553/77331
ISSN: 1424-8220
DOI: 10.3390/s21030680
Source: Sensors (Switzerland) [ISSN 1424-8220], v. 21 (3), p. 1-13
Appears in Collections:Artículos
Thumbnail
Adobe PDF (1,46 MB)
Show full item record

SCOPUSTM   
Citations

2
checked on Nov 24, 2024

WEB OF SCIENCETM
Citations

1
checked on Nov 24, 2024

Page view(s)

199
checked on Aug 24, 2024

Download(s)

126
checked on Aug 24, 2024

Google ScholarTM

Check

Altmetric


Share



Export metadata



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