Please use this identifier to cite or link to this item:
Title: Recent advances in hyperspectral imaging for melanoma detection
Authors: Johansen, Thomas Haugland
Møllersen, Kajsa
Ortega Sarmiento, Samuel 
Fabelo Gómez, Himar Antonio 
García Romero, Leví Aday 
Marrero Callicó, Gustavo Iván 
Godtliebsen, Fred
UNESCO Clasification: 3314 Tecnología médica
Keywords: Hyperspectral imaging
Machine learning
Skin cancer
Issue Date: 2020
Project: Identificación Hiperespectral de Tumores Cerebrales (Ithaca)
Journal: Wiley Interdisciplinary Reviews: Computational Statistics 
Abstract: Skin cancer is one of the most common types of cancer. Skin cancers are classified as nonmelanoma and melanoma, with the first type being the most frequent and the second type being the most deadly. The key to effective treatment of skin cancer is early detection. With the recent increase of computational power, the number of algorithms to detect and classify skin lesions has increased. The overall verdict on systems based on clinical and dermoscopic images captured with conventional RGB (red, green, and blue) cameras is that they do not outperform dermatologists. Computer-based systems based on conventional RGB images seem to have reached an upper limit in their performance, while emerging technologies such as hyperspectral and multispectral imaging might possibly improve the results. These types of images can explore spectral regions beyond the human eye capabilities. Feature selection and dimensionality reduction are crucial parts of extracting salient information from this type of data. It is necessary to extend current classification methodologies to use all of the spatiospectral information, and deep learning models should be explored since they are capable of learning robust feature detectors from data. There is a lack of large, high-quality datasets of hyperspectral skin lesion images, and there is a need for tools that can aid with monitoring the evolution of skin lesions over time. To understand the rich information contained in hyperspectral images, further research using data science and statistical methodologies, such as functional data analysis, scale-space theory, machine learning, and so on, are essential. This article is categorized under: Applications of Computational Statistics > Health and Medical Data/Informatics.
ISSN: 1939-5108
DOI: 10.1002/wics.1465
Source: Wiley interdisciplinary reviews. Computational statistics [ISSN 1939-0068], v. 12(1), e1465
Appears in Collections:Artículos
Show full item record


checked on Sep 18, 2022

Page view(s)

checked on Sep 24, 2022

Google ScholarTM




Export metadata

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