Please use this identifier to cite or link to this item: http://hdl.handle.net/10553/118307
Title: Deep Convolutional Generative Adversarial Networks to Enhance Artificial Intelligence in Healthcare: A Skin Cancer Application
Authors: La Salvia, Marco
Torti, Emanuele
León, Raquel 
Fabelo, Himar A. 
Ortega, Samuel 
Martínez Vega, Beatriz 
Callicó, Gustavo M. 
Leporati, Francesco
UNESCO Clasification: 3307 Tecnología electrónica
Keywords: Deep Convolutional Generative Adversarial Networks
Deep Learning
Hyperspectral Imaging
Medical Hyperspectral Images
Synthetic Data Generation
Issue Date: 2022
Journal: Sensors (Switzerland) 
Abstract: In recent years, researchers designed several artificial intelligence solutions for healthcare applications, which usually evolved into functional solutions for clinical practice. Furthermore, deep learning (DL) methods are well-suited to process the broad amounts of data acquired by wearable devices, smartphones, and other sensors employed in different medical domains. Conceived to serve the role of diagnostic tool and surgical guidance, hyperspectral images emerged as a non-contact, non-ionizing, and label-free technology. However, the lack of large datasets to efficiently train the models limits DL applications in the medical field. Hence, its usage with hyperspectral images is still at an early stage. We propose a deep convolutional generative adversarial network to generate synthetic hyperspectral images of epidermal lesions, targeting skin cancer diagnosis, and overcome small-sized datasets challenges to train DL architectures. Experimental results show the effectiveness of the proposed framework, capable of generating synthetic data to train DL classifiers.
URI: http://hdl.handle.net/10553/118307
DOI: 10.3390/s22166145
Source: Sensors (Basel, Switzerland)[EISSN 1424-8220],v. 22 (16), (Agosto 2022)
Appears in Collections:Artículos
Adobe PDF (2,86 MB)
Show full item record

SCOPUSTM   
Citations

6
checked on Mar 24, 2024

Page view(s)

56
checked on Feb 10, 2024

Download(s)

44
checked on Feb 10, 2024

Google ScholarTM

Check

Altmetric


Share



Export metadata



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