Cargando…
Neural Networks-Based On-Site Dermatologic Diagnosis through Hyperspectral Epidermal Images
Cancer originates from the uncontrolled growth of healthy cells into a mass. Chromophores, such as hemoglobin and melanin, characterize skin spectral properties, allowing the classification of lesions into different etiologies. Hyperspectral imaging systems gather skin-reflected and transmitted ligh...
Autores principales: | , , , , , , , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9571453/ https://www.ncbi.nlm.nih.gov/pubmed/36236240 http://dx.doi.org/10.3390/s22197139 |
_version_ | 1784810367905431552 |
---|---|
author | La Salvia, Marco Torti, Emanuele Leon, Raquel Fabelo, Himar Ortega, Samuel Balea-Fernandez, Francisco Martinez-Vega, Beatriz Castaño, Irene Almeida, Pablo Carretero, Gregorio Hernandez, Javier A. Callico, Gustavo M. Leporati, Francesco |
author_facet | La Salvia, Marco Torti, Emanuele Leon, Raquel Fabelo, Himar Ortega, Samuel Balea-Fernandez, Francisco Martinez-Vega, Beatriz Castaño, Irene Almeida, Pablo Carretero, Gregorio Hernandez, Javier A. Callico, Gustavo M. Leporati, Francesco |
author_sort | La Salvia, Marco |
collection | PubMed |
description | Cancer originates from the uncontrolled growth of healthy cells into a mass. Chromophores, such as hemoglobin and melanin, characterize skin spectral properties, allowing the classification of lesions into different etiologies. Hyperspectral imaging systems gather skin-reflected and transmitted light into several wavelength ranges of the electromagnetic spectrum, enabling potential skin-lesion differentiation through machine learning algorithms. Challenged by data availability and tiny inter and intra-tumoral variability, here we introduce a pipeline based on deep neural networks to diagnose hyperspectral skin cancer images, targeting a handheld device equipped with a low-power graphical processing unit for routine clinical testing. Enhanced by data augmentation, transfer learning, and hyperparameter tuning, the proposed architectures aim to meet and improve the well-known dermatologist-level detection performances concerning both benign-malignant and multiclass classification tasks, being able to diagnose hyperspectral data considering real-time constraints. Experiments show 87% sensitivity and 88% specificity for benign-malignant classification and specificity above 80% for the multiclass scenario. AUC measurements suggest classification performance improvement above 90% with adequate thresholding. Concerning binary segmentation, we measured skin DICE and IOU higher than 90%. We estimated 1.21 s, at most, consuming 5 Watts to segment the epidermal lesions with the U-Net++ architecture, meeting the imposed time limit. Hence, we can diagnose hyperspectral epidermal data assuming real-time constraints. |
format | Online Article Text |
id | pubmed-9571453 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2022 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-95714532022-10-17 Neural Networks-Based On-Site Dermatologic Diagnosis through Hyperspectral Epidermal Images La Salvia, Marco Torti, Emanuele Leon, Raquel Fabelo, Himar Ortega, Samuel Balea-Fernandez, Francisco Martinez-Vega, Beatriz Castaño, Irene Almeida, Pablo Carretero, Gregorio Hernandez, Javier A. Callico, Gustavo M. Leporati, Francesco Sensors (Basel) Article Cancer originates from the uncontrolled growth of healthy cells into a mass. Chromophores, such as hemoglobin and melanin, characterize skin spectral properties, allowing the classification of lesions into different etiologies. Hyperspectral imaging systems gather skin-reflected and transmitted light into several wavelength ranges of the electromagnetic spectrum, enabling potential skin-lesion differentiation through machine learning algorithms. Challenged by data availability and tiny inter and intra-tumoral variability, here we introduce a pipeline based on deep neural networks to diagnose hyperspectral skin cancer images, targeting a handheld device equipped with a low-power graphical processing unit for routine clinical testing. Enhanced by data augmentation, transfer learning, and hyperparameter tuning, the proposed architectures aim to meet and improve the well-known dermatologist-level detection performances concerning both benign-malignant and multiclass classification tasks, being able to diagnose hyperspectral data considering real-time constraints. Experiments show 87% sensitivity and 88% specificity for benign-malignant classification and specificity above 80% for the multiclass scenario. AUC measurements suggest classification performance improvement above 90% with adequate thresholding. Concerning binary segmentation, we measured skin DICE and IOU higher than 90%. We estimated 1.21 s, at most, consuming 5 Watts to segment the epidermal lesions with the U-Net++ architecture, meeting the imposed time limit. Hence, we can diagnose hyperspectral epidermal data assuming real-time constraints. MDPI 2022-09-21 /pmc/articles/PMC9571453/ /pubmed/36236240 http://dx.doi.org/10.3390/s22197139 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). |
spellingShingle | Article La Salvia, Marco Torti, Emanuele Leon, Raquel Fabelo, Himar Ortega, Samuel Balea-Fernandez, Francisco Martinez-Vega, Beatriz Castaño, Irene Almeida, Pablo Carretero, Gregorio Hernandez, Javier A. Callico, Gustavo M. Leporati, Francesco Neural Networks-Based On-Site Dermatologic Diagnosis through Hyperspectral Epidermal Images |
title | Neural Networks-Based On-Site Dermatologic Diagnosis through Hyperspectral Epidermal Images |
title_full | Neural Networks-Based On-Site Dermatologic Diagnosis through Hyperspectral Epidermal Images |
title_fullStr | Neural Networks-Based On-Site Dermatologic Diagnosis through Hyperspectral Epidermal Images |
title_full_unstemmed | Neural Networks-Based On-Site Dermatologic Diagnosis through Hyperspectral Epidermal Images |
title_short | Neural Networks-Based On-Site Dermatologic Diagnosis through Hyperspectral Epidermal Images |
title_sort | neural networks-based on-site dermatologic diagnosis through hyperspectral epidermal images |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9571453/ https://www.ncbi.nlm.nih.gov/pubmed/36236240 http://dx.doi.org/10.3390/s22197139 |
work_keys_str_mv | AT lasalviamarco neuralnetworksbasedonsitedermatologicdiagnosisthroughhyperspectralepidermalimages AT tortiemanuele neuralnetworksbasedonsitedermatologicdiagnosisthroughhyperspectralepidermalimages AT leonraquel neuralnetworksbasedonsitedermatologicdiagnosisthroughhyperspectralepidermalimages AT fabelohimar neuralnetworksbasedonsitedermatologicdiagnosisthroughhyperspectralepidermalimages AT ortegasamuel neuralnetworksbasedonsitedermatologicdiagnosisthroughhyperspectralepidermalimages AT baleafernandezfrancisco neuralnetworksbasedonsitedermatologicdiagnosisthroughhyperspectralepidermalimages AT martinezvegabeatriz neuralnetworksbasedonsitedermatologicdiagnosisthroughhyperspectralepidermalimages AT castanoirene neuralnetworksbasedonsitedermatologicdiagnosisthroughhyperspectralepidermalimages AT almeidapablo neuralnetworksbasedonsitedermatologicdiagnosisthroughhyperspectralepidermalimages AT carreterogregorio neuralnetworksbasedonsitedermatologicdiagnosisthroughhyperspectralepidermalimages AT hernandezjaviera neuralnetworksbasedonsitedermatologicdiagnosisthroughhyperspectralepidermalimages AT callicogustavom neuralnetworksbasedonsitedermatologicdiagnosisthroughhyperspectralepidermalimages AT leporatifrancesco neuralnetworksbasedonsitedermatologicdiagnosisthroughhyperspectralepidermalimages |