|Title:||Neural Networks-Based On-Site Dermatologic Diagnosis through Hyperspectral Epidermal Images||Authors:||La Salvia, Marco
León Martín, Sonia Raquel
Fabelo Gómez, Himar Antonio
Balea Fernandez, Francisco Javier
Martínez Vega, Beatriz
Castaño González, Irene
Almeida Martín, Pablo Julio
Carretero Hernández, Gregorio
Hernández, Javier A.
Marrero Callicó, Gustavo Iván
|UNESCO Clasification:||3314 Tecnología médica
|Issue Date:||2022||Project:||Talent Imágenes Hiperespectrales Para Aplicaciones de Inteligencia Artificial||Journal:||Sensors (Switzerland)||Abstract:||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.||URI:||http://hdl.handle.net/10553/119299||ISSN:||1424-8220||DOI:||10.3390/s22197139||Source:||Sensors (Switzerland) [ISSN 1424-8220], v. 22 (19), 7139, (Septiembre 2022)|
|Appears in Collections:||Artículos|
Items in accedaCRIS are protected by copyright, with all rights reserved, unless otherwise indicated.