Cargando…

Towards Accurate Diagnosis of Skin Lesions Using Feedforward Back Propagation Neural Networks

In the automatic detection framework, there have been many attempts to develop models for real-time melanoma detection. To effectively discriminate benign and malign skin lesions, this work investigates sixty different architectures of the Feedforward Back Propagation Network (FFBPN), based on shape...

Descripción completa

Detalles Bibliográficos
Autores principales: Moldovanu, Simona, Obreja, Cristian-Dragos, Biswas, Keka C., Moraru, Luminita
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8224667/
https://www.ncbi.nlm.nih.gov/pubmed/34067493
http://dx.doi.org/10.3390/diagnostics11060936
_version_ 1783711936553156608
author Moldovanu, Simona
Obreja, Cristian-Dragos
Biswas, Keka C.
Moraru, Luminita
author_facet Moldovanu, Simona
Obreja, Cristian-Dragos
Biswas, Keka C.
Moraru, Luminita
author_sort Moldovanu, Simona
collection PubMed
description In the automatic detection framework, there have been many attempts to develop models for real-time melanoma detection. To effectively discriminate benign and malign skin lesions, this work investigates sixty different architectures of the Feedforward Back Propagation Network (FFBPN), based on shape asymmetry for an optimal structural design that includes both the hidden neuron number and the input data selection. The reason for the choice of shape asymmetry was based on the 5–10% disagreement between dermatologists regarding the efficacy of asymmetry in the diagnosis of malignant melanoma. Asymmetry is quantified based on lesion shape (contour), moment of inertia of the lesion shape and histograms. The FFBPN has a high architecture flexibility, which indicates it as a favorable tool to avoid the over-parameterization of the ANN and, equally, to discard those redundant input datasets that usually result in poor test performance. The FFBPN was tested on four public image datasets containing melanoma, dysplastic nevus and nevus images. Experimental results on multiple benchmark data sets demonstrate that asymmetry A2 is a meaningful feature for skin lesion classification, and FFBPN with 16 neurons in the hidden layer can model the data without compromising prediction accuracy.
format Online
Article
Text
id pubmed-8224667
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-82246672021-06-25 Towards Accurate Diagnosis of Skin Lesions Using Feedforward Back Propagation Neural Networks Moldovanu, Simona Obreja, Cristian-Dragos Biswas, Keka C. Moraru, Luminita Diagnostics (Basel) Article In the automatic detection framework, there have been many attempts to develop models for real-time melanoma detection. To effectively discriminate benign and malign skin lesions, this work investigates sixty different architectures of the Feedforward Back Propagation Network (FFBPN), based on shape asymmetry for an optimal structural design that includes both the hidden neuron number and the input data selection. The reason for the choice of shape asymmetry was based on the 5–10% disagreement between dermatologists regarding the efficacy of asymmetry in the diagnosis of malignant melanoma. Asymmetry is quantified based on lesion shape (contour), moment of inertia of the lesion shape and histograms. The FFBPN has a high architecture flexibility, which indicates it as a favorable tool to avoid the over-parameterization of the ANN and, equally, to discard those redundant input datasets that usually result in poor test performance. The FFBPN was tested on four public image datasets containing melanoma, dysplastic nevus and nevus images. Experimental results on multiple benchmark data sets demonstrate that asymmetry A2 is a meaningful feature for skin lesion classification, and FFBPN with 16 neurons in the hidden layer can model the data without compromising prediction accuracy. MDPI 2021-05-22 /pmc/articles/PMC8224667/ /pubmed/34067493 http://dx.doi.org/10.3390/diagnostics11060936 Text en © 2021 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
Moldovanu, Simona
Obreja, Cristian-Dragos
Biswas, Keka C.
Moraru, Luminita
Towards Accurate Diagnosis of Skin Lesions Using Feedforward Back Propagation Neural Networks
title Towards Accurate Diagnosis of Skin Lesions Using Feedforward Back Propagation Neural Networks
title_full Towards Accurate Diagnosis of Skin Lesions Using Feedforward Back Propagation Neural Networks
title_fullStr Towards Accurate Diagnosis of Skin Lesions Using Feedforward Back Propagation Neural Networks
title_full_unstemmed Towards Accurate Diagnosis of Skin Lesions Using Feedforward Back Propagation Neural Networks
title_short Towards Accurate Diagnosis of Skin Lesions Using Feedforward Back Propagation Neural Networks
title_sort towards accurate diagnosis of skin lesions using feedforward back propagation neural networks
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8224667/
https://www.ncbi.nlm.nih.gov/pubmed/34067493
http://dx.doi.org/10.3390/diagnostics11060936
work_keys_str_mv AT moldovanusimona towardsaccuratediagnosisofskinlesionsusingfeedforwardbackpropagationneuralnetworks
AT obrejacristiandragos towardsaccuratediagnosisofskinlesionsusingfeedforwardbackpropagationneuralnetworks
AT biswaskekac towardsaccuratediagnosisofskinlesionsusingfeedforwardbackpropagationneuralnetworks
AT moraruluminita towardsaccuratediagnosisofskinlesionsusingfeedforwardbackpropagationneuralnetworks