Cargando…

Computer Aided Diagnosis of Melanoma Using Deep Neural Networks and Game Theory: Application on Dermoscopic Images of Skin Lesions

Early detection of melanoma remains a daily challenge due to the increasing number of cases and the lack of dermatologists. Thus, AI-assisted diagnosis is considered as a possible solution for this issue. Despite the great advances brought by deep learning and especially convolutional neural network...

Descripción completa

Detalles Bibliográficos
Autores principales: Foahom Gouabou, Arthur Cartel, Collenne, Jules, Monnier, Jilliana, Iguernaissi, Rabah, Damoiseaux, Jean-Luc, Moudafi, Abdellatif, Merad, Djamal
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9696950/
https://www.ncbi.nlm.nih.gov/pubmed/36430315
http://dx.doi.org/10.3390/ijms232213838
_version_ 1784838437052874752
author Foahom Gouabou, Arthur Cartel
Collenne, Jules
Monnier, Jilliana
Iguernaissi, Rabah
Damoiseaux, Jean-Luc
Moudafi, Abdellatif
Merad, Djamal
author_facet Foahom Gouabou, Arthur Cartel
Collenne, Jules
Monnier, Jilliana
Iguernaissi, Rabah
Damoiseaux, Jean-Luc
Moudafi, Abdellatif
Merad, Djamal
author_sort Foahom Gouabou, Arthur Cartel
collection PubMed
description Early detection of melanoma remains a daily challenge due to the increasing number of cases and the lack of dermatologists. Thus, AI-assisted diagnosis is considered as a possible solution for this issue. Despite the great advances brought by deep learning and especially convolutional neural networks (CNNs), computer-aided diagnosis (CAD) systems are still not used in clinical practice. This may be explained by the dermatologist’s fear of being misled by a false negative and the assimilation of CNNs to a “black box”, making their decision process difficult to understand by a non-expert. Decision theory, especially game theory, is a potential solution as it focuses on identifying the best decision option that maximizes the decision-maker’s expected utility. This study presents a new framework for automated melanoma diagnosis. Pursuing the goal of improving the performance of existing systems, our approach also attempts to bring more transparency in the decision process. The proposed framework includes a multi-class CNN and six binary CNNs assimilated to players. The players’ strategies is to first cluster the pigmented lesions (melanoma, nevus, and benign keratosis), using the introduced method of evaluating the confidence of the predictions, into confidence level (confident, medium, uncertain). Then, a subset of players has the strategy to refine the diagnosis for difficult lesions with medium and uncertain prediction. We used EfficientNetB5 as the backbone of our networks and evaluated our approach on the public ISIC dataset consisting of 8917 lesions: melanoma (1113), nevi (6705) and benign keratosis (1099). The proposed framework achieved an area under the receiver operating curve (AUROC) of 0.93 for melanoma, 0.96 for nevus and 0.97 for benign keratosis. Furthermore, our approach outperformed existing methods in this task, improving the balanced accuracy (BACC) of the best compared method from 77% to 86%. These results suggest that our framework provides an effective and explainable decision-making strategy. This approach could help dermatologists in their clinical practice for patients with atypical and difficult-to-diagnose pigmented lesions. We also believe that our system could serve as a didactic tool for less experienced dermatologists.
format Online
Article
Text
id pubmed-9696950
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-96969502022-11-26 Computer Aided Diagnosis of Melanoma Using Deep Neural Networks and Game Theory: Application on Dermoscopic Images of Skin Lesions Foahom Gouabou, Arthur Cartel Collenne, Jules Monnier, Jilliana Iguernaissi, Rabah Damoiseaux, Jean-Luc Moudafi, Abdellatif Merad, Djamal Int J Mol Sci Article Early detection of melanoma remains a daily challenge due to the increasing number of cases and the lack of dermatologists. Thus, AI-assisted diagnosis is considered as a possible solution for this issue. Despite the great advances brought by deep learning and especially convolutional neural networks (CNNs), computer-aided diagnosis (CAD) systems are still not used in clinical practice. This may be explained by the dermatologist’s fear of being misled by a false negative and the assimilation of CNNs to a “black box”, making their decision process difficult to understand by a non-expert. Decision theory, especially game theory, is a potential solution as it focuses on identifying the best decision option that maximizes the decision-maker’s expected utility. This study presents a new framework for automated melanoma diagnosis. Pursuing the goal of improving the performance of existing systems, our approach also attempts to bring more transparency in the decision process. The proposed framework includes a multi-class CNN and six binary CNNs assimilated to players. The players’ strategies is to first cluster the pigmented lesions (melanoma, nevus, and benign keratosis), using the introduced method of evaluating the confidence of the predictions, into confidence level (confident, medium, uncertain). Then, a subset of players has the strategy to refine the diagnosis for difficult lesions with medium and uncertain prediction. We used EfficientNetB5 as the backbone of our networks and evaluated our approach on the public ISIC dataset consisting of 8917 lesions: melanoma (1113), nevi (6705) and benign keratosis (1099). The proposed framework achieved an area under the receiver operating curve (AUROC) of 0.93 for melanoma, 0.96 for nevus and 0.97 for benign keratosis. Furthermore, our approach outperformed existing methods in this task, improving the balanced accuracy (BACC) of the best compared method from 77% to 86%. These results suggest that our framework provides an effective and explainable decision-making strategy. This approach could help dermatologists in their clinical practice for patients with atypical and difficult-to-diagnose pigmented lesions. We also believe that our system could serve as a didactic tool for less experienced dermatologists. MDPI 2022-11-10 /pmc/articles/PMC9696950/ /pubmed/36430315 http://dx.doi.org/10.3390/ijms232213838 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
Foahom Gouabou, Arthur Cartel
Collenne, Jules
Monnier, Jilliana
Iguernaissi, Rabah
Damoiseaux, Jean-Luc
Moudafi, Abdellatif
Merad, Djamal
Computer Aided Diagnosis of Melanoma Using Deep Neural Networks and Game Theory: Application on Dermoscopic Images of Skin Lesions
title Computer Aided Diagnosis of Melanoma Using Deep Neural Networks and Game Theory: Application on Dermoscopic Images of Skin Lesions
title_full Computer Aided Diagnosis of Melanoma Using Deep Neural Networks and Game Theory: Application on Dermoscopic Images of Skin Lesions
title_fullStr Computer Aided Diagnosis of Melanoma Using Deep Neural Networks and Game Theory: Application on Dermoscopic Images of Skin Lesions
title_full_unstemmed Computer Aided Diagnosis of Melanoma Using Deep Neural Networks and Game Theory: Application on Dermoscopic Images of Skin Lesions
title_short Computer Aided Diagnosis of Melanoma Using Deep Neural Networks and Game Theory: Application on Dermoscopic Images of Skin Lesions
title_sort computer aided diagnosis of melanoma using deep neural networks and game theory: application on dermoscopic images of skin lesions
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9696950/
https://www.ncbi.nlm.nih.gov/pubmed/36430315
http://dx.doi.org/10.3390/ijms232213838
work_keys_str_mv AT foahomgouabouarthurcartel computeraideddiagnosisofmelanomausingdeepneuralnetworksandgametheoryapplicationondermoscopicimagesofskinlesions
AT collennejules computeraideddiagnosisofmelanomausingdeepneuralnetworksandgametheoryapplicationondermoscopicimagesofskinlesions
AT monnierjilliana computeraideddiagnosisofmelanomausingdeepneuralnetworksandgametheoryapplicationondermoscopicimagesofskinlesions
AT iguernaissirabah computeraideddiagnosisofmelanomausingdeepneuralnetworksandgametheoryapplicationondermoscopicimagesofskinlesions
AT damoiseauxjeanluc computeraideddiagnosisofmelanomausingdeepneuralnetworksandgametheoryapplicationondermoscopicimagesofskinlesions
AT moudafiabdellatif computeraideddiagnosisofmelanomausingdeepneuralnetworksandgametheoryapplicationondermoscopicimagesofskinlesions
AT meraddjamal computeraideddiagnosisofmelanomausingdeepneuralnetworksandgametheoryapplicationondermoscopicimagesofskinlesions