Melanoma Skin Cancer Recognition with a Convolutional Neural Network and Feature Dimensions Reduction with Aquila Optimizer

<b>Background:</b> Melanoma is a highly aggressive form of skin cancer, necessitating early and accurate detection for effective treatment. This study aims to develop a novel classification system for melanoma detection that integrates Convolutional Neural Networks (CNNs) for feature ext...

Full description

Saved in:
Bibliographic Details
Main Authors: Jalaleddin Mohamed, Necmi Serkan Tezel, Javad Rahebi, Raheleh Ghadami
Format: Article
Language:English
Published: MDPI AG 2025-03-01
Series:Diagnostics
Subjects:
Online Access:https://www.mdpi.com/2075-4418/15/6/761
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850089860658888704
author Jalaleddin Mohamed
Necmi Serkan Tezel
Javad Rahebi
Raheleh Ghadami
author_facet Jalaleddin Mohamed
Necmi Serkan Tezel
Javad Rahebi
Raheleh Ghadami
author_sort Jalaleddin Mohamed
collection DOAJ
description <b>Background:</b> Melanoma is a highly aggressive form of skin cancer, necessitating early and accurate detection for effective treatment. This study aims to develop a novel classification system for melanoma detection that integrates Convolutional Neural Networks (CNNs) for feature extraction and the Aquila Optimizer (AO) for feature dimension reduction, improving both computational efficiency and classification accuracy. <b>Methods:</b> The proposed method utilized CNNs to extract features from melanoma images, while the AO was employed to reduce feature dimensionality, enhancing the performance of the model. The effectiveness of this hybrid approach was evaluated on three publicly available datasets: ISIC 2019, ISBI 2016, and ISBI 2017. <b>Results:</b> For the ISIC 2019 dataset, the model achieved 97.46% sensitivity, 98.89% specificity, 98.42% accuracy, 97.91% precision, 97.68% F1-score, and 99.12% AUC-ROC. On the ISBI 2016 dataset, it reached 98.45% sensitivity, 98.24% specificity, 97.22% accuracy, 97.84% precision, 97.62% F1-score, and 98.97% AUC-ROC. For ISBI 2017, the results were 98.44% sensitivity, 98.86% specificity, 97.96% accuracy, 98.12% precision, 97.88% F1-score, and 99.03% AUC-ROC. The proposed method outperforms existing advanced techniques, with a 4.2% higher accuracy, a 6.2% improvement in sensitivity, and a 5.8% increase in specificity. Additionally, the AO reduced computational complexity by up to 37.5%. <b>Conclusions:</b> The deep learning-Aquila Optimizer (DL-AO) framework offers a highly efficient and accurate approach for melanoma detection, making it suitable for deployment in resource-constrained environments such as mobile and edge computing platforms. The integration of DL with metaheuristic optimization significantly enhances accuracy, robustness, and computational efficiency in melanoma detection.
format Article
id doaj-art-427f8ad6a0774bc897cc32fb09cd384a
institution DOAJ
issn 2075-4418
language English
publishDate 2025-03-01
publisher MDPI AG
record_format Article
series Diagnostics
spelling doaj-art-427f8ad6a0774bc897cc32fb09cd384a2025-08-20T02:42:40ZengMDPI AGDiagnostics2075-44182025-03-0115676110.3390/diagnostics15060761Melanoma Skin Cancer Recognition with a Convolutional Neural Network and Feature Dimensions Reduction with Aquila OptimizerJalaleddin Mohamed0Necmi Serkan Tezel1Javad Rahebi2Raheleh Ghadami3Electrical and Electronics Engineering Department, Karabuk University, 78050 Karabuk, TürkiyeElectrical and Electronics Engineering Department, Karabuk University, 78050 Karabuk, TürkiyeDepartment of Software Engineering, Istanbul Topkapi University, 34662 Istanbul, TürkiyeDepartment of Computer Engineering, Istanbul Topkapi University, 34662 Istanbul, Türkiye<b>Background:</b> Melanoma is a highly aggressive form of skin cancer, necessitating early and accurate detection for effective treatment. This study aims to develop a novel classification system for melanoma detection that integrates Convolutional Neural Networks (CNNs) for feature extraction and the Aquila Optimizer (AO) for feature dimension reduction, improving both computational efficiency and classification accuracy. <b>Methods:</b> The proposed method utilized CNNs to extract features from melanoma images, while the AO was employed to reduce feature dimensionality, enhancing the performance of the model. The effectiveness of this hybrid approach was evaluated on three publicly available datasets: ISIC 2019, ISBI 2016, and ISBI 2017. <b>Results:</b> For the ISIC 2019 dataset, the model achieved 97.46% sensitivity, 98.89% specificity, 98.42% accuracy, 97.91% precision, 97.68% F1-score, and 99.12% AUC-ROC. On the ISBI 2016 dataset, it reached 98.45% sensitivity, 98.24% specificity, 97.22% accuracy, 97.84% precision, 97.62% F1-score, and 98.97% AUC-ROC. For ISBI 2017, the results were 98.44% sensitivity, 98.86% specificity, 97.96% accuracy, 98.12% precision, 97.88% F1-score, and 99.03% AUC-ROC. The proposed method outperforms existing advanced techniques, with a 4.2% higher accuracy, a 6.2% improvement in sensitivity, and a 5.8% increase in specificity. Additionally, the AO reduced computational complexity by up to 37.5%. <b>Conclusions:</b> The deep learning-Aquila Optimizer (DL-AO) framework offers a highly efficient and accurate approach for melanoma detection, making it suitable for deployment in resource-constrained environments such as mobile and edge computing platforms. The integration of DL with metaheuristic optimization significantly enhances accuracy, robustness, and computational efficiency in melanoma detection.https://www.mdpi.com/2075-4418/15/6/761Aquila Optimizerconvolutional neural networkfeature dimensions reductionmelanoma skin cancer
spellingShingle Jalaleddin Mohamed
Necmi Serkan Tezel
Javad Rahebi
Raheleh Ghadami
Melanoma Skin Cancer Recognition with a Convolutional Neural Network and Feature Dimensions Reduction with Aquila Optimizer
Diagnostics
Aquila Optimizer
convolutional neural network
feature dimensions reduction
melanoma skin cancer
title Melanoma Skin Cancer Recognition with a Convolutional Neural Network and Feature Dimensions Reduction with Aquila Optimizer
title_full Melanoma Skin Cancer Recognition with a Convolutional Neural Network and Feature Dimensions Reduction with Aquila Optimizer
title_fullStr Melanoma Skin Cancer Recognition with a Convolutional Neural Network and Feature Dimensions Reduction with Aquila Optimizer
title_full_unstemmed Melanoma Skin Cancer Recognition with a Convolutional Neural Network and Feature Dimensions Reduction with Aquila Optimizer
title_short Melanoma Skin Cancer Recognition with a Convolutional Neural Network and Feature Dimensions Reduction with Aquila Optimizer
title_sort melanoma skin cancer recognition with a convolutional neural network and feature dimensions reduction with aquila optimizer
topic Aquila Optimizer
convolutional neural network
feature dimensions reduction
melanoma skin cancer
url https://www.mdpi.com/2075-4418/15/6/761
work_keys_str_mv AT jalaleddinmohamed melanomaskincancerrecognitionwithaconvolutionalneuralnetworkandfeaturedimensionsreductionwithaquilaoptimizer
AT necmiserkantezel melanomaskincancerrecognitionwithaconvolutionalneuralnetworkandfeaturedimensionsreductionwithaquilaoptimizer
AT javadrahebi melanomaskincancerrecognitionwithaconvolutionalneuralnetworkandfeaturedimensionsreductionwithaquilaoptimizer
AT rahelehghadami melanomaskincancerrecognitionwithaconvolutionalneuralnetworkandfeaturedimensionsreductionwithaquilaoptimizer