Achieving high-accuracy skin cancer classification with deep learning optimized by ant colony algorithm

Abstract Skin cancer, particularly melanoma, poses a critical global health challenge due to its high mortality rate. Early and precise detection is vital for effective treatment and better prognosis. Recent advancements in deep learning have shown significant promise in medical image analysis, incl...

Full description

Saved in:
Bibliographic Details
Main Authors: Amany M. Sarhan, Hesham A. Ali, Shady Yasser, Mohamed Gobara, Ahmed A. Kandil, Ghada Sherif, Esraa Moustafa
Format: Article
Language:English
Published: SpringerOpen 2025-07-01
Series:Journal of Electrical Systems and Information Technology
Subjects:
Online Access:https://doi.org/10.1186/s43067-025-00243-8
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849237769113567232
author Amany M. Sarhan
Hesham A. Ali
Shady Yasser
Mohamed Gobara
Ahmed A. Kandil
Ghada Sherif
Esraa Moustafa
author_facet Amany M. Sarhan
Hesham A. Ali
Shady Yasser
Mohamed Gobara
Ahmed A. Kandil
Ghada Sherif
Esraa Moustafa
author_sort Amany M. Sarhan
collection DOAJ
description Abstract Skin cancer, particularly melanoma, poses a critical global health challenge due to its high mortality rate. Early and precise detection is vital for effective treatment and better prognosis. Recent advancements in deep learning have shown significant promise in medical image analysis, including skin cancer classification. This study investigates the automated classification of skin lesions using the HAM10000 dataset, which features high-resolution images across seven distinct classes. We focus on utilizing deep learning, specifically convolutional neural networks (CNNs), to enhance the accuracy of skin lesion classification. Our research examines several CNN architectures, including XceptionNet, DenseNet201, DenseNet169, DenseNet121, MobileNetV2, and GoogleNet, alongside a customized CNN model tailored for skin cancer classification. We incorporate techniques such as data augmentation and transfer learning to further refine model performance. Hyperparameter optimization is achieved using the Ant Colony Optimization algorithm. The proposed models are evaluated on the HAM10000 dataset with standard metrics; accuracy, precision, recall, and F1-score. Our results highlight the effectiveness of deep learning in distinguishing between various skin cancer types attaining values of 96.5%, 97.0%, and 97.0% for accuracy, precision, recall, and F1-score, respectively, showing improvements over existing state-of-the-art methods in both classification accuracy. These findings offer significant implications for dermatology and healthcare by facilitating automated skin cancer classification, potentially aiding dermatologists in early diagnosis and improving patient outcomes. Additionally, this framework provides a foundation for future research in applying deep learning to medical image analysis and healthcare diagnostics.
format Article
id doaj-art-58dbfd656a4b4cbeb5ab0c8fcfd035b5
institution Kabale University
issn 2314-7172
language English
publishDate 2025-07-01
publisher SpringerOpen
record_format Article
series Journal of Electrical Systems and Information Technology
spelling doaj-art-58dbfd656a4b4cbeb5ab0c8fcfd035b52025-08-20T04:01:52ZengSpringerOpenJournal of Electrical Systems and Information Technology2314-71722025-07-0112112510.1186/s43067-025-00243-8Achieving high-accuracy skin cancer classification with deep learning optimized by ant colony algorithmAmany M. Sarhan0Hesham A. Ali1Shady Yasser2Mohamed Gobara3Ahmed A. Kandil4Ghada Sherif5Esraa Moustafa6Department of Computer and Control Engineering, Tanta UniversityDepartment of Artificial Intelligence, Faculty of Artificial Intelligence, Delta UniversityDepartment of Artificial Intelligence, Faculty of Artificial Intelligence, Delta UniversityDepartment of Artificial Intelligence, Faculty of Artificial Intelligence, Delta UniversityDepartment of Artificial Intelligence, Faculty of Artificial Intelligence, Delta UniversityDepartment of Artificial Intelligence, Faculty of Artificial Intelligence, Delta UniversityDepartment of Artificial Intelligence, Faculty of Artificial Intelligence, Delta UniversityAbstract Skin cancer, particularly melanoma, poses a critical global health challenge due to its high mortality rate. Early and precise detection is vital for effective treatment and better prognosis. Recent advancements in deep learning have shown significant promise in medical image analysis, including skin cancer classification. This study investigates the automated classification of skin lesions using the HAM10000 dataset, which features high-resolution images across seven distinct classes. We focus on utilizing deep learning, specifically convolutional neural networks (CNNs), to enhance the accuracy of skin lesion classification. Our research examines several CNN architectures, including XceptionNet, DenseNet201, DenseNet169, DenseNet121, MobileNetV2, and GoogleNet, alongside a customized CNN model tailored for skin cancer classification. We incorporate techniques such as data augmentation and transfer learning to further refine model performance. Hyperparameter optimization is achieved using the Ant Colony Optimization algorithm. The proposed models are evaluated on the HAM10000 dataset with standard metrics; accuracy, precision, recall, and F1-score. Our results highlight the effectiveness of deep learning in distinguishing between various skin cancer types attaining values of 96.5%, 97.0%, and 97.0% for accuracy, precision, recall, and F1-score, respectively, showing improvements over existing state-of-the-art methods in both classification accuracy. These findings offer significant implications for dermatology and healthcare by facilitating automated skin cancer classification, potentially aiding dermatologists in early diagnosis and improving patient outcomes. Additionally, this framework provides a foundation for future research in applying deep learning to medical image analysis and healthcare diagnostics.https://doi.org/10.1186/s43067-025-00243-8Skin cancerDeep learningConvolutional neural networksCNNsHAM10000Medical image analysis
spellingShingle Amany M. Sarhan
Hesham A. Ali
Shady Yasser
Mohamed Gobara
Ahmed A. Kandil
Ghada Sherif
Esraa Moustafa
Achieving high-accuracy skin cancer classification with deep learning optimized by ant colony algorithm
Journal of Electrical Systems and Information Technology
Skin cancer
Deep learning
Convolutional neural networks
CNNs
HAM10000
Medical image analysis
title Achieving high-accuracy skin cancer classification with deep learning optimized by ant colony algorithm
title_full Achieving high-accuracy skin cancer classification with deep learning optimized by ant colony algorithm
title_fullStr Achieving high-accuracy skin cancer classification with deep learning optimized by ant colony algorithm
title_full_unstemmed Achieving high-accuracy skin cancer classification with deep learning optimized by ant colony algorithm
title_short Achieving high-accuracy skin cancer classification with deep learning optimized by ant colony algorithm
title_sort achieving high accuracy skin cancer classification with deep learning optimized by ant colony algorithm
topic Skin cancer
Deep learning
Convolutional neural networks
CNNs
HAM10000
Medical image analysis
url https://doi.org/10.1186/s43067-025-00243-8
work_keys_str_mv AT amanymsarhan achievinghighaccuracyskincancerclassificationwithdeeplearningoptimizedbyantcolonyalgorithm
AT heshamaali achievinghighaccuracyskincancerclassificationwithdeeplearningoptimizedbyantcolonyalgorithm
AT shadyyasser achievinghighaccuracyskincancerclassificationwithdeeplearningoptimizedbyantcolonyalgorithm
AT mohamedgobara achievinghighaccuracyskincancerclassificationwithdeeplearningoptimizedbyantcolonyalgorithm
AT ahmedakandil achievinghighaccuracyskincancerclassificationwithdeeplearningoptimizedbyantcolonyalgorithm
AT ghadasherif achievinghighaccuracyskincancerclassificationwithdeeplearningoptimizedbyantcolonyalgorithm
AT esraamoustafa achievinghighaccuracyskincancerclassificationwithdeeplearningoptimizedbyantcolonyalgorithm