Accelerated and precise skin cancer detection through an enhanced machine learning pipeline for improved diagnostic accuracy

Unrepaired DNA damage in skin cells causes mutations leading to skin cancer, a highly aggressive malignancy. This study proposes a machine learning (ML)-based framework for accurate and automated skin cancer detection, integrating EfficientNetV2L for advanced feature extraction and LightGBM (LGBM) f...

Full description

Saved in:
Bibliographic Details
Main Authors: SM Masfequier Rahman Swapno, S.M. Nuruzzaman Nobel, P.K. Meena, V.P. Meena, Jitendra Bahadur, Abhishek Appaji
Format: Article
Language:English
Published: Elsevier 2025-03-01
Series:Results in Engineering
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2590123025002567
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832582117325799424
author SM Masfequier Rahman Swapno
S.M. Nuruzzaman Nobel
P.K. Meena
V.P. Meena
Jitendra Bahadur
Abhishek Appaji
author_facet SM Masfequier Rahman Swapno
S.M. Nuruzzaman Nobel
P.K. Meena
V.P. Meena
Jitendra Bahadur
Abhishek Appaji
author_sort SM Masfequier Rahman Swapno
collection DOAJ
description Unrepaired DNA damage in skin cells causes mutations leading to skin cancer, a highly aggressive malignancy. This study proposes a machine learning (ML)-based framework for accurate and automated skin cancer detection, integrating EfficientNetV2L for advanced feature extraction and LightGBM (LGBM) for gradient boosting. The ensemble model effectively classifies benign and malignant skin lesions, leveraging EfficientNetV2L's feature extraction capabilities and LGBM's computational efficiency. A dataset comprising 3,297 images of benign and malignant skin cancer classes was used for training. Data augmentation techniques were applied to enhance dataset reliability. The proposed training pipeline, optimized for modularity and performance, demonstrated significant improvements in accuracy and computational efficiency over state-of-the-art methods. The model achieved a training accuracy of 99.57% and a validation accuracy of 99.93%. Using 5-fold cross-validation, it recorded a test accuracy of 99.90% in the fifth fold. For benign cases, the model achieved a precision of 0.99, recall of 0.98, and F1-score of 0.98. Similarly, malignant cases achieved a precision of 0.98, recall of 0.98, and F1-score of 0.98. The ROC-AUC scores for both classes were 0.98, further validating the system's reliability. These results highlight the robustness and effectiveness of the EfficientNetV2L-LGBM framework in skin cancer classification, offering a reliable and scalable solution for early detection. This approach demonstrates significant potential in advancing diagnostic systems for improved patient outcomes.
format Article
id doaj-art-af5b5231bce544e18a8c90349cee86d9
institution Kabale University
issn 2590-1230
language English
publishDate 2025-03-01
publisher Elsevier
record_format Article
series Results in Engineering
spelling doaj-art-af5b5231bce544e18a8c90349cee86d92025-01-30T05:14:53ZengElsevierResults in Engineering2590-12302025-03-0125104168Accelerated and precise skin cancer detection through an enhanced machine learning pipeline for improved diagnostic accuracySM Masfequier Rahman Swapno0S.M. Nuruzzaman Nobel1P.K. Meena2V.P. Meena3Jitendra Bahadur4Abhishek Appaji5Department of Computer Science and Engineering (CSE), Bangladesh University of Business and Technology, Dhaka, 1216, Bangladesh; Corresponding authors.Department of Computer Science and Engineering (CSE), Bangladesh University of Business and Technology, Dhaka, 1216, BangladeshDepartment of Physics, Indian Institute of Science Education and Research (IISERB), Bhopal, Madhya Pradesh, 462066, IndiaDepartment of Electrical Engineering, National Institute of Technology, Jamshedpur, Jharkhand, 831001, India; Corresponding authors.Department of Electronics and Communication Engineering, Amrita School of Engineering, Bengaluru, Amrita Vishwa Vidyapeetham, Bengaluru, 560035, IndiaDepartment of Medical Electronics Engineering, B.M.S. College of Engineering, Bangalore, 560019, India; Maastricht University, University Eye Clinic Maastricht, Maastricht, the Netherlands; Corresponding author at: Department of Medical Electronics Engineering, B.M.S. College of Engineering, Bangalore, 560019, India.Unrepaired DNA damage in skin cells causes mutations leading to skin cancer, a highly aggressive malignancy. This study proposes a machine learning (ML)-based framework for accurate and automated skin cancer detection, integrating EfficientNetV2L for advanced feature extraction and LightGBM (LGBM) for gradient boosting. The ensemble model effectively classifies benign and malignant skin lesions, leveraging EfficientNetV2L's feature extraction capabilities and LGBM's computational efficiency. A dataset comprising 3,297 images of benign and malignant skin cancer classes was used for training. Data augmentation techniques were applied to enhance dataset reliability. The proposed training pipeline, optimized for modularity and performance, demonstrated significant improvements in accuracy and computational efficiency over state-of-the-art methods. The model achieved a training accuracy of 99.57% and a validation accuracy of 99.93%. Using 5-fold cross-validation, it recorded a test accuracy of 99.90% in the fifth fold. For benign cases, the model achieved a precision of 0.99, recall of 0.98, and F1-score of 0.98. Similarly, malignant cases achieved a precision of 0.98, recall of 0.98, and F1-score of 0.98. The ROC-AUC scores for both classes were 0.98, further validating the system's reliability. These results highlight the robustness and effectiveness of the EfficientNetV2L-LGBM framework in skin cancer classification, offering a reliable and scalable solution for early detection. This approach demonstrates significant potential in advancing diagnostic systems for improved patient outcomes.http://www.sciencedirect.com/science/article/pii/S2590123025002567Machine learningHealthcareSkin cancerEnsemble methodBenignMalignant
spellingShingle SM Masfequier Rahman Swapno
S.M. Nuruzzaman Nobel
P.K. Meena
V.P. Meena
Jitendra Bahadur
Abhishek Appaji
Accelerated and precise skin cancer detection through an enhanced machine learning pipeline for improved diagnostic accuracy
Results in Engineering
Machine learning
Healthcare
Skin cancer
Ensemble method
Benign
Malignant
title Accelerated and precise skin cancer detection through an enhanced machine learning pipeline for improved diagnostic accuracy
title_full Accelerated and precise skin cancer detection through an enhanced machine learning pipeline for improved diagnostic accuracy
title_fullStr Accelerated and precise skin cancer detection through an enhanced machine learning pipeline for improved diagnostic accuracy
title_full_unstemmed Accelerated and precise skin cancer detection through an enhanced machine learning pipeline for improved diagnostic accuracy
title_short Accelerated and precise skin cancer detection through an enhanced machine learning pipeline for improved diagnostic accuracy
title_sort accelerated and precise skin cancer detection through an enhanced machine learning pipeline for improved diagnostic accuracy
topic Machine learning
Healthcare
Skin cancer
Ensemble method
Benign
Malignant
url http://www.sciencedirect.com/science/article/pii/S2590123025002567
work_keys_str_mv AT smmasfequierrahmanswapno acceleratedandpreciseskincancerdetectionthroughanenhancedmachinelearningpipelineforimproveddiagnosticaccuracy
AT smnuruzzamannobel acceleratedandpreciseskincancerdetectionthroughanenhancedmachinelearningpipelineforimproveddiagnosticaccuracy
AT pkmeena acceleratedandpreciseskincancerdetectionthroughanenhancedmachinelearningpipelineforimproveddiagnosticaccuracy
AT vpmeena acceleratedandpreciseskincancerdetectionthroughanenhancedmachinelearningpipelineforimproveddiagnosticaccuracy
AT jitendrabahadur acceleratedandpreciseskincancerdetectionthroughanenhancedmachinelearningpipelineforimproveddiagnosticaccuracy
AT abhishekappaji acceleratedandpreciseskincancerdetectionthroughanenhancedmachinelearningpipelineforimproveddiagnosticaccuracy