RETRACTED ARTICLE: Multiclass skin lesion classification using deep learning networks optimal information fusion
Abstract A serious, all-encompassing, and deadly cancer that affects every part of the body is skin cancer. The most prevalent causes of skin lesions are UV radiation, which can damage human skin, and moles. If skin cancer is discovered early, it may be adequately treated. In order to diagnose skin...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Springer
2024-05-01
|
| Series: | Discover Applied Sciences |
| Subjects: | |
| Online Access: | https://doi.org/10.1007/s42452-024-05998-9 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841544370102206464 |
|---|---|
| author | Muhammad Attique Khan Ameer Hamza Mohammad Shabaz Seifeine Kadry Saddaf Rubab Muhammad Abdullah Bilal Muhammad Naeem Akbar Suresh Manic Kesavan |
| author_facet | Muhammad Attique Khan Ameer Hamza Mohammad Shabaz Seifeine Kadry Saddaf Rubab Muhammad Abdullah Bilal Muhammad Naeem Akbar Suresh Manic Kesavan |
| author_sort | Muhammad Attique Khan |
| collection | DOAJ |
| description | Abstract A serious, all-encompassing, and deadly cancer that affects every part of the body is skin cancer. The most prevalent causes of skin lesions are UV radiation, which can damage human skin, and moles. If skin cancer is discovered early, it may be adequately treated. In order to diagnose skin lesions with less effort, dermatologists are increasingly turning to machine learning (ML) techniques and computer-aided diagnostic (CAD) systems. This paper proposes a computerized method for multiclass lesion classification using a fusion of optimal deep-learning model features. The dataset used in this work, ISIC2018, is imbalanced; therefore, augmentation is performed based on a few mathematical operations. After that, two pre-trained deep learning models (DarkNet-19 and MobileNet-V2) have been fine-tuned and trained on the selected dataset. After training, features are extracted from the average pool layer and optimized using a hybrid firefly optimization technique. The selected features are fused in two ways: (i) original serial approach and (ii) proposed threshold approach. Machine learning classifiers are used to classify the chosen features at the end. Using the ISIC2018 dataset, the experimental procedure produced an accuracy of 89.0%. Whereas, 87.34, 87.57, and 87.45 are sensitivity, precision, and F1 score respectively. At the end, comparison is also conducted with recent techniques, and it shows the proposed method shows improved accuracy along with other performance measures. |
| format | Article |
| id | doaj-art-85d2fca3a1c84f0692932c7d73dc02a9 |
| institution | Kabale University |
| issn | 3004-9261 |
| language | English |
| publishDate | 2024-05-01 |
| publisher | Springer |
| record_format | Article |
| series | Discover Applied Sciences |
| spelling | doaj-art-85d2fca3a1c84f0692932c7d73dc02a92025-01-12T12:35:15ZengSpringerDiscover Applied Sciences3004-92612024-05-016611310.1007/s42452-024-05998-9RETRACTED ARTICLE: Multiclass skin lesion classification using deep learning networks optimal information fusionMuhammad Attique Khan0Ameer Hamza1Mohammad Shabaz2Seifeine Kadry3Saddaf Rubab4Muhammad Abdullah Bilal5Muhammad Naeem Akbar6Suresh Manic Kesavan7Department of Computer Science, HITEC UniversityDepartment of Computer Science, HITEC UniversityModel Institute of Engineering and TechnologyDepartment of Applied Data Science, Noroff University CollegeDepartment of Computer Engineering, College of Computing and Informatics, University of SharjahDepartment of CS, SEECS NUSTNational University of Sciences and Technology (NUST)Department of Electrical and Communication Engineering, National University of Science and TechnologyAbstract A serious, all-encompassing, and deadly cancer that affects every part of the body is skin cancer. The most prevalent causes of skin lesions are UV radiation, which can damage human skin, and moles. If skin cancer is discovered early, it may be adequately treated. In order to diagnose skin lesions with less effort, dermatologists are increasingly turning to machine learning (ML) techniques and computer-aided diagnostic (CAD) systems. This paper proposes a computerized method for multiclass lesion classification using a fusion of optimal deep-learning model features. The dataset used in this work, ISIC2018, is imbalanced; therefore, augmentation is performed based on a few mathematical operations. After that, two pre-trained deep learning models (DarkNet-19 and MobileNet-V2) have been fine-tuned and trained on the selected dataset. After training, features are extracted from the average pool layer and optimized using a hybrid firefly optimization technique. The selected features are fused in two ways: (i) original serial approach and (ii) proposed threshold approach. Machine learning classifiers are used to classify the chosen features at the end. Using the ISIC2018 dataset, the experimental procedure produced an accuracy of 89.0%. Whereas, 87.34, 87.57, and 87.45 are sensitivity, precision, and F1 score respectively. At the end, comparison is also conducted with recent techniques, and it shows the proposed method shows improved accuracy along with other performance measures.https://doi.org/10.1007/s42452-024-05998-9Skin cancerDermoscopyAugmentationDeep learningOptimizationFusion |
| spellingShingle | Muhammad Attique Khan Ameer Hamza Mohammad Shabaz Seifeine Kadry Saddaf Rubab Muhammad Abdullah Bilal Muhammad Naeem Akbar Suresh Manic Kesavan RETRACTED ARTICLE: Multiclass skin lesion classification using deep learning networks optimal information fusion Discover Applied Sciences Skin cancer Dermoscopy Augmentation Deep learning Optimization Fusion |
| title | RETRACTED ARTICLE: Multiclass skin lesion classification using deep learning networks optimal information fusion |
| title_full | RETRACTED ARTICLE: Multiclass skin lesion classification using deep learning networks optimal information fusion |
| title_fullStr | RETRACTED ARTICLE: Multiclass skin lesion classification using deep learning networks optimal information fusion |
| title_full_unstemmed | RETRACTED ARTICLE: Multiclass skin lesion classification using deep learning networks optimal information fusion |
| title_short | RETRACTED ARTICLE: Multiclass skin lesion classification using deep learning networks optimal information fusion |
| title_sort | retracted article multiclass skin lesion classification using deep learning networks optimal information fusion |
| topic | Skin cancer Dermoscopy Augmentation Deep learning Optimization Fusion |
| url | https://doi.org/10.1007/s42452-024-05998-9 |
| work_keys_str_mv | AT muhammadattiquekhan retractedarticlemulticlassskinlesionclassificationusingdeeplearningnetworksoptimalinformationfusion AT ameerhamza retractedarticlemulticlassskinlesionclassificationusingdeeplearningnetworksoptimalinformationfusion AT mohammadshabaz retractedarticlemulticlassskinlesionclassificationusingdeeplearningnetworksoptimalinformationfusion AT seifeinekadry retractedarticlemulticlassskinlesionclassificationusingdeeplearningnetworksoptimalinformationfusion AT saddafrubab retractedarticlemulticlassskinlesionclassificationusingdeeplearningnetworksoptimalinformationfusion AT muhammadabdullahbilal retractedarticlemulticlassskinlesionclassificationusingdeeplearningnetworksoptimalinformationfusion AT muhammadnaeemakbar retractedarticlemulticlassskinlesionclassificationusingdeeplearningnetworksoptimalinformationfusion AT sureshmanickesavan retractedarticlemulticlassskinlesionclassificationusingdeeplearningnetworksoptimalinformationfusion |