{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,16]],"date-time":"2026-10-16T16:30:11Z","timestamp":1792168211678,"version":"4.4.0"},"reference-count":32,"publisher":"Public Library of Science (PLoS)","issue":"10","license":[{"start":{"date-parts":[[2024,10,24]],"date-time":"2024-10-24T00:00:00Z","timestamp":1729728000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS ONE"],"abstract":"<jats:p>Skin lesions encompass a variety of skin abnormalities, including skin diseases that affect structure and function, and skin cancer, which can be fatal and arise from abnormal cell growth. Early detection of lesions and automated prediction is crucial, yet accurately identifying responsible regions post-dominance dispersion remains a challenge in current studies. Thus, we propose a Convolutional Neural Network (CNN)-based approach employing a Customized Transfer Learning (CTL) model and Triple Attention (TA) modules in conjunction with Ensemble Learning (EL). While Ensemble Learning has become an integral component of both Machine Learning (ML) and Deep Learning (DL) methodologies, a specific technique ensuring optimal allocation of weights for each model\u2019s prediction is currently lacking. Consequently, the primary objective of this study is to introduce a novel method for determining optimal weights to aggregate the contributions of models for achieving desired outcomes. We term this approach \u201cInformation Gain Proportioned Averaging (IGPA),\u201d further refining it to \u201cMulti-Level Information Gain Proportioned Averaging (ML-IGPA),\u201d which specifically involves the utilization of IGPA at multiple levels. Empirical evaluation of the HAM1000 dataset demonstrates that our approach achieves 94.93% accuracy with ML-IGPA, surpassing state-of-the-art methods. Given previous studies\u2019 failure to elucidate the exact focus of black-box models on specific regions, we utilize the Gradient Class Activation Map (GradCAM) to identify responsible regions and enhance explainability. Our study enhances both accuracy and interpretability, facilitating early diagnosis and preventing the consequences of neglecting skin lesion detection, thereby addressing issues related to time, accessibility, and costs.<\/jats:p>","DOI":"10.1371\/journal.pone.0309430","type":"journal-article","created":{"date-parts":[[2024,10,24]],"date-time":"2024-10-24T17:35:31Z","timestamp":1729791331000},"page":"e0309430","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":35,"title":["A Multi-level ensemble approach for skin lesion classification using Customized Transfer Learning with Triple Attention"],"prefix":"10.1371","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-7999-1512","authenticated-orcid":true,"given":"Anwar Hossain","family":"Efat","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"S. M. Mahedy","family":"Hasan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Md. Palash","family":"Uddin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Md. Al","family":"Mamun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2024,10,24]]},"reference":[{"issue":"19","key":"pone.0309430.ref001","doi-asserted-by":"crossref","first-page":"3063","DOI":"10.3390\/diagnostics13193063","article-title":"MSRNet: multiclass skin lesion recognition using additional residual block based fine-tuned deep models information fusion and best feature selection","volume":"13","author":"S Bibi","year":"2023","journal-title":"Diagnostics"},{"key":"pone.0309430.ref002","article-title":"D2LFS2Net: Multi\u2010class skin lesion diagnosis using deep learning and variance\u2010controlled Marine Predator optimisation: An application for precision medicine","author":"V Dillshad","year":"2023","journal-title":"CAAI Transactions on Intelligence Technology"},{"issue":"18","key":"pone.0309430.ref003","doi-asserted-by":"crossref","first-page":"2869","DOI":"10.3390\/diagnostics13182869","article-title":"SkinNet-INIO: multiclass skin lesion localization and classification using fusion-assisted deep neural networks and improved nature-inspired optimization algorithm","volume":"13","author":"M Hussain","year":"2023","journal-title":"Diagnostics"},{"key":"pone.0309430.ref004","doi-asserted-by":"crossref","first-page":"1151257","DOI":"10.3389\/fonc.2023.1151257","article-title":"A novel framework of multiclass skin lesion recognition from dermoscopic images using deep learning and explainable AI","volume":"13","author":"N Ahmad","year":"2023","journal-title":"Frontiers in Oncology"},{"issue":"7","key":"pone.0309430.ref005","doi-asserted-by":"crossref","first-page":"1285","DOI":"10.3390\/diagnostics13071285","article-title":"An improved skin lesion boundary estimation for enhanced-intensity images using hybrid metaheuristics","volume":"13","author":"S Malik","year":"2023","journal-title":"Diagnostics"},{"issue":"4","key":"pone.0309430.ref006","doi-asserted-by":"crossref","first-page":"e0284437","DOI":"10.1371\/journal.pone.0284437","article-title":"Design and validation of a new machine-learning-based diagnostic tool for the differentiation of dermatoscopic skin cancer images","volume":"18","author":"A Tajerian","year":"2023","journal-title":"PLoS One"},{"issue":"10","key":"pone.0309430.ref007","doi-asserted-by":"crossref","first-page":"e0276836","DOI":"10.1371\/journal.pone.0276836","article-title":"SkiNet: A deep learning framework for skin lesion diagnosis with uncertainty estimation and explainability","volume":"17","author":"RK Singh","year":"2022","journal-title":"Plos one"},{"issue":"12","key":"pone.0309430.ref008","doi-asserted-by":"crossref","first-page":"e0295151","DOI":"10.1371\/journal.pone.0295151","article-title":"SkinViT: A transformer based method for Melanoma and Nonmelanoma classification","volume":"18","author":"S Khan","year":"2023","journal-title":"Plos one"},{"issue":"5","key":"pone.0309430.ref009","doi-asserted-by":"crossref","first-page":"e0217293","DOI":"10.1371\/journal.pone.0217293","article-title":"Classification of skin lesions using transfer learning and augmentation with Alex-net","volume":"14","author":"KM Hosny","year":"2019","journal-title":"PloS one"},{"issue":"11","key":"pone.0309430.ref010","doi-asserted-by":"crossref","first-page":"e0277578","DOI":"10.1371\/journal.pone.0277578","article-title":"TC-Net: Dual coding network of Transformer and CNN for skin lesion segmentation","volume":"17","author":"Y Dong","year":"2022","journal-title":"Plos one"},{"issue":"1","key":"pone.0309430.ref011","doi-asserted-by":"crossref","first-page":"18134","DOI":"10.1038\/s41598-022-22644-9","article-title":"Skin lesion classification of dermoscopic images using machine learning and convolutional neural network","volume":"12","author":"B Shetty","year":"2022","journal-title":"Scientific Reports"},{"issue":"18","key":"pone.0309430.ref012","doi-asserted-by":"crossref","first-page":"12039","DOI":"10.1007\/s00521-021-05929-4","article-title":"A deep convolutional neural network-based pigmented skin lesion classification application and experts evaluation","volume":"33","author":"O Sevli","year":"2021","journal-title":"Neural Computing and Applications"},{"issue":"19","key":"pone.0309430.ref013","doi-asserted-by":"crossref","first-page":"9545","DOI":"10.3390\/app12199545","article-title":"Robustness, stability, and fidelity of explanations for a deep skin cancer classification model","volume":"12","author":"M Saarela","year":"2022","journal-title":"Applied Sciences"},{"issue":"1","key":"pone.0309430.ref014","doi-asserted-by":"crossref","first-page":"72","DOI":"10.3390\/diagnostics13010072","article-title":"A deep cnn transformer hybrid model for skin lesion classification of dermoscopic images using focal loss","volume":"13","author":"Y Nie","year":"2022","journal-title":"Diagnostics"},{"issue":"5","key":"pone.0309430.ref015","doi-asserted-by":"crossref","first-page":"2677","DOI":"10.3390\/app12052677","article-title":"Multiclass skin lesion classification using a novel lightweight deep learning framework for smart healthcare","volume":"12","author":"L Hoang","year":"2022","journal-title":"Applied Sciences"},{"issue":"1","key":"pone.0309430.ref016","first-page":"6673852","article-title":"Skin lesion classification using additional patient information","volume":"2021","author":"Q Sun","year":"2021","journal-title":"BioMed research international"},{"issue":"30","key":"pone.0309430.ref017","doi-asserted-by":"crossref","first-page":"22115","DOI":"10.1007\/s00521-022-08084-6","article-title":"BF2SkNet: Best deep learning features fusion-assisted framework for multiclass skin lesion classification","volume":"35","author":"M Ajmal","year":"2023","journal-title":"Neural Computing and Applications"},{"issue":"4","key":"pone.0309430.ref018","doi-asserted-by":"crossref","first-page":"1275","DOI":"10.1002\/ima.22863","article-title":"SkinNet\u2010ENDO: Multiclass skin lesion recognition using deep neural network and Entropy\u2010Normal distribution optimization algorithm with ELM","volume":"33","author":"MA Khan","year":"2023","journal-title":"International Journal of Imaging Systems and Technology"},{"key":"pone.0309430.ref019","doi-asserted-by":"crossref","first-page":"105475","DOI":"10.1016\/j.cmpb.2020.105475","article-title":"Transfer learning using a multi-scale and multi-network ensemble for skin lesion classification","volume":"193","author":"A Mahbod","year":"2020","journal-title":"Computer methods and programs in biomedicine"},{"key":"pone.0309430.ref020","doi-asserted-by":"crossref","first-page":"100659","DOI":"10.1016\/j.imu.2021.100659","article-title":"An approach for multiclass skin lesion classification based on ensemble learning","volume":"25","author":"Z Rahman","year":"2021","journal-title":"Informatics in Medicine Unlocked"},{"issue":"1","key":"pone.0309430.ref021","doi-asserted-by":"crossref","first-page":"5146543","DOI":"10.1155\/2023\/5146543","article-title":"Multiscale feature fusion for skin lesion classification","volume":"2023","author":"G Wang","year":"2023","journal-title":"BioMed Research International"},{"key":"pone.0309430.ref022","doi-asserted-by":"crossref","first-page":"102041","DOI":"10.1016\/j.bspc.2020.102041","article-title":"Assisted deep learning framework for multi-class skin lesion classification considering a binary classification support","volume":"62","author":"B Harangi","year":"2020","journal-title":"Biomedical Signal Processing and Control"},{"key":"pone.0309430.ref023","doi-asserted-by":"crossref","first-page":"106956","DOI":"10.1016\/j.compeleceng.2020.106956","article-title":"Pixels to classes: intelligent learning framework for multiclass skin lesion localization and classification","volume":"90","author":"MA Khan","year":"2021","journal-title":"Computers & Electrical Engineering"},{"issue":"12","key":"pone.0309430.ref024","doi-asserted-by":"crossref","first-page":"4399","DOI":"10.3390\/s22124399","article-title":"Skin lesion classification using collective intelligence of multiple neural networks","volume":"22","author":"D Popescu","year":"2022","journal-title":"Sensors"},{"issue":"7","key":"pone.0309430.ref025","doi-asserted-by":"crossref","first-page":"1183","DOI":"10.3390\/healthcare10071183","article-title":"Detection of skin cancer based on skin lesion images using deep learning","volume":"10","author":"W Gouda","year":"2022","journal-title":"Healthcare"},{"key":"pone.0309430.ref026","doi-asserted-by":"crossref","first-page":"113715","DOI":"10.1109\/ACCESS.2022.3217217","article-title":"A deep learning approach based on explainable artificial intelligence for skin lesion classification","volume":"10","author":"N Nigar","year":"2022","journal-title":"IEEE Access"},{"issue":"19","key":"pone.0309430.ref027","doi-asserted-by":"crossref","first-page":"7530","DOI":"10.3390\/s22197530","article-title":"Skin lesion classification on imbalanced data using deep learning with soft attention","volume":"22","author":"VD Nguyen","year":"2022","journal-title":"Sensors"},{"key":"pone.0309430.ref028","doi-asserted-by":"crossref","unstructured":"Datta SK, Shaikh MA, Srihari SN, Gao M. Soft attention improves skin cancer classification performance. InInterpretability of Machine Intelligence in Medical Image Computing, and Topological Data Analysis and Its Applications for Medical Data: 4th International Workshop, iMIMIC 2021, and 1st International Workshop, TDA4MedicalData 2021, Held in Conjunction with MICCAI 2021, Strasbourg, France, September 27, 2021, Proceedings 4 2021 (pp. 13-23). Springer International Publishing.","DOI":"10.1007\/978-3-030-87444-5_2"},{"issue":"1","key":"pone.0309430.ref029","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/sdata.2018.161","article-title":"The HAM10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions","volume":"5","author":"P Tschandl","year":"2018","journal-title":"Scientific data"},{"key":"pone.0309430.ref030","unstructured":"HAM10000: Splitted and Augmented IGPA (70 15 15); https:\/\/www.kaggle.com\/datasets\/anwarhossaine\/ham10000-splitted-and-augmented-igpa-70-15-15."},{"key":"pone.0309430.ref031","doi-asserted-by":"crossref","unstructured":"Woo S, Park J, Lee JY, Kweon IS. Cbam: Convolutional block attention module. InProceedings of the European conference on computer vision (ECCV) 2018 (pp. 3-19).","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"pone.0309430.ref032","doi-asserted-by":"crossref","unstructured":"Hu J, Shen L, Sun G. Squeeze-and-excitation networks. InProceedings of the IEEE conference on computer vision and pattern recognition 2018 (pp. 7132-7141).","DOI":"10.1109\/CVPR.2018.00745"}],"container-title":["PLOS ONE"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0309430","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,24]],"date-time":"2024-10-24T17:35:54Z","timestamp":1729791354000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0309430"}},"subtitle":[],"editor":[{"given":"Andrew","family":"J","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2024,10,24]]},"references-count":32,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2024,10,24]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0309430","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,24]]}}}