{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T06:01:33Z","timestamp":1781157693606,"version":"3.54.1"},"reference-count":45,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T00:00:00Z","timestamp":1781136000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Automated classification of skin lesion remains a challenging task due to high inter-class similarity, intra-class variance and extreme class imbalance in the dermoscopic datasets. To overcome these limitations, the proposed study presents a Hybrid Bi-Feature Network model as HB-Net, in which the convolutional neural networks are fine-tuned to extract features and subsequently machine learning classifier are used for skin lesion classification.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>DenseNet201 and ResNet50 are both fully trainable deep architectures independently trained on the dermoscopic images to find discriminative representations. Global average pooled features are concatenated with fully connected embeddings from both networks to form a unified deep feature vector. Principal component analysis is employed to minimise redundancy and improve the separability of classes, and Synthetic Minority Over-sampling Technique is then used to address the problem of class imbalance. The refined features are further categorized with the help of support vector machine as well as with the stacking ensemble classifier consisting of the random forest and extreme gradient boosting models.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results and discussion<\/jats:title>\n                    <jats:p>The proposed HB-Net model was evaluated on the HAM10000 dataset, achieving a classification accuracy of 0.9049, recall of 0.8427, specificity of 0.9743, precision of 0.8594, and an F1-score of 0.8489. Experimental findings on a multi-class dataset of skin lesions prove that the proposed hybrid framework achieved better classification performance score than separate deep learning models.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>The proposed model is also validated on ISIC 2019 dataset. The findings validate that the integration of complementary deep features with ensemble machine learning classifiers are effective in addressing reliable skin lesion classification.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/frai.2026.1818852","type":"journal-article","created":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T05:48:57Z","timestamp":1781156937000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Hybrid deep feature fusion and ensemble learning for multi-class skin lesion classification"],"prefix":"10.3389","volume":"9","author":[{"given":"Mahalakshmi","family":"G","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Vellore Institute of Technology","place":["Chennai, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chanthini","family":"Baskar","sequence":"additional","affiliation":[{"name":"School of Electronics Engineering, Vellore Institute of Technology","place":["Chennai, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sasithradevi","family":"A","sequence":"additional","affiliation":[{"name":"Center for Advanced Data Science, Vellore Institute of Technology","place":["Chennai, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,6,11]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"24994","DOI":"10.1038\/s41598-025-08954-8","article-title":"Enhanced melanoma and non-melanoma skin cancer classification using a hybrid LSTM-CNN model","volume":"15","author":"Abohashish","year":"2025","journal-title":"Sci. Rep."},{"key":"ref2","doi-asserted-by":"publisher","first-page":"811","DOI":"10.1007\/s10462-020-09865-y","article-title":"Deep learning techniques for skin lesion analysis and melanoma cancer detection: a survey of state-of-the-art","volume":"54","author":"Adegun","year":"2021","journal-title":"Artif. Intell. Rev."},{"key":"ref3","doi-asserted-by":"publisher","first-page":"38306","DOI":"10.1109\/ACCESS.2019.2906241","article-title":"Skin lesion classification using convolutional neural network with novel regularizer","volume":"7","author":"Albahar","year":"2019","journal-title":"IEEE Access"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"100034","DOI":"10.1016\/j.neuri.2021.100034","article-title":"Multiclass skin cancer classification using EfficientNets \u2013 a first step towards preventing skin cancer","volume":"2","author":"Ali","year":"2022","journal-title":"Neurosci. Inform."},{"key":"ref5","doi-asserted-by":"publisher","first-page":"2481","DOI":"10.3390\/healthcare10122481","article-title":"Melanoma detection using deep learning-based classifications","volume":"10","author":"Alwakid","year":"2022","journal-title":"Healthcare"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"19379","DOI":"10.1007\/s11042-024-19837-x","article-title":"Skin lesion classification via ensemble method on deep learning","volume":"84","author":"Amiri","year":"2025","journal-title":"Multimed. Tools Appl."},{"key":"ref7","doi-asserted-by":"publisher","first-page":"108798","DOI":"10.1016\/j.compbiomed.2024.108798","article-title":"Skin-CAD: explainable deep learning classification of skin cancer from dermoscopic images by feature selection of dual high-level CNNs features and transfer learning","volume":"178","author":"Attallah","year":"2024","journal-title":"Comput. Biol. Med."},{"key":"ref8","doi-asserted-by":"publisher","first-page":"108044","DOI":"10.1016\/j.cmpb.2024.108044","article-title":"Understanding skin color bias in deep learning-based skin lesion segmentation","volume":"245","author":"Ben\u010devi\u0107","year":"2024","journal-title":"Comput. Methods Prog. Biomed."},{"key":"ref9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1046\/j.1365-2133.146.s61.2.x","article-title":"The epidemiology of skin cancer","volume":"146","author":"Diepgen","year":"2002","journal-title":"Br. J. Dermatol."},{"key":"ref10","doi-asserted-by":"publisher","first-page":"104186","DOI":"10.1016\/j.bspc.2022.104186","article-title":"A comprehensive analysis of dermoscopy images for melanoma detection via deep CNN features","volume":"79","author":"Gajera","year":"2023","journal-title":"Biomed. Signal Process. Control"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"107449","DOI":"10.1016\/j.bspc.2024.107449","article-title":"Multi-residual attention network for skin lesion classification","volume":"103","author":"Ghazouani","year":"2025","journal-title":"Biomed. Signal Process. Control"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"50205","DOI":"10.1109\/ACCESS.2023.3274848","article-title":"DeepSkin: a deep learning approach for skin cancer classification","volume":"11","author":"Gururaj","year":"2023","journal-title":"IEEE Access"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"106324","DOI":"10.1016\/j.bspc.2024.106324","article-title":"Timely detection of skin cancer: an AI-based approach on the basis of the integration of Echo state network and adapted seasons optimization algorithm","volume":"94","author":"Han","year":"2024","journal-title":"Biomed. Signal Process. Control"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"106624","DOI":"10.1016\/j.compbiomed.2023.106624","article-title":"A survey, review, and future trends of skin lesion segmentation and classification","volume":"155","author":"Hasan","year":"2023","journal-title":"Comput. Biol. Med."},{"key":"ref15","doi-asserted-by":"publisher","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":"Hoang","year":"2022","journal-title":"Appl. Sci."},{"key":"ref16","doi-asserted-by":"publisher","first-page":"15763","DOI":"10.1007\/s11042-022-13847-3","article-title":"Classification of skin cancer from dermoscopic images using deep neural network architectures","volume":"82","author":"Jaisakthi","year":"2023","journal-title":"Multimed. Tools Appl."},{"key":"ref17","first-page":"357","article-title":"Early detection and treatment of skin cancer","volume-title":"Am. Fam. Physician","author":"Jerant","year":"2000"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"12020344","DOI":"10.3390\/diagnostics12020344","article-title":"Preprocessing effects on performance of skin lesion saliency segmentation","volume":"12","author":"Joseph","year":"2022","journal-title":"Diagnostics"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"106620","DOI":"10.1016\/j.cmpb.2022.106620","article-title":"ExAID: a multimodal explanation framework for computer-aided diagnosis of skin lesions","volume":"215","author":"Lucieri","year":"2022","journal-title":"Comput. Methods Prog. Biomed."},{"key":"ref20","doi-asserted-by":"publisher","first-page":"47","DOI":"10.5815\/ijigsp.2022.03.05","article-title":"Mobile-based skin disease diagnosis system using convolutional neural networks (CNN)","volume":"14","author":"Maduranga","year":"2022","journal-title":"Int. J. Image Graph. Signal Process."},{"key":"ref21","doi-asserted-by":"publisher","first-page":"24533","DOI":"10.1038\/s41598-025-09938-4","article-title":"Explainable deep learning approaches for high precision early melanoma detection using dermoscopic images","volume":"15","author":"Mahmud","year":"2025","journal-title":"Sci. Rep."},{"key":"ref22","doi-asserted-by":"crossref","first-page":"1178","DOI":"10.1001\/archderm.1996.03890340038007","article-title":"Frequency and morphologic characteristics of invasive melanomas lacking specific surface microscopic features","volume":"132","author":"Menzies","year":"1996","journal-title":"Arch. Dermatol."},{"key":"ref23","doi-asserted-by":"publisher","first-page":"45321","DOI":"10.1007\/s11042-025-20951-7","article-title":"MiSC: a hybrid multi-modal deep learning approach for accurate skin cancer detection","volume":"84","author":"Mohamed","year":"2025","journal-title":"Multimed. Tools Appl."},{"key":"ref24","doi-asserted-by":"publisher","first-page":"87105","DOI":"10.1007\/s11042-024-19817-1","article-title":"A deep learning based architecture for multi-class skin cancer classification","volume":"83","author":"Mushtaq","year":"2024","journal-title":"Multimed. Tools Appl."},{"key":"ref25","doi-asserted-by":"publisher","first-page":"551","DOI":"10.1016\/s0190-9622(94)70061-3","article-title":"The ABCD rule of dermatoscopy. High prospective value in the diagnosis of doubtful melanocytic skin lesions","volume":"30","author":"Nachbar","year":"1994","journal-title":"J. Am. Acad. Dermatol."},{"key":"ref26","doi-asserted-by":"publisher","first-page":"314","DOI":"10.1007\/s00530-025-01952-w","article-title":"SkinDWNet: a novel deep learning model for multiclass classification of skin cancers using dermoscopic images","volume":"31","author":"Naeem","year":"2025","journal-title":"Multimedia Systems"},{"key":"ref27","doi-asserted-by":"publisher","first-page":"7252","DOI":"10.1038\/s41598-025-91446-6","article-title":"Skin cancer detection using dermoscopic images with convolutional neural network","volume":"15","author":"Nawaz","year":"2025","journal-title":"Sci. Rep."},{"key":"ref28","first-page":"12671","author":"Ouali","year":"2020"},{"key":"ref29","doi-asserted-by":"publisher","first-page":"4938","DOI":"10.1038\/s41598-025-89230-7","article-title":"A robust deep learning framework for multiclass skin cancer classification","volume":"15","author":"Ozdemir","year":"2025","journal-title":"Sci. Rep."},{"key":"ref30","doi-asserted-by":"publisher","first-page":"444","DOI":"10.1111\/jocd.14547","article-title":"Non-invasive diagnostic techniques in pigmentary skin disorders and skin cancer","volume":"21","author":"Pathania","year":"2022","journal-title":"J. Cosmet. Dermatol."},{"key":"ref31","doi-asserted-by":"publisher","first-page":"129302","DOI":"10.1016\/j.eswa.2025.129302","article-title":"Efficient ensemble learning with multi-scale fusion based deep neural network for skin lesion classification","volume":"296","author":"Reis","year":"2026","journal-title":"Expert Syst. Appl."},{"key":"ref32","doi-asserted-by":"publisher","first-page":"100103","DOI":"10.1016\/j.cmpbup.2023.100103","article-title":"A hybrid approach for melanoma classification using ensemble machine learning techniques with deep transfer learning","volume":"3","author":"Roshni Thanka","year":"2023","journal-title":"Comput. Methods Programs Biomed. Update"},{"key":"ref33","doi-asserted-by":"publisher","first-page":"100143","DOI":"10.1016\/j.health.2023.100143","article-title":"An in-depth analysis of convolutional neural network architectures with transfer learning for skin disease diagnosis","volume":"3","author":"Sadik","year":"2023","journal-title":"Healthcare Analytics"},{"key":"ref34","doi-asserted-by":"publisher","first-page":"103423","DOI":"10.1016\/j.compbiomed.2019.103423","article-title":"Gabor wavelet-based deep learning for skin lesion classification","volume":"113","author":"Serte","year":"2019","journal-title":"Comput. Biol. Med."},{"key":"ref35","doi-asserted-by":"publisher","first-page":"332","DOI":"10.3390\/jimaging10120332","article-title":"Explainable AI-based skin Cancer detection using CNN, particle swarm optimization and machine learning","volume":"10","author":"Shah","year":"2024","journal-title":"J. Imaging"},{"key":"ref36","doi-asserted-by":"publisher","first-page":"76","DOI":"10.1016\/j.ceh.2023.08.002","article-title":"A comprehensive study on skin cancer detection using artificial neural network (ANN) and convolutional neural network (CNN)","volume":"6","author":"Shah","year":"2023","journal-title":"Clinical eHealth"},{"key":"ref37","doi-asserted-by":"publisher","first-page":"12","DOI":"10.3322\/caac.21820","article-title":"Cancer statistics, 2024","volume":"74","author":"Siegel","year":"2024","journal-title":"CA Cancer J. Clin."},{"key":"ref38","doi-asserted-by":"publisher","first-page":"209","DOI":"10.3322\/caac.21660","article-title":"Global Cancer statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries","volume":"71","author":"Sung","year":"2021","journal-title":"CA Cancer J. Clin."},{"key":"ref39","doi-asserted-by":"publisher","first-page":"27501","DOI":"10.1007\/s11042-023-14697-3","article-title":"Skin cancer detection using ensemble of machine learning and deep learning techniques","volume":"82","author":"Tembhurne","year":"2023","journal-title":"Multimed. Tools Appl."},{"key":"ref40","doi-asserted-by":"publisher","first-page":"112193","DOI":"10.1109\/ACCESS.2021.3103410","article-title":"Skin lesion classification by ensembles of deep convolutional networks and regularly spaced shifting","volume":"9","author":"Thurnhofer-Hemsi","year":"2021","journal-title":"IEEE Access"},{"key":"ref41","doi-asserted-by":"publisher","first-page":"180161","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":"Tschandl","year":"2018","journal-title":"Sci. Data"},{"key":"ref42","doi-asserted-by":"publisher","first-page":"676","DOI":"10.1111\/j.1365-2133.2008.08713.x","article-title":"Dermoscopy compared with naked eye examination for the diagnosis of primary melanoma: a meta-analysis of studies performed in a clinical setting","volume":"159","author":"Vestergaard","year":"2008","journal-title":"Br. J. Dermatol."},{"key":"ref43","doi-asserted-by":"crossref","DOI":"10.1109\/IEMBS.2011.6090866","article-title":"Implementation of the 7-point checklist for melanoma detection on smart handheld devices","author":"Wadhawan","year":"2011"},{"key":"ref44","doi-asserted-by":"publisher","first-page":"2482","DOI":"10.1109\/TMI.2020.2972964","article-title":"A mutual bootstrapping model for automated skin lesion segmentation and classification","volume":"39","author":"Xie","year":"2020","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref45","article-title":"Projection guided personalized federated learning for low dose CT denoising","author":"Zafar","year":"2026"}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1818852\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T05:48:58Z","timestamp":1781156938000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1818852\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,11]]},"references-count":45,"alternative-id":["10.3389\/frai.2026.1818852"],"URL":"https:\/\/doi.org\/10.3389\/frai.2026.1818852","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,11]]},"article-number":"1818852"}}