{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T19:21:14Z","timestamp":1790364074149,"version":"4.1.0"},"reference-count":36,"publisher":"MDPI AG","issue":"6","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":[],"crossmark-restriction":false},"short-container-title":["Bioengineering"],"abstract":"<jats:p>Deep learning-based automated classification of dermatoscopic skin lesions has exhibited promising potential in diagnostics. However, two prominent issues need to be addressed before achieving high-quality diagnostic tools: inconsistent performance in the case of imbalanced classes and poor clinical interpretability of models. Even though some studies have attempted to leverage both deep and shallow learning by combining pretrained convolutional neural networks (CNNs)-based feature extraction with classical machine learning (ML) models, very few of them systematically explore several model combinations based on various clinically important metrics, such as F1-score, precision, recall, accuracy, etc., and utilize decision threshold calibration techniques. In this research, we present an evaluation of a systematic framework with threshold calibration for the comparison of several hybrid models on seven-class skin lesion classification (multi-class) on the HAM10000 dataset. In particular, we used deep features extracted from three pretrained CNN architectures, i.e., DenseNet201, InceptionV3 and EfficientNet-B4. These deep features were used as inputs for six different classical classifiers. As a result, we obtained 18 comparable hybrid models that were then systematically compared by multiple clinically relevant metrics: accuracy, macro-precision, macro-recall, macro-F1, ROC-AUC, Precision-Recall-AUC, and log loss. Also, fold-wise optimization of decision thresholds was performed, which was based on the maximization of the macro-F1 score. Finally, we found out that DenseNet201 with an SVM-RBF classifier yielded the highest performance among all 18 tested models, showing 90.88% accuracy, 90.7% macro-precision, and 0.921 ROC-AUC. To analyze the clinical plausibility, top-performing models were further explained with explainable artificial intelligence (XAI) techniques: Grad-CAM, LIME and Occlusion Sensitivity. Results show that the most successful models concentrated mostly on lesion-specific areas. Overall, this study contributes a reproducible hybrid-XAI model-selection framework rather than a single black-box classifier, supporting more transparent and clinically meaningful skin lesion diagnosis.<\/jats:p>","DOI":"10.3390\/bioengineering13060677","type":"journal-article","created":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T06:57:17Z","timestamp":1781161037000},"page":"677","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Interpretable Skin Cancer Identification Using a Hybrid Deep Learning and XAI Framework on HAM10000"],"prefix":"10.3390","volume":"13","author":[{"given":"Bhagyashri S.","family":"Sonune","sequence":"first","affiliation":[{"name":"Department of Computer Science, Kalinga University, Raipur 492101, Chhattisgarh, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"R. Udaya","family":"Kumar","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Kalinga University, Raipur 492101, Chhattisgarh, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0120-6575","authenticated-orcid":false,"given":"K.","family":"Sankar","sequence":"additional","affiliation":[{"name":"Department of Artificial Intelligence and Data Science, Vel Tech High Tech Dr.Rangarajan Dr.Sakunthala Engineering College, Avadi, Chennai 600062, Tamil Nadu, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-6137-4171","authenticated-orcid":false,"given":"Puja S.","family":"Agrawal","sequence":"additional","affiliation":[{"name":"Department of Electronics and Communication Engineering, School of Electrical and Electronics Engineering, Ramdeobaba University, Nagpur 440013, Maharashtra, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-8898-3758","authenticated-orcid":false,"given":"Shon G.","family":"Nemane","sequence":"additional","affiliation":[{"name":"Department of Electronics and Telecommunication Engineering, Shri Sant Gajanan Maharaj College of Engineering, Shegaon 444203, Maharashtra, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6540-2471","authenticated-orcid":false,"given":"Dhiraj P.","family":"Tulaskar","sequence":"additional","affiliation":[{"name":"Department of Electronics and Telecommunication Engineering, Shri Sant Gajanan Maharaj College of Engineering, Shegaon 444203, Maharashtra, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Manish","family":"Bhaiyya","sequence":"additional","affiliation":[{"name":"Department of Electronics and Telecommunication Engineering, Shri Sant Gajanan Maharaj College of Engineering, Shegaon 444203, Maharashtra, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2911-3784","authenticated-orcid":false,"given":"Madhusudan B.","family":"Kulkarni","sequence":"additional","affiliation":[{"name":"Manipal Institute of Technology, Manipal Academy of Higher Education (MAHE), Manipal 576104, Karnataka, India"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,6,11]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"5996","DOI":"10.1038\/s41598-025-90485-3","article-title":"Global, regional, and national trends in the burden of melanoma and non-melanoma skin cancer: Insights from the global burden of disease study 1990\u20132021","volume":"15","author":"Zhou","year":"2025","journal-title":"Sci. Rep."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1110","DOI":"10.1002\/ijc.35463","article-title":"Global burden of cutaneous melanoma incidence attributable to ultraviolet radiation in 2022","volume":"157","author":"Langselius","year":"2025","journal-title":"Int. J. Cancer"},{"key":"ref_3","first-page":"CD011901","article-title":"Visual inspection and dermoscopy, alone or in combination, for diagnosing keratinocyte skin cancers in adults","volume":"12","author":"Dinnes","year":"2018","journal-title":"Cochrane Database Syst. Rev."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"281","DOI":"10.2340\/actadv.v101.281","article-title":"Interobserver agreement on dermoscopic features and their associations with in situ and invasive cutaneous melanomas","volume":"101","author":"Polesie","year":"2021","journal-title":"Acta Derm. Venereol."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"47","DOI":"10.1016\/j.ejca.2019.04.001","article-title":"Deep learning outperformed 136 of 157 dermatologists in a head-to-head dermoscopic melanoma image classification task","volume":"113","author":"Brinker","year":"2019","journal-title":"Eur. J. Cancer"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Codella, N.C.F., Gutman, D., Celebi, M.E., Helba, B., Marchetti, M.A., Dusza, S.W., Kalloo, A., Liopyris, K., Mishra, N., and Kittler, H. (2018, January 4\u20137). Skin lesion analysis toward melanoma detection: A challenge at the 2017 international symposium on biomedical imaging (isbi), hosted by the international skin imaging collaboration (isic). Proceedings of the 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018), Washington, DC, USA.","DOI":"10.1109\/ISBI.2018.8363547"},{"key":"ref_7","doi-asserted-by":"crossref","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":"ref_8","doi-asserted-by":"crossref","unstructured":"Manole, I., Butacu, A.-I., Bejan, R.N., and Tiplica, G.-S. (2024). Enhancing dermatological diagnostics with efficientnet: A deep learning approach. Bioengineering, 11.","DOI":"10.20944\/preprints202407.1322.v1"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"101843","DOI":"10.1016\/j.compmedimag.2020.101843","article-title":"Automated multi-class classification of skin lesions through deep convolutional neural network with dermoscopic images","volume":"88","author":"Iqbal","year":"2021","journal-title":"Comput. Med. Imaging Graph."},{"key":"ref_10","first-page":"200149","article-title":"Automated identification of human gastrointestinal tract abnormalities based on deep convolutional neural network with endoscopic images","volume":"16","author":"Iqbal","year":"2022","journal-title":"Intell. Syst. Appl."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Zhang, X., Liu, Y., Ouyang, G., Chen, W., Xu, A., Hara, T., Zhou, X., and Wu, D. (2025). DermViT: Diagnosis-Guided Vision Transformer for Robust and Efficient Skin Lesion Classification. Bioengineering, 12.","DOI":"10.3390\/bioengineering12040421"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Garcia, A., Zhou, J., Pinero-Crespo, G., Beachkofsky, T., and Huang, X. (2025). Clinical Application of Vision Transformers for Melanoma Classification: A Multi-Dataset Evaluation Study. Cancers, 17.","DOI":"10.20944\/preprints202510.0303.v1"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"3022192","DOI":"10.1155\/2024\/3022192","article-title":"Skin cancer segmentation and classification using vision transformer for automatic analysis in dermatoscopy-based noninvasive digital system","volume":"2024","author":"Himel","year":"2024","journal-title":"Int. J. Biomed. Imaging"},{"key":"ref_14","unstructured":"Agarwal, S., and Mahto, A.K. (2025). Skin Cancer Classification: Hybrid CNN-Transformer Models with KAN-Based Fusion. arXiv."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1664","DOI":"10.1007\/s10278-024-01065-2","article-title":"Checklist for reproducibility of deep learning in medical imaging","volume":"37","author":"Moassefi","year":"2024","journal-title":"J. Imaging Inform. Med."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Liu, R., Chen, Z., and Zhang, P. (2025). Exploring the Challenge and Value of Deep Learning in Automated Skin Disease Diagnosis. arXiv.","DOI":"10.1016\/j.bspc.2026.109589"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"102470","DOI":"10.1016\/j.media.2022.102470","article-title":"Explainable artificial intelligence (XAI) in deep learning-based medical image analysis","volume":"79","author":"Kuijf","year":"2022","journal-title":"Med. Image Anal."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"4793","DOI":"10.1109\/TNNLS.2020.3027314","article-title":"A survey on explainable artificial intelligence (xai): Toward medical xai","volume":"32","author":"Tjoa","year":"2020","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"7","DOI":"10.32628\/IJSRST25126288","article-title":"Explainable AI (XAI) in Healthcare: Building Trust in Medical Diagnosis Systems","volume":"12","author":"Khade","year":"2025","journal-title":"Int. J. Sci. Res. Sci. Technol."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"62126","DOI":"10.1109\/ACCESS.2026.3684257","article-title":"Interpretable Deep Learning in Dermoscopy: An XAI-Driven Ensemble for Skin Lesion Diagnosis","volume":"14","author":"Sonune","year":"2026","journal-title":"IEEE Access"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Ahmed, I.A., Senan, E.M., Shatnawi, H.S.A., Alkhraisha, Z.M., and Al-Azzam, M.M.A. (2023). Multi-models of analyzing dermoscopy images for early detection of multi-class skin lesions based on fused features. Processes, 11.","DOI":"10.3390\/pr11030910"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Debelee, T.G. (2023). Skin lesion classification and detection using machine learning techniques: A systematic review. Diagnostics, 13.","DOI":"10.3390\/diagnostics13193147"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"100069","DOI":"10.1016\/j.bea.2022.100069","article-title":"Hybrid convolutional neural networks with SVM classifier for classification of skin cancer","volume":"5","author":"Keerthana","year":"2023","journal-title":"Biomed. Eng. Adv."},{"key":"ref_24","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":"Shetty","year":"2022","journal-title":"Sci. Rep."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Nie, Y., Sommella, P., Carrat\u00f9, M., O\u2019Nils, M., and Lundgren, J. (2022). A deep CNN transformer hybrid model for skin lesion classification of dermoscopic images using focal loss. Diagnostics, 13.","DOI":"10.3390\/diagnostics13010072"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"100034","DOI":"10.1016\/j.neuri.2021.100034","article-title":"Multiclass skin cancer classification using EfficientNets\u2014A first step towards preventing skin cancer","volume":"2","author":"Ali","year":"2022","journal-title":"Neurosci. Inform."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Tajerian, A., Kazemian, M., Tajerian, M., and Malayeri, A.A. (2023). Design and validation of a new machine-learning-based diagnostic tool for the differentiation of dermatoscopic skin cancer images. PLoS ONE, 18.","DOI":"10.1371\/journal.pone.0284437"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"105939","DOI":"10.1016\/j.compbiomed.2022.105939","article-title":"An improved transformer network for skin cancer classification","volume":"149","author":"Xin","year":"2022","journal-title":"Comput. Biol. Med."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Shah, S.A.H., Shah, S.T.H., Khaled, R., Buccoliero, A., Shah, S.B.H., Di Terlizzi, A., Di Benedetto, G., and Deriu, M.A. (2024). Explainable AI-based skin cancer detection using CNN, particle swarm optimization and machine learning. J. Imaging, 10.","DOI":"10.3390\/jimaging10120332"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"438","DOI":"10.1002\/hcs2.121","article-title":"SkinSage XAI: An explainable deep learning solution for skin lesion diagnosis","volume":"3","author":"Munjal","year":"2024","journal-title":"Health Care Sci."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1038\/nature21056","article-title":"Dermatologist-level classification of skin cancer with deep neural networks","volume":"542","author":"Esteva","year":"2017","journal-title":"Nature"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"5455","DOI":"10.1007\/s10462-020-09825-6","article-title":"A survey of the recent architectures of deep convolutional neural networks","volume":"53","author":"Khan","year":"2020","journal-title":"Artif. Intell. Rev."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Abufadel, A., Slabaugh, G., Unal, G., Zhang, L., and Odry, B. (2006, January 20\u201324). Interacting active rectangles for estimation of intervertebral disk orientation. Proceedings of the 18th International Conference on Pattern Recognition (ICPR\u201906), Hong Kong, China.","DOI":"10.1109\/ICPR.2006.719"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"104115","DOI":"10.1016\/j.compbiomed.2020.104115","article-title":"A scoping review of transfer learning research on medical image analysis using ImageNet","volume":"128","author":"Morid","year":"2021","journal-title":"Comput. Biol. Med."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"19781","DOI":"10.1038\/s41598-024-70231-x","article-title":"Radiomic and deep learning analysis of dermoscopic images for skin lesion pattern decoding","volume":"14","author":"Wang","year":"2024","journal-title":"Sci. Rep."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Mavaie, P., Holder, L., and Skinner, M.K. (2023). Hybrid deep learning approach to improve classification of low-volume high-dimensional data. BMC Bioinform., 24.","DOI":"10.1186\/s12859-023-05557-w"}],"container-title":["Bioengineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2306-5354\/13\/6\/677\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T07:42:46Z","timestamp":1781163766000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2306-5354\/13\/6\/677"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,11]]},"references-count":36,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2026,6]]}},"alternative-id":["bioengineering13060677"],"URL":"https:\/\/doi.org\/10.3390\/bioengineering13060677","relation":{},"ISSN":["2306-5354"],"issn-type":[{"value":"2306-5354","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,11]]}}}