{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,6]],"date-time":"2026-11-06T17:51:00Z","timestamp":1793987460895,"version":"4.8.0"},"reference-count":40,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,2,3]],"date-time":"2025-02-03T00:00:00Z","timestamp":1738540800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,2,3]],"date-time":"2025-02-03T00:00:00Z","timestamp":1738540800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100019904","name":"Vellore Institute of Technology, Chennai","doi-asserted-by":"crossref","id":[{"id":"10.13039\/100019904","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Diabetic Foot Ulcer (DFU) is a severe complication of diabetes mellitus, resulting in significant health and socio-economic challenges for the diagnosed individual. Severe cases of DFU can lead to lower limb amputation in diabetic patients, making their diagnosis a complex and costly process that poses challenges for medical professionals. Manual identification of DFU is particularly difficult due to their diverse visual characteristics, leading to multiple cases going undiagnosed. To address this challenge, Deep Learning (DL) methods offer an efficient and automated approach to facilitate timely treatment and improve patient outcomes. This research proposes a novel feature fusion-based model that incorporates two parallel tracks for efficient feature extraction. The first track utilizes the Swin transformer, which captures long-range dependencies by employing shifted windows and self-attention mechanisms. The second track involves the Efficient Multi-Scale Attention-Driven Network (EMADN), which leverages Light-weight Multi-scale Deformable Shuffle (LMDS) and Global Dilated Attention (GDA) blocks to extract local features efficiently. These blocks dynamically adjust kernel sizes and leverage attention modules, enabling effective feature extraction. To the best of our knowledge, this is the first work reporting the findings of a dual track architecture for DFU classification, leveraging Swin transformer and EMADN networks. The obtained feature maps from both the networks are concatenated and subjected to shuffle attention for feature refinement at a reduced computational cost. The proposed work also incorporates Grad-CAM-based Explainable Artificial Intelligence (XAI) to visualize and interpret the decision making of the network. The proposed model demonstrated better performance on the DFUC-2021 dataset, surpassing existing works and pre-trained CNN architectures with an accuracy of 78.79% and a macro F1-score of 80%.<\/jats:p>","DOI":"10.1038\/s41598-025-87519-1","type":"journal-article","created":{"date-parts":[[2025,2,3]],"date-time":"2025-02-03T05:56:57Z","timestamp":1738562217000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":37,"title":["An explainable deep learning model for diabetic foot ulcer classification using swin transformer and efficient multi-scale attention-driven network"],"prefix":"10.1038","volume":"15","author":[{"given":"R.","family":"Karthik","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Armaano","family":"Ajay","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anshika","family":"Jhalani","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kruthik","family":"Ballari","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Suganthi","family":"K","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,2,3]]},"reference":[{"key":"87519_CR1","doi-asserted-by":"publisher","unstructured":"Shata, A. & Abdulaziz, N. Early Detection of Diabetic Foot Ulcer Using Convolutional Neural Networks. In 2021 IEEE Region 10 Symposium (TENSYMP). IEEE. (2021). https:\/\/doi.org\/10.1109\/tensymp52854.2021.9550812","DOI":"10.1109\/tensymp52854.2021.9550812"},{"key":"87519_CR2","doi-asserted-by":"publisher","first-page":"104596","DOI":"10.1016\/j.compbiomed.2021.104596","volume":"135","author":"MH Yap","year":"2021","unstructured":"Yap, M. H. et al. Deep learning in diabetic foot ulcers detection: a comprehensive evaluation. In computers in Biology and Medicine. Elsevier BV. 135, 104596. https:\/\/doi.org\/10.1016\/j.compbiomed.2021.104596 (2021).","journal-title":"Elsevier BV"},{"key":"87519_CR3","doi-asserted-by":"publisher","unstructured":"Mulyono, S. et al. Classification of Ischemic, Infectious, and Normal Diabetic Foot Ulcers Based on the EfficientNet Model. In 2023 10th International Conference on Electrical Engineering, Computer Science and Informatics (EECSI). IEEE. (2023). https:\/\/doi.org\/10.1109\/eecsi59885.2023.10295901","DOI":"10.1109\/eecsi59885.2023.10295901"},{"key":"87519_CR4","doi-asserted-by":"publisher","DOI":"10.1016\/j.ibmed.2023.100128","author":"S Biswas","year":"2023","unstructured":"Biswas, S. et al. Intelligence-Based Medicine. Elsevier BV. 8, 100128. https:\/\/doi.org\/10.1016\/j.ibmed.2023.100128 (2023). DFU_MultiNet: A deep neural network approach for detecting diabetic foot ulcers through multi-scale feature fusion using the DFU dataset."},{"key":"87519_CR5","doi-asserted-by":"publisher","unstructured":"Yap, M. H. et al. Analysis Towards Classification of Infection and Ischaemia of Diabetic Foot Ulcers. In 2021 IEEE EMBS International Conference on Biomedical and Health Informatics (BHI). IEEE. (2021). https:\/\/doi.org\/10.1109\/bhi50953.2021.9508563","DOI":"10.1109\/bhi50953.2021.9508563"},{"key":"87519_CR6","doi-asserted-by":"publisher","unstructured":"Wang, M. & Timbol-Cuison, L. Machine Learning Classification Techniques for Diabetic Foot Ulcers. In 2022 4th International Conference on Artificial Intelligence and Advanced Manufacturing (AIAM). IEEE. (2022). https:\/\/doi.org\/10.1109\/aiam57466.2022.00054","DOI":"10.1109\/aiam57466.2022.00054"},{"key":"87519_CR7","doi-asserted-by":"publisher","first-page":"103616","DOI":"10.1016\/j.compbiomed.2020.103616","volume":"117","author":"M Goyal","year":"2020","unstructured":"Goyal, M. et al. Recognition of ischaemia and infection in diabetic foot ulcers: dataset and techniques. In computers in Biology and Medicine. Elsevier BV. 117, 103616. https:\/\/doi.org\/10.1016\/j.compbiomed.2020.103616 (2020).","journal-title":"Elsevier BV"},{"issue":"Issue 1","key":"87519_CR8","doi-asserted-by":"publisher","first-page":"100150","DOI":"10.1016\/j.xjidi.2022.100150","volume":"3","author":"HK Jeong","year":"2023","unstructured":"Jeong, H. K. et al. Deep learning in Dermatology: a systematic review of current approaches, outcomes, and limitations. In JID innovations. Elsevier BV. 3 (Issue 1), 100150. https:\/\/doi.org\/10.1016\/j.xjidi.2022.100150 (2023).","journal-title":"Elsevier BV"},{"key":"87519_CR9","doi-asserted-by":"publisher","first-page":"91","DOI":"10.3390\/computers12050091","volume":"12","author":"MM Taye","year":"2023","unstructured":"Taye, M. M. Understanding of Machine Learning with Deep Learning: architectures, Workflow, applications and future directions. Computers 12, 91. https:\/\/doi.org\/10.3390\/computers12050091 (2023).","journal-title":"Computers"},{"key":"87519_CR10","doi-asserted-by":"publisher","first-page":"4396","DOI":"10.3390\/app9204396","volume":"9","author":"H Liu","year":"2019","unstructured":"Liu, H. & Lang, B. Machine learning and deep learning methods for intrusion detection systems: a Survey. Appl. Sci. 9, 4396. https:\/\/doi.org\/10.3390\/app9204396 (2019).","journal-title":"Appl. Sci."},{"key":"87519_CR11","doi-asserted-by":"publisher","first-page":"13521","DOI":"10.1007\/s10462-023-10466-8","volume":"56","author":"SF Ahmed","year":"2023","unstructured":"Ahmed, S. F. et al. Deep learning modelling techniques: current progress, applications, advantages, and challenges. Artif. Intell. Rev. 56, 13521\u201313617. https:\/\/doi.org\/10.1007\/s10462-023-10466-8 (2023).","journal-title":"Artif. Intell. Rev."},{"key":"87519_CR12","doi-asserted-by":"publisher","first-page":"1590","DOI":"10.3390\/cancers13071590","volume":"13","author":"L Alzubaidi","year":"2021","unstructured":"Alzubaidi, L. et al. Novel Transfer Learning Approach for Medical Imaging with limited labeled data. Cancers 13, 1590. https:\/\/doi.org\/10.3390\/cancers13071590 (2021).","journal-title":"Cancers"},{"key":"87519_CR13","doi-asserted-by":"publisher","first-page":"36","DOI":"10.3390\/info14010036","volume":"14","author":"M Ahsan","year":"2023","unstructured":"Ahsan, M., Naz, S., Ahmad, R., Ehsan, H. & Sikandar, A. A Deep Learning Approach for Diabetic Foot Ulcer classification and recognition. Information 14, 36. https:\/\/doi.org\/10.3390\/info14010036 (2023).","journal-title":"Information"},{"key":"87519_CR14","doi-asserted-by":"publisher","unstructured":"Nakka, S. S., Chakraborty, B., Sanada, T., Wang, W. & Chakraborty, G. Identification and classification of diabetic foot ulcers by deep neural networks: A comparative study. 2022 IEEE 5th International Conference on Knowledge Innovation and Invention (ICKII) 2022. https:\/\/doi.org\/10.1109\/ickii55100.2022.9983553","DOI":"10.1109\/ickii55100.2022.9983553"},{"key":"87519_CR15","doi-asserted-by":"publisher","DOI":"10.1016\/j.ibmed.2023.100128","author":"S Biswas","year":"2023","unstructured":"Biswas, S. et al. A deep neural network approach for detecting diabetic foot ulcers through multi-scale feature fusion using the DFU dataset. Intelligence-Based Med. ;8:100128. https:\/\/doi.org\/10.1016\/j.ibmed.2023.100128. (2023)."},{"key":"87519_CR16","doi-asserted-by":"publisher","unstructured":"Wu, X., Liu, R., Wen, Q., Ao, B. & Li, K. DFUC2021 dataset classification based on deep semi-supervised Learning Methods. 2nd International Conference on Consumer Electronics and Computer Engineering (ICCECE) 2022. (2022). https:\/\/doi.org\/10.1109\/iccece54139.2022.9712776","DOI":"10.1109\/iccece54139.2022.9712776"},{"key":"87519_CR17","doi-asserted-by":"publisher","unstructured":"Alavi, A. & Akhoundi, H. Deep subspace analysing for semi-supervised multi-label classification of Dia-betic Foot Ulcer. Diabet. Foot Ulcers Grand Chall. 2022:109\u2013120. https:\/\/doi.org\/10.1007\/978-3-030-94907-5_8","DOI":"10.1007\/978-3-030-94907-5_8"},{"key":"87519_CR18","doi-asserted-by":"publisher","unstructured":"Ahmed, S. & Naveed, H. Bias adjustable activation network for imbalanced data\u2014diabetic foot ulcer challenge 2021. Diabet. Foot Ulcers Grand Chall. 2022:50\u201361. https:\/\/doi.org\/10.1007\/978-3-030-94907-5_4","DOI":"10.1007\/978-3-030-94907-5_4"},{"key":"87519_CR19","doi-asserted-by":"publisher","unstructured":"Bloch, L., Br\u00fcngel, R. & Friedrich, C. M. Boosting efficientnets ensemble performance via pseudo-labels and synthetic images by pix2pixHD for infection and ischaemia classification in diabetic foot ulcers. Diabet. Foot Ulcers Grand Chall. 2022:30\u201349. https:\/\/doi.org\/10.1007\/978-3-030-94907-5_3","DOI":"10.1007\/978-3-030-94907-5_3"},{"key":"87519_CR20","doi-asserted-by":"publisher","unstructured":"Wu, X., Xu, P., Chen, H., Yin, J. & Li, K. Improving DFU image classification by an adaptive augmentation pool and voting with expertise. 2023 11th International Conference on Bioinformatics and Computational Biology (ICBCB) 2023. https:\/\/doi.org\/10.1109\/icbcb57893.2023.10246573","DOI":"10.1109\/icbcb57893.2023.10246573"},{"key":"87519_CR21","doi-asserted-by":"publisher","unstructured":"Qayyum, A., Benzinou, A., Mazher, M. & Meriaudeau, F. Efficient multi-model vision transformer based on feature fusion for classification of DFUC2021 challenge. Diabet. Foot Ulcers Grand Chall. 2022:62\u201375. https:\/\/doi.org\/10.1007\/978-3-030-94907-5_5","DOI":"10.1007\/978-3-030-94907-5_5"},{"key":"87519_CR22","doi-asserted-by":"publisher","unstructured":"Galdran, A., Carneiro, G. & Ballester, M. A. Convolutional nets versus Vision transformers for diabetic foot ulcer classification. Diabet. Foot Ulcers Grand Chall. 21\u201329. https:\/\/doi.org\/10.1007\/978-3-030-94907-5_2 (2022).","DOI":"10.1007\/978-3-030-94907-5_2"},{"key":"87519_CR23","doi-asserted-by":"publisher","first-page":"271","DOI":"10.1016\/j.icte.2021.08.022","volume":"8","author":"SK Das","year":"2022","unstructured":"Das, S. K., Roy, P., Mishra, A. K. & DFU_SPNet A stacked parallel convolution layers based CNN to improve Diabetic Foot Ulcer classification. ICT Express. 8, 271\u2013275. https:\/\/doi.org\/10.1016\/j.icte.2021.08.022 (2022).","journal-title":"ICT Express"},{"key":"87519_CR24","doi-asserted-by":"publisher","first-page":"105195","DOI":"10.1016\/j.imavis.2024.105195","volume":"149","author":"H Khan","year":"2024","unstructured":"Khan, H. et al. Visionary vigilance: optimized YOLOV8 for fallen person detection with large-scale benchmark dataset. Image Vis. Comput. 149, 105195. https:\/\/doi.org\/10.1016\/j.imavis.2024.105195 (2024).","journal-title":"Image Vis. Comput."},{"key":"87519_CR25","doi-asserted-by":"publisher","unstructured":"Liu, Z. et al. Swin Transformer: hierarchical vision transformer using shifted Windows. IEEE\/CVF Int. Conf. Comput. Vis. (ICCV). 2021 https:\/\/doi.org\/10.1109\/iccv48922.2021.00986 (2021).","DOI":"10.1109\/iccv48922.2021.00986"},{"key":"87519_CR26","doi-asserted-by":"publisher","unstructured":"Han, K. et al. More Features From Cheap Operations. 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2020. https:\/\/doi.org\/10.1109\/cvpr42600.2020.00165","DOI":"10.1109\/cvpr42600.2020.00165"},{"key":"87519_CR27","unstructured":"Tan, M., Le, Q. V. & MixConv Mixed Depthwise Convolutional Kernels. Proceedings of the British Machine Vision Conference, (2019)."},{"key":"87519_CR28","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2017.89","author":"J Dai","year":"2017","unstructured":"Dai, J. et al. Deformable Convolutional Networks. 2017 IEEE Int. Conf. Comput. Vis. (ICCV). https:\/\/doi.org\/10.1109\/iccv.2017.89 (2017).","journal-title":"2017 IEEE Int. Conf. Comput. Vis. (ICCV)"},{"key":"87519_CR29","doi-asserted-by":"publisher","unstructured":"Usman, M. T., Khan, H., Singh, S. K., Lee, M. Y. & Koo, J. Efficient deepfake detection via Layer-Frozen Assisted Dual Attention Network for Consumer Imaging Devices. IEEE Trans. Consumer Electron. 2024:1\u20131. https:\/\/doi.org\/10.1109\/tce.2024.3476477","DOI":"10.1109\/tce.2024.3476477"},{"key":"87519_CR30","doi-asserted-by":"publisher","first-page":"6881","DOI":"10.1109\/tpami.2020.3047209","volume":"45","author":"Y Cao","year":"2023","unstructured":"Cao, Y., Xu, J., Lin, S., Wei, F. & Hu, H. Global context networks. IEEE Trans. Pattern Anal. Mach. Intell. 45, 6881\u20136895. https:\/\/doi.org\/10.1109\/tpami.2020.3047209 (2023).","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"87519_CR31","doi-asserted-by":"publisher","first-page":"109299","DOI":"10.1016\/j.compeleceng.2024.109299","volume":"117","author":"J Fang","year":"2024","unstructured":"Fang, J. et al. A multi-focus image fusion network combining dilated convolution with learnable spacings and residual dense network. Comput. Electr. Eng. 117, 109299. https:\/\/doi.org\/10.1016\/j.compeleceng.2024.109299 (2024).","journal-title":"Comput. Electr. Eng."},{"key":"87519_CR32","doi-asserted-by":"crossref","unstructured":"Hou, Q. Daquan Zhou and Jiashi Feng. Coordinate Attention for Efficient Mobile Network Design. 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) : 13708\u201313717. (2021).","DOI":"10.1109\/CVPR46437.2021.01350"},{"key":"87519_CR33","doi-asserted-by":"publisher","first-page":"105308","DOI":"10.1016\/j.imavis.2024.105308","volume":"152","author":"H Khan","year":"2024","unstructured":"Khan, H., Usman, M. T., Rida, I. & Koo, J. Attention enhanced machine instinctive vision with human-inspired saliency detection. Image Vis. Comput. 152, 105308. https:\/\/doi.org\/10.1016\/j.imavis.2024.105308 (2024).","journal-title":"Image Vis. Comput."},{"key":"87519_CR34","doi-asserted-by":"publisher","unstructured":"Zhang, Q-L. & Yang, Y-B. SA-Net: Shuffle Attention for Deep Convolutional Neural Networks. ICASSP 2021\u20132021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). (2021). https:\/\/doi.org\/10.1109\/icassp39728.2021.9414568","DOI":"10.1109\/icassp39728.2021.9414568"},{"key":"87519_CR35","doi-asserted-by":"publisher","unstructured":"Yap, M. H. et al. Development of diabetic foot ulcer datasets: an overview. Diabet. Foot Ulcers Grand Chall. 2022:1\u201318. https:\/\/doi.org\/10.1007\/978-3-030-94907-5_1","DOI":"10.1007\/978-3-030-94907-5_1"},{"key":"87519_CR36","doi-asserted-by":"publisher","unstructured":"Selvaraju, R. R. et al. Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization. IEEE International Conference on Computer Vision (ICCV) 2017. (2017). https:\/\/doi.org\/10.1109\/iccv.2017.74","DOI":"10.1109\/iccv.2017.74"},{"key":"87519_CR37","doi-asserted-by":"publisher","first-page":"15655","DOI":"10.1007\/s11042-019-07820-w","volume":"79","author":"L Alzubaidi","year":"2019","unstructured":"Alzubaidi, L., Fadhel, M. A., Oleiwi, S. R., Al-Shamma, O. & Zhang, J. DFU_QUTNet: diabetic foot ulcer classification using novel deep convolutional neural network. Multimed Tools Appl. 79, 15655\u201315677. https:\/\/doi.org\/10.1007\/s11042-019-07820-w (2019).","journal-title":"Multimed Tools Appl."},{"key":"87519_CR38","doi-asserted-by":"publisher","first-page":"13289","DOI":"10.1007\/s11042-021-10942-9","volume":"81","author":"L Alzubaidi","year":"2021","unstructured":"Alzubaidi, L. et al. Robust application of new deep learning tools: an experimental study in medical imaging. Multimed Tools Appl. 81, 13289\u201313317. https:\/\/doi.org\/10.1007\/s11042-021-10942-9 (2021).","journal-title":"Multimed Tools Appl."},{"key":"87519_CR39","doi-asserted-by":"publisher","first-page":"4523","DOI":"10.3390\/app10134523","volume":"10","author":"L Alzubaidi","year":"2020","unstructured":"Alzubaidi, L. et al. Towards a Better Understanding of Transfer Learning for Medical Imaging: a Case Study. Appl. Sci. 10, 4523. https:\/\/doi.org\/10.3390\/app10134523 (2020).","journal-title":"Appl. Sci."},{"key":"87519_CR40","doi-asserted-by":"publisher","DOI":"10.1016\/j.dib.2020.106221","author":"AGC Pacheco","year":"2020","unstructured":"Pacheco, A. G. C. et al. PAD-UFES-20: A skin lesion dataset composed of patient data and clinical images collected from smartphones. Data Brief. ;32:106221. https:\/\/doi.org\/10.1016\/j.dib.2020.106221. (2020)."}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-87519-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-87519-1","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-87519-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,3]],"date-time":"2025-02-03T05:57:00Z","timestamp":1738562220000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-87519-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2,3]]},"references-count":40,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["87519"],"URL":"https:\/\/doi.org\/10.1038\/s41598-025-87519-1","relation":{"references":[{"id-type":"uri","id":"","asserted-by":"subject"},{"id-type":"uri","id":"","asserted-by":"subject"},{"id-type":"uri","id":"","asserted-by":"subject"}]},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,2,3]]},"assertion":[{"value":"12 August 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 January 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 February 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}},{"value":"All the authors have read and agreed to the publication of this manuscript.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent to publish"}}],"article-number":"4057"}}