{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,19]],"date-time":"2026-08-19T18:30:38Z","timestamp":1787164238835,"version":"build-2736575974"},"reference-count":31,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T00:00:00Z","timestamp":1767312000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T00:00:00Z","timestamp":1769731200000},"content-version":"vor","delay-in-days":28,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Manipal Academy of Higher Education, Manipal"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>The most serious complication of diabetes, Diabetic Foot Ulcer (DFU), can result in chronic infection, damage to tissues, and even amputation if not identified in a timely way. It is even more dangerous for disabled people. Accurate and timely diagnosis is therefore essential for improved patient outcomes. However, it is difficult to perform a manual assessment of DFU images due to variations in the textures of ulcers, light effects, and severities. Herein is presented an enhanced deep learning framework DenseNet121 with Variational Autoencoder and Contrastive Learning (DenseVAE-CL) which incorporates DenseNet121 to extract robust features and integrates a Variational Autoencoder together with Contrastive Learning to enhance representation discrimination. The model was trained and tested on 2,673 publicly available images from the Kaggle DFU dataset, which was divided into training, validation, and testing subsets in a ratio of 80:10:10, respectively. DenseVAE-CL emerged as the best performer with an accuracy of 99.6%, precision of 99.5%, recall of 99.4%, specificity of 100%, sensitivity of 98.9%, an F1-score of 99.5%, and 0.99 Area Under the Receiver Operating Characteristic Curve (AUC-ROC). Five-fold cross-validation further demonstrated stable generalization with a mean accuracy of 99.4\u2009\u00b1\u20090.2%. Moreover, calibration analysis confirmed the model\u2019s reliability since a mean confidence of 0.9031 for abnormal cases and 0.9692 for normal cases results in an expected calibration error of 0.0457. Visualization through Grad-CAM and VAE residual heatmaps revealed sharp localization of ulcer regions, hence improving interpretability.<\/jats:p>","DOI":"10.1038\/s41598-025-34225-7","type":"journal-article","created":{"date-parts":[[2026,1,3]],"date-time":"2026-01-03T05:18:40Z","timestamp":1767417520000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Proposed dense variational autoencoder model integrated with contrastive learning for foot ulcer classification"],"prefix":"10.1038","volume":"16","author":[{"given":"Gunjan","family":"Shandilya","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sheifali","family":"Gupta","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Deepali","family":"Gupta","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sapna","family":"Juneja","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Krishnaraj","family":"Chadaga","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ali","family":"Nauman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Abeer A.","family":"Al-Masri","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,1,2]]},"reference":[{"key":"34225_CR1","doi-asserted-by":"crossref","unstructured":"Hyun, J. et al. Synthetic data generation system for AI-based diabetic foot diagnosis. SN Comput. Sci 2, 5 (2021).","DOI":"10.1007\/s42979-021-00667-9"},{"issue":"1","key":"34225_CR2","doi-asserted-by":"publisher","first-page":"114","DOI":"10.1111\/iwj.13603","volume":"19","author":"KS Chan","year":"2022","unstructured":"Chan, K. S. et al. Clinical validation of an artificial intelligence-enabled wound imaging mobile application in diabetic foot ulcers. Int. Wound J. 19(1), 114\u2013124 (2022).","journal-title":"Int. Wound J."},{"key":"34225_CR3","doi-asserted-by":"publisher","first-page":"1386613","DOI":"10.3389\/fendo.2024.1386613","volume":"15","author":"V Sendilraj","year":"2024","unstructured":"Sendilraj, V. et al. DFUCare: deep learning platform for diabetic foot ulcer detection, analysis, and monitoring. Front. Endocrinol. (Lausanne. 15, 1386613 (2024).","journal-title":"Front. Endocrinol. (Lausanne"},{"issue":"1","key":"34225_CR4","doi-asserted-by":"publisher","first-page":"31138","DOI":"10.1038\/s41598-025-13647-3","volume":"15","author":"S Anand","year":"2025","unstructured":"Anand, S. et al. CHASHNIt for enhancing skin disease classification using GAN augmented hybrid model with LIME and SHAP based XAI heatmaps. Sci. Rep. 15(1), 31138 (2025).","journal-title":"Sci. Rep."},{"key":"34225_CR5","doi-asserted-by":"crossref","unstructured":"Swerdlow, M., Shin, L., D\u2019Huyvetter, K., Mack, W. J. & Armstrong, D. G. Initial clinical experience with a simple home system for early detection and monitoring of diabetic foot ulcers: The foot selfie, J. Diabetes Sci. Technol. 17(1), 79\u201388 (2023).","DOI":"10.1177\/19322968211053348"},{"key":"34225_CR6","doi-asserted-by":"crossref","unstructured":"Chan, K. S. & Lo, Z. J. Wound assessment imaging and monitoring systems in diabetic foot ulcers: A systematic review, Int. Wound J. 17(6), 1909\u20131923 (2020).","DOI":"10.1111\/iwj.13481"},{"key":"34225_CR7","doi-asserted-by":"publisher","first-page":"98315","DOI":"10.1109\/ACCESS.2023.3312531","volume":"11","author":"MSA Toofanee","year":"2023","unstructured":"Toofanee, M. S. A. et al. DFU-SIAM a novel diabetic foot ulcer classification with deep learning. IEEE Access. 11, 98315\u201398332 (2023).","journal-title":"IEEE Access."},{"key":"34225_CR8","doi-asserted-by":"publisher","first-page":"127578","DOI":"10.1109\/ACCESS.2023.3332292","volume":"11","author":"S Nagaraju","year":"2023","unstructured":"Nagaraju, S. et al. Automated diabetic foot ulcer detection and classification using deep learning. IEEE Access. 11, 127578\u2013127588 (2023).","journal-title":"IEEE Access."},{"issue":"100210","key":"34225_CR9","doi-asserted-by":"publisher","first-page":"100210","DOI":"10.1016\/j.sintl.2022.100210","volume":"4","author":"PN Thotad","year":"2023","unstructured":"Thotad, P. N., Bharamagoudar, G. R. & Anami, B. S. Diabetic foot ulcer detection using deep learning approaches. Sens. Int. 4(100210), 100210 (2023).","journal-title":"Sens. Int."},{"key":"34225_CR10","doi-asserted-by":"publisher","first-page":"189","DOI":"10.1109\/OJEMB.2022.3219725","volume":"3","author":"Z Liu","year":"2022","unstructured":"Liu, Z., John, J. & Agu, E. Diabetic foot ulcer ischemia and infection classification using EfficientNet deep learning models. IEEE Open. J. Eng. Med. Biol. 3, 189\u2013201 (2022).","journal-title":"IEEE Open. J. Eng. Med. Biol."},{"issue":"103616","key":"34225_CR11","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. Comput. Biol. Med. 117(103616), 103616 (2020).","journal-title":"Comput. Biol. Med."},{"issue":"4","key":"34225_CR12","doi-asserted-by":"publisher","first-page":"910","DOI":"10.1111\/iwj.13691","volume":"19","author":"P Xie","year":"2022","unstructured":"Xie, P. et al. An explainable machine learning model for predicting in-hospital amputation rate of patients with diabetic foot ulcer. Int. Wound J. 19(4), 910\u2013918 (2022).","journal-title":"Int. Wound J."},{"issue":"11","key":"34225_CR13","doi-asserted-by":"publisher","first-page":"4249","DOI":"10.3390\/s22114249","volume":"22","author":"A Khandakar","year":"2022","unstructured":"Khandakar, A. et al. A novel machine learning approach for severity classification of diabetic foot complications using thermogram images. Sens. (Basel). 22(11), 4249 (2022).","journal-title":"Sens. (Basel)"},{"issue":"1","key":"34225_CR14","first-page":"1","volume":"14","author":"Z Wang","year":"2024","unstructured":"Wang, Z. et al. Smart diabetic foot ulcer scoring system. Sci. Rep. 14(1), 1\u201312 (2024).","journal-title":"Sci. Rep."},{"issue":"1","key":"34225_CR15","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-025-87519-1","volume":"15","author":"R Karthik","year":"2025","unstructured":"Karthik, R., Ajay, A., Jhalani, A., Ballari, K. & Suganthi An explainable deep learning model for diabetic foot ulcer classification using Swin transformer and efficient multi-scale attention-driven network. Sci. Rep. 15(1), 1\u201320 (2025).","journal-title":"Sci. Rep."},{"issue":"105044","key":"34225_CR16","doi-asserted-by":"publisher","first-page":"105044","DOI":"10.1016\/j.ijmedinf.2023.105044","volume":"174","author":"M Yin","year":"2023","unstructured":"Yin, M. et al. Deep learning for pancreatic diseases based on endoscopic ultrasound: A systematic review. Int. J. Med. Inf. 174(105044), 105044 (2023).","journal-title":"Int. J. Med. Inf."},{"issue":"1","key":"34225_CR17","doi-asserted-by":"publisher","first-page":"601","DOI":"10.3233\/THC-241444","volume":"33","author":"Sumithra","year":"2025","unstructured":"Sumithra & Venkatesan, C. SwinDFU-Net: deep learning transformer network for infection identification in diabetic foot ulcer. Technol. Health Care. 33(1), 601\u2013618 (2025).","journal-title":"Technol. Health Care"},{"issue":"2","key":"34225_CR18","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(2), 271\u2013275 (2022).","journal-title":"ICT Express"},{"issue":"105055","key":"34225_CR19","doi-asserted-by":"publisher","first-page":"105055","DOI":"10.1016\/j.compbiomed.2021.105055","volume":"140","author":"N Al-Garaawi","year":"2022","unstructured":"Al-Garaawi, N., Ebsim, R., Alharan, A. F. H. & Yap, M. H. Diabetic foot ulcer classification using mapped binary patterns and convolutional neural networks. Comput. Biol. Med. 140(105055), 105055 (2022).","journal-title":"Comput. Biol. Med."},{"key":"34225_CR20","unstructured":"Alzubaidi, L., Abbood, A. A., Fadhel, M. A., Al-Shamma, O. & Zhang, J. Comparison of hybrid convolutional neural networks models for diabetic foot ulcer classification, Edu.my. [Online]. Available: https:\/\/jestec.taylors.edu.my\/Vol%2016%20issue%203%20June%202021\/16_3_11.pdf. [Accessed: 01-Mar-2025]."},{"key":"34225_CR21","doi-asserted-by":"crossref","unstructured":"Alshayeji, M. H., Sindhu, S. C. & Abed, S. Early detection of diabetic foot ulcers from thermal images using the bag of features technique, Biomed. Signal Process. Control, vol. 79, Jan. (2023).","DOI":"10.1016\/j.bspc.2022.104143"},{"key":"34225_CR22","doi-asserted-by":"crossref","unstructured":"Santos, E. et al. Diabetic foot ulcers classification using a fine-tuned CNNs Ensemble. in IEEE 35th International Symposium on Computer-Based Medical Systems (CBMS) 282\u2013287 (2022).","DOI":"10.1109\/CBMS55023.2022.00056"},{"key":"34225_CR23","doi-asserted-by":"crossref","unstructured":"Santos, F et al., DFU-VGG, a novel and improved VGG-19 network for diabetic foot ulcer classification, in 2022 29th International Conference on Systems, Signals and Image Processing (IWSSIP) 1\u20134 (2022).","DOI":"10.1109\/IWSSIP55020.2022.9854392"},{"issue":"4","key":"34225_CR24","doi-asserted-by":"publisher","first-page":"1175","DOI":"10.1007\/s13246-022-01185-5","volume":"45","author":"L Ai","year":"2022","unstructured":"Ai, L., Yang, M. & Xie, Z. ACTNet: asymmetric convolutional transformer network for diabetic foot ulcers classification. Phys. Eng. Sci. Med. 45(4), 1175\u20131181 (2022).","journal-title":"Phys. Eng. Sci. Med."},{"issue":"23","key":"34225_CR25","doi-asserted-by":"publisher","first-page":"12776","DOI":"10.3390\/app132312776","volume":"13","author":"MSA Toofanee","year":"2023","unstructured":"Toofanee, M. S. A. et al. Federated learning: centralized and P2P for a Siamese deep learning model for diabetes foot ulcer classification. Appl. Sci. (Basel). 13(23), 12776 (2023).","journal-title":"Appl. Sci. (Basel)"},{"key":"34225_CR26","unstructured":"https:\/\/www.kaggle.com\/datasets\/laithjj\/diabetic-foot-ulcer-dfu"},{"key":"34225_CR27","doi-asserted-by":"publisher","unstructured":"Shravya, V., Sunil, M., Natarajan, B. & Elakkiya, R. Encouraging discriminative attention through contrastive explainability learning for lung cancer diagnosis. IEEE Access 13, 176958\u2013176976. https:\/\/doi.org\/10.1109\/ACCESS.2025.3616056 (2025).","DOI":"10.1109\/ACCESS.2025.3616056"},{"key":"34225_CR28","doi-asserted-by":"publisher","unstructured":"Nguyen, T. N., Yang, H. J., Kho, B. G., Kang, S. R. & Kim, S. H. Explainable deep contrastive federated learning system for early prediction of clinical status in intensive care unit. IEEE Access 12, 117176\u2013117202. https:\/\/doi.org\/10.1109\/ACCESS.2024.3447759 (2024).","DOI":"10.1109\/ACCESS.2024.3447759"},{"key":"34225_CR29","doi-asserted-by":"publisher","unstructured":"Bansal, N. & Vidyarthi, A. DFootNet: A domain adaptive classification framework for diabetic foot ulcers using dense neural network architecture, Cognitive Computation 16, pp. 2511\u20132527, [Online]. (2024). Available: https:\/\/doi.org\/10.1007\/s12559-024-10282-4","DOI":"10.1007\/s12559-024-10282-4"},{"issue":"2","key":"34225_CR30","doi-asserted-by":"publisher","first-page":"1225","DOI":"10.1007\/s44174-024-00165-5","volume":"2","author":"S Biswas","year":"2024","unstructured":"Biswas, S. et al. DFU_XAI: A deep learning-based approach to diabetic foot ulcer detection using feature explainability. Biomed. Mater. Devices. 2(2), 1225\u20131245 (2024).","journal-title":"Biomed. Mater. Devices"},{"issue":"1","key":"34225_CR31","doi-asserted-by":"publisher","first-page":"6758","DOI":"10.1038\/s41598-025-90780-z","volume":"15","author":"PS Rathore","year":"2025","unstructured":"Rathore, P. S., Kumar, A., Nandal, A., Dhaka, A. & Sharma, A. K. A feature explainability-based deep learning technique for diabetic foot ulcer identification. Sci. Rep. 15(1), 6758 (2025).","journal-title":"Sci. Rep."}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-34225-7","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-34225-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-34225-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T16:00:46Z","timestamp":1781625646000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-34225-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,2]]},"references-count":31,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["34225"],"URL":"https:\/\/doi.org\/10.1038\/s41598-025-34225-7","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,2]]},"assertion":[{"value":"10 September 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 December 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 January 2026","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"}}],"article-number":"4171"}}