{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,30]],"date-time":"2026-10-30T03:19:19Z","timestamp":1793330359658,"version":"4.5.0"},"reference-count":41,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T00:00:00Z","timestamp":1785888000000},"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. Med."],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Kidney-related disorders are one of the global health concerns that require timely detection to prevent severe health complications. The use of computed tomography (CT) images for accurate classification of kidney diseases is important. However, it is challenging to differentiate between classes due to the subtle visual differences. This study introduces a novel two-stage deep learning architecture that integrates self-supervised representation learning with supervised classification for kidney CT image analysis using a publicly available kidney CT image dataset.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>In the first stage, the DINO framework with a Data-efficient Image Transformer (DeiT-Tiny) backbone is used to learn useful features from kidney CT images independent of labels. In the second stage, the pre-trained model is fine-tuned using labeled data to classify kidney abnormalities. To ensure model transparency and clinical trustworthiness, two explainable AI techniques are applied. Grad-CAM++ is used to highlight important regions contributing to predictions in kidney CT images. In addition, DINO\u2019s inherent multi-head self-attention mechanism is analyzed across all attention heads to capture diverse attention patterns.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results and discussion<\/jats:title>\n                    <jats:p>Experimental findings indicate that the proposed framework achieves strong classification performance, with a test accuracy of 99.16%, AUC-ROC of 99.99%, F1 score of 98.97%, precision of 98.90%, and recall of 99.05%, while also providing clear interpretability for automated kidney disease classification. External validation on a CT dataset from Iraq has yielded 97.03% accuracy, supporting the generalizability of the proposed framework.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fmed.2026.1893419","type":"journal-article","created":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T05:41:56Z","timestamp":1785908516000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Explainable and reliable kidney CT image classification using self-supervised DeiT-Tiny transformer"],"prefix":"10.3389","volume":"13","author":[{"given":"Sai Sri Hemantha","family":"Konala","sequence":"first","affiliation":[{"name":"School of Computer Science Engineering and Information Systems, Vellore Institute of Technology","place":["Vellore, Tamil Nadu, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Srinivas","family":"Koppu","sequence":"additional","affiliation":[{"name":"School of Computer Science Engineering and Information Systems, Vellore Institute of Technology","place":["Vellore, Tamil Nadu, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,8,5]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"786","DOI":"10.1016\/s0140-6736(21)00519-5","article-title":"Chronic kidney disease","volume":"398","author":"Kalantar-Zadeh","year":"2021","journal-title":"Lancet"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"1294","DOI":"10.1001\/jama.2019.14745","article-title":"Chronic kidney disease diagnosis and management: a review","volume":"322","author":"Chen","year":"2019","journal-title":"JAMA"},{"key":"ref3","volume-title":"StatPearls [Internet]","author":"Vaidya","year":"2024"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"4163","DOI":"10.1007\/s11831-024-10112-8","article-title":"A comprehensive study of deep learning methods for kidney tumor, cyst, and stone diagnostics and detection using CT images","volume":"31","author":"Kumar","year":"2024","journal-title":"Arch Comput Methods Eng"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1016\/j.kint.2018.09.001","article-title":"The state of nephrology in South Asia","volume":"95","author":"Jha","year":"2019","journal-title":"Kidney Int"},{"key":"ref6","first-page":"208","article-title":"Referral pattern of patients with end-stage renal disease at a public sector hospital and its impact on outcome","volume":"24","author":"Parameswaran","year":"2011","journal-title":"Natl Med J India"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"654","DOI":"10.1038\/nrurol.2016.154","article-title":"An overview of kidney stone imaging techniques","volume":"13","author":"Brisbane","year":"2016","journal-title":"Nat Rev Urol"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1016\/j.media.2017.07.005","article-title":"A survey on deep learning in medical image analysis","volume":"42","author":"Litjens","year":"2017","journal-title":"Med Image Anal"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"9052","DOI":"10.1109\/TPAMI.2024.3415112","article-title":"A survey on self-supervised learning: algorithms, applications, and future trends","volume":"46","author":"Gui","year":"2024","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"4037","DOI":"10.1109\/tpami.2020.2992393","article-title":"Self-supervised visual feature learning with deep neural networks: a survey","volume":"43","author":"Jing","year":"2020","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"10741","DOI":"10.1038\/s41598-025-94905-2","article-title":"Fine-tuned deep learning models for early detection and classification of kidney conditions in CT imaging","volume":"15","author":"Pimpalkar","year":"2025","journal-title":"Sci Rep"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"101663","DOI":"10.1016\/j.imu.2025.101663","article-title":"Multi-model deep learning approach for the classification of kidney diseases using medical images","volume":"57","author":"Obaid","year":"2025","journal-title":"Inform Med Unlocked"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"30358","DOI":"10.1038\/s41598-025-15414-w","article-title":"Optimized machine learning based comparative analysis of predictive models for classification of kidney tumors","volume":"15","author":"Anand","year":"2025","journal-title":"Sci Rep"},{"key":"ref14","first-page":"1","volume-title":"Kidney Disease Classification Using Deep Learning and Model Interpretability","author":"Tamuly","year":"2025"},{"key":"ref15","article-title":"Hybrid deep learning framework for classification of kidney CT images: diagnosis of stones, cysts, and tumors","author":"Sharma","year":"2025","journal-title":"arXiv preprint arXiv:250204367"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"21147","DOI":"10.1109\/access.2024.3351181","article-title":"Multi-class kidney abnormalities detecting novel system through computed tomography","volume":"12","author":"Pande","year":"2024","journal-title":"IEEE Access"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"11440","DOI":"10.1038\/s41598-022-15634-4","article-title":"Vision transformer and explainable transfer learning models for auto detection of kidney cyst, stone and tumor from CT-radiography","volume":"12","author":"Islam","year":"2022","journal-title":"Sci Rep"},{"key":"ref18","first-page":"1597","volume-title":"A Simple Framework for Contrastive Learning of Visual Representations, (PmLR)","author":"Chen","year":"2020"},{"key":"ref19","first-page":"13","volume-title":"Momentum Contrast for Unsupervised Visual Representation Learning","author":"He","year":"2020"},{"key":"ref20","first-page":"9650","volume-title":"Emerging Properties in Self-Supervised Vision Transformers","author":"Caron","year":"2021"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"108554","DOI":"10.1016\/j.compbiomed.2024.108554","article-title":"Kidney tumor classification on CT images using self-supervised learning","volume":"176","author":"\u00d6zbay","year":"2024","journal-title":"Comput Biol Med"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"1930","DOI":"10.3390\/electronics9111930","article-title":"Self-supervised learning to increase the performance of skin lesion classification","volume":"9","author":"Kwasigroch","year":"2020","journal-title":"Electronics"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"107876","DOI":"10.1016\/j.cmpb.2023.107876","article-title":"Self-supervised learning with self-distillation on COVID-19 medical image classification","volume":"243","author":"Tan","year":"2024","journal-title":"Comput Methods Prog Biomed"},{"key":"ref24","doi-asserted-by":"publisher","first-page":"976467","DOI":"10.3389\/fmed.2022.976467","article-title":"Self-supervised learning mechanism for identification of eyelid malignant melanoma in pathologic slides with limited annotation","volume":"9","author":"Wang","year":"2022","journal-title":"Front Med"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"298","DOI":"10.30871\/jaic.v10i1.11844","article-title":"Implementation of SSL-vision transformer (ViT) for multi-lung disease classification on X-ray images","volume":"10","author":"Baasith","year":"2026","journal-title":"J Appl Inform Computing"},{"key":"ref26","volume-title":"Training data-Efficient Image Transformers & Distillation Through Attention","author":"Touvron","year":"2021"},{"key":"ref27","article-title":"An image is worth 16x16 words: transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv preprint arXiv:201011929"},{"key":"ref28","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3505244","article-title":"Transformers in vision: a survey","volume":"54","author":"Khan","year":"2022","journal-title":"ACM Comput Surv"},{"key":"ref29","first-page":"6000","volume-title":"Attention is All you Need. Advances in Neural Information Processing Systems","author":"Vaswani","year":"2017"},{"key":"ref30","first-page":"10012","volume-title":"Swin Transformer: Hierarchical Vision Transformer Using Shifted Windows","author":"Liu","year":"2021"},{"key":"ref31","doi-asserted-by":"crossref","DOI":"10.1109\/ICCV48922.2021.00010","volume-title":"Going Deeper with Image Transformers","author":"Touvron","year":"2021"},{"key":"ref32","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1038\/s41598-025-26035-8","article-title":"Hybrid model integrating LeViT transformer and distillation techniques for pattern detection and dance classification","volume":"16","author":"Wang","year":"2025","journal-title":"Sci Rep"},{"key":"ref33","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1145\/3236386.3241340","article-title":"The mythos of model interpretability: in machine learning, the concept of interpretability is both important and slippery","volume":"16","author":"Lipton","year":"2018","journal-title":"Queue"},{"key":"ref34","doi-asserted-by":"publisher","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":"ref35","volume-title":"Grad-Cam: Visual Explanations from Deep Networks Via Gradient-Based Localization","author":"Selvaraju","year":"2017"},{"key":"ref36","first-page":"839","volume-title":"Grad-cam++: Generalized Gradient-Based Visual Explanations for Deep Convolutional Networks (IEEE)","author":"Chattopadhay","year":"2018"},{"key":"ref37","article-title":"Evaluating and aggregating feature-based model explanations","author":"Bhatt","year":"2020","journal-title":"arXiv preprint arXiv:200500631"},{"key":"ref38","volume-title":"On the (in) Fidelity and Sensitivity of Explanations. Advances in Neural Information Processing Systems","author":"Yeh","year":"2019"},{"key":"ref39","first-page":"4190","volume-title":"Quantifying Attention Flow in Transformers","author":"Abnar","year":"2020"},{"key":"ref40","doi-asserted-by":"publisher","first-page":"1895","DOI":"10.1162\/089976698300017197","article-title":"Approximate statistical tests for comparing supervised classification learning algorithms","volume":"10","author":"Dietterich","year":"1998","journal-title":"Neural Comput"},{"key":"ref41","doi-asserted-by":"publisher","first-page":"185","DOI":"10.1007\/BF02289261","article-title":"Note on the \u201ccorrection for continuity\u201d in testing the significance of the difference between correlated proportions","volume":"13","author":"Edwards","year":"1948","journal-title":"Psychometrika"}],"container-title":["Frontiers in Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1893419\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T05:41:59Z","timestamp":1785908519000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1893419\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,5]]},"references-count":41,"alternative-id":["10.3389\/fmed.2026.1893419"],"URL":"https:\/\/doi.org\/10.3389\/fmed.2026.1893419","relation":{},"ISSN":["2296-858X"],"issn-type":[{"value":"2296-858X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,5]]},"article-number":"1893419"}}