{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T23:56:27Z","timestamp":1790639787993,"version":"4.1.0"},"reference-count":29,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T00:00:00Z","timestamp":1782777600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T00:00:00Z","timestamp":1790640000000},"content-version":"vor","delay-in-days":91,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Medical image classification in federated healthcare environments is challenged by the difficulty of learning robust and generalized representations from heterogeneous, non-IID data distributed across multiple institutions. Conventional federated learning approaches primarily rely on visual features and often fail to capture structural relationships among medical images, leading to reduced classification performance and limited generalization across diverse clinical settings. This study proposes GraphMedFL, a federated learning framework that integrates knowledge graphs and Node2Vec-based structural embeddings to enhance classification performance in multi-source environments. Local knowledge graphs are constructed from image features to capture inter-sample relationships, and Node2Vec embeddings are fused with feature representations to enrich local model training. A similarity-aware adaptive aggregation strategy is introduced to address non-IID data distributions across clients. Experiments conducted on three breast cancer imaging datasets (BreakHis, CBIS-DDSM, and INbreast) demonstrate that GraphMedFL achieves superior performance compared to locally trained models, with an accuracy of 98.3% and strong precision-recall balance. The proposed GraphMedFL achieves an accuracy of 98.3% and consistently outperforms baseline federated learning and local training approaches across BreakHis, CBIS-DDSM, and INbreast datasets. It improves precision, recall, and F1-score by a measurable margin compared to conventional methods, demonstrating enhanced robustness and generalization in heterogeneous medical imaging environments.<\/jats:p>","DOI":"10.1038\/s41598-026-60172-y","type":"journal-article","created":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T20:25:29Z","timestamp":1782851129000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A federated learning framework integrating knowledge graphs and Node2Vec for multi-source medical image classification"],"prefix":"10.1038","volume":"16","author":[{"given":"Abdullah Ali","family":"Alqarni","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,30]]},"reference":[{"key":"60172_CR1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.54254\/2755-2721\/2026.TJ31146","volume":"222","author":"C Li","year":"2026","unstructured":"Li, C. A Review of Hybrid Models Combining Convolutional Neural Networks and Vision Transformers in Medical Image Processing. Appl. Comput. Eng. 222, 1\u20138 (2026).","journal-title":"Appl. Comput. Eng."},{"issue":"1180","key":"60172_CR2","doi-asserted-by":"publisher","first-page":"609","DOI":"10.1093\/bjr\/tqag053","volume":"99","author":"MJ Corines","year":"2026","unstructured":"Corines, M. J., Christianson, B., Comstock, C., Drotman, M. & Dodelzon, K. Artificial intelligence in mammography screening: a narrative review of progress, pitfalls, and potential. Br. J. Radiol. 99 (1180), 609\u2013627 (2026).","journal-title":"Br. J. Radiol."},{"issue":"1","key":"60172_CR3","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1080\/17474124.2025.2607575","volume":"20","author":"CM Sergi","year":"2026","unstructured":"Sergi, C. M. The pediatric medical liver biopsy: indications, procedures, and histopathology. Expert Rev. Gastroenterol. Hepatol. 20 (1), 39\u201356 (2026).","journal-title":"Expert Rev. Gastroenterol. Hepatol."},{"key":"60172_CR4","doi-asserted-by":"publisher","first-page":"128882","DOI":"10.1016\/j.eswa.2025.128882","volume":"296","author":"SP Karuppiah","year":"2026","unstructured":"Karuppiah, S. P., Rose, J. T. A., Subasini, C. A. & Vinnarasi, F. S. F. Enhanced medical image analysis using hybrid Henry gas Solubility optimization algorithm with optimized AdaBoost stacked neural networks. Expert Syst. Appl. 296, 128882 (2026).","journal-title":"Expert Syst. Appl."},{"issue":"1","key":"60172_CR5","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1007\/s44186-025-00411-4","volume":"5","author":"S Andreas","year":"2026","unstructured":"Andreas, S. et al. Artificial intelligence driven image recognition in medical education: current applications, educational impact, challenges, and future directions. Glob Surg. Educ. Assoc. Surg. Educ. 5 (1), 36 (2026).","journal-title":"Glob Surg. Educ. Assoc. Surg. Educ."},{"key":"60172_CR6","unstructured":"Rokuss, M. et al. Voxtell: Free-text promptable universal 3d medical image segmentation, in Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 37538\u201337557. (2026)."},{"key":"60172_CR7","doi-asserted-by":"crossref","unstructured":"Mir, B. A., Abbas, S. R. & Lee, S. W. Federated Learning in Healthcare Ethics: A Systematic Review of Privacy-Preserving and Equitable Medical AI, in Healthcare, vol. 14, no. 3, p. 306. (2026).","DOI":"10.3390\/healthcare14030306"},{"key":"60172_CR8","doi-asserted-by":"publisher","first-page":"e3033","DOI":"10.7717\/peerj-cs.3033","volume":"11","author":"M Zhu","year":"2025","unstructured":"Zhu, M., Cheng, D., Mao, Y., Sun, L. & Jing, W. Local-global multi-scale attention network for medical image segmentation. PeerJ Comput. Sci. 11, e3033 (2025).","journal-title":"PeerJ Comput. Sci."},{"key":"60172_CR9","doi-asserted-by":"crossref","unstructured":"A. Garc\u00eda Seco de Herrera et al., Ensemble deep learning architectures for detecting pulmonary tuberculosis in chest X-rays, Sci. Rep., vol. 16, no. 1, p. 1242, (2026).","DOI":"10.1038\/s41598-025-30792-x"},{"key":"60172_CR10","unstructured":"Jurik, A. G., Lambert, R. G. W. & Kiil, R. M. MRI sacroiliitis mimics. Curr Opin. Rheumatol, pp. 10\u20131097, (2026)."},{"issue":"1","key":"60172_CR11","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1002\/dug2.12138","volume":"5","author":"A Bera","year":"2026","unstructured":"Bera, A., Shukla, B. & Jogani, D. A perspective review of applications of the computed tomography (CT) scan imaging technique for microscopic reservoir rock characterization. Deep Undergr. Sci. Eng. 5 (1), 4\u201327 (2026).","journal-title":"Deep Undergr. Sci. Eng."},{"key":"60172_CR12","doi-asserted-by":"crossref","unstructured":"Gu, C., Wang, L., Wu, H., Dual-Chain, A. & Control, A. and Differential Privacy-Based Solution for Medical Data Privacy Protection and Int J. Adv. Comput. Sci. Appl, 17, 2, (2026).","DOI":"10.14569\/IJACSA.2026.0170288"},{"key":"60172_CR13","doi-asserted-by":"crossref","unstructured":"Wu, J., Xia, Y., Wang, X., Shi, F. & Shen, D. Radiomics++: Review of Habitat Imaging Analysis for Decoding Tumor Heterogeneity, Annu. Rev. Biomed. Eng., vol. 28, (2026).","DOI":"10.1146\/annurev-bioeng-031825-040442"},{"key":"60172_CR14","doi-asserted-by":"crossref","unstructured":"Shafik, W. et al. A systematic literature review on transparency and interpretability of AI models in healthcare: taxonomies, tools, techniques, datasets, open research challenges, and future trends. Health Technol. (Berl), pp. 1\u201322, (2026).","DOI":"10.1007\/s12553-025-01051-w"},{"key":"60172_CR15","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1016\/j.ejmp.2021.05.003","volume":"85","author":"Y Fu","year":"2021","unstructured":"Fu, Y. et al. A review of deep learning based methods for medical image multi-organ segmentation. Phys. Med. 85, 107\u2013122 (2021).","journal-title":"Phys. Med."},{"key":"60172_CR16","unstructured":"Yue, Y. & Li, Z. Medmamba: Vision mamba for medical image classification, arXiv Prepr. arXiv2403.03849, (2024)."},{"issue":"3","key":"60172_CR17","doi-asserted-by":"publisher","first-page":"355","DOI":"10.3390\/diagnostics15030355","volume":"15","author":"L Rey-Barroso","year":"2025","unstructured":"Rey-Barroso, L. et al. Training state-of-the-art deep learning algorithms with visible and extended near-infrared multispectral images of skin lesions for the improvement of skin cancer diagnosis. Diagnostics 15 (3), 355 (2025).","journal-title":"Diagnostics"},{"issue":"9","key":"60172_CR18","doi-asserted-by":"publisher","first-page":"1532","DOI":"10.3390\/diagnostics13091532","volume":"13","author":"S Nazir","year":"2023","unstructured":"Nazir, S. & Kaleem, M. Federated learning for medical image analysis with deep neural networks. Diagnostics 13 (9), 1532 (2023).","journal-title":"Diagnostics"},{"issue":"1","key":"60172_CR19","doi-asserted-by":"publisher","first-page":"110","DOI":"10.1186\/s12880-024-01261-0","volume":"24","author":"E Albalawi","year":"2024","unstructured":"Albalawi, E. et al. Integrated approach of federated learning with transfer learning for classification and diagnosis of brain tumor. BMC Med. Imaging. 24 (1), 110 (2024).","journal-title":"BMC Med. Imaging"},{"key":"60172_CR20","unstructured":"Ren, S., Hu, Y., Chen, S. & Wang, G. Federated distillation for medical image classification: Towards trustworthy computer-aided diagnosis, arXiv Prepr. arXiv2407.02261, (2024)."},{"issue":"2","key":"60172_CR21","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1002\/ird3.20","volume":"1","author":"L Zhang","year":"2023","unstructured":"Zhang, L., Zhao, Y., Che, T., Li, S. & Wang, X. Graph neural networks for image-guided disease diagnosis: A review. Iradiology 1 (2), 151\u2013166 (2023).","journal-title":"Iradiology"},{"key":"60172_CR22","doi-asserted-by":"publisher","first-page":"108971","DOI":"10.1016\/j.compbiomed.2024.108971","volume":"180","author":"E G\u00fcrsoy","year":"2024","unstructured":"G\u00fcrsoy, E. & Kaya, Y. Brain-gcn-net: Graph-convolutional neural network for brain tumor identification. Comput. Biol. Med. 180, 108971 (2024).","journal-title":"Comput. Biol. Med."},{"issue":"1","key":"60172_CR23","doi-asserted-by":"publisher","first-page":"1037","DOI":"10.1186\/s12885-023-11516-8","volume":"23","author":"R Aftab","year":"2023","unstructured":"Aftab, R., Qiang, Y., Zhao, J., Urrehman, Z. & Zhao, Z. Graph Neural Network for representation learning of lung cancer. BMC Cancer. 23 (1), 1037 (2023).","journal-title":"BMC Cancer"},{"issue":"2","key":"60172_CR24","doi-asserted-by":"publisher","first-page":"e0342185","DOI":"10.1371\/journal.pone.0342185","volume":"21","author":"P Devadas","year":"2026","unstructured":"Devadas, P. & Mathivanan, G. Mask-Region-based Convolutional Neural Networks (R-CNN) with Radiomics Integration and Gray Level Co-occurrence Matrix (GLCM) for brain tumor detection and segmentation. PLoS One. 21 (2), e0342185 (2026).","journal-title":"PLoS One"},{"key":"60172_CR25","doi-asserted-by":"crossref","unstructured":"Grover, A. & Leskovec, J. node2vec: Scalable feature learning for networks, in Proceedings of the 22nd ACM SIGKDD international conference on Knowledge discovery and data mining, pp. 855\u2013864. (2016).","DOI":"10.1145\/2939672.2939754"},{"issue":"7","key":"60172_CR26","doi-asserted-by":"publisher","first-page":"1455","DOI":"10.1109\/TBME.2015.2496264","volume":"63","author":"FA Spanhol","year":"2015","unstructured":"Spanhol, F. A., Oliveira, L. S., Petitjean, C. & Heutte, L. A dataset for breast cancer histopathological image classification. Ieee Trans. Biomed. Eng. 63 (7), 1455\u20131462 (2015).","journal-title":"Ieee Trans. Biomed. Eng."},{"issue":"1","key":"60172_CR27","doi-asserted-by":"publisher","first-page":"170177","DOI":"10.1038\/sdata.2017.177","volume":"4","author":"RS Lee","year":"2017","unstructured":"Lee, R. S. et al. A curated mammography data set for use in computer-aided detection and diagnosis research. Sci. data. 4 (1), 170177 (2017).","journal-title":"Sci. data"},{"issue":"2","key":"60172_CR28","doi-asserted-by":"publisher","first-page":"236","DOI":"10.1016\/j.acra.2011.09.014","volume":"19","author":"IC Moreira","year":"2012","unstructured":"Moreira, I. C. et al. Inbreast: toward a full-field digital mammographic database. Acad. Radiol. 19 (2), 236\u2013248 (2012).","journal-title":"Acad. Radiol."},{"key":"60172_CR29","unstructured":"Koyejo, O., Natarajan, N., Ravikumar, P. & Dhillon, I. S. Consistent binary classification with generalized performance metrics. Adv Neural Inf. Process. Syst, 27, (2014)."}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-60172-y","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-60172-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-60172-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T22:58:48Z","timestamp":1790636328000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-60172-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,30]]},"references-count":29,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["60172"],"URL":"https:\/\/doi.org\/10.1038\/s41598-026-60172-y","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,30]]},"assertion":[{"value":"14 May 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 June 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 June 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"and informed consent were not required for this study because only publicly available and anonymized datasets were used. No new human participants, clinical interventions, or identifiable personal data were involved in this research. All methods were carried out in accordance with relevant guidelines and regulations.","order":2,"name":"Ethics","label":"Ethical approval","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"30122"}}