{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,28]],"date-time":"2026-08-28T15:58:49Z","timestamp":1787932729943,"version":"build-2784847793"},"reference-count":32,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,12,11]],"date-time":"2025-12-11T00:00:00Z","timestamp":1765411200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T00:00:00Z","timestamp":1767571200000},"content-version":"vor","delay-in-days":25,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Vellore Institute of Technology, Vellore"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Leukemia diagnosis with medical imaging necessitates the development of highly accurate and individualized models that uphold data privacy among institutions. This research proposes a framework named FedPerLoRA-Health, a communication-efficient federated learning framework that combines federated personalization and low rank adaptation with EfficientNet architectures for personalized leukemia detection. The proposed PerFLR-EffNet algorithm holds the structural efficiency of EfficientNet variants B0 and B2 as backbone models, facilitating parameter-efficient updates and local personalization across diverse client datasets. Within this framework, personalized layers undergo local training, whereas LoRA-adapted global layers are disseminated to reduce communication overhead. The proposed method is assessed on a Blood Cells Cancer Acute Lymphoblastic Leukemia (ALL) dataset with classification-based metrics such as accuracy, precision, recall and F1-score and federated learning-based metrics such as communication cost and convergence rate. The efficiency of the proposed model is analysed by comparing it with the baseline models such as centralized EfficientNetB0 and EfficientNetB2 without personalized Federation. Experimental results indicate that PerFLR-EffNet attains a better average classification accuracy of 98.67% and also proves to be communication efficient by reporting reduced number of trainable parameters and a reduction in communication overhead by 88.12% when compared with the baseline models.<\/jats:p>","DOI":"10.1038\/s41598-025-29672-1","type":"journal-article","created":{"date-parts":[[2025,12,11]],"date-time":"2025-12-11T15:04:28Z","timestamp":1765465468000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["A personalized communication efficient federated learning framework with low rank adaptation for intelligent leukemia diagnosis"],"prefix":"10.1038","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9815-2982","authenticated-orcid":false,"given":"P.","family":"Suresh","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9420-6389","authenticated-orcid":false,"given":"P.","family":"Keerthika","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"A. R. Nitesh","family":"Kumar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,12,11]]},"reference":[{"issue":"7","key":"29672_CR1","doi-asserted-by":"publisher","first-page":"e36490","DOI":"10.2196\/36490","volume":"24","author":"Y El Alaoui","year":"2022","unstructured":"El Alaoui, Y. et al. A review of artificial intelligence applications in hematology management: current practices and future prospects. J Med Internet Res 24(7), e36490. https:\/\/doi.org\/10.2196\/36490 (2022).","journal-title":"J Med Internet Res"},{"key":"29672_CR2","unstructured":"Tan M., Le V. Q., EfficientNet: Rethinking model scaling for convolutional neural networks, In: 36th International Conference on Machine Learning, ICML 2019, May 2019, vol. 2019-June, pp. 10691\u201310700. Accessed: Aug. 17, 2025. [Online]. Available: https:\/\/proceedings.mlr.press\/v97\/tan19a.html"},{"key":"29672_CR3","doi-asserted-by":"publisher","first-page":"28628","DOI":"10.1109\/ACCESS.2023.3260027","volume":"11","author":"MF Sohan","year":"2023","unstructured":"Sohan, M. F. & Basalamah, A. A systematic review on federated learning in medical image analysis. IEEE Access, IEEE Access 11, 28628\u201328644. https:\/\/doi.org\/10.1109\/ACCESS.2023.3260027 (2023).","journal-title":"IEEE Access, IEEE Access"},{"issue":"12","key":"29672_CR4","doi-asserted-by":"publisher","first-page":"1985","DOI":"10.3390\/covid4120140","volume":"4","author":"FS Alhafiz","year":"2024","unstructured":"Alhafiz, F. S. & Basuhail, A. A. Non-IID medical imaging data on COVID-19 in the federated learning framework: Impact and directions. COVID 4(12), 1985\u20132016. https:\/\/doi.org\/10.3390\/covid4120140 (2024).","journal-title":"COVID"},{"key":"29672_CR5","doi-asserted-by":"publisher","first-page":"100742","DOI":"10.1016\/j.iot.2023.100742","volume":"22","author":"ORA Almanifi","year":"2023","unstructured":"Almanifi, O. R. A., Chow, C. O., Tham, M. L., Chuah, J. H. & Kanesan, J. Communication and computation efficiency in Federated Learning: A survey. Internet Things 22, 100742. https:\/\/doi.org\/10.1016\/j.iot.2023.100742 (2023).","journal-title":"Internet Things"},{"issue":"6","key":"29672_CR6","doi-asserted-by":"publisher","first-page":"10407","DOI":"10.1109\/TNNLS.2024.3517658","volume":"36","author":"H Zhang","year":"2025","unstructured":"Zhang, H., Li, C., Dai, W., Zou, J. & Xiong, H. Federated learning based on model discrepancy and variance reduction. IEEE Trans. Neural Networks Learn. Syst. 36(6), 10407\u201310421. https:\/\/doi.org\/10.1109\/TNNLS.2024.3517658 (2025).","journal-title":"IEEE Trans. Neural Networks Learn. Syst."},{"key":"29672_CR7","doi-asserted-by":"publisher","first-page":"61928","DOI":"10.1109\/ACCESS.2025.3556587","volume":"13","author":"E Fani","year":"2025","unstructured":"Fani, E., Camoriano, R., Caputo, B. & Ciccone, M. Resource-efficient personalization in federated learning with closed-form classifiers. IEEE Access 13, 61928\u201361957. https:\/\/doi.org\/10.1109\/ACCESS.2025.3556587 (2025).","journal-title":"IEEE Access"},{"issue":"7","key":"29672_CR8","doi-asserted-by":"publisher","first-page":"197605","DOI":"10.1007\/s11704-024-40663-9","volume":"19","author":"Y Mao","year":"2025","unstructured":"Mao, Y. et al. A survey on LoRA of large language models. Front Comput Sci 19(7), 197605. https:\/\/doi.org\/10.1007\/s11704-024-40663-9 (2025).","journal-title":"Front Comput Sci"},{"issue":"12","key":"29672_CR9","doi-asserted-by":"publisher","first-page":"556","DOI":"10.3390\/a16120556","volume":"16","author":"AK Alzahrani","year":"2023","unstructured":"Alzahrani, A. K., Alsheikhy, A. A., Shawly, T., Azzahrani, A. & Said, Y. A novel deep learning segmentation and classification framework for leukemia diagnosis. Algorithms 16(12), 556. https:\/\/doi.org\/10.3390\/a16120556 (2023).","journal-title":"Algorithms"},{"issue":"1","key":"29672_CR10","doi-asserted-by":"publisher","first-page":"9","DOI":"10.3390\/applbiosci4010009","volume":"4","author":"RF OybekKizi","year":"2025","unstructured":"OybekKizi, R. F., Theodore Armand, T. P. & Kim, H. C. A review of deep learning techniques for leukemia cancer classification based on blood smear images. Appl Biosci 4(1), 9. https:\/\/doi.org\/10.3390\/applbiosci4010009 (2025).","journal-title":"Appl Biosci"},{"key":"29672_CR11","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2021.115311","volume":"183","author":"PK Das","year":"2021","unstructured":"Das, P. K. & Meher, S. An efficient deep convolutional neural Network based detection and classification of acute lymphoblastic Leukemia. Expert Syst. Appl. 183, 115311. https:\/\/doi.org\/10.1016\/j.eswa.2021.115311 (2021).","journal-title":"Expert Syst. Appl."},{"key":"29672_CR12","doi-asserted-by":"publisher","DOI":"10.1016\/j.array.2023.100292","volume":"18","author":"W Rahman","year":"2023","unstructured":"Rahman, W. et al. Multiclass blood cancer classification using deep CNN with optimized features. Array 18, 100292. https:\/\/doi.org\/10.1016\/j.array.2023.100292 (2023).","journal-title":"Array"},{"key":"29672_CR13","doi-asserted-by":"publisher","first-page":"106023","DOI":"10.1016\/j.ijmedinf.2025.106023","volume":"203","author":"AA Soladoye","year":"2025","unstructured":"Soladoye, A. A., Olawade, D. B., Adeyanju, I. A., Adereni, T. & Olagunju, K. M. Clement David-Olawade, \u201cEnhancing leukemia detection in medical imaging using deep transfer learning. Int. J. Med. Inform. 203, 106023. https:\/\/doi.org\/10.1016\/j.ijmedinf.2025.106023 (2025).","journal-title":"Int. J. Med. Inform."},{"key":"29672_CR14","doi-asserted-by":"publisher","first-page":"37203","DOI":"10.1109\/ACCESS.2023.3266511","volume":"11","author":"A Batool","year":"2023","unstructured":"Batool, A. & Byun, Y. C. Lightweight EfficientNetB3 model based on depthwise separable convolutions for enhancing classification of leukemia white blood cell images. IEEE Access 11, 37203\u201337215. https:\/\/doi.org\/10.1109\/ACCESS.2023.3266511 (2023).","journal-title":"IEEE Access"},{"issue":"6","key":"29672_CR15","doi-asserted-by":"publisher","first-page":"337","DOI":"10.3390\/fractalfract9060337","volume":"9","author":"HM Rai","year":"2025","unstructured":"Rai, H. M. et al. Deep learning for leukemia classification: Performance analysis and challenges across multiple architectures. Fractal Fract. 9(6), 337. https:\/\/doi.org\/10.3390\/fractalfract9060337 (2025).","journal-title":"Fractal Fract."},{"key":"29672_CR16","doi-asserted-by":"publisher","first-page":"1330977","DOI":"10.3389\/fonc.2023.1330977","volume":"13","author":"B Elsayed","year":"2023","unstructured":"Elsayed, B. et al. Deep learning enhances acute lymphoblastic leukemia diagnosis and classification using bone marrow images. Front Oncol 13, 1330977. https:\/\/doi.org\/10.3389\/fonc.2023.1330977 (2023).","journal-title":"Front Oncol"},{"key":"29672_CR17","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2023.107861","volume":"169","author":"J Zhou","year":"2024","unstructured":"Zhou, J. et al. Personalized and privacy-preserving federated heterogeneous medical image analysis with PPPML-HMI. Comput. Biol. Med. 169, 107861. https:\/\/doi.org\/10.1016\/j.compbiomed.2023.107861 (2024).","journal-title":"Comput. Biol. Med."},{"issue":"1150","key":"29672_CR18","doi-asserted-by":"publisher","first-page":"20220890","DOI":"10.1259\/bjr.20220890","volume":"96","author":"MHU Rehman","year":"2023","unstructured":"Rehman, M. H. U., Pinaya, W. H. L., Nachev, P., Teo, J. T. & Cardoso, M. J. Federated learning for medical imaging radiology. Br Inst Radiol 96(1150), 20220890. https:\/\/doi.org\/10.1259\/bjr.20220890 (2023).","journal-title":"Br Inst Radiol"},{"key":"29672_CR19","doi-asserted-by":"publisher","first-page":"110424","DOI":"10.1016\/j.patcog.2024.110424","volume":"151","author":"H Guan","year":"2024","unstructured":"Guan, H., Yap, P. T., Bozoki, A. & Liu, M. Federated learning for medical image analysis: A survey. Pattern Recognit 151, 110424. https:\/\/doi.org\/10.1016\/j.patcog.2024.110424 (2024).","journal-title":"Pattern Recognit"},{"issue":"6","key":"29672_CR20","doi-asserted-by":"publisher","first-page":"101006","DOI":"10.1016\/j.patter.2024.101006","volume":"5","author":"F Zhang","year":"2024","unstructured":"Zhang, F. et al. Recent methodological advances in federated learning for healthcare. Patterns 5(6), 101006. https:\/\/doi.org\/10.1016\/j.patter.2024.101006 (2024).","journal-title":"Patterns"},{"issue":"4","key":"29672_CR21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10586-024-04896-4","volume":"28","author":"A Mazid","year":"2025","unstructured":"Mazid, A., Kirmani, S., Abid, M. & Pawar, V. A secure and efficient framework for internet of medical things through blockchain driven customized federated learning. Cluster Comput. 28(4), 1\u201316. https:\/\/doi.org\/10.1007\/s10586-024-04896-4 (2025).","journal-title":"Cluster Comput."},{"key":"29672_CR22","doi-asserted-by":"publisher","unstructured":"Nezhadsistani, N., Moayedian, N. S., Stiller, B. Blockchain-enabled federated learning in healthcare: survey and state-of-the-art, IEEE Access. Institute of electrical and electronics engineers Inc., 2025. https:\/\/doi.org\/10.1109\/ACCESS.2025.3587345.","DOI":"10.1109\/ACCESS.2025.3587345"},{"issue":"4","key":"29672_CR23","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3638252","volume":"18","author":"J Tu","year":"2024","unstructured":"Tu, J., Huang, J., Yang, L. & Lin, W. Personalized federated learning with layer-wise feature transformation via meta-learning. ACM Trans Knowl Discov Data 18(4), 1\u201321. https:\/\/doi.org\/10.1145\/3638252 (2024).","journal-title":"ACM Trans Knowl Discov Data"},{"key":"29672_CR24","first-page":"21394","volume":"33","author":"CT Dinh","year":"2020","unstructured":"Dinh, C. T., Tran, N. H. & Nguyen, T. D. Personalized federated learning with moreau envelopes. Adv Neural Inf Process Syst 33, 21394\u201321405 (2020).","journal-title":"Adv Neural Inf Process Syst"},{"issue":"6","key":"29672_CR25","doi-asserted-by":"publisher","first-page":"1936","DOI":"10.1109\/TC.2025.3547138","volume":"74","author":"Y Liu","year":"2025","unstructured":"Liu, Y., He, L., Zhang, Z. & Ren, S. PFed-NS: An adaptive personalized federated learning scheme through neural network segmentation. IEEE Trans. Comput. 74(6), 1936\u20131948. https:\/\/doi.org\/10.1109\/TC.2025.3547138 (2025).","journal-title":"IEEE Trans. Comput."},{"key":"29672_CR26","doi-asserted-by":"publisher","unstructured":"Xu, J., Yan, Y., Huang, S. L., FedPer++: Toward improved personalized federated learning on heterogeneous and imbalanced data, In: Proceedings of the International Joint Conference on Neural Networks, 2022, vol. 2022-July. https:\/\/doi.org\/10.1109\/IJCNN55064.2022.9892585.","DOI":"10.1109\/IJCNN55064.2022.9892585"},{"key":"29672_CR27","unstructured":"Li, X., Jiang, M., Zhang, X., Kamp, M., Dou, Q. FEDBN: FEDERATED LEARNING ON NON-IID FEATURES VIA LOCAL BATCH NORMALIZATION, In: ICLR 2021\u20149th International Conference on Learning Representations, 2021. Accessed: Sep. 29, 2025. [Online]. Available: https:\/\/github.com\/med-air\/FedBN."},{"key":"29672_CR28","doi-asserted-by":"publisher","unstructured":"Huang et al. Y. Personalized cross-silo federated learning on non-IID data, In: 35th AAAI Conference on Artificial Intelligence, AAAI 2021, May 2021, vol. 9A, no. 9, pp. 7865\u20137873. https:\/\/doi.org\/10.1609\/aaai.v35i9.16960.","DOI":"10.1609\/aaai.v35i9.16960"},{"key":"29672_CR29","unstructured":"Collins, L., Hassani, H., Mokhtari, A., Shakkottai, S Exploiting shared representations for personalized federated learning, In: Proceedings of Machine Learning Research, Jul. 2021, vol. 139, pp. 2089\u20132099. Accessed: Sep. 29, 2025. [Online]. Available: https:\/\/proceedings.mlr.press\/v139\/collins21a.html"},{"key":"29672_CR30","doi-asserted-by":"publisher","first-page":"296","DOI":"10.1109\/OJEMB.2025.3530841","volume":"6","author":"BP Veasey","year":"2025","unstructured":"Veasey, B. P. & Amini, A. A. Low-rank adaptation of pre-trained large vision models for improved lung nodule malignancy classification. IEEE Open J. Eng. Med. Biol. 6, 296\u2013304. https:\/\/doi.org\/10.1109\/OJEMB.2025.3530841 (2025).","journal-title":"IEEE Open J. Eng. Med. Biol."},{"key":"29672_CR31","doi-asserted-by":"publisher","DOI":"10.1007\/S00530-025-01778-6","author":"Y Zheng","year":"2025","unstructured":"Zheng, Y., Gao, Y., Liu, J., Yao, N. & Ji, Z. Radlora: A smart low-rank adaptive approach for radiological image classification. Multimed. Syst. https:\/\/doi.org\/10.1007\/S00530-025-01778-6 (2025).","journal-title":"Multimed. Syst."},{"key":"29672_CR32","doi-asserted-by":"publisher","DOI":"10.1016\/j.compmedimag.2025.102583","volume":"124","author":"JP Kao","year":"2025","unstructured":"Kao, J. P., Chung, Y. C., Hung, H. Y., Chen, C. P. & Chen, W. S. LoRA-enhanced RT-DETR: First low-rank adaptation based DETR for real-time full body anatomical structures identification in musculoskeletal ultrasound. Comput. Med. Imaging Graph. 124, 102583. https:\/\/doi.org\/10.1016\/j.compmedimag.2025.102583 (2025).","journal-title":"Comput. Med. Imaging Graph."}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-29672-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-29672-1","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-29672-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T14:10:48Z","timestamp":1767622248000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-29672-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,11]]},"references-count":32,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["29672"],"URL":"https:\/\/doi.org\/10.1038\/s41598-025-29672-1","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,11]]},"assertion":[{"value":"22 August 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 November 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 December 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 potential conflicts of interest with respect to the research, authorship, and\/or publication of this article. To the best of my knowledge and belief, any actual, perceived, or potential conflicts between my duties as an employee and my private and\/or business interests have been fully disclosed in this form in accordance with the requirements of the journal.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"339"}}