{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T19:14:46Z","timestamp":1786994086243,"version":"build-2736575974"},"reference-count":57,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T00:00:00Z","timestamp":1759968000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001804","name":"Canada Research Chairs","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001804","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Medical Image Analysis"],"published-print":{"date-parts":[[2026,1]]},"DOI":"10.1016\/j.media.2025.103807","type":"journal-article","created":{"date-parts":[[2025,9,13]],"date-time":"2025-09-13T14:06:05Z","timestamp":1757772365000},"page":"103807","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":7,"special_numbering":"PB","title":["A novel gradient inversion attack framework to investigate privacy vulnerabilities during retinal image-based federated learning"],"prefix":"10.1016","volume":"107","author":[{"given":"Christopher","family":"Nielsen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8845-360X","authenticated-orcid":false,"given":"Matthias","family":"Wilms","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2556-3224","authenticated-orcid":false,"given":"Nils D.","family":"Forkert","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.media.2025.103807_bib0001","doi-asserted-by":"crossref","unstructured":"Abadi, M., Chu, A., Goodfellow, I., McMahan, H.B., Mironov, I., Talwar, K., & Zhang, L. (2016). Deep learning with differential privacy. Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security, 308\u2013318. https:\/\/doi.org\/10.1145\/2976749.2978318.","DOI":"10.1145\/2976749.2978318"},{"key":"10.1016\/j.media.2025.103807_bib0002","doi-asserted-by":"crossref","DOI":"10.1016\/j.imu.2020.100377","article-title":"Diabetic retinopathy detection through deep learning techniques: a review","volume":"20","author":"Alyoubi","year":"2020","journal-title":"Inform. Med. Unlocked"},{"key":"10.1016\/j.media.2025.103807_bib0003","unstructured":"Bagdasaryan, E., & Shmatikov, V. (2019). Differential privacy has disparate impact on model accuracy (arXiv:1905.12101). arXiv. https:\/\/doi.org\/10.48550\/arXiv.1905.12101."},{"key":"10.1016\/j.media.2025.103807_bib0004","unstructured":"Bonawitz, K., Ivanov, V., Kreuter, B., Marcedone, A., McMahan, H.B., Patel, S., Ramage, D., Segal, A., & Seth, K. (2017). Pract. Secure Aggreg. Priv. Preserv. Mach. Learn. (2017\/281). Cryptology ePrint Archive. https:\/\/eprint.iacr.org\/2017\/281."},{"issue":"7726","key":"10.1016\/j.media.2025.103807_bib0005","doi-asserted-by":"crossref","first-page":"203","DOI":"10.1038\/s41586-018-0579-z","article-title":"The UK Biobank resource with deep phenotyping and genomic data","volume":"562","author":"Bycroft","year":"2018","journal-title":"Nature"},{"issue":"3","key":"10.1016\/j.media.2025.103807_bib0006","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0194116","article-title":"The relationship between age, axial length and retinal nerve fiber layer thickness in the normal elderly population in Taiwan: the Chiayi eye study in Taiwan","volume":"13","author":"Chen","year":"2018","journal-title":"PLoS ONE"},{"key":"10.1016\/j.media.2025.103807_bib0007","doi-asserted-by":"crossref","DOI":"10.1016\/j.diabres.2023.110817","article-title":"Glycemic status and its association with retinal age gap: insights from the UK biobank study","volume":"202","author":"Chen","year":"2023","journal-title":"Diabetes Res. Clin. Pr."},{"issue":"11","key":"10.1016\/j.media.2025.103807_bib0008","doi-asserted-by":"crossref","first-page":"e806","DOI":"10.1016\/S2589-7500(22)00169-8","article-title":"A deep learning model for detection of Alzheimer\u2019s disease based on retinal photographs: a retrospective, multicentre case-control study","volume":"4","author":"Cheung","year":"2022","journal-title":"Lancet Digit. Health"},{"key":"10.1016\/j.media.2025.103807_bib0009","unstructured":"Costan, V., & Devadas, S. (2016). Intel SGX Explained (2016\/086). Cryptology ePrint Archive. https:\/\/eprint.iacr.org\/2016\/086."},{"key":"10.1016\/j.media.2025.103807_bib0010","doi-asserted-by":"crossref","DOI":"10.21553\/rev-jec.338","article-title":"Performance analysis of gradient inversion attack in federated learning with Healthcare Systems","author":"Dao","year":"2023","journal-title":"REV J. Electron. Commun."},{"key":"10.1016\/j.media.2025.103807_bib0011","doi-asserted-by":"crossref","DOI":"10.1016\/j.eclinm.2021.100875","article-title":"Artificial intelligence for the detection of age-related macular degeneration in color fundus photographs: a systematic review and meta-analysis","volume":"35","author":"Dong","year":"2021","journal-title":"eClinicalMedicine"},{"key":"10.1016\/j.media.2025.103807_bib0012","unstructured":"Du, J., Hu, J., Wang, Z., Sun, P., Gong, N.Z., Ren, K., & Chen, C. (2025). SoK: on gradient leakage in federated learning (arXiv:2404.05403). arXiv. https:\/\/doi.org\/10.48550\/arXiv.2404.05403."},{"key":"10.1016\/j.media.2025.103807_bib0013","doi-asserted-by":"crossref","DOI":"10.1016\/j.asoc.2021.107330","article-title":"Federated learning for COVID-19 screening from chest X-ray images","volume":"106","author":"Feki","year":"2021","journal-title":"Appl. Soft Comput."},{"key":"10.1016\/j.media.2025.103807_bib0014","doi-asserted-by":"crossref","unstructured":"Fu, H., Wang, B., Shen, J., Cui, S., Xu, Y., Liu, J., & Shao, L. (2019). Evaluation of retinal image quality assessment networks in different color-spaces (Vol. 11764, pp. 48\u201356). https:\/\/doi.org\/10.1007\/978-3-030-32239-7_6.","DOI":"10.1007\/978-3-030-32239-7_6"},{"key":"10.1016\/j.media.2025.103807_bib0015","first-page":"16937","article-title":"Inverting gradients\u2014How easy is it to break privacy in federated learning?","volume":"33","author":"Geiping","year":"2020","journal-title":"Adv. Neural Inf. Process Syst."},{"key":"10.1016\/j.media.2025.103807_bib0016","article-title":"Federated learning for diagnosis of age-related macular degeneration","volume":"10","author":"Gholami","year":"2023","journal-title":"Front. Med. (Lausanne)"},{"key":"10.1016\/j.media.2025.103807_bib0017","doi-asserted-by":"crossref","unstructured":"Guan, H., Yap, P.-T., Bozoki, A., & Liu, M. (2023). Federated learning for medical image analysis: a survey (arXiv:2306.05980). arXiv. https:\/\/doi.org\/10.48550\/arXiv.2306.05980.","DOI":"10.1016\/j.patcog.2024.110424"},{"issue":"8","key":"10.1016\/j.media.2025.103807_bib0018","doi-asserted-by":"crossref","first-page":"650","DOI":"10.1016\/j.oret.2022.03.005","article-title":"Federated learning for Multicenter collaboration in ophthalmology: implications for clinical diagnosis and disease epidemiology","volume":"6","author":"Hanif","year":"2022","journal-title":"Ophthalmol. Retina"},{"issue":"7","key":"10.1016\/j.media.2025.103807_bib0019","doi-asserted-by":"crossref","first-page":"2044","DOI":"10.1109\/TMI.2023.3239391","article-title":"Do gradient inversion attacks make federated learning unsafe?","volume":"42","author":"Hatamizadeh","year":"2023","journal-title":"IEEE Trans. Med. Imaging"},{"key":"10.1016\/j.media.2025.103807_bib0020","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J. (2015, December 10). Deep Residual Learn. Image Recognit.. arXiv.Org. https:\/\/arxiv.org\/abs\/1512.03385v1."},{"issue":"3","key":"10.1016\/j.media.2025.103807_bib0021","doi-asserted-by":"crossref","first-page":"afac062","DOI":"10.1093\/ageing\/afac062","article-title":"Retinal age gap as a predictive biomarker of future risk of Parkinson\u2019s disease","volume":"51","author":"Hu","year":"2022","journal-title":"Age Ageing"},{"key":"10.1016\/j.media.2025.103807_bib0022","article-title":"Densely connected convolutional networks (arXiv:1608.06993)","author":"Huang","year":"2018","journal-title":"arXiv"},{"key":"10.1016\/j.media.2025.103807_bib0023","unstructured":"Huang, Y., Gupta, S., Song, Z., Li, K., & Arora, S. (2021, November 30). Evaluating Gradient Inversion Attacks and Defenses in Federated Learning. arXiv.Org. https:\/\/arxiv.org\/abs\/2112.00059v1."},{"key":"10.1016\/j.media.2025.103807_bib0024","doi-asserted-by":"crossref","unstructured":"Isola, P., Zhu, J.-Y., Zhou, T., & Efros, A.A. (2018). Image-to-Image translation with conditional adversarial networks (arXiv:1611.07004). arXiv. https:\/\/doi.org\/10.48550\/arXiv.1611.07004.","DOI":"10.1109\/CVPR.2017.632"},{"key":"10.1016\/j.media.2025.103807_bib0025","unstructured":"Jin, W., Yao, Y., Han, S., Joe-Wong, C., Ravi, S., Avestimehr, S., & He, C. (2023). FedML-HE: An Efficient Homomorphic-Encryption-Based Privacy-Preserving Federated Learning System (arXiv:2303.10837). arXiv. http:\/\/arxiv.org\/abs\/2303.10837."},{"key":"10.1016\/j.media.2025.103807_bib0026","unstructured":"Li, X., Zhao, B., Yang, G., Xiang, T., Weng, J., & Deng, R.H. (2023). A survey of secure computation using trusted execution environments (arXiv:2302.12150). arXiv. https:\/\/doi.org\/10.48550\/arXiv.2302.12150."},{"issue":"1","key":"10.1016\/j.media.2025.103807_bib0027","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1186\/s42400-021-00105-6","article-title":"Threats, attacks and defenses to federated learning: issues, taxonomy and perspectives","volume":"5","author":"Liu","year":"2022","journal-title":"Cybersecurity"},{"key":"10.1016\/j.media.2025.103807_bib0028","unstructured":"McMahan, H.B., Moore, E., Ramage, D., Hampson, S., & Arcas, B.A. y. (2023). Communication-efficient learning of deep networks from decentralized data (arXiv:1602.05629). arXiv. https:\/\/doi.org\/10.48550\/arXiv.1602.05629."},{"issue":"12","key":"10.1016\/j.media.2025.103807_bib0029","doi-asserted-by":"crossref","first-page":"5726","DOI":"10.3390\/s23125726","article-title":"Using deep learning architectures for detection and classification of diabetic retinopathy","volume":"23","author":"Mohanty","year":"2023","journal-title":"Sensors"},{"key":"10.1016\/j.media.2025.103807_bib0030","unstructured":"Mouches, P., Wilms, M., Rajashekar, D., Langner, S., & Forkert, N. (2021). Unifying brain age prediction and age-conditioned template generation with a deterministic autoencoder. Proceedings of the Fourth Conference on Medical Imaging with Deep Learning, 497\u2013506. https:\/\/proceedings.mlr.press\/v143\/mouches21a.html."},{"issue":"2","key":"10.1016\/j.media.2025.103807_bib0031","first-page":"67","article-title":"Retinal scans and data sharing: the privacy and scientific development equilibrium","volume":"1","author":"Nakayama","year":"2023","journal-title":"Mayo Clin. Proc.: Digit. Health"},{"key":"10.1016\/j.media.2025.103807_bib0032","first-page":"ocae220","article-title":"Foundation model-driven distributed learning for enhanced retinal age prediction","author":"Nielsen","year":"2024","journal-title":"J. Am. Med. Inform. Assoc."},{"key":"10.1016\/j.media.2025.103807_bib0033","series-title":"Ophthalmic Medical Image Analysis","first-page":"183","article-title":"Investigating the vulnerability of federated learning-based diabetic retinopathy grade classification to gradient inversion attacks","author":"Nielsen","year":"2022"},{"issue":"3","key":"10.1016\/j.media.2025.103807_bib0034","article-title":"Highly efficient homomorphic encryption-based federated learning for diabetic retinopathy classification","volume":"12","author":"Nielsen","year":"2025","journal-title":"J. Med. Imaging (Bellingham)"},{"issue":"2046","key":"10.1016\/j.media.2025.103807_bib0035","doi-asserted-by":"crossref","DOI":"10.1098\/rspb.2024.2233","article-title":"The retinal age gap: an affordable and highly accessible biomarker for population-wide disease screening across the globe","volume":"292","author":"Nielsen","year":"2025","journal-title":"Proc. R. Soc. B: Biol. Sci."},{"key":"10.1016\/j.media.2025.103807_bib0036","unstructured":"ODIR-2019\u2014Grand Challenge. 2019. Grand-Challenge.Org. Retrieved March 5, 2024, from https:\/\/odir2019.grand-challenge.org\/."},{"key":"10.1016\/j.media.2025.103807_bib0037","doi-asserted-by":"crossref","DOI":"10.3389\/fneur.2021.663899","article-title":"Prediction of clinical outcomes in acute ischaemic stroke patients: a comparative study","volume":"12","author":"Rajashekar","year":"2021","journal-title":"Front. Neurol."},{"key":"10.1016\/j.media.2025.103807_bib0038","unstructured":"Rolf, E., Worledge, T.T., Recht, B., & Jordan, M. (2021). Representation matters: assessing the importance of subgroup allocations in training data. Proceedings of the 38th International Conference on Machine Learning, 9040\u20139051. https:\/\/proceedings.mlr.press\/v139\/rolf21a.html."},{"issue":"6","key":"10.1016\/j.media.2025.103807_bib0039","doi-asserted-by":"crossref","first-page":"e295","DOI":"10.1016\/S2589-7500(20)30063-7","article-title":"A deep learning algorithm to detect chronic kidney disease from retinal photographs in community-based populations","volume":"2","author":"Sabanayagam","year":"2020","journal-title":"Lancet Digit. Health"},{"key":"10.1016\/j.media.2025.103807_bib0040","unstructured":"Simonyan, K., & Zisserman, A. (2015). Very deep convolutional networks for large-scale image recognition (arXiv:1409.1556). arXiv. https:\/\/doi.org\/10.48550\/arXiv.1409.1556."},{"key":"10.1016\/j.media.2025.103807_bib0041","doi-asserted-by":"crossref","DOI":"10.1016\/j.jclepro.2024.142272","article-title":"The sustainable development goals of the United Nations: a comparative midterm research review","volume":"453","author":"Sorooshian","year":"2024","journal-title":"J. Clean Prod."},{"issue":"1","key":"10.1016\/j.media.2025.103807_bib0042","doi-asserted-by":"crossref","first-page":"112","DOI":"10.1093\/jamia\/ocac204","article-title":"An analysis of the effects of limited training data in distributed learning scenarios for brain age prediction","volume":"30","author":"Souza","year":"2023","journal-title":"J. Am. Med. Inform. Assoc."},{"issue":"2","key":"10.1016\/j.media.2025.103807_bib0043","doi-asserted-by":"crossref","first-page":"42","DOI":"10.1167\/tvst.9.2.42","article-title":"A review of deep learning for screening, diagnosis, and detection of glaucoma progression","volume":"9","author":"Thompson","year":"2020","journal-title":"Transl. Vis. Sci. Technol."},{"key":"10.1016\/j.media.2025.103807_bib0044","unstructured":"U.S. Department of Defense, Privacy and Civil Liberties Directorate. (n.d.). Retrieved April 21, 2025, from https:\/\/pclt.defense.gov\/DIRECTORATES\/Privacy-and-Civil-Liberties-Directorate\/Privacy\/About-the-Office\/FAQs\/."},{"issue":"1","key":"10.1016\/j.media.2025.103807_bib0045","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s43856-021-00028-w","article-title":"Mitigating bias in machine learning for medicine","volume":"1","author":"Vokinger","year":"2021","journal-title":"Commun. Med."},{"key":"10.1016\/j.media.2025.103807_bib0046","article-title":"Applications of federated learning in Mobile health: scoping review","volume":"25","author":"Wang","year":"2023","journal-title":"J. Med. Internet Res."},{"issue":"4","key":"10.1016\/j.media.2025.103807_bib0047","doi-asserted-by":"crossref","first-page":"600","DOI":"10.1109\/TIP.2003.819861","article-title":"Image quality assessment: from error visibility to structural similarity","volume":"13","author":"Wang","year":"2004","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.media.2025.103807_bib0048","unstructured":"Wu, Y., Zeng, D., Wang, Z., Sheng, Y., Yang, L., James, A.J., Shi, Y., & Hu, J. (2022). Federated Contrastive Learning for Dermatological Disease Diagnosis via On-device Learning (arXiv:2202.07470). arXiv. http:\/\/arxiv.org\/abs\/2202.07470."},{"key":"10.1016\/j.media.2025.103807_bib0049","doi-asserted-by":"crossref","unstructured":"Yin, H., Mallya, A., Vahdat, A., Alvarez, J.M., Kautz, J., & Molchanov, P. (2021). See through gradients: image batch recovery via GradInversion (arXiv:2104.07586). arXiv. https:\/\/doi.org\/10.48550\/arXiv.2104.07586.","DOI":"10.1109\/CVPR46437.2021.01607"},{"key":"10.1016\/j.media.2025.103807_bib0050","doi-asserted-by":"crossref","DOI":"10.1016\/j.compbiomed.2021.104716","article-title":"Privacy preserving distributed learning classifiers \u2013 Sequential learning with small sets of data","volume":"136","author":"Zerka","year":"2021","journal-title":"Comput. Biol. Med."},{"key":"10.1016\/j.media.2025.103807_bib0051","doi-asserted-by":"crossref","unstructured":"Zhang, R., Isola, P., Efros, A.A., Shechtman, E., & Wang, O. (2018). The unreasonable effectiveness of deep features as a perceptual metric (arXiv:1801.03924). arXiv. https:\/\/doi.org\/10.48550\/arXiv.1801.03924.","DOI":"10.1109\/CVPR.2018.00068"},{"key":"10.1016\/j.media.2025.103807_bib0052","unstructured":"Zhao, B., Mopuri, K.R., & Bilen, H. (2020). iDLG: improved deep leakage from gradients (arXiv:2001.02610). arXiv. https:\/\/doi.org\/10.48550\/arXiv.2001.02610."},{"key":"10.1016\/j.media.2025.103807_bib0053","unstructured":"Zhioua, S., & Binkyt\u0117, R. (2023). Shedding light on underrepresentation and Sampling Bias in machine learning (arXiv:2306.05068). arXiv. http:\/\/arxiv.org\/abs\/2306.05068."},{"issue":"7","key":"10.1016\/j.media.2025.103807_bib0054","doi-asserted-by":"crossref","first-page":"12","DOI":"10.1167\/tvst.11.7.12","article-title":"AutoMorph: automated retinal vascular morphology quantification via a deep learning pipeline","volume":"11","author":"Zhou","year":"2022","journal-title":"Transl. Vis. Sci. Technol."},{"issue":"11","key":"10.1016\/j.media.2025.103807_bib0055","doi-asserted-by":"crossref","first-page":"3320","DOI":"10.1161\/STROKEAHA.122.038809","article-title":"Association of retinal age gap with arterial stiffness and incident cardiovascular disease","volume":"53","author":"Zhu","year":"2022","journal-title":"Stroke"},{"issue":"4","key":"10.1016\/j.media.2025.103807_bib0056","doi-asserted-by":"crossref","first-page":"547","DOI":"10.1136\/bjophthalmol-2021-319807","article-title":"Retinal age gap as a predictive biomarker for mortality risk","volume":"107","author":"Zhu","year":"2023","journal-title":"Br. J. Ophthalmol."},{"issue":"1","key":"10.1016\/j.media.2025.103807_bib0057","doi-asserted-by":"crossref","DOI":"10.1038\/s41598-021-93030-0","article-title":"Medical imaging deep learning with differential privacy","volume":"11","author":"Ziller","year":"2021","journal-title":"Sci. Rep."}],"container-title":["Medical Image Analysis"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1361841525003536?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1361841525003536?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T15:00:24Z","timestamp":1773154824000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1361841525003536"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":57,"alternative-id":["S1361841525003536"],"URL":"https:\/\/doi.org\/10.1016\/j.media.2025.103807","relation":{},"ISSN":["1361-8415"],"issn-type":[{"value":"1361-8415","type":"print"}],"subject":[],"published":{"date-parts":[[2026,1]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"A novel gradient inversion attack framework to investigate privacy vulnerabilities during retinal image-based federated learning","name":"articletitle","label":"Article Title"},{"value":"Medical Image Analysis","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.media.2025.103807","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2025 The Authors. Published by Elsevier B.V.","name":"copyright","label":"Copyright"}],"article-number":"103807"}}