{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T11:30:29Z","timestamp":1790076629370,"version":"4.0.1"},"reference-count":41,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,3,23]],"date-time":"2026-03-23T00:00:00Z","timestamp":1774224000000},"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. Aging Neurosci."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Amyloid-related imaging abnormalities with hemorrhage (ARIA-H) are a key safety concern in anti-amyloid therapies for Alzheimer\u2019s disease, as they are radiologically indistinguishable from cerebral microbleeds (CMBs). Accurate detection of CMBs is therefore essential for both treatment eligibility assessment and post-treatment safety monitoring. However, manual identification on 2D T2*-weighted gradient-recalled echo (GRE) MRI is labor-intensive and subject to variability.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>To develop and validate an artificial intelligence (AI)-based model for automated CMB detection using only 2D T2*-weighted GRE MRI, which is widely used in clinical settings.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We implemented a YOLOv11-based deep learning model, preceded by a novel multi-channel preprocessing pipeline that enhances CMB visibility. The model was trained and tested using a dataset of 758 participants, with expert consensus used as the reference standard.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Using the optimized basic preprocessing with super-resolution (BP\u202f+\u202fSR) pipeline, the model achieved a lesion-level sensitivity of 0.694, precision of 0.705, and F1-score of 0.699. In patient-level analysis for detecting elevated CMB burden (\u22654), the system demonstrated sensitivity of 0.933 and specificity of 0.935, supporting reliable stratification of CMB severity. Regional analysis showed sensitivity of 0.625 for lobar CMBs and 0.627 for deep structures.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>This study demonstrates the feasibility of robust CMB detection using only 2D T2*-weighted GRE MRI. Based on current performance, we position this system as a decision-support tool for GRE-based CMB screening, in which lesion-level detections may be aggregated to inform patient-level CMB burden relevant to ARIA-H risk stratification, while final ARIA grading and clinical decisions require expert neuroradiological confirmation.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fnagi.2026.1729422","type":"journal-article","created":{"date-parts":[[2026,3,23]],"date-time":"2026-03-23T06:42:36Z","timestamp":1774248156000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Deep learning-based detection of cerebral microbleeds on 2D T2*-weighted GRE MRI: toward ARIA-H risk assessment in Alzheimer\u2019s treatment"],"prefix":"10.3389","volume":"18","author":[{"given":"Soo-Oh","family":"Yang","sequence":"first","affiliation":[{"name":"BeauBrain Healthcare, Inc.","place":["Seoul, Republic of Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jehyun","family":"Ahn","sequence":"additional","affiliation":[{"name":"Alzheimer\u2019s Disease Convergence Research Center, Samsung Medical Center","place":["Seoul, Republic of Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Young Hee","family":"Jung","sequence":"additional","affiliation":[{"name":"Department of Neurology, Hallym University Sacred Heart Hospital, College of Medicine, Hallym University","place":["Anyang, Republic of Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hyemin","family":"Jang","sequence":"additional","affiliation":[{"name":"Department of Neurology, Asan Medical Center","place":["Seoul, Republic of Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Duk L.","family":"Na","sequence":"additional","affiliation":[{"name":"BeauBrain Healthcare, Inc.","place":["Seoul, Republic of Korea"]},{"name":"Department of Neurology, Samsung Medical Center, Sungkyunkwan University School of Medicine","place":["Seoul, Republic of Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Heejin","family":"Kim","sequence":"additional","affiliation":[{"name":"Alzheimer\u2019s Disease Convergence Research Center, Samsung Medical Center","place":["Seoul, Republic of Korea"]},{"name":"Department of Neurology, Samsung Medical Center, Sungkyunkwan University School of Medicine","place":["Seoul, Republic of Korea"]},{"name":"Department of Health Sciences and Technology, SAIHST, Sungkyunkwan University","place":["Seoul, Republic of Korea"]},{"name":"Department of Digital Health, SAIHST, Sungkyunkwan University","place":["Seoul, Republic of Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun Pyo","family":"Kim","sequence":"additional","affiliation":[{"name":"Alzheimer\u2019s Disease Convergence Research Center, Samsung Medical Center","place":["Seoul, Republic of Korea"]},{"name":"Department of Neurology, Samsung Medical Center, Sungkyunkwan University School of Medicine","place":["Seoul, Republic of Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sang Won","family":"Seo","sequence":"additional","affiliation":[{"name":"Alzheimer\u2019s Disease Convergence Research Center, Samsung Medical Center","place":["Seoul, Republic of Korea"]},{"name":"Department of Neurology, Samsung Medical Center, Sungkyunkwan University School of Medicine","place":["Seoul, Republic of Korea"]},{"name":"Department of Health Sciences and Technology, SAIHST, Sungkyunkwan University","place":["Seoul, Republic of Korea"]},{"name":"Department of Digital Health, SAIHST, Sungkyunkwan University","place":["Seoul, Republic of Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kichang","family":"Kwak","sequence":"additional","affiliation":[{"name":"BeauBrain Healthcare, Inc.","place":["Seoul, Republic of Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,3,23]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"169","DOI":"10.25259\/JNRP_351_2023","article-title":"Cerebral microbleeds: causes, clinical relevance, and imaging approach\u2013a narrative review","volume":"15","author":"Agarwal","year":"2024","journal-title":"J Neurosci Rural Pract"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"1071","DOI":"10.3346\/jkms.2010.25.7.1071","article-title":"Seoul neuropsychological screening battery-dementia version (SNSB-D): a useful tool for assessing and monitoring cognitive impairments in dementia patients","volume":"25","author":"Ahn","year":"2010","journal-title":"J. Korean Med. Sci."},{"key":"ref3","doi-asserted-by":"publisher","first-page":"102464","DOI":"10.1016\/j.nicl.2020.102464","article-title":"Automated detection of cerebral microbleeds in MR images: a two-stage deep learning approach","volume":"28","author":"Al-Masni","year":"2020","journal-title":"NeuroImage"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"1958","DOI":"10.3174\/ajnr.A3500","article-title":"MR imaging features of amyloid-related imaging abnormalities","volume":"34","author":"Barakos","year":"2013","journal-title":"AJNR Am. J. Neuroradiol."},{"key":"ref5","doi-asserted-by":"publisher","first-page":"2126","DOI":"10.1093\/brain\/awv162","article-title":"Cortical superficial siderosis: detection and clinical significance in cerebral amyloid angiopathy and related conditions","volume":"138","author":"Charidimou","year":"2015","journal-title":"Brain"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"454","DOI":"10.1177\/1747493017751931","article-title":"Clinical significance of cerebral microbleeds on MRI: a comprehensive meta-analysis of risk of intracerebral hemorrhage, ischemic stroke, mortality, and dementia in cohort studies","volume":"13","author":"Charidimou","year":"2018","journal-title":"Int. J. Stroke"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"587","DOI":"10.2217\/fnl.11.42","article-title":"Cerebral microbleeds: detection, mechanisms and clinical challenges","volume":"6","author":"Charidimou","year":"2011","journal-title":"Future Neurol."},{"key":"ref9","doi-asserted-by":"publisher","first-page":"766","DOI":"10.1007\/s10278-018-0146-z","article-title":"Toward automatic detection of radiation-induced cerebral microbleeds using a 3D deep residual network","volume":"32","author":"Chen","year":"2019","journal-title":"J. Digit. Imaging"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"E19","DOI":"10.3174\/ajnr.A7586","article-title":"Amyloid-related imaging abnormalities with emerging Alzheimer disease therapeutics: detection and reporting recommendations for clinical practice","volume":"43","author":"Cogswell","year":"2022","journal-title":"AJNR Am. J. Neuroradiol."},{"key":"ref11","doi-asserted-by":"publisher","first-page":"52","DOI":"10.1002\/jmri.22223","article-title":"Visualization of cerebral microbleeds with dual-echo T2*-weighted magnetic resonance imaging at 7.0 T","volume":"32","author":"Conijn","year":"2010","journal-title":"J. Magn. Reson. Imaging"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"94","DOI":"10.1161\/STROKEAHA.108.526996","article-title":"Improving interrater agreement about brain microbleeds: development of the brain observer MicroBleed scale (BOMBS)","volume":"40","author":"Cordonnier","year":"2009","journal-title":"Stroke"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"1182","DOI":"10.1109\/TMI.2016.2528129","article-title":"Automatic detection of cerebral microbleeds from MR images via 3D convolutional neural networks","volume":"35","author":"Dou","year":"2016","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"1683","DOI":"10.1212\/WNL.43.9.1683","article-title":"Pathologic correlates of incidental MRI white matter signal hyperintensities","volume":"43","author":"Fazekas","year":"1993","journal-title":"Neurology"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"1894","DOI":"10.1161\/STROKEAHA.110.599837","article-title":"Clinical relevance of improved microbleed detection by susceptibility-weighted magnetic resonance imaging","volume":"42","author":"Goos","year":"2011","journal-title":"Stroke"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"1759","DOI":"10.1212\/WNL.0b013e3181c34a7d","article-title":"The microbleed anatomical rating scale (MARS): reliability of a tool to map brain microbleeds","volume":"73","author":"Gregoire","year":"2009","journal-title":"Neurology"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"456","DOI":"10.3389\/fimmu.2020.00456","article-title":"A path toward precision medicine for neuroinflammatory mechanisms in Alzheimer's disease","volume":"11","author":"Hampel","year":"2020","journal-title":"Front. Immunol."},{"key":"ref18","doi-asserted-by":"publisher","first-page":"4414","DOI":"10.1093\/brain\/awad188","article-title":"Amyloid-related imaging abnormalities (ARIA): radiological, biological and clinical characteristics","volume":"146","author":"Hampel","year":"2023","journal-title":"Brain"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"1463","DOI":"10.3390\/biomedicines12071463","article-title":"Cerebral microbleeds associate with brain endothelial cell activation-dysfunction and blood-brain barrier dysfunction\/disruption with increased risk of Hemorrhagic and ischemic stroke","volume":"12","author":"Hayden","year":"2024","journal-title":"Biomedicine"},{"key":"ref20","first-page":"2410.17725","article-title":"Yolov11: an overview of the key architectural enhancements","author":"Khanam","year":"2024","journal-title":"arXiv"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"103415","DOI":"10.1016\/j.media.2024.103415","article-title":"Toward automated detection of microbleeds with anatomical scale localization using deep learning","volume":"101","author":"Kim","year":"2025","journal-title":"Med. Image Anal."},{"key":"ref22","first-page":"1132","volume-title":"Proceedings of the IEEE Conference on Computer vision and Pattern Recognition Workshops (CVPRW)","author":"Lim","year":"2017"},{"key":"ref23","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":"ref24","doi-asserted-by":"publisher","first-page":"271","DOI":"10.1016\/j.neuroimage.2019.05.046","article-title":"Cerebral microbleed detection using susceptibility weighted imaging and deep learning","volume":"198","author":"Liu","year":"2019","journal-title":"NeuroImage"},{"key":"ref25","first-page":"1711.05101","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1186\/alzrt263","article-title":"Cerebral microbleeds: overview and implications in cognitive impairment","volume":"6","author":"Martinez-Ramirez","year":"2014","journal-title":"Alzheimer's Res. Ther."},{"key":"ref27","doi-asserted-by":"publisher","first-page":"263","DOI":"10.1016\/j.jalz.2011.03.005","article-title":"The diagnosis of dementia due to Alzheimer's disease: recommendations from the National Institute on Aging-Alzheimer's Association workgroups on diagnostic guidelines for Alzheimer's disease","volume":"7","author":"McKhann","year":"2011","journal-title":"Alzheimers Dement."},{"key":"ref28","doi-asserted-by":"publisher","first-page":"105886","DOI":"10.1016\/j.jstrokecerebrovasdis.2021.105886","article-title":"Novel approaches to detection of cerebral microbleeds: single deep learning model to achieve a balanced performance","volume":"30","author":"Myung","year":"2021","journal-title":"J. Stroke Cerebrovasc. Dis."},{"key":"ref29","doi-asserted-by":"publisher","first-page":"338","DOI":"10.3174\/ajnr.A1355","article-title":"MR imaging detection of cerebral microbleeds: effect of susceptibility-weighted imaging, section thickness, and field strength","volume":"30","author":"Nandigam","year":"2009","journal-title":"Am. J. Neuroradiol."},{"key":"ref30","doi-asserted-by":"publisher","first-page":"S103","DOI":"10.1161\/STROKEAHA.110.595181","article-title":"Prevalence and risk factors of cerebral microbleeds: an update of the Rotterdam scan study","volume":"41","author":"Poels","year":"2010","journal-title":"Stroke"},{"key":"ref31","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1001\/jamaneurol.2021.4161","article-title":"Amyloid-related imaging abnormalities in 2 phase 3 studies evaluating aducanumab in patients with early Alzheimer disease","volume":"79","author":"Salloway","year":"2022","journal-title":"JAMA Neurol."},{"key":"ref32","doi-asserted-by":"publisher","first-page":"1089","DOI":"10.3174\/ajnr.A4248","article-title":"SWI or T2*: which MRI sequence to use in the detection of cerebral microbleeds? The Karolinska imaging dementia study","volume":"36","author":"Shams","year":"2015","journal-title":"Am. J. Neuroradiol."},{"key":"ref33","doi-asserted-by":"publisher","first-page":"528","DOI":"10.1159\/000331466","article-title":"Cerebral microbleeds: histopathological correlation of neuroimaging","volume":"32","author":"Shoamanesh","year":"2011","journal-title":"Cerebrovasc. Dis."},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2023.55800","article-title":"Artificial intelligence assistive software tool for automated detection and quantification of amyloid-related imaging abnormalities","volume":"7","author":"Sima","year":"2024","journal-title":"JAMA Netw. Open"},{"key":"ref35","doi-asserted-by":"crossref","first-page":"143","DOI":"10.1002\/hbm.10062","article-title":"Fast robust automated brain extraction","volume":"17","author":"Smith","year":"2002","journal-title":"Hum. Brain Mapp."},{"key":"ref36","doi-asserted-by":"publisher","first-page":"367","DOI":"10.1016\/j.jalz.2011.05.2351","article-title":"Amyloid-related imaging abnormalities in amyloid-modifying therapeutic trials: recommendations from the Alzheimer's Association research roundtable workgroup","volume":"7","author":"Sperling","year":"2011","journal-title":"Alzheimers Dement."},{"key":"ref37","doi-asserted-by":"publisher","first-page":"895","DOI":"10.1016\/j.acra.2008.01.013","article-title":"Detection of asymptomatic cerebral microbleeds","volume":"15","author":"Stehling","year":"2008","journal-title":"Acad. Radiol."},{"key":"ref38","doi-asserted-by":"publisher","first-page":"106233","DOI":"10.1016\/j.compbiomed.2022.106233","article-title":"CMB-HUNT: automatic detection of cerebral microbleeds using a deep neural network","volume":"151","author":"Suwalska","year":"2022","journal-title":"Comput. Biol. Med."},{"key":"ref39","doi-asserted-by":"publisher","first-page":"30901","DOI":"10.1038\/s41598-024-81870-5","article-title":"SHIVA-CMB: a deep-learning-based robust cerebral microbleed segmentation tool trained on multi-source T2* GRE-and susceptibility-weighted MRI","volume":"14","author":"Tsuchida","year":"2024","journal-title":"Sci. Rep."},{"key":"ref40","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1056\/nejmoa2212948","article-title":"Lecanemab in early Alzheimer's disease","volume":"388","author":"van Dyck","year":"2023","journal-title":"N. Engl. J. Med."},{"key":"ref41","doi-asserted-by":"publisher","first-page":"205","DOI":"10.1148\/radiol.13130743","article-title":"Increased number of microinfarcts in Alzheimer disease at 7-T MR imaging","volume":"270","author":"van Rooden","year":"2014","journal-title":"Radiology"},{"key":"ref42","doi-asserted-by":"crossref","first-page":"474","DOI":"10.1016\/B978-0-12-336156-1.50061-6","volume-title":"Graphics Gems IV","author":"Zuiderveld","year":"1994"}],"container-title":["Frontiers in Aging Neuroscience"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnagi.2026.1729422\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,23]],"date-time":"2026-03-23T06:42:38Z","timestamp":1774248158000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnagi.2026.1729422\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,23]]},"references-count":41,"alternative-id":["10.3389\/fnagi.2026.1729422"],"URL":"https:\/\/doi.org\/10.3389\/fnagi.2026.1729422","relation":{},"ISSN":["1663-4365"],"issn-type":[{"value":"1663-4365","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,23]]},"article-number":"1729422"}}