{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T11:30:30Z","timestamp":1790076630328,"version":"4.0.1"},"reference-count":24,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T00:00:00Z","timestamp":1772582400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003569","name":"Ministry of Food and Drug Safety","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003569","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Ministry of Health & Welfare"},{"DOI":"10.13039\/501100003052","name":"Ministry of Trade, Industry and Energy","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003052","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100014188","name":"Ministry of Science and ICT","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100014188","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100002380","name":"Hanyang University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002380","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Korea government"},{"DOI":"10.13039\/501100003665","name":"National IT Industry Promotion Agency","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003665","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Neurosci."],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Cerebral microbleeds (CMBs) are small hemorrhagic lesions visible as hypointense foci on susceptibility-sensitive MRI and are established biomarkers of stroke risk and amyloid-related imaging abnormalities (ARIA-H) in patients receiving anti-amyloid therapy. However, automated detection remains challenging because true CMBs closely resemble veins, calcifications, and susceptibility artifacts. This visual ambiguity results in a persistent precision\u2013recall trade-off, where models optimized for high sensitivity tend to generate excessive false positives, while precision-focused models risk missing clinically relevant lesions. To address this limitation, we propose an attention-enhanced segmentation framework designed to suppress confounding activations while preserving lesion sensitivity.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We developed RLK-UNet with Convolutional Block Attention Modules (CBAM), a single-stage encoder\u2013decoder architecture that redefines skip connections as context-filtered pathways. The encoder incorporates large 13\u00d713 residual local kernel (RLK) convolutions to capture broad contextual information for distinguishing spherical microbleeds from elongated vascular structures. CBAM modules are embedded in all skip connections to selectively enhance lesion-relevant features and suppress irrelevant background responses before feature fusion. The model was trained and evaluated on a multi-site dataset of 506 T2*-GRE and SWI scans, with lesion-level detection assessed using precision, recall, F1-score, and average false positives per scan. Subject-level burden estimation was further evaluated using ARIA-H severity intervals.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      The proposed model achieved state-of-the-art lesion-level performance, with a precision of 0.891, recall of 0.887, F1-score of 0.887, and a markedly reduced false positive rate of 0.83 per subject. Five-fold cross-validation demonstrated stable performance with minimal variance across splits. In lesions \u22643 mm, the model maintained strong detection performance (F1-score 0.869) while effectively controlling false positives. Cross-modality evaluation between T2*-GRE and SWI confirmed robust generalization. Ablation studies verified that CBAM significantly improved precision while preserving sensitivity, and Grad-CAM visualizations demonstrated more spatially focused and clinically interpretable attention patterns. Subject-level CMB counts strongly correlated with ground truth (Spearman\n                      <jats:italic>\u03c1<\/jats:italic>\n                      = 0.93), and severity classification aligned with ARIA-H intervals.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>RLK-UNet with CBAM provides a robust and interpretable solution for automated CMB detection by directly addressing false-positive propagation through attention-guided skip connections. The framework achieves balanced precision and sensitivity within a single-stage architecture and demonstrates reliable subject-level burden estimation aligned with clinically meaningful ARIA-H categories. These findings support its potential application in vascular risk stratification and treatment monitoring in patients undergoing anti-amyloid therapy.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fnins.2026.1743039","type":"journal-article","created":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T07:02:13Z","timestamp":1772607733000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Attention-enhanced segmentation network for automated cerebral microbleed detection and burden assessment"],"prefix":"10.3389","volume":"20","author":[{"given":"Kwon Hwi","family":"Cho","sequence":"first","affiliation":[{"name":"Department of Artificial Intelligence, Hanyang University","place":["Seoul, Republic of Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jonghyun","family":"Jeon","sequence":"additional","affiliation":[{"name":"Department of Neurology, Hanyang University College of Medicine","place":["Seoul, Republic of Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Seonggyu","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, Hanyang University","place":["Seoul, Republic of Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Young Seo","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Neurology, Hanyang University College of Medicine","place":["Seoul, Republic of Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu-Mi","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Preventive Medicine, Hanyang University College of Medicine","place":["Seoul, Republic of Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mi Kyung","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Preventive Medicine, Hanyang University College of Medicine","place":["Seoul, Republic of Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Min-Ho","family":"Shin","sequence":"additional","affiliation":[{"name":"Department of Preventive Medicine, Chonnam National University Medical School","place":["Gwangju, Republic of Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Insung","family":"Chung","sequence":"additional","affiliation":[{"name":"Department of Occupational and Environmental Medicine, Keimyung University School of Medicine","place":["Daegu, Republic of Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sang Baek","family":"Koh","sequence":"additional","affiliation":[{"name":"Department of Preventive Medicine and Institute of Occupational Medicine, Yonsei Wonju College of Medicine","place":["Wonju, Republic of Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hyeon Chang","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Preventive Medicine, Yonsei University College of Medicine","place":["Seoul, Republic of Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chae Jung","family":"Park","sequence":"additional","affiliation":[{"name":"Department of Radiology, Research Institute of Radiological Science, Yongin Severance Hospital, Yonsei University Health System","place":["Yongin, Republic of Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jong-Min","family":"Lee","sequence":"additional","affiliation":[{"name":"Department of Artificial Intelligence, Hanyang University","place":["Seoul, Republic of Korea"]},{"name":"Department of Biomedical Engineering, Hanyang University","place":["Seoul, Republic of Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,3,4]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"934","DOI":"10.1001\/jamaneurol.2016.1017","article-title":"Association of cerebral microbleeds with cognitive decline and dementia","volume":"73","author":"Akoudad","year":"2016","journal-title":"JAMA Neurol."},{"key":"ref2","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 Clin."},{"key":"ref3","doi-asserted-by":"publisher","first-page":"844","DOI":"10.1016\/j.mri.2011.02.028","article-title":"Semiautomated detection of cerebral microbleeds in magnetic resonance images","volume":"29","author":"Barnes","year":"2011","journal-title":"Magn. Reson. Imaging"},{"key":"ref4","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): development of the brain observer MicroBleed scale (BOMBS)","volume":"40","author":"Cordonnier","year":"2009","journal-title":"Stroke"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"335","DOI":"10.1093\/brain\/awq321","article-title":"Brain microbleeds and Alzheimer\u2019s disease: innocent observation or key player?","volume":"134","author":"Cordonnier","year":"2011","journal-title":"Brain"},{"key":"ref6","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":"ref7","doi-asserted-by":"publisher","first-page":"807443","DOI":"10.3389\/fmed.2022.807443","article-title":"Cerebral microbleed automatic detection system based on the \u201cdeep learning.\u201d","volume":"9","author":"Fan","year":"2022","journal-title":"Front. Med."},{"key":"ref8","first-page":"637","article-title":"Histopathologic analysis of foci of signal loss on gradient-echo T2*-weighted MR images in patients with spontaneous intracerebral hemorrhage: evidence of microangiopathy-related microbleeds","volume":"20","author":"Fazekas","year":"1999","journal-title":"AJNR Am. J. Neuroradiol."},{"key":"ref9","author":"Ghafaryasl","year":"2012"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"165","DOI":"10.1016\/S1474-4422(09)70013-4","article-title":"Cerebral microbleeds: a guide to detection and interpretation","volume":"8","author":"Greenberg","year":"2009","journal-title":"Lancet Neurol."},{"key":"ref11","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":"ref12","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":"ref13","doi-asserted-by":"publisher","first-page":"782","DOI":"10.1016\/j.neuroimage.2011.09.015","article-title":"FSL","volume":"62","author":"Jenkinson","year":"2012","journal-title":"NeuroImage"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"e66610","DOI":"10.1371\/journal.pone.0066610","article-title":"Semi-automated detection of cerebral microbleeds on 3.0 T MR images","volume":"8","author":"Kuijf","year":"2013","journal-title":"PLoS One"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"106051","DOI":"10.1016\/j.cmpb.2021.106051","article-title":"Detecting cerebral microbleeds via deep learning with features enhancement by reusing ground truth","volume":"204","author":"Li","year":"2021","journal-title":"Comput. Methods Prog. Biomed."},{"key":"ref16","doi-asserted-by":"crossref","first-page":"1222","DOI":"10.1161\/STROKEAHA.109.572594","article-title":"Antithrombotic drug use, cerebral microbleeds, and intracerebral hemorrhage: a systematic review of published and unpublished studies: a systematic review of published and unpublished studies","volume":"41","author":"Lovelock","year":"2010","journal-title":"Stroke"},{"key":"ref17","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":"ref18","author":"Selvaraju","year":"2017"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"1273013","DOI":"10.3389\/fonc.2023.1273013","article-title":"Development of RLK-Unet: a clinically favorable deep learning algorithm for brain metastasis detection and treatment response assessment","volume":"13","author":"Son","year":"2023","journal-title":"Front. Oncol."},{"key":"ref20","doi-asserted-by":"publisher","first-page":"103029","DOI":"10.1016\/j.media.2023.103029","article-title":"Where is VALDO? Vascular lesions detection and segmentation challenge at MICCAI 2021","volume":"91","author":"Sudre","year":"2024","journal-title":"Med. Image Anal."},{"key":"ref21","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":"ref22","doi-asserted-by":"publisher","first-page":"1310","DOI":"10.1109\/TMI.2010.2046908","article-title":"N4ITK: improved N3 bias correction","volume":"29","author":"Tustison","year":"2010","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"937314","DOI":"10.3389\/fbioe.2022.937314","article-title":"Construction of a medical micro-object cascade network for automated segmentation of cerebral microbleeds in susceptibility weighted imaging","volume":"10","author":"Wei","year":"2022","journal-title":"Front. Bioeng. Biotechnol."},{"key":"ref24","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1007\/978-3-030-01234-2_1","volume-title":"Computer vision \u2013 ECCV 2018","author":"Woo","year":"2018"}],"container-title":["Frontiers in Neuroscience"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnins.2026.1743039\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T07:02:16Z","timestamp":1772607736000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnins.2026.1743039\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,4]]},"references-count":24,"alternative-id":["10.3389\/fnins.2026.1743039"],"URL":"https:\/\/doi.org\/10.3389\/fnins.2026.1743039","relation":{},"ISSN":["1662-453X"],"issn-type":[{"value":"1662-453X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,4]]},"article-number":"1743039"}}