{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T05:03:49Z","timestamp":1790053429276,"version":"4.0.1"},"reference-count":38,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T00:00:00Z","timestamp":1790035200000},"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. Neurol."],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Non-contrast computed tomography (NCCT) is widely used for post-treatment monitoring of patients with ischemic stroke due to its rapid acquisition, low cost, and non-invasiveness. Segmentation of ischemic lesions on NCCT images is critical for assessing disease severity and guiding clinical decision-making.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We propose an ensemble-based semi-supervised segmentation (ESS) framework to reduce the dependence of convolutional neural networks (CNNs) on a large number of manual annotations. The proposed method mainly consists of two components: first, strong data augmentation is introduced to increase sample diversity and alleviate overfitting in the presence of limited labeled data; second, a parameter-free ensemble module is adopted to generate more stable supervision signals for unlabeled samples and improve the reliability of pseudo-labels by fusing the predictions of the two student models. The proposed ESS is evaluated on a manually annotated follow-up NCCT dataset consisting of 9,020 image slices.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>ESS consistently achieves the highest Dice coefficient among all compared methods under all four labeled-data ratios, with a more pronounced performance advantage when labeled data are scarce.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>These results demonstrate the effectiveness of ESS for semi-supervised segmentation of follow-up NCCT under limited annotation conditions.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fneur.2026.1910269","type":"journal-article","created":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T04:22:02Z","timestamp":1790050922000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Parameter-free dual-student ensemble for semi-supervised ischemic stroke segmentation on follow-up NCCT"],"prefix":"10.3389","volume":"17","author":[{"given":"Yuqing","family":"Sha","sequence":"first","affiliation":[{"name":"School of Computer and Communication Engineering, University of Science and Technology Beijing","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Long","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer and Communication Engineering, University of Science and Technology Beijing","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chao","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Computer and Communication Engineering, University of Science and Technology Beijing","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ximing","family":"Nie","sequence":"additional","affiliation":[{"name":"Department of Neurology, Beijing Tiantan Hospital, Capital Medical University","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,9,22]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"769","DOI":"10.4103\/1673-5374.382228","article-title":"Machine learning applications in stroke medicine: advancements, challenges, and future Prospectives","volume":"19","author":"Daidone","year":"2024","journal-title":"Neural Regen Res"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"e16481","DOI":"10.1111\/ene.16481","article-title":"Global, regional, and National Epidemiology of ischemic stroke from 1990 to 2021","volume":"31","author":"Hou","year":"2024","journal-title":"Eur J Neurol"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"26331055241292600","DOI":"10.1177\/26331055241292600","article-title":"Ischemic stroke: pathophysiology and evolving treatment approaches","volume":"19","author":"Majumder","year":"2024","journal-title":"Neuroscience Insights"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"e0277573","DOI":"10.1371\/journal.pone.0277573","article-title":"Artificial intelligence for localization of the acute ischemic stroke by non-contrast computed tomography","volume":"17","author":"Kaothanthong","year":"2022","journal-title":"PLoS One"},{"key":"ref5","first-page":"410","author":"Thoma","year":"2025"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"1643479","DOI":"10.3389\/fnins.2025.1643479","article-title":"Automated ischemic stroke lesion detection on non-contrast brain CT: a large-scale clinical feasibility test AI stroke lesion detection on NCCT","volume":"19","author":"Heo","year":"2025","journal-title":"Front Neurosci"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"2623","DOI":"10.7150\/ijms.101166","article-title":"Regional reliability of combining CT angiography-source image and non-contrast CT in acute ischemic stroke","volume":"21","author":"Xu","year":"2024","journal-title":"Int J Med Sci"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"e70073","DOI":"10.1111\/ene.70073","article-title":"Bridging the gaps: addressing inequities in neurological care for underserved populations","volume":"32","author":"Uwishema","year":"2025","journal-title":"Eur J Neurol"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"2456550","DOI":"10.1155\/2022\/2456550","article-title":"Deep learning in ischemic stroke imaging analysis: a comprehensive review","volume":"2022","author":"Cui","year":"2022","journal-title":"Biomed Res Int"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"192","DOI":"10.1186\/s12911-023-02289-y","article-title":"CNN-res: deep learning framework for segmentation of acute ischemic stroke lesions on multimodal MRI images","volume":"23","author":"Gheibi","year":"2023","journal-title":"BMC Med Inform Decis Mak"},{"key":"ref11","first-page":"724","author":"Aboudi","year":"2022"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"100145","DOI":"10.1016\/j.neuri.2023.100145","article-title":"Automatic brain ischemic stroke segmentation with deep learning: a review","volume":"3","author":"Abbasi","year":"2023","journal-title":"Neurosci Inform"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"41485","DOI":"10.1007\/s11042-023-16689-9","article-title":"A robust ischemic stroke lesion segmentation technique using two-pathway 3D deep neural network in MR images","volume":"83","author":"Bal","year":"2024","journal-title":"Multimed Tools Appl"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"107157","DOI":"10.1016\/j.cmpb.2022.107157","article-title":"A lightweight asymmetric U-net framework for acute ischemic stroke lesion segmentation in CT and CTP images","volume":"226","author":"Kumar","year":"2022","journal-title":"Comput Methods Prog Biomed"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"e17934","DOI":"10.1002\/mp.17934","article-title":"Prompt-enhanced multi-task learning network for acute ischemic stroke lesion and penumbra segmentation using computed tomography perfusion scans","volume":"52","author":"Wang","year":"2025","journal-title":"Med Phys"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"1853","DOI":"10.1007\/s13246-025-01626-x","article-title":"3D CoAt U SegNet-enhanced deep learning framework for accurate segmentation of acute ischemic stroke lesions from non-contrast CT scans","volume":"48","author":"Nag","year":"2025","journal-title":"Phys Eng Sci Med"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"126319","DOI":"10.1109\/ACCESS.2025.3586745","article-title":"DB-net: a dual-branch hybrid network for stroke lesion segmentation on non-contrast CT images","volume":"13","author":"Jia","year":"2025","journal-title":"IEEE Access"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"33363","DOI":"10.1038\/s41598-025-17337-y","article-title":"Automated deep U-net model for ischemic stroke lesion segmentation in the sub-acute phase","volume":"15","author":"E","year":"2025","journal-title":"Sci Rep"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"123052","DOI":"10.1016\/j.eswa.2023.123052","article-title":"Deep semi-supervised learning for medical image segmentation: a review","volume":"245","author":"Han","year":"2024","journal-title":"Expert Syst Appl"},{"key":"ref20","article-title":"Temporal ensembling for semi-supervised learning","author":"Laine","year":"2016","journal-title":"arXiv:1610.02242"},{"key":"ref21","first-page":"1195","author":"Tarvainen","year":"2017"},{"key":"ref22","first-page":"5937","author":"Yang","year":"2021"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"175010","DOI":"10.1088\/1361-6560\/ac89c8","article-title":"A regularization-driven mean teacher model based on semi-supervised learning for medical image segmentation","volume":"67","author":"Wang","year":"2022","journal-title":"Phys Med Biol"},{"key":"ref24","first-page":"6727","author":"Ke","year":"2019"},{"key":"ref25","first-page":"429","author":"Ke","year":"2020"},{"key":"ref26","first-page":"2613","author":"Chen","year":"2021"},{"key":"ref27","first-page":"11514","author":"Bai","year":"2023"},{"key":"ref28","doi-asserted-by":"publisher","first-page":"3296","DOI":"10.1007\/s11263-024-02328-9","article-title":"PICK: predict and mask for semi-supervised medical image segmentation","volume":"133","author":"Zeng","year":"2025","journal-title":"Int J Comput Vis"},{"key":"ref29","doi-asserted-by":"publisher","first-page":"106391","DOI":"10.1016\/j.compbiomed.2022.106391","article-title":"Data augmentation for medical imaging: a systematic literature review","volume":"152","author":"Garcea","year":"2023","journal-title":"Comput Biol Med"},{"key":"ref30","doi-asserted-by":"publisher","first-page":"107602","DOI":"10.1016\/j.engappai.2023.107602","article-title":"Enhanced transfer learning with data augmentation","volume":"129","author":"Su","year":"2024","journal-title":"Eng Appl Artif Intell"},{"key":"ref31","first-page":"6022","author":"Yun","year":"2019"},{"key":"ref32","first-page":"1","author":"Jiang","year":"2024"},{"key":"ref33","doi-asserted-by":"publisher","first-page":"443","DOI":"10.1007\/s13246-022-01110-w","article-title":"Multi-task semantic segmentation of CT images for COVID-19 infections using DeepLabV3+ based on dilated residual network","volume":"45","author":"Polat","year":"2022","journal-title":"Phys Eng Sci Med"},{"key":"ref34","doi-asserted-by":"publisher","first-page":"348","DOI":"10.3390\/electronics12020348","article-title":"Semi-supervised remote sensing image semantic segmentation method based on deep learning","volume":"12","author":"Li","year":"2023","journal-title":"Electronics"},{"key":"ref35","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-01234-2_49","volume-title":"Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation","author":"Chen","year":"2018"},{"key":"ref36","doi-asserted-by":"publisher","first-page":"3603","DOI":"10.3390\/rs12213603","article-title":"Semi-supervised remote sensing image semantic segmentation via consistency regularization and average update of pseudo-label","volume":"12","author":"Wang","year":"2020","journal-title":"Remote Sens"},{"key":"ref37","doi-asserted-by":"publisher","first-page":"793","DOI":"10.1109\/TCSVT.2022.3206496","article-title":"Adversarial dual-student with differentiable spatial warping for semi-supervised semantic segmentation","volume":"33","author":"Cao","year":"2023","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"ref38","doi-asserted-by":"publisher","first-page":"107882","DOI":"10.1016\/j.neunet.2025.107882","article-title":"A lightweight dual-student mean teacher semi-supervised semantic segmentation method for skin lesions","volume":"192","author":"Zhang","year":"2025","journal-title":"Neural Netw"}],"container-title":["Frontiers in Neurology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fneur.2026.1910269\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T04:22:03Z","timestamp":1790050923000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fneur.2026.1910269\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,22]]},"references-count":38,"alternative-id":["10.3389\/fneur.2026.1910269"],"URL":"https:\/\/doi.org\/10.3389\/fneur.2026.1910269","relation":{},"ISSN":["1664-2295"],"issn-type":[{"value":"1664-2295","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,22]]},"article-number":"1910269"}}