{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T04:47:03Z","timestamp":1785818823127,"version":"3.56.0"},"reference-count":51,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T00:00:00Z","timestamp":1785801600000},"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. Med."],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Brain tissue segmentation in magnetic resonance imaging (MRI) is a fundamental step in quantitative neuroimaging and supports the analysis of structural brain alterations associated with aging. However, voxel-level annotation is expensive and labor-intensive, which limits the development of artificial intelligence methods in annotation-scarce neuroimaging settings. Existing mutual-information-based unsupervised segmentation methods mainly model consistency across different views of the same sample, while the representation derived from draft segmentation remains underexplored for mutual information modeling.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>In this paper, we propose Post-MI, an unsupervised brain tissue segmentation method that estimates mutual information between deep features extracted from the raw image and deep features derived from the probability map of the draft segmentation. A post-training strategy is introduced to enable this objective to refine the segmentation network after draft segmentation generation. In addition, edge information and a discriminative loss are incorporated to enhance boundary preservation and inter-class separability. We evaluate the proposed method primarily on IBSR-18 and further conduct exploratory experiments on BraTS2018.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>On IBSR-18, Post-MI achieves a mean intersection over union of 0.3635 and a mean Dice score of 0.4661, outperforming the compared unsupervised baselines. Ablation experiments further verify the positive contributions of edge information and discriminative loss. On BraTS2018, exploratory results indicate that more complex tumor structures and weaker boundaries remain challenging for the current method.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>Post-MI provides a feasible solution for brain MRI segmentation under annotation-scarce conditions and may facilitate quantitative structural brain analysis in aging-related neuroimaging research and other studies of age-related neurological conditions where large-scale manual delineation is difficult to obtain.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fmed.2026.1852159","type":"journal-article","created":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T04:27:40Z","timestamp":1785817660000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Post-MI: unsupervised brain tissue segmentation via post-maximized mutual information"],"prefix":"10.3389","volume":"13","author":[{"given":"Ke","family":"Niu","sequence":"first","affiliation":[{"name":"Computer School, Beijing Information Science and Technology University","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiadong","family":"Guo","sequence":"additional","affiliation":[{"name":"Computer School, Beijing Information Science and Technology University","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ming","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Pediatrics, Zhongshan Hospital Xiamen University","place":["Xiamen, Fujian, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhongmin","family":"Guo","sequence":"additional","affiliation":[{"name":"Computer School, Beijing Information Science and Technology University","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiuyun","family":"Cai","sequence":"additional","affiliation":[{"name":"Computer School, Beijing Information Science and Technology University","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Naian","family":"Xiao","sequence":"additional","affiliation":[{"name":"Department of Neurology, The Third Hospital of Xiamen","place":["Xiamen, Fujian, China"]},{"name":"Department of Neurology and Geriatrics, Fujian Institute of Geriatrics, Fujian Medical University Union Hospital","place":["Fuzhou, Fujian, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bin","family":"Jiang","sequence":"additional","affiliation":[{"name":"Department of Neurology and Department of Neuroscience, The First Affiliated Hospital of Xiamen University, School of Medicine, Xiamen University","place":["Xiamen, Fujian, China"]},{"name":"Xiamen Medical Quality Control Center for Neurology","place":["Xiamen, Fujian, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Heng","family":"Miao","sequence":"additional","affiliation":[{"name":"Department of Ophthalmology, Peking University People's Hospital","place":["Beijing, China"]},{"name":"Beijing Key Laboratory of Ocular Disease and Optometry Science, Peking University People's Hospital","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,8,4]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"20852","DOI":"10.1109\/CVPR52734.2025.01942","article-title":"nnWNet: rethinking the use of transformers in biomedical image segmentation and calling for a unified evaluation benchmark","author":"Zhou","year":"2025","journal-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition"},{"key":"B2","doi-asserted-by":"publisher","first-page":"10435","DOI":"10.1109\/CVPR52734.2025.00976","article-title":"EffiDec3D: an optimized decoder for high-performance and efficient 3D medical image segmentation","author":"Rahman","year":"2025","journal-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition"},{"key":"B3","doi-asserted-by":"publisher","first-page":"25982","DOI":"10.1109\/CVPR52734.2025.02420","article-title":"Incomplete multi-modal brain tumor segmentation via learnable sorting state space model","author":"Zhang","year":"2025","journal-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition"},{"key":"B4","doi-asserted-by":"publisher","first-page":"5197","DOI":"10.1109\/CVPR52734.2025.00490","article-title":"SuperLightNet: lightweight parameter aggregation network for multimodal brain tumor segmentation","author":"Yu","year":"2025","journal-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition"},{"key":"B5","doi-asserted-by":"publisher","first-page":"1034","DOI":"10.3390\/bioengineering11101034","article-title":"Advances in medical image segmentation: a comprehensive review of traditional, deep learning and hybrid approaches","volume":"11","author":"Xu","year":"2024","journal-title":"Bioengineering"},{"key":"B6","doi-asserted-by":"publisher","first-page":"654","DOI":"10.1038\/s41467-024-44824-z","article-title":"Segment anything in medical images","volume":"15","author":"Ma","year":"2024","journal-title":"Nat Commun"},{"key":"B7","doi-asserted-by":"publisher","first-page":"1283","DOI":"10.1038\/s41597-024-04159-2","article-title":"MedSegBench: a comprehensive benchmark for medical image segmentation in diverse data modalities","volume":"11","author":"Ku\u015f","year":"2024","journal-title":"Sci Data."},{"key":"B8","doi-asserted-by":"publisher","first-page":"52","DOI":"10.3390\/tomography11050052","article-title":"Medical image segmentation: a comprehensive review of deep learning-based methods","volume":"11","author":"Gao","year":"2025","journal-title":"Tomography"},{"key":"B9","doi-asserted-by":"publisher","first-page":"433","DOI":"10.3390\/info16060433","article-title":"A review of non-fully supervised deep learning for medical image segmentation","volume":"16","author":"Zhang","year":"2025","journal-title":"Information"},{"key":"B10","doi-asserted-by":"publisher","first-page":"6486","DOI":"10.1038\/s41467-025-61754-6","article-title":"Generative AI enables medical image segmentation in ultra low-data regimes","volume":"16","author":"Zhang","year":"2025","journal-title":"Nat Commun"},{"key":"B11","doi-asserted-by":"publisher","first-page":"20830","DOI":"10.1109\/CVPR52734.2025.01940","article-title":"Show and segment: universal medical image segmentation via in-context learning","author":"Gao","year":"2025","journal-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition"},{"key":"B12","doi-asserted-by":"publisher","first-page":"20863","DOI":"10.1109\/CVPR52734.2025.01943","article-title":"VISTA3D: a unified segmentation foundation model for 3D medical imaging","author":"He","year":"2025","journal-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition"},{"key":"B13","doi-asserted-by":"publisher","first-page":"11735","DOI":"10.1038\/s41598-024-61798-6","article-title":"A deep learning model for brain segmentation across pediatric and adult populations","volume":"14","author":"Simarro","year":"2024","journal-title":"Sci Rep"},{"key":"B14","doi-asserted-by":"publisher","first-page":"2","DOI":"10.1038\/s41698-024-00789-2","article-title":"A review of deep learning for brain tumor analysis in MRI","volume":"9","author":"Dorfner","year":"2025","journal-title":"NPJ Precis Oncol"},{"key":"B15","doi-asserted-by":"publisher","first-page":"9865","DOI":"10.1109\/ICCV.2019.00996","article-title":"Invariant information clustering for unsupervised image classification and segmentation","author":"Ji","year":"2019","journal-title":"Proceedings of the IEEE\/CVF international conference on computer vision"},{"key":"B16","doi-asserted-by":"publisher","first-page":"142","DOI":"10.1007\/978-3-030-58571-6_9","article-title":"Autoregressive unsupervised image segmentation","author":"Ouali","year":"2020","journal-title":"European conference on computer vision"},{"key":"B17","doi-asserted-by":"publisher","first-page":"6931","DOI":"10.1109\/LRA.2021.3095311","article-title":"Unsupervised image segmentation by mutual information maximization and adversarial regularization","volume":"6","author":"Mirsadeghi","year":"2021","journal-title":"IEEE Rob Autom Lett"},{"key":"B18","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1007\/978-3-030-92659-5_2","article-title":"InfoSeg: unsupervised semantic image segmentation with mutual information maximization","author":"Harb","year":"2021","journal-title":"DAGM german conference on pattern recognition"},{"key":"B19","doi-asserted-by":"publisher","first-page":"129287","DOI":"10.1016\/j.neucom.2024.129287","article-title":"Semi-supervised medical image segmentation via collaborative intra-inter contrastive learning and multi-perspective consistency","volume":"621","author":"Du","year":"2025","journal-title":"Neurocomputing"},{"key":"B20","doi-asserted-by":"publisher","first-page":"111216","DOI":"10.1016\/j.patcog.2024.111216","article-title":"Multi-consistency for semi-supervised medical image segmentation via diffusion models","volume":"161","author":"Chen","year":"2025","journal-title":"Pattern Recognit"},{"key":"B21","doi-asserted-by":"publisher","first-page":"112310","DOI":"10.1016\/j.patcog.2025.112310","article-title":"Semi-supervised medical image segmentation via pseudo-labeling refinement and dual-adaptive adjustment schemes","volume":"171","author":"Zheng","year":"2025","journal-title":"Pattern Recognit"},{"key":"B22","doi-asserted-by":"publisher","first-page":"110020","DOI":"10.1016\/j.patcog.2023.110020","article-title":"Semi-supervised medical image segmentation via hard positives oriented contrastive learning","volume":"146","author":"Tang","year":"2024","journal-title":"Pattern Recognit"},{"key":"B23","doi-asserted-by":"publisher","first-page":"108570","DOI":"10.1016\/j.compbiomed.2024.108570","article-title":"Semi-supervised multi-modal medical image segmentation with unified translation","volume":"176","author":"Sun","year":"2024","journal-title":"Comput Biol Med"},{"key":"B24","doi-asserted-by":"publisher","first-page":"111722","DOI":"10.1016\/j.patcog.2025.111722","article-title":"Prototype-augmented mean teacher for robust semi-supervised medical image segmentation","volume":"166","author":"Zhang","year":"2025","journal-title":"Pattern Recognit"},{"key":"B25","doi-asserted-by":"publisher","first-page":"103150","DOI":"10.1016\/j.media.2024.103150","article-title":"Boundary-aware information maximization for self-supervised medical image segmentation","volume":"94","author":"Peng","year":"2024","journal-title":"Med Image Anal"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.66","article-title":"Semantic instance segmentation with a discriminative loss function","author":"De Brabandere","year":"2017","journal-title":"arXiv"},{"key":"B27","doi-asserted-by":"publisher","first-page":"565","DOI":"10.1109\/3DV.2016.79","article-title":"V-Net: fully convolutional neural networks for volumetric medical image segmentation","author":"Milletari","year":"2016","journal-title":"2016 fourth international conference on 3D vision (3DV)"},{"key":"B28","doi-asserted-by":"publisher","first-page":"138","DOI":"10.1007\/978-3-319-55524-9_14","article-title":"DeepMedic for brain tumor segmentation","author":"Kamnitsas","year":"2016","journal-title":"International workshop on brainlesion: glioma, multiple sclerosis, stroke and traumatic brain injuries"},{"key":"B29","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1016\/j.media.2016.10.004","article-title":"Efficient multi-scale 3D CNN with fully connected CRF for accurate brain lesion segmentation","volume":"36","author":"Kamnitsas","year":"2017","journal-title":"Med Image Anal"},{"key":"B30","doi-asserted-by":"publisher","first-page":"103302","DOI":"10.1016\/j.media.2024.103302","article-title":"Diversity matters: cross-head mutual mean-teaching for semi-supervised medical image segmentation","volume":"97","author":"Li","year":"2024","journal-title":"Med Image Anal"},{"key":"B31","doi-asserted-by":"publisher","first-page":"10052","DOI":"10.1109\/ICCV48922.2021.00990","article-title":"Unsupervised semantic segmentation by contrasting object mask proposals","author":"Van Gansbeke","year":"2021","journal-title":"Proceedings of the IEEE\/CVF international conference on computer vision"},{"key":"B32","article-title":"W-Net: a deep model for fully unsupervised image segmentation","author":"Xia","year":"2017","journal-title":"arXiv"},{"key":"B33","doi-asserted-by":"publisher","first-page":"8055","DOI":"10.1109\/TIP.2020.3011269","article-title":"Unsupervised learning of image segmentation based on differentiable feature clustering","volume":"29","author":"Kim","year":"2020","journal-title":"IEEE Trans Image Process"},{"key":"B34","doi-asserted-by":"publisher","first-page":"330","DOI":"10.1016\/j.neucom.2021.08.102","article-title":"Deep level set learning for optic disc and cup segmentation","volume":"464","author":"Yin","year":"2021","journal-title":"Neurocomputing"},{"key":"B35","doi-asserted-by":"publisher","first-page":"1543","DOI":"10.1109\/ICASSP.2018.8462533","article-title":"Unsupervised image segmentation by backpropagation","author":"Kanezaki","year":"2018","journal-title":"2018 IEEE international conference on acoustics, speech and signal processing (ICASSP)"},{"key":"B36","doi-asserted-by":"publisher","first-page":"1100","DOI":"10.1109\/ISBI.2018.8363763","article-title":"Self-learning to detect and segment cysts in lung CT images without manual annotation","author":"Zhang","year":"2018","journal-title":"2018 IEEE 15th international symposium on biomedical imaging (ISBI 2018)"},{"key":"B37","doi-asserted-by":"publisher","first-page":"1496","DOI":"10.1109\/ICIP40778.2020.9190849","article-title":"You only need the image: unsupervised few-shot semantic segmentation with co-guidance network","author":"Wang","year":"2020","journal-title":"2020 IEEE international conference on image processing (ICIP)"},{"key":"B38","doi-asserted-by":"publisher","first-page":"1633","DOI":"10.1109\/EMBC44109.2020.9175987","article-title":"MRI-SegFlow: a novel unsupervised deep learning pipeline enabling accurate vertebral segmentation of MRI images","author":"Kuang","year":"2020","journal-title":"2020 42nd annual international conference of the IEEE engineering in medicine & biology society (EMBC)"},{"key":"B39","doi-asserted-by":"publisher","first-page":"1781","DOI":"10.1109\/ISBI48211.2021.9433854","article-title":"3D unsupervised kidney graft segmentation based on deep learning and multi-sequence MRI","author":"Milecki","year":"2021","journal-title":"2021 IEEE 18th international symposium on biomedical imaging (ISBI)"},{"key":"B40","doi-asserted-by":"publisher","first-page":"30365","DOI":"10.1109\/CVPR52734.2025.02827","article-title":"UCOD-DPL: unsupervised camouflaged object detection via dynamic pseudo-label learning","author":"Yan","year":"2025","journal-title":"Proceedings of the computer vision and pattern recognition conference"},{"key":"B41","doi-asserted-by":"publisher","first-page":"20053","DOI":"10.1109\/ICCV51701.2025.01865","article-title":"Escnet: edge-semantic collaborative network for camouflaged object detection","author":"Ye","year":"2025","journal-title":"Proceedings of the IEEE\/CVF international conference on computer vision"},{"key":"B42","article-title":"Learning deep representations by mutual information estimation and maximization","author":"Hjelm","year":"2018","journal-title":"arXiv"},{"key":"B43","first-page":"531","article-title":"Mutual information neural estimation","author":"Belghazi","year":"2018","journal-title":"International conference on machine learning"},{"key":"B44","doi-asserted-by":"publisher","first-page":"9928","DOI":"10.1109\/ICCV48922.2021.00978","article-title":"Clustering by maximizing mutual information across views","author":"Do","year":"2021","journal-title":"Proceedings of the IEEE\/CVF international conference on computer vision"},{"key":"B45","article-title":"On mutual information maximization for representation learning","author":"Tschannen","year":"2019","journal-title":"arXiv"},{"key":"B46","doi-asserted-by":"publisher","first-page":"311","DOI":"10.1007\/978-3-030-11726-9_28","article-title":"3D MRI brain tumor segmentation using autoencoder regularization","author":"Myronenko","year":"2018","journal-title":"International MICCAI brainlesion workshop"},{"key":"B47","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1007\/978-3-319-24574-4_28","article-title":"U-Net: convolutional networks for biomedical image segmentation","author":"Ronneberger","year":"2015","journal-title":"International conference on medical image computing and computer-assisted intervention"},{"key":"B48","article-title":"f-GAN: training generative neural samplers using variational divergence minimization","volume-title":"Advances in Neural Information Processing Systems 29","author":"Nowozin","year":"2016"},{"key":"B49","doi-asserted-by":"publisher","first-page":"8827","DOI":"10.1109\/CVPR.2019.00903","article-title":"JSIS3D: joint semantic-instance segmentation of 3D point clouds with multi-task pointwise networks and multi-value conditional random fields","author":"Pham","year":"2019","journal-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition"},{"key":"B50","doi-asserted-by":"publisher","first-page":"431","DOI":"10.1016\/j.neuroimage.2008.10.066","article-title":"Online resource for validation of brain segmentation methods","volume":"45","author":"Shattuck","year":"2009","journal-title":"Neuroimage"},{"key":"B51","doi-asserted-by":"publisher","first-page":"1993","DOI":"10.1109\/TMI.2014.2377694","article-title":"The multimodal brain tumor image segmentation benchmark (BRATS)","volume":"34","author":"Menze","year":"2014","journal-title":"IEEE Trans Med Imaging"}],"container-title":["Frontiers in Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1852159\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T04:27:41Z","timestamp":1785817661000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1852159\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,4]]},"references-count":51,"alternative-id":["10.3389\/fmed.2026.1852159"],"URL":"https:\/\/doi.org\/10.3389\/fmed.2026.1852159","relation":{},"ISSN":["2296-858X"],"issn-type":[{"value":"2296-858X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,4]]},"article-number":"1852159"}}