{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T12:13:48Z","timestamp":1783426428244,"version":"3.54.6"},"reference-count":48,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100014219","name":"National Science Fund for Distinguished Young Scholars","doi-asserted-by":"publisher","award":["2022AH020071"],"award-info":[{"award-number":["2022AH020071"]}],"id":[{"id":"10.13039\/501100014219","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003995","name":"Natural Science Foundation of Anhui Province","doi-asserted-by":"publisher","award":["2308085Y48"],"award-info":[{"award-number":["2308085Y48"]}],"id":[{"id":"10.13039\/501100003995","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62106001"],"award-info":[{"award-number":["62106001"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62101491"],"award-info":[{"award-number":["62101491"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62401508"],"award-info":[{"award-number":["62401508"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62476001"],"award-info":[{"award-number":["62476001"]}],"id":[{"id":"10.13039\/501100001809","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":[[2026,5]]},"DOI":"10.1016\/j.media.2026.103971","type":"journal-article","created":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T17:11:36Z","timestamp":1770397896000},"page":"103971","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Diversity-driven MG-MAE: Multi-granularity representation learning for non-salient object segmentation"],"prefix":"10.1016","volume":"110","author":[{"given":"Chengjin","family":"Yu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bin","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8253-1686","authenticated-orcid":false,"given":"Chenchu","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dongsheng","family":"Ruan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5843-2178","authenticated-orcid":false,"given":"Rui","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9737-9437","authenticated-orcid":false,"given":"Huafeng","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaohu","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuo","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.media.2026.103971_bib0001","doi-asserted-by":"crossref","DOI":"10.3389\/fnins.2021.629469","article-title":"Visual illusions in radiology: untrue perceptions in medical images and their implications for diagnostic accuracy","volume":"15","author":"Alexander","year":"2021","journal-title":"Front Neurosci."},{"key":"10.1016\/j.media.2026.103971_bib0002","series-title":"European Conference on Computer Vision","first-page":"205","article-title":"Swin-UNet: UNet-like pure transformer for medical image segmentation","author":"Cao","year":"2022"},{"key":"10.1016\/j.media.2026.103971_bib0003","unstructured":"Chen, J., Lu, Y., Yu, Q., Luo, X., Adeli, E., Wang, Y., Lu, L., Yuille, A. L., Zhou, Y., 2021a. TransUNet: transformers make strong encoders for medical image segmentation. arXiv: 2102.04306."},{"key":"10.1016\/j.media.2026.103971_bib0004","series-title":"International Conference on Machine Learning","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","author":"Chen","year":"2020"},{"key":"10.1016\/j.media.2026.103971_bib0005","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"15750","article-title":"Exploring simple siamese representation learning","author":"Chen","year":"2021"},{"key":"10.1016\/j.media.2026.103971_bib0006","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"9640","article-title":"An empirical study of training self-supervised vision transformers","author":"Chen","year":"2021"},{"key":"10.1016\/j.media.2026.103971_bib0007","series-title":"Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision","first-page":"1970","article-title":"Masked image modeling advances 3d medical image analysis","author":"Chen","year":"2023"},{"key":"10.1016\/j.media.2026.103971_bib0008","series-title":"Medical Image Computing and Computer-Assisted Intervention\u2013MICCAI 2016: 19th International Conference, Athens, Greece, October 17\u201321, 2016, Proceedings, Part II 19","first-page":"424","article-title":"3D U-Net: learning dense volumetric segmentation from sparse annotation","author":"\u00c7i\u00e7ek","year":"2016"},{"key":"10.1016\/j.media.2026.103971_bib0009","doi-asserted-by":"crossref","first-page":"94","DOI":"10.1016\/j.isprsjprs.2020.01.013","article-title":"ResUNet-A: a deep learning framework for semantic segmentation of remotely sensed data","volume":"162","author":"Diakogiannis","year":"2020","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"10.1016\/j.media.2026.103971_bib0010","series-title":"2025 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","first-page":"6890","article-title":"Magma: manifold regularization for maes","author":"Dondera","year":"2025"},{"key":"10.1016\/j.media.2026.103971_bib0011","doi-asserted-by":"crossref","DOI":"10.1007\/s10586-024-04474-8","article-title":"HCA-YOLO: a non-salient object detection method based on hierarchical attention mechanism","volume":"27","author":"Dong","year":"2024","journal-title":"Cluster Comput."},{"key":"10.1016\/j.media.2026.103971_bib0012","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2023.102745","article-title":"A novel multi-attention, multi-scale 3D deep network for coronary artery segmentation","volume":"85","author":"Dong","year":"2023","journal-title":"Med. Image Anal."},{"key":"10.1016\/j.media.2026.103971_bib0013","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., et al., 2020. An image is worth 16\u202f\u202f\u00d7\u202f\u202f16 words: transformers for image recognition at scale. arXiv: 2010.11929."},{"issue":"17","key":"10.1016\/j.media.2026.103971_bib0014","doi-asserted-by":"crossref","first-page":"1928","DOI":"10.3390\/diagnostics14171928","article-title":"Discrepancies between coronary artery calcium score and coronary artery disease severity in computed tomography angiography studies","volume":"14","author":"Ga\u0107","year":"2024","journal-title":"Diagnostics"},{"issue":"6","key":"10.1016\/j.media.2026.103971_bib0015","doi-asserted-by":"crossref","first-page":"2154","DOI":"10.3390\/jcm12062154","article-title":"A novel CT perfusion-based fractional flow reserve algorithm for detecting coronary artery disease","volume":"12","author":"Gao","year":"2023","journal-title":"J. Clin. Med."},{"key":"10.1016\/j.media.2026.103971_bib0016","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"12094","article-title":"Multi-scale high-resolution vision transformer for semantic segmentation","author":"Gu","year":"2022"},{"key":"10.1016\/j.media.2026.103971_bib0017","doi-asserted-by":"crossref","DOI":"10.1016\/j.compbiomed.2022.105620","article-title":"Deep learning techniques for liver and liver tumor segmentation: a review","volume":"147","author":"Gul","year":"2022","journal-title":"Comput. Biol. Med."},{"key":"10.1016\/j.media.2026.103971_bib0018","series-title":"Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision","first-page":"574","article-title":"UNETR: transformers for 3D medical image segmentation","author":"Hatamizadeh","year":"2022"},{"issue":"9","key":"10.1016\/j.media.2026.103971_bib0019","doi-asserted-by":"crossref","first-page":"2763","DOI":"10.1109\/TMI.2023.3264513","article-title":"H2former: an efficient hierarchical hybrid transformer for medical image segmentation","volume":"42","author":"He","year":"2023","journal-title":"IEEE Trans. Med. Imaging"},{"key":"10.1016\/j.media.2026.103971_bib0020","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"16000","article-title":"Masked autoencoders are scalable vision learners","author":"He","year":"2022"},{"key":"10.1016\/j.media.2026.103971_bib0021","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"9729","article-title":"Momentum contrast for unsupervised visual representation learning","author":"He","year":"2020"},{"key":"10.1016\/j.media.2026.103971_bib0022","series-title":"European Conference on Computer Vision","first-page":"444","article-title":"ViC-MAE: self-supervised representation learning from images and video with contrastive masked autoencoders","author":"Hernandez","year":"2024"},{"key":"10.1016\/j.media.2026.103971_bib0023","doi-asserted-by":"crossref","DOI":"10.1016\/j.bspc.2025.108900","article-title":"SETD-Net: multi-scale spatiotemporal enhancement and multi-granularity temporal difference network for depression detection","volume":"112","author":"Huang","year":"2026","journal-title":"Biomed. Signal Process. Control"},{"key":"10.1016\/j.media.2026.103971_bib0024","doi-asserted-by":"crossref","first-page":"2506","DOI":"10.1109\/TPAMI.2023.3336525","article-title":"Contrastive masked autoencoders are stronger vision learners","volume":"46","author":"Huang","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.media.2026.103971_bib0025","doi-asserted-by":"crossref","first-page":"20","DOI":"10.1016\/j.ymeth.2020.05.022","article-title":"Radiomics for precision medicine: current challenges, future prospects, and the proposal of a new framework","volume":"188","author":"Ibrahim","year":"2021","journal-title":"Methods"},{"key":"10.1016\/j.media.2026.103971_bib0026","series-title":"10th International Conference on Learning Representations, ICLR 2022","article-title":"Understanding dimensional collapse in contrastive self-supervised learning","author":"Jing","year":"2022"},{"key":"10.1016\/j.media.2026.103971_bib0027","series-title":"Proceedings of the 29th ACM International Conference on Multimedia","first-page":"2167","article-title":"UACANet: uncertainty augmented context attention for polyp segmentation","author":"Kim","year":"2021"},{"key":"10.1016\/j.media.2026.103971_bib0028","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"7287","article-title":"MPvit: multi-path vision transformer for dense prediction","author":"Lee","year":"2022"},{"issue":"1","key":"10.1016\/j.media.2026.103971_bib0029","doi-asserted-by":"crossref","first-page":"374","DOI":"10.1109\/JBHI.2022.3207597","article-title":"Generalizable pancreas segmentation modeling in CT imaging via meta-learning and latent-space feature flow generation","volume":"27","author":"Li","year":"2022","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"10.1016\/j.media.2026.103971_bib0030","doi-asserted-by":"crossref","first-page":"29191","DOI":"10.52202\/079017-0920","article-title":"MSPE: multi-scale patch embedding prompts vision transformers to any resolution","volume":"37","author":"Liu","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.media.2026.103971_bib0031","unstructured":"Liu, Y., Zhang, S., Chen, J., Chen, K., Lin, D., 2023. Pixmim: rethinking pixel reconstruction in masked image modeling. arXiv: 2303.02416."},{"key":"10.1016\/j.media.2026.103971_bib0032","series-title":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","first-page":"2179","article-title":"Sparsity aware minimum error entropy algorithms","author":"Ma","year":"2015"},{"key":"10.1016\/j.media.2026.103971_bib0033","series-title":"2016 Fourth International Conference on 3D Vision (3DV)","first-page":"565","article-title":"V-Net: fully convolutional neural networks for volumetric medical image segmentation","author":"Milletari","year":"2016"},{"key":"10.1016\/j.media.2026.103971_bib0034","series-title":"The Twelfth International Conference on Learning Representations","article-title":"R-MAE: regions meet masked autoencoders","author":"Nguyen","year":"2024"},{"key":"10.1016\/j.media.2026.103971_bib0035","unstructured":"Ren, S., Wei, F., Albanie, S., Zhang, Z., Hu, H., 2023. Deepmim: deep supervision for masked image modeling. arXiv: 2303.08817."},{"key":"10.1016\/j.media.2026.103971_bib0036","series-title":"Medical Image Computing and Computer-assisted Intervention\u2013MICCAI 2015: 18th International Conference, Munich, Germany, October 5\u20139, 2015, Proceedings, Part III 18","first-page":"234","article-title":"U-Net: convolutional networks for biomedical image segmentation","author":"Ronneberger","year":"2015"},{"key":"10.1016\/j.media.2026.103971_bib0037","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"2132","article-title":"Siamese image modeling for self-supervised vision representation learning","author":"Tao","year":"2023"},{"key":"10.1016\/j.media.2026.103971_bib0038","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.media.2026.103971_bib0039","series-title":"Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision","first-page":"7860","article-title":"Fremim: fourier transform meets masked image modeling for medical image segmentation","author":"Wang","year":"2024"},{"key":"10.1016\/j.media.2026.103971_bib0040","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"14668","article-title":"Masked feature prediction for self-supervised visual pre-training","author":"Wei","year":"2022"},{"key":"10.1016\/j.media.2026.103971_bib0041","article-title":"MGIPS-CL: multimodal ner with multi-granularity interweave and implicit positive sample contrastive learning","author":"Wei","year":"2025","journal-title":"Appl. Soft Comput."},{"key":"10.1016\/j.media.2026.103971_bib0042","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"9653","article-title":"SimMIM: a simple framework for masked image modeling","author":"Xie","year":"2022"},{"key":"10.1016\/j.media.2026.103971_bib0043","series-title":"2023 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","first-page":"3587","article-title":"MGFuseSeg: attention-guided multi-granularity fusion for medical image segmentation","author":"Xu","year":"2023"},{"key":"10.1016\/j.media.2026.103971_bib0044","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"438","article-title":"Multiscale graph and multi-step cross-frame mamba for myocarditis lesion segmentation","author":"Yu","year":"2025"},{"key":"10.1016\/j.media.2026.103971_bib0045","doi-asserted-by":"crossref","first-page":"27127","DOI":"10.52202\/068431-1967","article-title":"How mask matters: towards theoretical understandings of masked autoencoders","volume":"35","author":"Zhang","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.media.2026.103971_bib0046","doi-asserted-by":"crossref","first-page":"723","DOI":"10.1109\/TMI.2023.3319720","article-title":"An anatomy-and topology-preserving framework for coronary artery segmentation","volume":"43","author":"Zhang","year":"2023","journal-title":"IEEE Trans. Med. Imaging"},{"key":"10.1016\/j.media.2026.103971_bib0047","unstructured":"Zhou, H.-Y., Guo, J., Zhang, Y., Yu, L., Wang, L., Yu, Y., 2021. nnformer: interleaved transformer for volumetric segmentation. arXiv: 2109.03201."},{"key":"10.1016\/j.media.2026.103971_bib0048","article-title":"Advancing volumetric medical image segmentation via global-local masked autoencoders","author":"Zhuang","year":"2025","journal-title":"IEEE Trans. Med. Imaging"}],"container-title":["Medical Image Analysis"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S136184152600040X?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S136184152600040X?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T11:17:23Z","timestamp":1783423043000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S136184152600040X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":48,"alternative-id":["S136184152600040X"],"URL":"https:\/\/doi.org\/10.1016\/j.media.2026.103971","relation":{},"ISSN":["1361-8415"],"issn-type":[{"value":"1361-8415","type":"print"}],"subject":[],"published":{"date-parts":[[2026,5]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Diversity-driven MG-MAE: Multi-granularity representation learning for non-salient object segmentation","name":"articletitle","label":"Article Title"},{"value":"Medical Image Analysis","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.media.2026.103971","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"103971"}}