{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T20:42:49Z","timestamp":1792788169508,"version":"4.5.0"},"reference-count":59,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2024,8,23]],"date-time":"2024-08-23T00:00:00Z","timestamp":1724371200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Medical Image Analysis"],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1016\/j.media.2024.103304","type":"journal-article","created":{"date-parts":[[2024,8,17]],"date-time":"2024-08-17T22:44:45Z","timestamp":1723934685000},"page":"103304","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":28,"special_numbering":"C","title":["Rethinking masked image modelling for medical image representation"],"prefix":"10.1016","volume":"98","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6644-1250","authenticated-orcid":false,"given":"Yutong","family":"Xie","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7419-6240","authenticated-orcid":false,"given":"Lin","family":"Gu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3712-3691","authenticated-orcid":false,"given":"Tatsuya","family":"Harada","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianpeng","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9273-2847","authenticated-orcid":false,"given":"Yong","family":"Xia","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qi","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.media.2024.103304_b1","series-title":"Publicly available clinical BERT embeddings","author":"Alsentzer","year":"2019"},{"key":"10.1016\/j.media.2024.103304_b2","unstructured":"Bao, H., Dong, L., Piao, S., Wei, F., 2022. BEiT: BERT Pre-Training of Image Transformers. In: International Conference on Learning Representations. ICLR."},{"key":"10.1016\/j.media.2024.103304_b3","series-title":"Medical Image Computing and Computer Assisted Intervention\u2013MICCAI 2022: 25th International Conference, Singapore, September 18\u201322, 2022, Proceedings, Part VIII","first-page":"88","article-title":"Uni4Eye: Unified 2D and 3D self-supervised pre-training via masked image modeling transformer for ophthalmic image classification","author":"Cai","year":"2022"},{"key":"10.1016\/j.media.2024.103304_b4","series-title":"ICCV","article-title":"Emerging properties in self-supervised vision transformers","author":"Caron","year":"2021"},{"key":"10.1016\/j.media.2024.103304_b5","series-title":"NeurIPS","article-title":"Contrastive learning of global and local features for medical image segmentation with limited annotations","volume":"Vol. 33","author":"Chaitanya","year":"2020"},{"key":"10.1016\/j.media.2024.103304_b6","doi-asserted-by":"crossref","unstructured":"Chen, Z., Agarwal, D., Aggarwal, K., Safta, W., Balan, M.M., Brown, K., 2023. Masked image modeling advances 3d medical image analysis. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision. pp. 1970\u20131980.","DOI":"10.1109\/WACV56688.2023.00201"},{"key":"10.1016\/j.media.2024.103304_b7","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2019.101539","article-title":"Self-supervised learning for medical image analysis using image context restoration","volume":"58","author":"Chen","year":"2019","journal-title":"Med. Image Anal."},{"key":"10.1016\/j.media.2024.103304_b8","series-title":"Medical Image Computing and Computer Assisted Intervention\u2013MICCAI 2022: 25th International Conference, Singapore, September 18\u201322, 2022, Proceedings, Part V","first-page":"679","article-title":"Multi-modal masked autoencoders for medical vision-and-language pre-training","author":"Chen","year":"2022"},{"key":"10.1016\/j.media.2024.103304_b9","series-title":"ICML","article-title":"A simple framework for contrastive learning of visual representations","author":"Chen","year":"2020"},{"key":"10.1016\/j.media.2024.103304_b10","series-title":"ICCV","article-title":"An empirical study of training self-supervised vision transformers","author":"Chen","year":"2021"},{"key":"10.1016\/j.media.2024.103304_b11","series-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"issue":"8","key":"10.1016\/j.media.2024.103304_b12","doi-asserted-by":"crossref","first-page":"2092","DOI":"10.1109\/TMI.2021.3071951","article-title":"Echo-SyncNet: self-supervised cardiac view synchronization in echocardiography","volume":"40","author":"Dezaki","year":"2021","journal-title":"IEEE Trans. Med. Imaging"},{"key":"10.1016\/j.media.2024.103304_b13","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., et al., 2021. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. In: International Conference on Learning Representations. ICLR."},{"key":"10.1016\/j.media.2024.103304_b14","series-title":"NeurIPS","article-title":"Bootstrap your own latent-a new approach to self-supervised learning","author":"Grill","year":"2020"},{"key":"10.1016\/j.media.2024.103304_b15","doi-asserted-by":"crossref","unstructured":"Haghighi, F., Taher, M.R.H., Gotway, M.B., Liang, J., 2022. Dira: Discriminative, restorative, and adversarial learning for self-supervised medical image analysis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 20824\u201320834.","DOI":"10.1109\/CVPR52688.2022.02016"},{"key":"10.1016\/j.media.2024.103304_b16","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R., 2022. Masked autoencoders are scalable vision learners. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 16000\u201316009.","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"10.1016\/j.media.2024.103304_b17","series-title":"CVPR","first-page":"9729","article-title":"Momentum contrast for unsupervised visual representation learning","author":"He","year":"2020"},{"key":"10.1016\/j.media.2024.103304_b18","doi-asserted-by":"crossref","unstructured":"Huang, S.-C., Shen, L., Lungren, M.P., Yeung, S., 2021. Gloria: A multimodal global-local representation learning framework for label-efficient medical image recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 3942\u20133951.","DOI":"10.1109\/ICCV48922.2021.00391"},{"key":"10.1016\/j.media.2024.103304_b19","doi-asserted-by":"crossref","unstructured":"Irvin, J., Rajpurkar, P., Ko, M., Yu, Y., Ciurea-Ilcus, S., Chute, C., Marklund, H., Haghgoo, B., Ball, R., Shpanskaya, K., et al., 2019. Chexpert: A large chest radiograph dataset with uncertainty labels and expert comparison. In: Proceedings of the AAAI Conference on Artificial Intelligence. Vol. 33, pp. 590\u2013597.","DOI":"10.1609\/aaai.v33i01.3301590"},{"issue":"2","key":"10.1016\/j.media.2024.103304_b20","doi-asserted-by":"crossref","first-page":"203","DOI":"10.1038\/s41592-020-01008-z","article-title":"nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation","volume":"18","author":"Isensee","year":"2021","journal-title":"Nature Methods"},{"key":"10.1016\/j.media.2024.103304_b21","series-title":"Medical Image Computing and Computer Assisted Intervention\u2013MICCAI 2022: 25th International Conference, Singapore, September 18\u201322, 2022, Proceedings, Part IV","first-page":"556","article-title":"Self-supervised 3D anatomy segmentation using self-distilled masked image transformer (SMIT)","author":"Jiang","year":"2022"},{"issue":"1","key":"10.1016\/j.media.2024.103304_b22","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41597-019-0322-0","article-title":"MIMIC-CXR, a de-identified publicly available database of chest radiographs with free-text reports","volume":"6","author":"Johnson","year":"2019","journal-title":"Sci. Data"},{"issue":"1","key":"10.1016\/j.media.2024.103304_b23","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/sdata.2016.35","article-title":"MIMIC-III, a freely accessible critical care database","volume":"3","author":"Johnson","year":"2016","journal-title":"Sci. Data"},{"key":"10.1016\/j.media.2024.103304_b24","series-title":"Computer Vision\u2013ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23\u201327, 2022, Proceedings, Part XXX","first-page":"300","article-title":"What to hide from your students: Attention-guided masked image modeling","author":"Kakogeorgiou","year":"2022"},{"key":"10.1016\/j.media.2024.103304_b25","first-page":"13165","article-title":"MST: Masked self-supervised transformer for visual representation","volume":"34","author":"Li","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"3","key":"10.1016\/j.media.2024.103304_b26","first-page":"265","article-title":"Medical subject headings (MeSH)","volume":"88","author":"Lipscomb","year":"2000","journal-title":"Bull. Med. Libr. Assoc."},{"key":"10.1016\/j.media.2024.103304_b27","series-title":"ICLR","article-title":"Sgdr: Stochastic gradient descent with warm restarts","author":"Loshchilov","year":"2017"},{"key":"10.1016\/j.media.2024.103304_b28","series-title":"Fixing weight decay regularization in adam","author":"Loshchilov","year":"2018"},{"key":"10.1016\/j.media.2024.103304_b29","series-title":"CVPR","first-page":"6707","article-title":"Self-supervised learning of pretext-invariant representations","author":"Misra","year":"2020"},{"issue":"1","key":"10.1016\/j.media.2024.103304_b30","doi-asserted-by":"crossref","first-page":"429","DOI":"10.1038\/s41597-022-01498-w","article-title":"VinDr-CXR: An open dataset of chest X-rays with radiologist\u2019s annotations","volume":"9","author":"Nguyen","year":"2022","journal-title":"Sci. Data"},{"key":"10.1016\/j.media.2024.103304_b31","series-title":"Representation learning with contrastive predictive coding","author":"Oord","year":"2018"},{"key":"10.1016\/j.media.2024.103304_b32","doi-asserted-by":"crossref","unstructured":"Pathak, D., Krahenbuhl, P., Donahue, J., Darrell, T., Efros, A.A., 2016. Context encoders: Feature learning by inpainting. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 2536\u20132544.","DOI":"10.1109\/CVPR.2016.278"},{"key":"10.1016\/j.media.2024.103304_b33","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D., 2017. Grad-cam: Visual explanations from deep networks via gradient-based localization. In: Proceedings of the IEEE International Conference on Computer Vision. pp. 618\u2013626.","DOI":"10.1109\/ICCV.2017.74"},{"key":"10.1016\/j.media.2024.103304_b34","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2020.101693","article-title":"Embracing imperfect datasets: A review of deep learning solutions for medical image segmentation","volume":"63","author":"Tajbakhsh","year":"2020","journal-title":"Med. Image Anal."},{"key":"10.1016\/j.media.2024.103304_b35","series-title":"NeurIPS","first-page":"18158","article-title":"3D self-supervised methods for medical imaging","volume":"Vol. 33","author":"Taleb","year":"2020"},{"key":"10.1016\/j.media.2024.103304_b36","series-title":"ECCV","article-title":"Contrastive multiview coding","author":"Tian","year":"2020"},{"issue":"12","key":"10.1016\/j.media.2024.103304_b37","doi-asserted-by":"crossref","first-page":"1399","DOI":"10.1038\/s41551-022-00936-9","article-title":"Expert-level detection of pathologies from unannotated chest X-ray images via self-supervised learning","volume":"6","author":"Tiu","year":"2022","journal-title":"Nat. Biomed. Eng."},{"key":"10.1016\/j.media.2024.103304_b38","doi-asserted-by":"crossref","unstructured":"Wang, S., Ding, Z., Fu, Y., 2017. Feature selection guided auto-encoder. In: Proceedings of the AAAI Conference on Artificial Intelligence. Vol. 31.","DOI":"10.1609\/aaai.v31i1.10811"},{"issue":"1","key":"10.1016\/j.media.2024.103304_b39","first-page":"1","article-title":"Covid-net: A tailored deep convolutional neural network design for detection of covid-19 cases from chest x-ray images","volume":"10","author":"Wang","year":"2020","journal-title":"Sci. Rep."},{"key":"10.1016\/j.media.2024.103304_b40","doi-asserted-by":"crossref","unstructured":"Wang, H., Song, K., Fan, J., Wang, Y., Xie, J., Zhang, Z., 2023. Hard patches mining for masked image modeling. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 10375\u201310385.","DOI":"10.1109\/CVPR52729.2023.01000"},{"key":"10.1016\/j.media.2024.103304_b41","series-title":"Advances in Neural Information Processing Systems","article-title":"Multi-granularity cross-modal alignment for generalized medical visual representation learning","author":"Wang","year":"2022"},{"key":"10.1016\/j.media.2024.103304_b42","series-title":"Google\u2019s neural machine translation system: Bridging the gap between human and machine translation","author":"Wu","year":"2016"},{"key":"10.1016\/j.media.2024.103304_b43","doi-asserted-by":"crossref","unstructured":"Xiao, J., Bai, Y., Yuille, A., Zhou, Z., 2023. Delving into masked autoencoders for multi-label thorax disease classification. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision. pp. 3588\u20133600.","DOI":"10.1109\/WACV56688.2023.00358"},{"key":"10.1016\/j.media.2024.103304_b44","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"13","article-title":"MedIM: Boost medical image representation via radiology report-guided masking","author":"Xie","year":"2023"},{"key":"10.1016\/j.media.2024.103304_b45","doi-asserted-by":"crossref","unstructured":"Xie, Z., Zhang, Z., Cao, Y., Lin, Y., Bao, J., Yao, Z., Dai, Q., Hu, H., 2022b. Simmim: A simple framework for masked image modeling. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 9653\u20139663.","DOI":"10.1109\/CVPR52688.2022.00943"},{"key":"10.1016\/j.media.2024.103304_b46","doi-asserted-by":"crossref","DOI":"10.1109\/TPAMI.2023.3312587","article-title":"Learning from partially labeled data for multi-organ and tumor segmentation","author":"Xie","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.media.2024.103304_b47","series-title":"Computer Vision\u2013ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23\u201327, 2022, Proceedings, Part XXI","first-page":"558","article-title":"UniMiSS: Universal medical self-supervised learning via breaking dimensionality barrier","author":"Xie","year":"2022"},{"key":"10.1016\/j.media.2024.103304_b48","series-title":"Clinical-BERT: Vision-language pre-training for radiograph diagnosis and reports generation","first-page":"2982","author":"Yan","year":"2022"},{"key":"10.1016\/j.media.2024.103304_b49","series-title":"Society for Imaging Informatics in Medicine","article-title":"Siim-acr pneumothorax segmentation","author":"Zawacki","year":"2019"},{"key":"10.1016\/j.media.2024.103304_b50","doi-asserted-by":"crossref","unstructured":"Zhang, R., Isola, P., Efros, A.A., 2017. Split-brain autoencoders: Unsupervised learning by cross-channel prediction. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 1058\u20131067.","DOI":"10.1109\/CVPR.2017.76"},{"key":"10.1016\/j.media.2024.103304_b51","series-title":"CVPR","first-page":"1195","article-title":"DoDNet: Learning to segment multi-organ and tumors from multiple partially labeled datasets","author":"Zhang","year":"2021"},{"key":"10.1016\/j.media.2024.103304_b52","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1038\/s42256-021-00425-9","article-title":"Generalized radiograph representation learning via cross-supervision between images and free-text radiology reports","author":"Zhou","year":"2022","journal-title":"Nat. Mach. Intell."},{"key":"10.1016\/j.media.2024.103304_b53","unstructured":"Zhou, H.-Y., Lian, C., Wang, L., Yu, Y., 2023. Advancing Radiograph Representation Learning with Masked Record Modeling. In: International Conference on Learning Representations. ICLR."},{"key":"10.1016\/j.media.2024.103304_b54","series-title":"Self pre-training with masked autoencoders for medical image analysis","author":"Zhou","year":"2022"},{"key":"10.1016\/j.media.2024.103304_b55","series-title":"ICCV","first-page":"3499","article-title":"Preservational learning improves self-supervised medical image models by reconstructing diverse contexts","author":"Zhou","year":"2021"},{"key":"10.1016\/j.media.2024.103304_b56","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2022.102626","article-title":"Semantic instance segmentation with discriminative deep supervision for medical images","volume":"82","author":"Zhou","year":"2022","journal-title":"Med. Image Anal."},{"key":"10.1016\/j.media.2024.103304_b57","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2020.101840","article-title":"Models genesis","volume":"67","author":"Zhou","year":"2021","journal-title":"Med. Image Anal."},{"key":"10.1016\/j.media.2024.103304_b58","unstructured":"Zhou, J., Wei, C., Wang, H., Shen, W., Xie, C., Yuille, A., Kong, T., 2022b. Image BERT Pre-training with Online Tokenizer. In: International Conference on Learning Representations. ICLR."},{"key":"10.1016\/j.media.2024.103304_b59","series-title":"Medical Image Computing and Computer Assisted Intervention\u2013MICCAI 2022: 25th International Conference, Singapore, September 18\u201322, 2022, Proceedings, Part VIII","first-page":"57","article-title":"Aggregative self-supervised feature learning from limited medical images","author":"Zhu","year":"2022"}],"container-title":["Medical Image Analysis"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1361841524002299?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1361841524002299?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2024,9,8]],"date-time":"2024-09-08T03:48:01Z","timestamp":1725767281000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1361841524002299"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":59,"alternative-id":["S1361841524002299"],"URL":"https:\/\/doi.org\/10.1016\/j.media.2024.103304","relation":{},"ISSN":["1361-8415"],"issn-type":[{"value":"1361-8415","type":"print"}],"subject":[],"published":{"date-parts":[[2024,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Rethinking masked image modelling for medical image representation","name":"articletitle","label":"Article Title"},{"value":"Medical Image Analysis","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.media.2024.103304","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2024 The Authors. Published by Elsevier B.V.","name":"copyright","label":"Copyright"}],"article-number":"103304"}}