{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,11]],"date-time":"2026-11-11T22:30:02Z","timestamp":1794436202056,"version":"4.9.1"},"reference-count":58,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100013317","name":"Shanxi Provincial Key Research and Development Project","doi-asserted-by":"publisher","award":["2021YFG0316"],"award-info":[{"award-number":["2021YFG0316"]}],"id":[{"id":"10.13039\/501100013317","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62206189"],"award-info":[{"award-number":["62206189"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2023M732427"],"award-info":[{"award-number":["2023M732427"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["clinicalkey.com","clinicalkey.com.au","clinicalkey.es","clinicalkey.fr","clinicalkey.jp","elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Computers in Biology and Medicine"],"published-print":{"date-parts":[[2025,6]]},"DOI":"10.1016\/j.compbiomed.2025.110159","type":"journal-article","created":{"date-parts":[[2025,4,17]],"date-time":"2025-04-17T23:58:36Z","timestamp":1744934316000},"page":"110159","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":4,"special_numbering":"C","title":["BUS-M2AE: Multi-scale Masked Autoencoder for Breast Ultrasound Image Analysis"],"prefix":"10.1016","volume":"191","author":[{"given":"Le","family":"Yu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bo","family":"Gou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xun","family":"Xia","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yujia","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhang","family":"Yi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiangde","family":"Min","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9405-3979","authenticated-orcid":false,"given":"Tao","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.compbiomed.2025.110159_b1","series-title":"CVPR","first-page":"16000","article-title":"Masked autoencoders are scalable vision learners","author":"He","year":"2022"},{"key":"10.1016\/j.compbiomed.2025.110159_b2","series-title":"ICLR","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2021"},{"key":"10.1016\/j.compbiomed.2025.110159_b3","doi-asserted-by":"crossref","unstructured":"H. Chen, W. Zhang, Y. Wang, X. Yang, Improving masked autoencoders by learning where to mask, in: Chinese Conference on Pattern Recognition and Computer Vision, PRCV, 2023, pp. 377\u2013390.","DOI":"10.1007\/978-981-99-8543-2_31"},{"key":"10.1016\/j.compbiomed.2025.110159_b4","series-title":"ICML","first-page":"20026","article-title":"Adversarial masking for self-supervised learning","author":"Shi","year":"2022"},{"key":"10.1016\/j.compbiomed.2025.110159_b5","series-title":"ECCV","first-page":"300","article-title":"What to hide from your students: Attention-guided masked image modeling","author":"Kakogeorgiou","year":"2022"},{"key":"10.1016\/j.compbiomed.2025.110159_b6","series-title":"AAAI","first-page":"1799","article-title":"Good helper is around you: Attention-driven masked image modeling","author":"Liu","year":"2023"},{"key":"10.1016\/j.compbiomed.2025.110159_b7","first-page":"14290","article-title":"Semmae: Semantic-guided masking for learning masked autoencoders","author":"Li","year":"2022","journal-title":"NeurIPS"},{"key":"10.1016\/j.compbiomed.2025.110159_b8","series-title":"CVPR","first-page":"10375","article-title":"Hard patches mining for masked image modeling","author":"Wang","year":"2023"},{"key":"10.1016\/j.compbiomed.2025.110159_b9","series-title":"DPPMask: Masked image modeling with determinantal point processes","author":"Xu","year":"2023"},{"key":"10.1016\/j.compbiomed.2025.110159_b10","series-title":"Deblurring masked autoencoder is better recipe for ultrasound image recognition","author":"Kang","year":"2023"},{"key":"10.1016\/j.compbiomed.2025.110159_b11","series-title":"ICLR","article-title":"Denoising masked autoencoders help robust classification","author":"Wu","year":"2022"},{"key":"10.1016\/j.compbiomed.2025.110159_b12","series-title":"CVPR","first-page":"10386","article-title":"Evolved part masking for self-supervised learning","author":"Feng","year":"2023"},{"key":"10.1016\/j.compbiomed.2025.110159_b13","series-title":"Medical supervised masked autoencoders: Crafting a better masking strategy and efficient fine-tuning schedule for medical image classification","author":"Mao","year":"2023"},{"key":"10.1016\/j.compbiomed.2025.110159_b14","series-title":"Self pre-training with masked autoencoders for medical image classification and segmentation","author":"Zhou","year":"2022"},{"key":"10.1016\/j.compbiomed.2025.110159_b15","series-title":"WACV","first-page":"3588","article-title":"Delving into masked autoencoders for multi-label thorax disease classification","author":"Xiao","year":"2023"},{"key":"10.1016\/j.compbiomed.2025.110159_b16","series-title":"WACV","first-page":"574","article-title":"Unetr: Transformers for 3d medical image segmentation","author":"Hatamizadeh","year":"2022"},{"key":"10.1016\/j.compbiomed.2025.110159_b17","doi-asserted-by":"crossref","DOI":"10.1016\/j.dib.2019.104863","article-title":"Dataset of breast ultrasound images","volume":"28","author":"Al-Dhabyani","year":"2020","journal-title":"Data Brief"},{"key":"10.1016\/j.compbiomed.2025.110159_b18","series-title":"CVPR","first-page":"248","article-title":"ImageNet: A large-scale hierarchical image database","author":"Deng","year":"2009"},{"key":"10.1016\/j.compbiomed.2025.110159_b19","series-title":"CVPR","first-page":"16144","article-title":"Scaling vision transformers to gigapixel images via hierarchical self-supervised learning","author":"Chen","year":"2022"},{"key":"10.1016\/j.compbiomed.2025.110159_b20","series-title":"ICCV","first-page":"6824","article-title":"Multiscale vision transformers","author":"Fan","year":"2021"},{"key":"10.1016\/j.compbiomed.2025.110159_b21","series-title":"CVPR","first-page":"4804","article-title":"Mvitv2: Improved multiscale vision transformers for classification and detection","author":"Li","year":"2022"},{"key":"10.1016\/j.compbiomed.2025.110159_b22","series-title":"CVPR","first-page":"12094","article-title":"Multi-scale high-resolution vision transformer for semantic segmentation","author":"Gu","year":"2022"},{"key":"10.1016\/j.compbiomed.2025.110159_b23","first-page":"11960","article-title":"Not all images are worth 16x16 words: Dynamic transformers for efficient image recognition","volume":"34","author":"Wang","year":"2021","journal-title":"NeurIPS"},{"key":"10.1016\/j.compbiomed.2025.110159_b24","series-title":"ICCV","first-page":"10012","article-title":"Swin transformer: Hierarchical vision transformer using shifted windows","author":"Liu","year":"2021"},{"issue":"1","key":"10.1016\/j.compbiomed.2025.110159_b25","first-page":"1929","article-title":"Dropout: a simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.compbiomed.2025.110159_b26","series-title":"CL-MAE: Curriculum-learned masked autoencoders","author":"Madan","year":"2023"},{"key":"10.1016\/j.compbiomed.2025.110159_b27","series-title":"Beyond masking: Demystifying token-based pre-training for vision transformers","author":"Tian","year":"2022"},{"key":"10.1016\/j.compbiomed.2025.110159_b28","series-title":"ConvMAE: Masked convolution meets masked autoencoders","author":"Gao","year":"2022"},{"key":"10.1016\/j.compbiomed.2025.110159_b29","article-title":"Swin MAE: masked autoencoders for small datasets","volume":"161","author":"Dai","year":"2023","journal-title":"Comput. Biol. Med."},{"key":"10.1016\/j.compbiomed.2025.110159_b30","series-title":"ICCV","first-page":"4088","article-title":"Scale-mae: A scale-aware masked autoencoder for multiscale geospatial representation learning","author":"Reed","year":"2023"},{"key":"10.1016\/j.compbiomed.2025.110159_b31","series-title":"CVPR","first-page":"2122","article-title":"Masked image modeling with local multi-scale reconstruction","author":"Wang","year":"2023"},{"key":"10.1016\/j.compbiomed.2025.110159_b32","doi-asserted-by":"crossref","unstructured":"B. Shareef, M. Xian, A. Vakanski, Stan: Small Tumor-Aware Network for Breast Ultrasound Image Segmentation, in: 2020 IEEE 17th International Symposium on Biomedical Imaging, ISBI, 2020, pp. 1\u20135.","DOI":"10.1109\/ISBI45749.2020.9098691"},{"issue":"11","key":"10.1016\/j.compbiomed.2025.110159_b33","doi-asserted-by":"crossref","DOI":"10.3390\/healthcare10112262","article-title":"ESTAN: Enhanced small tumor-aware network for breast ultrasound image segmentation","volume":"10","author":"Shareef","year":"2022","journal-title":"Healthcare"},{"key":"10.1016\/j.compbiomed.2025.110159_b34","first-page":"1","article-title":"Breast tumor ultrasound image segmentation method based on improved residual U-Net network","volume":"2022","author":"Zhao","year":"2022","journal-title":"Comput. Intell. Neurosci."},{"key":"10.1016\/j.compbiomed.2025.110159_b35","series-title":"A2DMN: Anatomy-aware dilated multiscale network for breast ultrasound semantic segmentation","author":"Lucke","year":"2024"},{"key":"10.1016\/j.compbiomed.2025.110159_b36","series-title":"WACV","first-page":"2685","article-title":"Representation recovering for self-supervised pre-training on medical images","author":"Yan","year":"2023"},{"issue":"5","key":"10.1016\/j.compbiomed.2025.110159_b37","doi-asserted-by":"crossref","first-page":"562","DOI":"10.1109\/T-C.1971.223290","article-title":"Edge and curve detection for visual scene analysis","volume":"100","author":"Rosenfeld","year":"1971","journal-title":"IEEE Trans. Comput."},{"issue":"9","key":"10.1016\/j.compbiomed.2025.110159_b38","doi-asserted-by":"crossref","first-page":"1904","DOI":"10.1109\/TPAMI.2015.2389824","article-title":"Spatial pyramid pooling in deep convolutional networks for visual recognition","volume":"37","author":"He","year":"2015","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.compbiomed.2025.110159_b39","series-title":"CVPR","article-title":"Feature pyramid networks for object detection","author":"Lin","year":"2017"},{"issue":"1","key":"10.1016\/j.compbiomed.2025.110159_b40","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1109\/TAI.2021.3135248","article-title":"Multiscale representation learning for image classification: A survey","volume":"4","author":"Jiao","year":"2021","journal-title":"IEEE Trans. Artif. Intell."},{"issue":"12","key":"10.1016\/j.compbiomed.2025.110159_b41","doi-asserted-by":"crossref","first-page":"10823","DOI":"10.1109\/TNNLS.2022.3171572","article-title":"Hyperspectral and SAR image classification via multiscale interactive fusion network","volume":"34","author":"Wang","year":"2023","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.compbiomed.2025.110159_b42","series-title":"CVPR","first-page":"8759","article-title":"Path aggregation network for instance segmentation","author":"Liu","year":"2018"},{"key":"10.1016\/j.compbiomed.2025.110159_b43","article-title":"Transattunet: Multi-level attention-guided u-net with transformer for medical image segmentation","author":"Chen","year":"2023","journal-title":"Trans. Emerg. Top. Comput. Intell."},{"key":"10.1016\/j.compbiomed.2025.110159_b44","series-title":"CVPR","first-page":"12009","article-title":"Swin transformer v2: Scaling up capacity and resolution","author":"Liu","year":"2022"},{"key":"10.1016\/j.compbiomed.2025.110159_b45","series-title":"CVPR","first-page":"3202","article-title":"Video swin transformer","author":"Liu","year":"2022"},{"key":"10.1016\/j.compbiomed.2025.110159_b46","series-title":"ICCV","first-page":"357","article-title":"Crossvit: Cross-attention multi-scale vision transformer for image classification","author":"Chen","year":"2021"},{"key":"10.1016\/j.compbiomed.2025.110159_b47","series-title":"Spatio-temporal SwinMAE: A swin transformer based multiscale representation learner for temporal satellite imagery","author":"Nakayama","year":"2024"},{"key":"10.1016\/j.compbiomed.2025.110159_b48","article-title":"Masked image residual learning for scaling deeper vision transformers","volume":"36","author":"Huang","year":"2024","journal-title":"NeurIPS"},{"key":"10.1016\/j.compbiomed.2025.110159_b49","doi-asserted-by":"crossref","first-page":"1895","DOI":"10.1162\/089976698300017197","article-title":"Approximate statistical tests for comparing supervised classification learning algorithms","volume":"10","author":"Dietterich","year":"1998","journal-title":"Neural Comput."},{"key":"10.1016\/j.compbiomed.2025.110159_b50","article-title":"Neural memory state space models for medical image segmentation","author":"Wang","year":"2024","journal-title":"Int. J. Neural Syst."},{"key":"10.1016\/j.compbiomed.2025.110159_b51","series-title":"IJCAI-24","first-page":"821","article-title":"A lightweight U-like network utilizing neural memory ordinary differential equations for slimming the decoder","author":"He","year":"2024"},{"key":"10.1016\/j.compbiomed.2025.110159_b52","series-title":"MICCAI","first-page":"234","article-title":"U-net: Convolutional networks for biomedical image segmentation","author":"Ronneberger","year":"2015"},{"key":"10.1016\/j.compbiomed.2025.110159_b53","series-title":"CVPR","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"10.1016\/j.compbiomed.2025.110159_b54","series-title":"CVPR","first-page":"4700","article-title":"Densely connected convolutional networks","author":"Huang","year":"2017"},{"key":"10.1016\/j.compbiomed.2025.110159_b55","series-title":"ECCV","first-page":"205","article-title":"Swin-unet: Unet-like pure transformer for medical image segmentation","author":"Cao","year":"2022"},{"key":"10.1016\/j.compbiomed.2025.110159_b56","series-title":"Segment anything in medical images","author":"Ma","year":"2023"},{"key":"10.1016\/j.compbiomed.2025.110159_b57","series-title":"Segment anything","author":"Kirillov","year":"2023"},{"key":"10.1016\/j.compbiomed.2025.110159_b58","series-title":"CVPR","first-page":"5122","article-title":"Scene parsing through ADE20k dataset","author":"Zhou","year":"2017"}],"container-title":["Computers in Biology and Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0010482525005104?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0010482525005104?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,11,11]],"date-time":"2026-11-11T22:03:50Z","timestamp":1794434630000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0010482525005104"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6]]},"references-count":58,"alternative-id":["S0010482525005104"],"URL":"https:\/\/doi.org\/10.1016\/j.compbiomed.2025.110159","relation":{},"ISSN":["0010-4825"],"issn-type":[{"value":"0010-4825","type":"print"}],"subject":[],"published":{"date-parts":[[2025,6]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"BUS-M2AE: Multi-scale Masked Autoencoder for Breast Ultrasound Image Analysis","name":"articletitle","label":"Article Title"},{"value":"Computers in Biology and Medicine","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.compbiomed.2025.110159","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2025 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"110159"}}