{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T23:03:45Z","timestamp":1774047825928,"version":"3.50.1"},"reference-count":47,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002920","name":"Research Grants Council, University Grants Committee","doi-asserted-by":"publisher","award":["R6005-24"],"award-info":[{"award-number":["R6005-24"]}],"id":[{"id":"10.13039\/501100002920","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002920","name":"Research Grants Council, University Grants Committee","doi-asserted-by":"publisher","award":["HKUST654\/24"],"award-info":[{"award-number":["HKUST654\/24"]}],"id":[{"id":"10.13039\/501100002920","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002920","name":"Research Grants Council, University Grants Committee","doi-asserted-by":"publisher","award":["AoE\/E-601\/24-N"],"award-info":[{"award-number":["AoE\/E-601\/24-N"]}],"id":[{"id":"10.13039\/501100002920","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":[[2026,6]]},"DOI":"10.1016\/j.media.2026.104015","type":"journal-article","created":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T16:17:20Z","timestamp":1772900240000},"page":"104015","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["MedSapiens: Taking a pose to rethink medical imaging landmark detection"],"prefix":"10.1016","volume":"111","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-5021-4281","authenticated-orcid":false,"given":"Marawan","family":"Elbatel","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0008-2527-707X","authenticated-orcid":false,"given":"Anbang","family":"Wang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0007-2051-0920","authenticated-orcid":false,"given":"Keyuan","family":"Liu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8991-9405","authenticated-orcid":false,"given":"Kaouther","family":"Mouheb","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0006-0610-3520","authenticated-orcid":false,"given":"Enrique","family":"Almar-Munoz","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6043-9849","authenticated-orcid":false,"given":"Lizhuo","family":"Lin","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3582-1277","authenticated-orcid":false,"given":"Yanqi","family":"Yang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9456-1612","authenticated-orcid":false,"given":"Karim","family":"Lekadir","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1105-8083","authenticated-orcid":false,"given":"Xiaomeng","family":"Li","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.media.2026.104015_bib0001","series-title":"Medical Image Computing and Computer Assisted Intervention - MICCAI 2024","first-page":"155","article-title":"Cephalometric landmark detection across ages with prototypical network","author":"Chong","year":"2024"},{"key":"10.1016\/j.media.2026.104015_bib0002","unstructured":"Contributors, M., 2020. OpenMMLab pose estimation toolbox and benchmark. https:\/\/github.com\/open-mmlab\/mmpose."},{"key":"10.1016\/j.media.2026.104015_bib0003","doi-asserted-by":"crossref","unstructured":"Demir, B., Tian, L., Greer, T. H., Kwitt, R., Vialard, F.-X., Estepar, R. S. J., Bouix, S., Rushmore, R. J., Ebrahim, E., Niethammer, M., 2024. multigradICON: a foundation model for multimodal medical image registration. arXiv preprint arXiv: 2408.00221.","DOI":"10.1007\/978-3-031-73480-9_1"},{"issue":"4","key":"10.1016\/j.media.2026.104015_bib0004","doi-asserted-by":"crossref","first-page":"386","DOI":"10.1001\/jamacardio.2021.6059","article-title":"High-throughput precision phenotyping of left ventricular hypertrophy with cardiovascular deep learning","volume":"7","author":"Duffy","year":"2022","journal-title":"JAMA Cardiol."},{"key":"10.1016\/j.media.2026.104015_bib0005","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"629","article-title":"FD-SOS: vision-language open-set detectors for bone fenestration and dehiscence detection from intraoral images","author":"Elbatel","year":"2024"},{"key":"10.1016\/j.media.2026.104015_bib0006","unstructured":"Ertl, A., Xiao, S., Denner, S., Peretzke, R., Zimmerer, D., Neher, P., Isensee, F., Maier-Hein,K., 2025. nnLandmark: a self-configuring method for 3D medical landmark detection. arXiv: 2504.06742."},{"issue":"4","key":"10.1016\/j.media.2026.104015_bib0007","doi-asserted-by":"crossref","first-page":"322","DOI":"10.1016\/j.compmedimag.2007.02.012","article-title":"Bone age assessment of children using a digital hand atlas","volume":"31","author":"Gertych","year":"2007","journal-title":"Comput. Med. Imaging Graphics"},{"key":"10.1016\/j.media.2026.104015_bib0008","series-title":"Simulation and Synthesis in Medical Imaging","first-page":"1","article-title":"Synthetic augmentation for anatomical landmark localization using DDPMs","author":"Hadzic","year":"2025"},{"key":"10.1016\/j.media.2026.104015_bib0009","doi-asserted-by":"crossref","DOI":"10.1093\/ehjci\/jeae333.042","article-title":"Deep learning in echocardiography: real-time measurements of left ventricular wall thickness and chamber dimensions in the parasternal long-axis view","volume":"26","author":"Holmstrom","year":"2025","journal-title":"Eur. Heart J. Cardiovasc. Imaging"},{"issue":"4","key":"10.1016\/j.media.2026.104015_bib0010","doi-asserted-by":"crossref","first-page":"306","DOI":"10.1001\/jama.2025.8731","article-title":"Complete AI-enabled echocardiography interpretation with multitask deep learning","volume":"334","author":"Holste","year":"2025","journal-title":"JAMA"},{"key":"10.1016\/j.media.2026.104015_bib0011","series-title":"Int. Conf. Learn. Represent.","article-title":"LoRA: low-rank adaptation of large language models","author":"Hu","year":"2022"},{"key":"10.1016\/j.media.2026.104015_bib0012","doi-asserted-by":"crossref","first-page":"4797","DOI":"10.1109\/JBHI.2024.3390241","article-title":"Involution transformer based U-Net for landmark detection in ultrasound images for diagnosis of infantile DDH","volume":"28","author":"Huang","year":"2024","journal-title":"IEEE J. Biomed. Health Inf."},{"key":"10.1016\/j.media.2026.104015_bib0013","doi-asserted-by":"crossref","first-page":"2679","DOI":"10.1109\/TMI.2024.3371948","article-title":"Landmark localization from medical images with generative distribution prior","volume":"43","author":"Huang","year":"2024","journal-title":"IEEE Trans. Med. Imaging"},{"key":"10.1016\/j.media.2026.104015_bib0014","series-title":"Medical Image Computing and Computer Assisted Intervention - MICCAI 2024","first-page":"599","article-title":"Learnable skeleton-based medical landmark estimation with graph sparsity and Fiedler regularizations","author":"Jiahao","year":"2024"},{"key":"10.1016\/j.media.2026.104015_bib0015","unstructured":"Jiang, C., Ding, T., Song, C., Tu, J., Yan, Z., Shao, Y., Wang, Z., Shang, Y., Han, T., Tian, Y., 2026. Medical SAM3: a foundation model for universal prompt-driven medical image segmentation. arXiv: 2601.10880."},{"key":"10.1016\/j.media.2026.104015_bib0016","unstructured":"Jiang, Q., Huo, J., Chen, X., Xiong, Y., Zeng, Z., Chen, Y., Ren, T., Yu, J., Zhang, L., 2025. Detect anything via next point prediction. arXiv: 2510.12798."},{"key":"10.1016\/j.media.2026.104015_bib0017","series-title":"Medical Image Computing and Computer Assisted Intervention - MICCAI 2024","first-page":"692","article-title":"Topological GCN for improving detection of hip landmarks from b-mode ultrasound images","author":"Jing","year":"2024"},{"key":"10.1016\/j.media.2026.104015_bib0018","doi-asserted-by":"crossref","unstructured":"Khirodkar, R., Bagautdinov, T., Martinez, J., Zhaoen, S., James, A., Selednik, P., Anderson, S., Saito, S., 2024. Sapiens: foundation for human vision models. In: Computer Vision \u2013 ECCV 2024. Lecture Notes in Computer Science, 15062. Springer Nature Switzerland, Cham, pp. 206\u2013228 10.1007\/978-3-031-73235-512.","DOI":"10.1007\/978-3-031-73235-5_12"},{"key":"10.1016\/j.media.2026.104015_bib0019","series-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2024","first-page":"643","article-title":"MedCLIP-SAM: bridging text and image towards universal medical image segmentation","author":"Koleilat","year":"2024"},{"key":"10.1016\/j.media.2026.104015_bib0020","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2024.128157","article-title":"UniverDetect: universal landmark detection method for multidomain x-ray images","volume":"600","author":"Lu","year":"2024","journal-title":"Neurocomputing"},{"key":"10.1016\/j.media.2026.104015_bib0021","series-title":"Proceedings of Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2024","article-title":"FM-OSD: foundation model-enabled one-shot detection of anatomical landmarks","author":"Miao","year":"2024"},{"key":"10.1016\/j.media.2026.104015_bib0022","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"19023","article-title":"Animal kingdom: a large and diverse dataset for animal behavior understanding","author":"Ng","year":"2022"},{"key":"10.1016\/j.media.2026.104015_bib0023","doi-asserted-by":"crossref","first-page":"207","DOI":"10.1016\/j.media.2019.03.007","article-title":"Integrating spatial configuration into heatmap regression based CNNs for landmark localization","volume":"54","author":"Payer","year":"2019","journal-title":"Med. Image Anal."},{"key":"10.1016\/j.media.2026.104015_bib0024","series-title":"Medical Image Computing and Computer Assisted Intervention - MICCAI 2024","first-page":"154","article-title":"Depth-driven geometric prompt learning for laparoscopic liver landmark detection","author":"Ruize","year":"2024"},{"issue":"13","key":"10.1016\/j.media.2026.104015_bib0025","doi-asserted-by":"crossref","first-page":"964","DOI":"10.1016\/j.jacc.2025.07.053","article-title":"Artificial intelligence automation of echocardiographic measurements","volume":"86","author":"Sahashi","year":"2025","journal-title":"JACC"},{"key":"10.1016\/j.media.2026.104015_bib0026","series-title":"Medical Image Computing and Computer Assisted Intervention - MICCAI 2023","first-page":"668","article-title":"Towards multi-modal anatomical landmark detection for ultrasound-guided brain tumor resection with contrastive learning","author":"Salari","year":"2023"},{"key":"10.1016\/j.media.2026.104015_bib0027","series-title":"Medical Image Computing and Computer Assisted Intervention - MICCAI 2023","first-page":"433","article-title":"Anatomical landmark detection using a multiresolution learning approach with a hybrid transformer-CNN model","author":"Serie","year":"2023"},{"key":"10.1016\/j.media.2026.104015_bib0028","unstructured":"Singh, D. K., Boubekki, A., Cao, Q., Aase, S. A., Jenssen, R., Kampffmeyer, M., 2025a. EnLVAM: enhanced left ventricle linear measurements utilizing anatomical motion mode. arXiv preprint arXiv: 2506.22063."},{"key":"10.1016\/j.media.2026.104015_bib0029","series-title":"Simplifying Medical Ultrasound: 6th International Workshop, ASMUS 2025, Held in Conjunction with MICCAI 2025, Daejeon, South Korea, September 28, 2025, Proceedings","first-page":"218","article-title":"WiseLVAM: a novel framework for left ventricle automatic measurements","author":"Singh","year":"2025"},{"key":"10.1016\/j.media.2026.104015_bib0030","doi-asserted-by":"crossref","first-page":"449","DOI":"10.1038\/s41597-023-02330-9","article-title":"Magnetic resonance imaging datasets with anatomical fiducials for quality control and registration","volume":"10","author":"Taha","year":"2023","journal-title":"Sci. Data"},{"key":"10.1016\/j.media.2026.104015_bib0031","unstructured":"Taratynova, D., Aly, A., Saeed, N., Yaqub, M., 2025. Cardiobench: do echocardiography foundation models generalize beyond the lab?arXiv: 2510.00520."},{"key":"10.1016\/j.media.2026.104015_bib0032","doi-asserted-by":"crossref","unstructured":"Tian, L., Greer, H., Kwitt, R., Vialard, F.-X., Estepar, R. S. J., Bouix, S., Rushmore, R., Niethammer, M., 2024. unigradICON: a foundation model for medical image registration. arXiv preprint arXiv: 2403.05780.","DOI":"10.1007\/978-3-031-72069-7_70"},{"key":"10.1016\/j.media.2026.104015_bib0033","unstructured":"Vukadinovic, M., Tang, X., Yuan, N., Cheng, P., Li, D., Cheng, S., He, B., Ouyang, D., 2024. EchoPrime: a multi-video view-informed vision-language model for comprehensive echocardiography interpretation. arXiv preprint arXiv: 2410.09704."},{"key":"10.1016\/j.media.2026.104015_bib0034","series-title":"Proceedings of Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2025","article-title":"Geometric-guided few-shot dental landmark detection with human-centric foundation model","author":"Wang","year":"2025"},{"key":"10.1016\/j.media.2026.104015_bib0035","doi-asserted-by":"crossref","first-page":"63","DOI":"10.1016\/j.media.2016.02.004","article-title":"A benchmark for comparison of dental radiography analysis algorithms","volume":"31","author":"Wang","year":"2016","journal-title":"Med. Image Anal."},{"issue":"9","key":"10.1016\/j.media.2026.104015_bib0036","doi-asserted-by":"crossref","first-page":"1890","DOI":"10.1109\/TMI.2015.2412951","article-title":"Evaluation and comparison of anatomical landmark detection methods for cephalometric x-ray images: a grand challenge","volume":"34","author":"Wang","year":"2015","journal-title":"IEEE Trans. Med. Imaging"},{"issue":"10","key":"10.1016\/j.media.2026.104015_bib0037","doi-asserted-by":"crossref","first-page":"3349","DOI":"10.1109\/TPAMI.2020.2983686","article-title":"Deep high-resolution representation learning for visual recognition","volume":"43","author":"Wang","year":"2021","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.media.2026.104015_bib0038","series-title":"MICCAI Workshop on Domain Adaptation and Representation Transfer","first-page":"156","article-title":"Self-prompting large vision models for few-shot medical image segmentation","author":"Wu","year":"2023"},{"issue":"2","key":"10.1016\/j.media.2026.104015_bib0039","doi-asserted-by":"crossref","first-page":"1212","DOI":"10.1109\/TPAMI.2023.3330016","article-title":"ViTPose++: vision transformer for generic body pose estimation","volume":"46","author":"Xu","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"1","key":"10.1016\/j.media.2026.104015_bib0040","doi-asserted-by":"crossref","first-page":"67","DOI":"10.2319\/040811-250.1","article-title":"Dehiscence and fenestration in skeletal class i, II, and III malocclusions assessed with cone-beam computed tomography","volume":"82","author":"Yagci","year":"2012","journal-title":"Angle Orthod."},{"key":"10.1016\/j.media.2026.104015_bib0041","unstructured":"Yao, Q., Wang, J., Sun, Y., Quan, Q., Zhu, H., Zhou, S. K., 2022. Relative distance matters for one-shot landmark detection. arXiv: 2203.01687."},{"key":"10.1016\/j.media.2026.104015_bib0042","doi-asserted-by":"crossref","unstructured":"Zhang, K., Liu, D., 2023. Customized segment anything model for medical image segmentation. arXiv preprint arXiv: 2304.13785.","DOI":"10.2139\/ssrn.4495221"},{"key":"10.1016\/j.media.2026.104015_bib0043","series-title":"MICCAI","article-title":"Text-guided foundation model adaptation for pathological image classification","author":"Zhang","year":"2023"},{"key":"10.1016\/j.media.2026.104015_bib0044","doi-asserted-by":"crossref","first-page":"166","DOI":"10.1038\/s41592-024-02499-w","article-title":"A foundation model for joint segmentation, detection, and recognition of biomedical objects across nine modalities","volume":"22","author":"Zhao","year":"2024","journal-title":"Nat. Methods"},{"key":"10.1016\/j.media.2026.104015_bib0045","series-title":"Medical Image Computing and Computer Assisted Intervention - MICCAI 2023","first-page":"24","article-title":"UOD: universal one-shot detection of anatomical landmarks","author":"Zhu","year":"2023"},{"key":"10.1016\/j.media.2026.104015_bib0046","series-title":"You only Learn Once: Universal Anatomical Landmark Detection","first-page":"85","author":"Zhu","year":"2021"},{"key":"10.1016\/j.media.2026.104015_bib0047","doi-asserted-by":"crossref","DOI":"10.34133\/2022\/9765095","article-title":"Learning to localize cross-anatomy landmarks in x-ray images with a universal model","volume":"2022","author":"Zhu","year":"2022","journal-title":"BME Front."}],"container-title":["Medical Image Analysis"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1361841526000848?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1361841526000848?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T21:54:20Z","timestamp":1774043660000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1361841526000848"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":47,"alternative-id":["S1361841526000848"],"URL":"https:\/\/doi.org\/10.1016\/j.media.2026.104015","relation":{},"ISSN":["1361-8415"],"issn-type":[{"value":"1361-8415","type":"print"}],"subject":[],"published":{"date-parts":[[2026,6]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"MedSapiens: Taking a pose to rethink medical imaging landmark detection","name":"articletitle","label":"Article Title"},{"value":"Medical Image Analysis","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.media.2026.104015","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Published by Elsevier B.V.","name":"copyright","label":"Copyright"}],"article-number":"104015"}}