{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,26]],"date-time":"2026-08-26T17:20:00Z","timestamp":1787764800631,"version":"build-2784847793"},"reference-count":23,"publisher":"Springer Science and Business Media LLC","license":[{"start":{"date-parts":[[2026,8,26]],"date-time":"2026-08-26T00:00:00Z","timestamp":1787702400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,8,26]],"date-time":"2026-08-26T00:00:00Z","timestamp":1787702400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Digit Imaging. Inform. med."],"DOI":"10.1007\/s10278-026-02219-0","type":"journal-article","created":{"date-parts":[[2026,8,26]],"date-time":"2026-08-26T16:38:44Z","timestamp":1787762324000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Feasibility of AI-Based Wheelchair Classification for MRI Anteroom Safety Management: A Single-Centre Deep Learning Object-Detection Study"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-8680-3026","authenticated-orcid":false,"given":"Toshinori","family":"Suzuki","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Satoshi","family":"Yamada","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Keiichiro","family":"Nakata","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shingo","family":"Uchikura","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jumpei","family":"Nagayoshi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,8,26]]},"reference":[{"key":"2219_CR1","doi-asserted-by":"crossref","unstructured":"ACR Committee on MR Safety, Greenberg TD, Hoff MN, et al.: ACR guidance document on MR safe practices: updates and critical information 2019. J Magn Reson Imaging 51:331\u2013338, 2020","DOI":"10.1002\/jmri.26880"},{"key":"2219_CR2","doi-asserted-by":"crossref","unstructured":"Pedrosa I, Altman DA, Dillman JR, et al.: American College of Radiology Manual on MR Safety: 2024 update and revisions. Radiology 315:e241405, 2025","DOI":"10.1148\/radiol.241405"},{"key":"2219_CR3","doi-asserted-by":"crossref","unstructured":"Delfino JG, Krainak DM, Flesher SA, et al.: MRI-related FDA adverse event reports: a 10-yr review. Med Phys 46:5562-5571, 2019","DOI":"10.1002\/mp.13768"},{"key":"2219_CR4","doi-asserted-by":"crossref","unstructured":"Mittendorff L, Young A, Sim J: A narrative review of current and emerging MRI safety issues: what every MRI technologist (radiographer) needs to know. J Med Radiat Sci 69:250-260, 2022","DOI":"10.1002\/jmrs.546"},{"key":"2219_CR5","unstructured":"Clinical MRI Safety Information Subcommittee, Japanese Society for Magnetic Resonance in Medicine: Analysis of incident reports up to the end of 2023. Tokyo: JSMRM, 2024 (in Japanese)"},{"key":"2219_CR6","doi-asserted-by":"crossref","unstructured":"Li M, Jiang Y, Zhang Y, et al.: Medical image analysis using deep learning algorithms. Front Public Health 11:1273253, 2023","DOI":"10.3389\/fpubh.2023.1273253"},{"key":"2219_CR7","doi-asserted-by":"crossref","unstructured":"Lie SO, Lysdahlgaard S: Detection of metallic objects on digital radiographs with convolutional neural networks: an MRI screening tool. Radiography 28:466-472, 2022","DOI":"10.1016\/j.radi.2022.01.001"},{"key":"2219_CR8","doi-asserted-by":"crossref","unstructured":"Redmon J, Divvala S, Girshick R, et al.: You only look once: unified, real-time object detection. In: Proc IEEE Conf Comput Vis Pattern Recognit (CVPR), 779\u2013788, 2016","DOI":"10.1109\/CVPR.2016.91"},{"key":"2219_CR9","doi-asserted-by":"crossref","unstructured":"Mukhtar A, Cree MJ, Scott JB, et al.: Mobility aids detection using convolution neural network (CNN). In: Proc Int Conf Image Vis Comput New Zealand (IVCNZ). IEEE, 1\u20135, 2018","DOI":"10.1109\/IVCNZ.2018.8634731"},{"key":"2219_CR10","unstructured":"Ngan KH, Kaur P, Abbas A, et al.: A systematic review of privacy-preserving techniques in computer vision: from federated learning to anonymisation. Sensors (Basel) 24:6708, 2024"},{"key":"2219_CR11","doi-asserted-by":"crossref","unstructured":"Li Y, Fan Z, Liu R, et al.: Dynamic Mosaic algorithm for data augmentation. Math Biosci Eng 20:7193-7216, 2023","DOI":"10.3934\/mbe.2023311"},{"key":"2219_CR12","doi-asserted-by":"crossref","unstructured":"Padilla R, Netto SL, da Silva EAB: A survey on performance metrics for object-detection algorithms. In: Proc Int Conf Syst Signals Image Process (IWSSIP), 237\u2013242, 2020","DOI":"10.1109\/IWSSIP48289.2020.9145130"},{"key":"2219_CR13","doi-asserted-by":"crossref","unstructured":"Mirzaei B, Nezamabadi-pour H, Raoof A, et al.: Small object detection and tracking: a comprehensive review. Sensors (Basel) 23:6887, 2023","DOI":"10.3390\/s23156887"},{"key":"2219_CR14","unstructured":"Guo C, Pleiss G, Sun Y, et al.: On calibration of modern neural networks. In: Proc Int Conf Mach Learn (ICML), 1321\u20131330, 2017"},{"key":"2219_CR15","unstructured":"Ovadia Y, Fertig E, Ren J, et al.: Can you trust your model's uncertainty? Evaluating predictive uncertainty under dataset shift. In: Adv Neural Inf Process Syst (NeurIPS), 2019"},{"key":"2219_CR16","doi-asserted-by":"crossref","unstructured":"Wojke N, Bewley A, Paulus D: Simple online and realtime tracking with a deep association metric. In: Proc IEEE Int Conf Image Process (ICIP), 3645\u20133649, 2017","DOI":"10.1109\/ICIP.2017.8296962"},{"key":"2219_CR17","doi-asserted-by":"crossref","unstructured":"Chen X, Ma H, Wan J, et al.: Multi-view 3D object detection network for autonomous driving. In: Proc IEEE Conf Comput Vis Pattern Recognit (CVPR), 6526\u20136534, 2017","DOI":"10.1109\/CVPR.2017.691"},{"key":"2219_CR18","doi-asserted-by":"crossref","unstructured":"Reason J: Human error: models and management. BMJ 320:768-770, 2000","DOI":"10.1136\/bmj.320.7237.768"},{"key":"2219_CR19","doi-asserted-by":"crossref","unstructured":"van der Sijs H, Aarts J, Vulto A, et al.: Overriding of drug safety alerts in computerized physician order entry. J Am Med Inform Assoc 13:138-147, 2006","DOI":"10.1197\/jamia.M1809"},{"key":"2219_CR20","doi-asserted-by":"crossref","unstructured":"He K, Girshick R, Doll\u00e1r P: Rethinking ImageNet pre-training. In: Proc IEEE\/CVF Int Conf Comput Vis (ICCV), 4918\u20134927, 2019","DOI":"10.1109\/ICCV.2019.00502"},{"key":"2219_CR21","unstructured":"Raghu M, Zhang C, Kleinberg J, et al.: Transfusion: understanding transfer learning for medical imaging. In: Adv Neural Inf Process Syst (NeurIPS), 3342\u20133352, 2019"},{"key":"2219_CR22","doi-asserted-by":"crossref","unstructured":"Guan H, Liu M: Domain adaptation for medical image analysis: a survey. IEEE Trans Biomed Eng 69:1173-1185, 2022","DOI":"10.1109\/TBME.2021.3117407"},{"key":"2219_CR23","doi-asserted-by":"crossref","unstructured":"Pooch EHP, Ballester P, Barros RC: Can we trust deep learning based diagnosis? The impact of domain shift in chest radiograph classification. In: Thoracic Image Analysis (LNCS 12502), 74\u201383, 2020","DOI":"10.1007\/978-3-030-62469-9_7"}],"container-title":["Journal of Imaging Informatics in Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10278-026-02219-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10278-026-02219-0","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10278-026-02219-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,26]],"date-time":"2026-08-26T16:38:47Z","timestamp":1787762327000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10278-026-02219-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,26]]},"references-count":23,"alternative-id":["2219"],"URL":"https:\/\/doi.org\/10.1007\/s10278-026-02219-0","relation":{},"ISSN":["2948-2933"],"issn-type":[{"value":"2948-2933","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,26]]},"assertion":[{"value":"8 July 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 August 2026","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 August 2026","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 August 2026","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Ethics approval was not required because the study fell outside the scope of the Japanese \u201cEthical Guidelines for Medical and Biological Research Involving Human Subjects.\u201d It involved the secondary analysis of surveillance footage originally recorded for routine safety-management purposes. No medical records or personally identifiable information were accessed, and no medical or biological data were obtained from individuals. Prior to analysis, all video frames were de-identified by automatic mosaic processing of faces, name badges, and other identifying information. Although formal ethics approval was not required,\u00a0the study was performed in line with the principles of the Declaration of Helsinki.","order":1,"name":"Ethics","label":"Ethics Approval","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"As the study used de-identified surveillance footage and no identifiable individual data, individual consent to participate was not applicable.","order":2,"name":"Ethics","label":"Consent to Participate","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"No images or data identifying individual persons are included in this article. All persons appearing in the source footage were de-identified by mosaic processing, and no identifying images are published.","order":3,"name":"Ethics","label":"Consent for Publication","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"During the preparation of this work, the authors used Claude (Anthropic, San Francisco, CA, USA) via the claude.ai web interface for (i) the generation and debugging of Python code for YOLOv8 model training, dataset construction, statistical analysis (bootstrap resampling, performance-metric calculation), and data visualisation; (ii) English-language editing; and (iii) reference-formatting assistance. During revision, the assistant was additionally used to help regenerate figures from the source data, to recompute the reported performance metrics for verification, and to draft manuscript text. All AI-assisted outputs, including all recomputed values and figures, were reviewed, verified against the source data, and edited by the authors, who take full responsibility for the accuracy, scientific validity, and completeness of all content in this manuscript. This use is also documented in the Methods section of the manuscript.","order":4,"name":"Ethics","label":"Declaration of Generative AI and AI-Assisted Technologies","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":5,"name":"Ethics","label":"Competing Interests","group":{"name":"EthicsHeading","label":"Declarations"}}]}}