{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,23]],"date-time":"2025-09-23T12:21:48Z","timestamp":1758630108287,"version":"3.37.3"},"reference-count":25,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2022,6,29]],"date-time":"2022-06-29T00:00:00Z","timestamp":1656460800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2022,6,29]],"date-time":"2022-06-29T00:00:00Z","timestamp":1656460800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100000272","name":"National Institute for Health Research","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000272","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Digit Imaging"],"published-print":{"date-parts":[[2022,12]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Flagging the presence of cardiac devices such as pacemakers before an MRI scan is essential to allow appropriate safety checks. We assess the accuracy with which a machine learning model can classify the presence or absence of a pacemaker on pre-existing chest radiographs. A total of 7973 chest radiographs were collected, 3996 with pacemakers visible and 3977 without. Images were identified from information available on the radiology information system (RIS) and correlated with report text. Manual review of images by two board certified radiologists was performed to ensure correct labeling. The data set was divided into training, validation, and a hold-back test set. The data were used to retrain a pre-trained image classification neural network. Final model performance was assessed on the test set. Accuracy of 99.67% on the test set was achieved. Re-testing the final model on the full training and validation data revealed a few additional misclassified examples which are further analyzed. Neural network image classification could be used to screen for the presence of cardiac devices, in addition to current safety processes, providing notification of device presence in advance of safety questionnaires. Computational power to run the model is low. Further work on misclassified examples could improve accuracy on edge cases. The focus of many healthcare applications of computer vision techniques has been for diagnosis and guiding management. This work illustrates an application of computer vision image classification to enhance current processes and improve patient safety.<\/jats:p>","DOI":"10.1007\/s10278-022-00663-2","type":"journal-article","created":{"date-parts":[[2022,6,29]],"date-time":"2022-06-29T16:02:53Z","timestamp":1656518573000},"page":"1673-1680","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Neural Network Detection of Pacemakers for MRI Safety"],"prefix":"10.1007","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6689-4033","authenticated-orcid":false,"given":"Mark Daniel Vernon","family":"Thurston","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniel H","family":"Kim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huub K","family":"Wit","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,6,29]]},"reference":[{"issue":"12","key":"663_CR1","doi-asserted-by":"publisher","first-page":"912","DOI":"10.1016\/j.crad.2019.07.006","volume":"74","author":"A Cunqueiro","year":"2019","unstructured":"Cunqueiro A, Lipton ML, Dym RJ, Jain VR, Sterman J, Scheinfeld MH. Performing MRI on patients with MRI-conditional and non-conditional cardiac implantable electronic devices: an update for radiologists. Clin Radiol. 2019 Dec;74(12):912\u20137.","journal-title":"Clin Radiol."},{"issue":"8","key":"663_CR2","doi-asserted-by":"publisher","first-page":"755","DOI":"10.1056\/NEJMoa1603265","volume":"376","author":"RJ Russo","year":"2017","unstructured":"Russo RJ, Costa HS, Silva PD, Anderson JL, Arshad A, Biederman RWW, et al. Assessing the Risks Associated with MRI in Patients with a Pacemaker or Defibrillator. N Engl J Med. 2017 Feb 23;376(8):755\u201364.","journal-title":"N Engl J Med."},{"issue":"1","key":"663_CR3","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1186\/1532-429X-13-63","volume":"13","author":"JS Shinbane","year":"2011","unstructured":"Shinbane JS, Colletti PM, Shellock FG. Magnetic resonance imaging in patients with cardiac pacemakers: era of \u2018MR Conditional\u2019 designs. J Cardiovasc Magn Reson. 2011 Dec;13(1):63.","journal-title":"J Cardiovasc Magn Reson."},{"issue":"9","key":"663_CR4","doi-asserted-by":"publisher","first-page":"1348","DOI":"10.1016\/j.hlc.2021.02.011","volume":"30","author":"D Kocyigit","year":"2021","unstructured":"Kocyigit D, Abozeed M, Kwon DH, Flamm SD, Wilkoff BL, Jellis CL. Predictors of Cardiac Implantable Electronic Device Artifact on Cardiac MRI: The Utility of a Device Related Score. Heart Lung Circ. 2021 Sep;30(9):1348\u201355.","journal-title":"Heart Lung Circ."},{"issue":"4","key":"663_CR5","doi-asserted-by":"publisher","first-page":"326","DOI":"10.1111\/j.1540-8159.2005.50024.x","volume":"28","author":"R Kalin","year":"2005","unstructured":"Kalin R, Stanton MS. Current Clinical Issues for MRI Scanning of Pacemaker and Defibrillator Patients. Pacing Clin Electrophysiol. 2005 Apr;28(4):326\u20138.","journal-title":"Pacing Clin Electrophysiol."},{"issue":"4","key":"663_CR6","doi-asserted-by":"publisher","first-page":"1140","DOI":"10.2214\/AJR.08.1038.2","volume":"191","author":"FG Shellock","year":"2008","unstructured":"Shellock FG, Spinazzi A. MRI Safety Update 2008: Part 2, Screening Patients for MRI. Am J Roentgenol. 2008 Oct;191(4):1140\u20139.","journal-title":"Am J Roentgenol."},{"issue":"1","key":"663_CR7","doi-asserted-by":"publisher","first-page":"171","DOI":"10.1007\/s13244-016-0534-1","volume":"8","author":"AP Brady","year":"2017","unstructured":"Brady AP. Error and discrepancy in radiology: inevitable or avoidable? Insights Imaging. 2017 Feb;8(1):171\u201382.","journal-title":"Insights Imaging."},{"key":"663_CR8","unstructured":"Syed M. Black box thinking: the surprising truth about success (and why some people never learn from their mistakes) [Internet]. 2015 [cited 2021 Jun 7]. Available from: https:\/\/www.overdrive.com\/search?q=3D424063-F4A2-422B-B5A6-1DF22253BB0D"},{"key":"663_CR9","doi-asserted-by":"crossref","unstructured":"Turing AM. I.\u2014COMPUTING MACHINERY AND INTELLIGENCE. Mind. 1950 Oct 1;LIX(236):433\u201360.","DOI":"10.1093\/mind\/LIX.236.433"},{"key":"663_CR10","first-page":"361","volume-title":"Deep learning with Python","author":"F Chollet","year":"2018","unstructured":"Chollet F. Deep learning with Python. Shelter Island, New York: Manning Publications Co; 2018. 361 p."},{"issue":"10","key":"663_CR11","doi-asserted-by":"publisher","first-page":"887","DOI":"10.1097\/MNM.0000000000000890","volume":"39","author":"DH Kim","year":"2018","unstructured":"Kim DH, Wit H, Thurston M. Artificial intelligence in the diagnosis of Parkinson\u2019s disease from ioflupane-123 single-photon emission computed tomography dopamine transporter scans using transfer learning. Nucl Med Commun. 2018 Oct;39(10):887\u201393.","journal-title":"Nucl Med Commun."},{"issue":"5","key":"663_CR12","doi-asserted-by":"publisher","first-page":"439","DOI":"10.1016\/j.crad.2017.11.015","volume":"73","author":"DH Kim","year":"2018","unstructured":"Kim DH, MacKinnon T. Artificial intelligence in fracture detection: transfer learning from deep convolutional neural networks. Clin Radiol. 2018 May;73(5):439\u201345.","journal-title":"Clin Radiol."},{"issue":"1122","key":"663_CR13","doi-asserted-by":"publisher","first-page":"20201407","DOI":"10.1259\/bjr.20201407","volume":"94","author":"D Kim","year":"2021","unstructured":"Kim D, Wit H, Thurston M, Long M, Maskell G, Strugnell M, et al. An artificial intelligence deep learning model for identification of small bowel obstruction on plain abdominal radiographs. Br J Radiol. 2021 Jun 1;94(1122):20201407.","journal-title":"Br J Radiol."},{"key":"663_CR14","unstructured":"Irvin J, Rajpurkar P, Ko M, Yu Y, Ciurea-Ilcus S, Chute C, et al. CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparison. ArXiv190107031 Cs Eess [Internet]. 2019 Jan 21 [cited 2021 Jun 7]; Available from: http:\/\/arxiv.org\/abs\/1901.07031"},{"key":"663_CR15","doi-asserted-by":"publisher","DOI":"10.1016\/j.measurement.2019.106945","volume":"148","author":"MM Sorkhabi","year":"2019","unstructured":"Sorkhabi MM, Saadat Khajeh M. Classification of alveolar bone density using 3-D deep convolutional neural network in the cone-beam CT images: A 6-month clinical study. Measurement. 2019 Dec;148:106945.","journal-title":"Measurement."},{"issue":"1","key":"663_CR16","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1038\/s41746-019-0103-3","volume":"2","author":"A Nelson","year":"2019","unstructured":"Nelson A, Herron D, Rees G, Nachev P. Predicting scheduled hospital attendance with artificial intelligence. Npj Digit Med. 2019 Dec;2(1):26.","journal-title":"Npj Digit Med."},{"key":"663_CR17","doi-asserted-by":"crossref","unstructured":"Eichelberg M, Riesmeier J, Wilkens T, Hewett AJ, Barth A, Jensch P. Ten years of medical imaging standardization and prototypical implementation: the DICOM standard and the OFFIS DICOM toolkit (DCMTK). In: Ratib OM, Huang HK, editors. San Diego, CA; 2004 [cited 2021 Jun 7]. p. 57. Available from: https:\/\/www.proceedings.spiedigitallibrary.org\/proceeding.aspx?doi=10.1117\/12.534853","DOI":"10.1117\/12.534853"},{"key":"663_CR18","unstructured":"Chollet F, others. Keras [Internet]. 2015. Available from: https:\/\/keras.io"},{"key":"663_CR19","unstructured":"Mart\u00edn Abadi, Ashish Agarwal, Paul Barham, Eugene Brevdo, Zhifeng Chen, Craig Citro, et al. TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems [Internet]. 2015. Available from: https:\/\/www.tensorflow.org\/"},{"key":"663_CR20","first-page":"87","volume-title":"Positioning and Power in Academic Publishing: Players, Agents and Agendas","author":"T Kluyver","year":"2016","unstructured":"Kluyver T, Ragan-Kelley B, P\u00e9rez F, Granger B, Bussonnier M, Frederic J, et al. Jupyter Notebooks \u2013 a publishing format for reproducible computational workflows. In: Loizides F, Schmidt B, editors. Positioning and Power in Academic Publishing: Players, Agents and Agendas. IOS Press; 2016. p. 87\u201390."},{"key":"663_CR21","unstructured":"Simonyan K, Zisserman A. Very Deep Convolutional Networks for Large-Scale Image Recognition. ArXiv14091556 Cs [Internet]. 2015 Apr 10 [cited 2021 Apr 29]; Available from: http:\/\/arxiv.org\/abs\/1409.1556"},{"key":"663_CR22","unstructured":"Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z. Rethinking the Inception Architecture for Computer Vision. ArXiv151200567 Cs [Internet]. 2015 Dec 11 [cited 2021 Jul 21]; Available from: http:\/\/arxiv.org\/abs\/1512.00567"},{"key":"663_CR23","first-page":"418","volume-title":"The book of why: the new science of cause and effect","author":"J Pearl","year":"2018","unstructured":"Pearl J, Mackenzie D. The book of why: the new science of cause and effect. London: Allen Lane; 2018. 418 p."},{"issue":"5","key":"663_CR24","doi-asserted-by":"publisher","first-page":"576","DOI":"10.1016\/j.jacep.2019.02.003","volume":"5","author":"JP Howard","year":"2019","unstructured":"Howard JP, Fisher L, Shun-Shin MJ, Keene D, Arnold AD, Ahmad Y, et al. Cardiac Rhythm Device Identification Using Neural Networks. JACC Clin Electrophysiol. 2019 May;5(5):576\u201386.","journal-title":"JACC Clin Electrophysiol."},{"issue":"1","key":"663_CR25","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1038\/s41746-020-00376-2","volume":"4","author":"A Esteva","year":"2021","unstructured":"Esteva A, Chou K, Yeung S, Naik N, Madani A, Mottaghi A, et al. Deep learning-enabled medical computer vision. Npj Digit Med. 2021 Dec;4(1):5.","journal-title":"Npj Digit Med."}],"container-title":["Journal of Digital Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10278-022-00663-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10278-022-00663-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10278-022-00663-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,30]],"date-time":"2022-11-30T19:20:24Z","timestamp":1669836024000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10278-022-00663-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6,29]]},"references-count":25,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2022,12]]}},"alternative-id":["663"],"URL":"https:\/\/doi.org\/10.1007\/s10278-022-00663-2","relation":{},"ISSN":["0897-1889","1618-727X"],"issn-type":[{"type":"print","value":"0897-1889"},{"type":"electronic","value":"1618-727X"}],"subject":[],"published":{"date-parts":[[2022,6,29]]},"assertion":[{"value":"31 October 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 April 2022","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 May 2022","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 June 2022","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The protocol was authored in collaboration with the research and development teams in Hospital 1 (lead site and study sponsor) and Hospital 2. The project protocol was registered prospectively via the Integrated Research Application System (IRAS). The protocol was approved by the UK Health Research Authority (HRA). We consulted extensively with the research and development department of the sponsor organization (Hospital 1) who determined that ethics approval was not required as the project was retrospective, using only anonymized and preexisting data.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics Approval"}},{"value":"This study was supported in part by National Institute for Health Research (NIHR) funding awarded to Dr Mark Thurston. Dr Daniel Kim is providing support to core research projects for the National Consortium of Intelligent Medical Imaging (NCIMI) which currently involves collaboration with the University of Oxford, General Electric, Brainomix, and Alliance Medical","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing Interests"}}]}}