{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,7]],"date-time":"2026-09-07T19:14:42Z","timestamp":1788808482773,"version":"build-2803163510"},"reference-count":17,"publisher":"Ovid Technologies (Wolters Kluwer Health)","issue":"18","content-domain":{"domain":["lww.com","ovid.com"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,9,21]]},"abstract":"<jats:sec>\n                    <jats:title>Background:<\/jats:title>\n                    <jats:p>Establishing imaging registries for large patient cohorts is challenging because manual labeling is tedious and relying solely on DICOM (digital imaging and communications in medicine) metadata can result in errors. We endeavored to establish an automated hip and pelvic radiography registry of total hip arthroplasty (THA) patients by utilizing deep-learning pipelines. The aims of the study were (1) to utilize these automated pipelines to identify all pelvic and hip radiographs with appropriate annotation of laterality and presence or absence of implants, and (2) to automatically measure acetabular component inclination and version for THA images.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods:<\/jats:title>\n                    <jats:p>We retrospectively retrieved 846,988 hip and pelvic radiography DICOM files from 20,378 patients who underwent primary or revision THA performed at our institution from 2000 to 2020. Metadata for the files were screened followed by extraction of imaging data. Two deep-learning algorithms (an EfficientNetB3 classifier and a YOLOv5 object detector) were developed to automatically determine the radiographic appearance of all files. Additional deep-learning algorithms were utilized to automatically measure the acetabular angles on anteroposterior pelvic and lateral hip radiographs. Algorithm performance was compared with that of human annotators on a random test sample of 5,000 radiographs.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results:<\/jats:title>\n                    <jats:p>Deep-learning algorithms enabled appropriate exclusion of 209,332 DICOM files (24.7%) as misclassified non-hip\/pelvic radiographs or having corrupted pixel data. The final registry was automatically curated and annotated in &lt;8 hours and included 168,551 anteroposterior pelvic, 176,890 anteroposterior hip, 174,637 lateral hip, and 117,578 oblique hip radiographs. The algorithms achieved 99.9% accuracy, 99.6% precision, 99.5% recall, and a 99.6% F1 score in determining the radiograph appearance.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions:<\/jats:title>\n                    <jats:p>We developed a highly accurate series of deep-learning algorithms to rapidly curate and annotate THA patient radiographs. This efficient pipeline can be utilized by other institutions or registries to construct radiography databases for patient care, longitudinal surveillance, and large-scale research. The stepwise approach for establishing a radiography registry can further be utilized as a workflow guide for other anatomic areas.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Level of Evidence:<\/jats:title>\n                    <jats:p>\n                      Diagnostic\n                      <jats:underline>Level IV<\/jats:underline>\n                      . See Instructions for Authors for a complete description of levels of evidence.\n                    <\/jats:p>\n                  <\/jats:sec>","DOI":"10.2106\/jbjs.21.01229","type":"journal-article","created":{"date-parts":[[2022,7,22]],"date-time":"2022-07-22T08:01:22Z","timestamp":1658476882000},"page":"1649-1658","update-policy":"https:\/\/doi.org\/10.1097\/lww.0000000000001000","source":"Crossref","is-referenced-by-count":46,"title":["Applying Deep Learning to Establish a Total Hip Arthroplasty Radiography Registry"],"prefix":"10.2106","volume":"104","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4664-0751","authenticated-orcid":false,"given":"Pouria","family":"Rouzrokh","sequence":"first","affiliation":[{"name":"Radiology Informatics Laboratory, Department of Radiology, Mayo Clinic, Rochester, Minnesota"},{"name":"Orthopedic Surgery Artificial Intelligence Laboratory (OSAIL), Mayo Clinic, Rochester, Minnesota"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7926-6095","authenticated-orcid":false,"given":"Bardia","family":"Khosravi","sequence":"additional","affiliation":[{"name":"Radiology Informatics Laboratory, Department of Radiology, Mayo Clinic, Rochester, Minnesota"},{"name":"Orthopedic Surgery Artificial Intelligence Laboratory (OSAIL), Mayo Clinic, Rochester, Minnesota"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6380-7261","authenticated-orcid":false,"given":"Quinn J.","family":"Johnson","sequence":"additional","affiliation":[{"name":"Orthopedic Surgery Artificial Intelligence Laboratory (OSAIL), Mayo Clinic, Rochester, Minnesota"},{"name":"Mayo Clinic Alix School of Medicine, Mayo Clinic, Rochester, Minnesota"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3275-2971","authenticated-orcid":false,"given":"Shahriar","family":"Faghani","sequence":"additional","affiliation":[{"name":"Radiology Informatics Laboratory, Department of Radiology, Mayo Clinic, Rochester, Minnesota"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Diana V.","family":"Vera Garcia","sequence":"additional","affiliation":[{"name":"Radiology Informatics Laboratory, Department of Radiology, Mayo Clinic, Rochester, Minnesota"},{"name":"Orthopedic Surgery Artificial Intelligence Laboratory (OSAIL), Mayo Clinic, Rochester, Minnesota"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bradley J.","family":"Erickson","sequence":"additional","affiliation":[{"name":"Radiology Informatics Laboratory, Department of Radiology, Mayo Clinic, Rochester, Minnesota"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3882-602X","authenticated-orcid":false,"given":"Hilal","family":"Maradit Kremers","sequence":"additional","affiliation":[{"name":"Orthopedic Surgery Artificial Intelligence Laboratory (OSAIL), Mayo Clinic, Rochester, Minnesota"},{"name":"Department of Health Sciences Research, Mayo Clinic, Rochester, Minnesota"},{"name":"Department of Orthopedic Surgery, Mayo Clinic, Rochester, Minnesota"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7636-0489","authenticated-orcid":false,"given":"Michael J.","family":"Taunton","sequence":"additional","affiliation":[{"name":"Orthopedic Surgery Artificial Intelligence Laboratory (OSAIL), Mayo Clinic, Rochester, Minnesota"},{"name":"Department of Orthopedic Surgery, Mayo Clinic, Rochester, Minnesota"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8629-7567","authenticated-orcid":false,"given":"Cody C.","family":"Wyles","sequence":"additional","affiliation":[{"name":"Orthopedic Surgery Artificial Intelligence Laboratory (OSAIL), Mayo Clinic, Rochester, Minnesota"},{"name":"Department of Orthopedic Surgery, Mayo Clinic, Rochester, Minnesota"},{"name":"Department of Clinical Anatomy, Mayo Clinic, Rochester, Minnesota"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"276","published-online":{"date-parts":[[2022,7,21]]},"reference":[{"issue":"3","key":"bib1-20260212","first-page":"1","article-title":"Patient registries and rare diseases","volume":"20","author":"Gliklich","year":"2011","journal-title":"Appl Clin Trials."},{"issue":"3","key":"bib3-20260212","doi-asserted-by":"crossref","first-page":"276","DOI":"10.1016\/j.jcmg.2017.01.003","article-title":"Imaging Registries and Single-Center Series","volume":"10","author":"Hachamovitch","year":"2017","journal-title":"JACC Cardiovasc Imaging."},{"issue":"20","key":"bib4-20260212","doi-asserted-by":"crossref","first-page":"2230","DOI":"10.1016\/j.jacc.2015.07.010","article-title":"ACC\/AHA\/STS Statement on the Future of Registries and the Performance Measurement Enterprise: A Report of the American College of Cardiology\/American Heart Association Task Force on Performance Measures and The Society of Thoracic Surgeons","volume":"66","author":"Bhatt","year":"2015","journal-title":"J Am Coll Cardiol."},{"issue":"11","key":"bib5-20260212","doi-asserted-by":"crossref","first-page":"1133","DOI":"10.1016\/j.crad.2005.07.003","article-title":"DICOM demystified: a review of digital file formats and their use in radiological practice","volume":"60","author":"Graham","year":"2005","journal-title":"Clin Radiol."},{"issue":"1","key":"bib6-20260212","doi-asserted-by":"crossref","first-page":"4","DOI":"10.4103\/0971-3026.95396","article-title":"Managing DICOM images: Tips and tricks for the radiologist","volume":"22","author":"Varma","year":"2012","journal-title":"Indian J Radiol Imaging."},{"issue":"3","key":"bib7-20260212","doi-asserted-by":"crossref","first-page":"199","DOI":"10.1136\/jamia.1997.0040199","article-title":"Understanding and using DICOM, the data interchange standard for biomedical imaging","volume":"4","author":"Bidgood","year":"1997","journal-title":"J Am Med Inform Assoc."},{"key":"bib8-20260212","doi-asserted-by":"crossref","first-page":"100134","DOI":"10.1016\/j.mlwa.2021.100134","article-title":"Deep learning in computer vision: A critical review of emerging techniques and application scenarios","volume":"6","author":"Chai","year":"2021","journal-title":"Machine Learning with Applications."},{"issue":"3 Pt B","key":"bib9-20260212","doi-asserted-by":"crossref","first-page":"521","DOI":"10.1016\/j.jacr.2017.12.027","article-title":"Deep Learning in Radiology: Does One Size Fit All?","volume":"15","author":"Erickson","year":"2018","journal-title":"J Am Coll Radiol."},{"issue":"11","key":"bib10-20260212","doi-asserted-by":"crossref","first-page":"713","DOI":"10.21037\/atm.2020.02.44","article-title":"A review of the application of deep learning in medical image classification and segmentation","volume":"8","author":"Cai","year":"2020","journal-title":"Ann Transl Med."},{"issue":"5","key":"bib11-20260212","doi-asserted-by":"crossref","first-page":"820","DOI":"10.1109\/JPROC.2021.3054390","article-title":"A Review of Deep Learning in Medical Imaging: Imaging Traits, Technology Trends, Case Studies With Progress Highlights, and Future Promises","volume":"109","author":"Zhou","year":"2021","journal-title":"Proc IEEE."},{"issue":"7","key":"bib14-20260212","doi-asserted-by":"crossref","first-page":"2510","DOI":"10.1016\/j.arth.2021.02.026","article-title":"Deep Learning Tool for Automated Radiographic Measurement of Acetabular Component Inclination and Version Following Total Hip Arthroplasty","volume":"36","author":"Rouzrokh","year":"2021","journal-title":"J Arthroplasty."},{"issue":"3","key":"bib15-20260212","doi-asserted-by":"crossref","first-page":"239","DOI":"10.2106\/JBJS.21.00406","article-title":"Redefining the 3D Topography of the Acetabular Safe Zone. A Multivariable Study Evaluating Prosthetic Hip Stability","volume":"104","author":"Hevesi","year":"2022","journal-title":"J Bone Joint Surg Am."},{"issue":"2","key":"bib16-20260212","doi-asserted-by":"crossref","first-page":"688","DOI":"10.1016\/j.arth.2020.07.076","article-title":"Automated Detection of Periprosthetic Joint Infections and Data Elements Using Natural Language Processing","volume":"36","author":"Fu","year":"2021","journal-title":"J Arthroplasty."},{"issue":"3","key":"bib17-20260212","doi-asserted-by":"crossref","first-page":"922","DOI":"10.1016\/j.arth.2020.09.029","article-title":"Use of Natural Language Processing Algorithms to Identify Common Data Elements in Operative Notes for Knee Arthroplasty","volume":"36","author":"Sagheb","year":"2021","journal-title":"J Arthroplasty."},{"issue":"10","key":"bib18-20260212","doi-asserted-by":"crossref","first-page":"2216","DOI":"10.1016\/j.arth.2019.07.025","article-title":"Use of Natural Language Processing Tools to Identify and Classify Periprosthetic Femur Fractures","volume":"34","author":"Tibbo","year":"2019","journal-title":"J Arthroplasty."},{"issue":"21","key":"bib19-20260212","doi-asserted-by":"crossref","first-page":"1931","DOI":"10.2106\/JBJS.19.00071","article-title":"Use of Natural Language Processing Algorithms to Identify Common Data Elements in Operative Notes for Total Hip Arthroplasty","volume":"101","author":"Wyles","year":"2019","journal-title":"J Bone Joint Surg Am."},{"issue":"3","key":"bib20-20260212","doi-asserted-by":"crossref","first-page":"e210206","DOI":"10.1148\/ryai.210206","article-title":"Deep Learning for Radiographic Measurement of Femoral Component Subsidence Following Total Hip Arthroplasty","volume":"4","author":"Rouzrokh","year":"2022","journal-title":"Radiol Artif Intell."}],"container-title":["Journal of Bone and Joint Surgery"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.ovid.com\/10.2106\/JBJS.21.01229","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,26]],"date-time":"2026-08-26T13:55:00Z","timestamp":1787752500000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ovid.com\/10.2106\/JBJS.21.01229"}},"subtitle":["A Stepwise Approach"],"short-title":[],"issued":{"date-parts":[[2022,7,21]]},"references-count":17,"journal-issue":{"issue":"18","published-print":{"date-parts":[[2022]]}},"URL":"https:\/\/doi.org\/10.2106\/jbjs.21.01229","relation":{},"ISSN":["0021-9355","1535-1386"],"issn-type":[{"value":"0021-9355","type":"print"},{"value":"1535-1386","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,7,21]]}}}