Jinchi Wei1, David Li2, David C Sing3, JaeWon Yang4, Indeevar Beeram3, Varun Puvanesarajah5, Craig J Della Valle6, Paul Tornetta3, Jan Fritz7, Paul H Yi8. 1. Department of Biomedical Engineering, Johns Hopkins University, Baltimore, MD, USA. 2. Faculty of Medicine, University of Ottawa, Ottawa, ON, Canada. 3. Department of Orthopaedic Surgery, Boston University School of Medicine, Boston, MA, USA. 4. Department of Orthopaedic Surgery, University of Washington School of Medicine, Seattle, WA, USA. 5. Department of Orthopaedic Surgery, Columbia University, New York, NY, USA. 6. Department of Orthopaedic Surgery, Rush University Medical Center, Chicago, IL, USA. 7. Department of Radiology, New York University Grossman School of Medicine, New York, NY, USA. 8. University of Maryland Medical Intelligent Imaging (UM2ii) Center, Department of Diagnostic Radiology and Nuclear Medicine, University of Maryland, University of Maryland School of Medicine, MD, Baltimore, USA. pyi@som.umaryland.edu.
Abstract
OBJECTIVE: Periprosthetic dislocations of total hip arthroplasty (THA) are time-sensitive injuries, as the longer diagnosis and treatment are delayed, the more difficult they are to reduce. Automated triage of radiographs with dislocations could help reduce these delays. We trained convolutional neural networks (CNNs) for the detection of THA dislocations, and evaluated their generalizability by evaluating them on external datasets. METHODS: We used 357 THA radiographs from a single hospital (185 with dislocation [51.8%]) to develop and internally test a variety of CNNs to identify THA dislocation. We performed external testing of these CNNs on two datasets to evaluate generalizability. CNN performance was evaluated using area under the receiving operating characteristic curve (AUROC). Class activation mapping (CAM) was used to create heatmaps of test images for visualization of regions emphasized by the CNNs. RESULTS: Multiple CNNs achieved AUCs of 1 for both internal and external test sets, indicating good generalizability. Heatmaps showed that CNNs consistently emphasized the THA for both dislocated and located THAs. CONCLUSION: CNNs can be trained to recognize THA dislocation with high diagnostic performance, which supports their potential use for triage in the emergency department. Importantly, our CNNs generalized well to external data from two sources, further supporting their potential clinical utility.
OBJECTIVE: Periprosthetic dislocations of total hip arthroplasty (THA) are time-sensitive injuries, as the longer diagnosis and treatment are delayed, the more difficult they are to reduce. Automated triage of radiographs with dislocations could help reduce these delays. We trained convolutional neural networks (CNNs) for the detection of THA dislocations, and evaluated their generalizability by evaluating them on external datasets. METHODS: We used 357 THA radiographs from a single hospital (185 with dislocation [51.8%]) to develop and internally test a variety of CNNs to identify THA dislocation. We performed external testing of these CNNs on two datasets to evaluate generalizability. CNN performance was evaluated using area under the receiving operating characteristic curve (AUROC). Class activation mapping (CAM) was used to create heatmaps of test images for visualization of regions emphasized by the CNNs. RESULTS: Multiple CNNs achieved AUCs of 1 for both internal and external test sets, indicating good generalizability. Heatmaps showed that CNNs consistently emphasized the THA for both dislocated and located THAs. CONCLUSION: CNNs can be trained to recognize THA dislocation with high diagnostic performance, which supports their potential use for triage in the emergency department. Importantly, our CNNs generalized well to external data from two sources, further supporting their potential clinical utility.
Authors: Paul H Yi; Tae Kyung Kim; Jinchi Wei; Jiwon Shin; Ferdinand K Hui; Haris I Sair; Gregory D Hager; Jan Fritz Journal: Pediatr Radiol Date: 2019-04-30
Authors: Joseph J Titano; Marcus Badgeley; Javin Schefflein; Margaret Pain; Andres Su; Michael Cai; Nathaniel Swinburne; John Zech; Jun Kim; Joshua Bederson; J Mocco; Burton Drayer; Joseph Lehar; Samuel Cho; Anthony Costa; Eric K Oermann Journal: Nat Med Date: 2018-08-13 Impact factor: 53.440
Authors: Justin D Krogue; Kaiyang V Cheng; Kevin M Hwang; Paul Toogood; Eric G Meinberg; Erik J Geiger; Musa Zaid; Kevin C McGill; Rina Patel; Jae Ho Sohn; Alexandra Wright; Bryan F Darger; Kevin A Padrez; Eugene Ozhinsky; Sharmila Majumdar; Valentina Pedoia Journal: Radiol Artif Intell Date: 2020-03-25
Authors: David K Eng; Nishith B Khandwala; Jin Long; Nancy R Fefferman; Shailee V Lala; Naomi A Strubel; Sarah S Milla; Ross W Filice; Susan E Sharp; Alexander J Towbin; Michael L Francavilla; Summer L Kaplan; Kirsten Ecklund; Sanjay P Prabhu; Brian J Dillon; Brian M Everist; Christopher G Anton; Mark E Bittman; Rebecca Dennis; David B Larson; Jayne M Seekins; Cicero T Silva; Arash R Zandieh; Curtis P Langlotz; Matthew P Lungren; Safwan S Halabi Journal: Radiology Date: 2021-09-28 Impact factor: 11.105