Artificial Intelligence for Automated Implant Identification in Total Hip Arthroplasty: A Multicenter External Validation Study Exceeding Two Million Plain Radiographs. Journal Article

Local Library Link: Find It @ Loyola

Authors: Karnuta, JM; Murphy, MP; Luu, BC; Ryan, MJ; Haeberle, HS; Brown, NM; Iorio, R; Chen, AF; Ramkumar, PN
Article Title: Artificial Intelligence for Automated Implant Identification in Total Hip Arthroplasty: A Multicenter External Validation Study Exceeding Two Million Plain Radiographs.
Abstract: BACKGROUND: The surgical management of complications after total hip arthroplasty (THA) necessitates accurate identification of the femoral implant manufacturer and model. Automated image processing using deep learning has been previously developed and internally validated; however, external validation is necessary prior to responsible application of artificial intelligence (AI)-based technologies. METHODS: We trained, validated, and externally tested a deep-learning system to classify femoral-sided THA implants as one of 8 models from two manufacturers derived from 2,954 original deidentified retrospectively collected anteroposterior (AP) plain radiographs across three academic referral centers and 13 surgeons. From these radiographs, 2,117 were used for training, 249 for validation, and 588 for external testing. Augmentation was applied to the training set (n=2,117,000) to increase model robustness. Performance was evaluated by area under the receiver-operating characteristic curve (AUC), sensitivity, specificity, and accuracy. Implant identification processing speed was calculated. RESULTS: The training and testing set were drawn from statistically different populations of implants (p 0.001). After 1,000 training epochs by the deep-learning system, the system discriminated 8 implant models with a mean AUC of 0.991, accuracy of 97.9%, sensitivity of 88.6%, and specificity of 98.9% in the external-testing dataset of 588 AP radiographs. The software classified implants at a mean speed of 0.02 seconds per image. CONCLUSIONS: An AI-based software demonstrated excellent internal and external validation. While continued surveillance is necessary with implant library expansion, this software represents responsible and meaningful clinical application of AI with immediate potential to globally scale and assist in preoperative planning prior to revision THA.
Journal Title: The Journal of arthroplasty
ISSN: 1532-8406; 0883-5403
Publisher: Unknown  
Date Published: 2022