دورية أكاديمية
THA-AID: Deep Learning Tool for Total Hip Arthroplasty Automatic Implant Detection With Uncertainty and Outlier Quantification.
| العنوان: | THA-AID: Deep Learning Tool for Total Hip Arthroplasty Automatic Implant Detection With Uncertainty and Outlier Quantification. |
|---|---|
| المؤلفون: | Rouzrokh P; Department of Radiology, Mayo Clinic, Rochester, Minnesota., Mickley JP; Department of Orthopedic Surgery, Mayo Clinic, Rochester, Minnesota., Khosravi B; Department of Radiology, Mayo Clinic, Rochester, Minnesota., Faghani S; Department of Radiology, Mayo Clinic, Rochester, Minnesota., Moassefi M; Department of Radiology, Mayo Clinic, Rochester, Minnesota., Schulz WR; Department of Orthopedic Surgery, Mayo Clinic, Rochester, Minnesota., Erickson BJ; Department of Radiology, Mayo Clinic, Rochester, Minnesota., Taunton MJ; Department of Orthopedic Surgery, Mayo Clinic, Rochester, Minnesota., Wyles CC; Department of Orthopedic Surgery, Mayo Clinic, Rochester, Minnesota. |
| المصدر: | The Journal of arthroplasty [J Arthroplasty] 2024 Apr; Vol. 39 (4), pp. 966-973.e17. Date of Electronic Publication: 2023 Sep 26. |
| نوع المنشور: | Journal Article |
| اللغة: | English |
| بيانات الدورية: | Publisher: Taylor and Francis Country of Publication: United States NLM ID: 8703515 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 1532-8406 (Electronic) Linking ISSN: 08835403 NLM ISO Abbreviation: J Arthroplasty Subsets: MEDLINE |
| أسماء مطبوعة: | Publication: New Brunswick, NJ : Taylor and Francis Original Publication: [New York, NY : Churchill Livingstone, c1986- |
| مواضيع طبية MeSH: | Arthroplasty, Replacement, Hip* , Deep Learning* , Hip Prosthesis*, Humans ; Uncertainty ; Acetabulum/surgery ; Retrospective Studies |
| مستخلص: | Background: Revision total hip arthroplasty (THA) requires preoperatively identifying in situ implants, a time-consuming and sometimes unachievable task. Although deep learning (DL) tools have been attempted to automate this process, existing approaches are limited by classifying few femoral and zero acetabular components, only classify on anterior-posterior (AP) radiographs, and do not report prediction uncertainty or flag outlier data. Methods: This study introduces Total Hip Arhtroplasty Automated Implant Detector (THA-AID), a DL tool trained on 241,419 radiographs that identifies common designs of 20 femoral and 8 acetabular components from AP, lateral, or oblique views and reports prediction uncertainty using conformal prediction and outlier detection using a custom framework. We evaluated THA-AID using internal, external, and out-of-domain test sets and compared its performance with human experts. Results: THA-AID achieved internal test set accuracies of 98.9% for both femoral and acetabular components with no significant differences based on radiographic view. The femoral classifier also achieved 97.0% accuracy on the external test set. Adding conformal prediction increased true label prediction by 0.1% for acetabular and 0.7 to 0.9% for femoral components. More than 99% of out-of-domain and >89% of in-domain outlier data were correctly identified by THA-AID. Conclusions: The THA-AID is an automated tool for implant identification from radiographs with exceptional performance on internal and external test sets and no decrement in performance based on radiographic view. Importantly, this is the first study in orthopedics to our knowledge including uncertainty quantification and outlier detection of a DL model. (Copyright © 2023 Elsevier Inc. All rights reserved.) |
| فهرسة مساهمة: | Keywords: artificial intelligence; conformal prediction; deep learning; implant identification; total hip arthroplasty; uncertainty quantification |
| تواريخ الأحداث: | Date Created: 20230928 Date Completed: 20240315 Latest Revision: 20240315 |
| رمز التحديث: | 20240315 |
| DOI: | 10.1016/j.arth.2023.09.025 |
| PMID: | 37770007 |
| قاعدة البيانات: | MEDLINE |
Full Text via ClinicalKey 
Full Text Finder | تدمد: | 1532-8406 |
|---|---|
| DOI: | 10.1016/j.arth.2023.09.025 |