Dataset Information

A Deep Learning Tool for Automated Radiographic Measurement of Acetabular Component Inclination and Version After Total Hip Arthroplasty.

ABSTRACT:

Background

Inappropriate acetabular component angular position is believed to increase the risk of hip dislocation after total hip arthroplasty. However, manual measurement of these angles is time consuming and prone to interobserver variability. The purpose of this study was to develop a deep learning tool to automate the measurement of acetabular component angles on postoperative radiographs.

Methods

Two cohorts of 600 anteroposterior (AP) pelvis and 600 cross-table lateral hip postoperative radiographs were used to develop deep learning models to segment the acetabular component and the ischial tuberosities. Cohorts were manually annotated, augmented, and randomly split to train-validation-test data sets on an 8:1:1 basis. Two U-Net convolutional neural network models (one for AP and one for cross-table lateral radiographs) were trained for 50 epochs. Image processing was then deployed to measure the acetabular component angles on the predicted masks for anatomical landmarks. Performance of the tool was tested on 80 AP and 80 cross-table lateral radiographs.

Results

The convolutional neural network models achieved a mean Dice similarity coefficient of 0.878 and 0.903 on AP and cross-table lateral test data sets, respectively. The mean difference between human-level and machine-level measurements was 1.35° (σ = 1.07°) and 1.39° (σ = 1.27°) for the inclination and anteversion angles, respectively. Differences of 5⁰ or more between human-level and machine-level measurements were observed in less than 2.5% of cases.

Conclusion

We developed a highly accurate deep learning tool to automate the measurement of angular position of acetabular components for use in both clinical and research settings.

Level of evidence

III.

SUBMITTER: Rouzrokh P

PROVIDER: S-EPMC8197739 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:The orientation of the acetabular cup component of a total hip arthroplasty can be evaluated in a number of ways, utilizing a myriad of imaging techniques and measurement parameters, including intraoperative surgical estimates, postoperative radiographs, and cross-sectional imaging such as computed tomography (CT) and magnetic resonance imaging (MRI).How do traditional versus corrected measurements of acetabular version vary from one another based on the inclination of the cup? What is the reliability of the corrected acetabular version measurements based on interobserver and intraobserver consistency?Two fellowship-trained musculoskeletal radiologists reviewed CT scans on 60 total hip arthroplasties. Acetabular inclination, traditional CT acetabular version, and CT acetabular version corrected for inclination (by utilizing multi-planar reformations to measure in the plane of the cup face) were each measured. The difference was then calculated between the "traditional" axial CT and "corrected" acetabular version measurements, and the association between this difference and the acetabular inclination was assessed.The "traditional" axial CT and "corrected" acetabular version measurements differed from one another in every case, with the traditional method yielding a version measurement that was on average 9.5° higher than the corrected technique. However, as the acetabular cup inclination angle decreased, the "traditional" measurement became more variable and increasingly discordant with the "corrected" version measurement.There is inherent variability between the many methods utilized for defining and measuring acetabular version, with axial CT measurements often used as an accepted proxy for true cup anteversion. However, the variability between different measurement techniques is correlated with acetabular inclination, and this variability is most pronounced when acetabular inclination is low, ultimately leading to potential confusion in measurement terminology. The increasingly widespread availability of multi-planar CT reformations provides an opportunity to standardize methodology, eliminate the impact of inclination on acetabular version measurements, and potentially provide a more reliable comparison of the impact of cup orientation on surgical outcomes.