Related Experiment Videos
John Charnley Award: Deep Learning Prediction of Hip Joint Center on Standard Pelvis Radiographs
Seong Jun Jang1, Kyle N Kunze2, Jonathan M Vigdorchik3
1Weill Cornell College of Medicine, New York, New York; Department of Orthopedic Surgery, Hospital for Special Surgery, New York, New York.
Insights
Deep learning accurately estimates hip joint center (HJC) from X-rays, improving total hip arthroplasty planning. Patient-specific models achieved 91% accuracy within 5mm, reducing errors and subjectivity in HJC determination.
Area of Science:
- Orthopedic surgery
- Radiology
- Artificial intelligence
Background:
- Accurate hip joint center (HJC) determination is crucial for total hip arthroplasty (THA) outcomes.
- Current HJC estimation methods are subjective and prone to human error.
- A need exists for objective and rapid HJC estimation tools.
Purpose of the Study:
- To develop a deep learning (DL) tool for rapid and objective HJC estimation.
- To utilize anteroposterior (AP) pelvis radiographs for HJC estimation.
- To compare DL-derived HJC estimation accuracy with existing methods.
Main Methods:
- A DL model workflow was developed using 3,965 patients (7,930 hips).
- The workflow detected bony landmarks and estimated HJC via a pelvic height ratio method.
- Optimal ratios (nonspecific, sex-specific, patient-specific) were determined and validated on an independent cohort.
Main Results:
- The DL algorithm estimated HJC at 0.65 seconds/hip.
- Patient-specific models achieved 91% accuracy within 5 mm error.
- Mean error was significantly reduced with patient-specific models (3.09 ± 1.69 mm).
Conclusions:
- Deep learning models can accurately estimate native HJC from AP pelvis radiographs.
- This DL tool offers potential clinical value for preoperative planning in THA.
- The developed models can reduce subjective variability in HJC estimation.
Background:
Accurate hip joint center (HJC) determination is critical for preoperative planning, intraoperative execution, clinical outcomes after total hip arthroplasty, and commonly used classification systems in primary and revision hip replacement. However, current methods of preoperative HJC estimation are prone to subjectivity and human error. The purpose of the study was to leverage deep learning (DL) to develop a rapid and objective HJC estimation tool on anteroposterior (AP) pelvis radiographs.
Methods:
Radiographs from 3,965 patients (7,930 hips) were included. A DL model workflow was created to detect bony landmarks and estimate HJC based on a pelvic height ratio method. The workflow was utilized to conduct a grid-search for optimal nonspecific, sex-specific, and patient-specific (using contralateral hip) pelvic height ratios on the training/validation cohort (6,344 hips). Algorithm performance was assessed on an independent testing cohort for HJC estimation comparison.
Results:
The algorithm estimated HJC for the testing cohort at a rate of 0.65 seconds/hip based on features in AP radiographs alone. The model predicted HJC within 5 mm of error for 80% of hips using nonspecific ratios, which increased to 83% with sex-specific and 91% with patient-specific pelvic height ratio models. Mean error decreased utilizing the patient-specific model (3.09 ± 1.69 mm, P < .001).
Conclusion:
Using DL, we developed nonspecific, sex-specific, and patient-specific models capable of estimating native HJC on AP pelvis radiographs. This tool may provide clinical value when considering preoperative component position in patients planned to undergo THA and in reducing the subjective variability in HJC estimation.
Level Of Evidence:
Diagnostic, level IV.