Using artificial neural networks to predict impingement and dislocation in total hip arthroplasty

A multiphysics-based artificial neural networks model for atherosclerosis

Atherosclerosis is a medical condition involving the hardening and/or thickening of arteries' walls. Mathematical multi-physics models have been developed to predict the development of atherosclerosis under different conditions. However, these models are typically computationally expensive. In this study, we used machine learning techniques, particularly artificial neural networks (ANN), to enhance the computational efficiency of these models. A database of multi-physics Finite Element Method (FEM) simulations was created and used for training and validating an ANN model. The model is capable of quick and accurate prediction of atherosclerosis development. A remarkable computational gain is obtained using the ANN model compared to the original FEM simulations.

Functional safe zone for THA considering the patient-specific pelvic tilts: An ultrasound-based approach

The usual Lewinnek orientation for cup positioning in total hip arthroplasty is not suitable for all patients as it does not consider the patient mobility. We propose an ultrasound-based approach to compute a Functional Safe Zone (FSZ) considering daily positions. Our goal was to validate it, and to evaluate how the input parameters impact the FSZ size and barycentre. The accuracy of the FSZ was first assessed by comparing the FSZ computed by the proposed approach and the true FSZ determined by 3D modelling. Then, the input parameters' impact on the FSZ was studied using a principal component analysis. The FSZ was estimated with errors below 0.5° for mean anteversion, mean inclination, and at edges. The pelvic tilts and the neck orientation were found correlated to the FSZ mean orientation, and the target ROM and the prosthesis dimensions to the FSZ size. Integrated into the clinical workflow, this non-ionising approach can be used to easily determine an optimal patient-specific cup orientation minimising the risks of dislocation.

A Machine-Learning-Based Approach for Predicting Mechanical Performance of Semi-Porous Hip Stems

Novel designs of porous and semi-porous hip stems attempt to alleviate complications such as aseptic loosening, stress shielding, and eventual implant failure. Various designs of hip stems are modeled to simulate biomechanical performance using finite element analysis; however, these models are computationally expensive. Therefore, the machine learning approach is incorporated with simulated data to predict the new biomechanical performance of new designs of hip stems. Six types of algorithms based on machine learning were employed to validate the simulated results of finite element analysis. Afterwards, new designs of semi-porous stems with outer dense layers of 2.5 and 3 mm and porosities of 10–80% were used to predict the stiffness of the stems, stresses in outer dense layers, stresses in porous sections, and factor of safety under physiological loads using machine learning algorithms. It was determined that decision tree regression is the top-performing machine learning algorithm as per the used simulation data in terms of the validation mean absolute percentage error which equals 19.62%. It was also found that ridge regression produces the most consistent test set trend as compared with the original simulated finite element analysis results despite relying on a relatively small data set. These predicted results employing trained algorithms provided the understanding that changing the design parameters of semi-porous stems affects the biomechanical performance without carrying out finite element analysis.

Moving fluoroscopy-based analysis of THA kinematics during unrestricted activities of daily living

Introduction: Knowledge of the accurate in-vivo kinematics of total hip arthroplasty (THA) during activities of daily living can potentially improve the in-vitro or computational wear and impingement prediction of hip implants. Fluoroscopy- based techniques provide more accurate kinematics compared to skin marker-based motion capture, which is affected by the soft tissue artefact. To date, stationary fluoroscopic machines allowed the measurement of only restricted movements, or only a portion of the whole motion cycle. Methods: In this study, a moving fluoroscopic robot was used to measure the hip joint motion of 15 THA subjects during whole cycles of unrestricted activities of daily living, i.e., overground gait, stair descent, chair rise and putting on socks. Results: The retrieved hip joint motions differed from the standard patterns applied for wear testing, demonstrating that current pre-clinical wear testing procedures do not reflect the experienced in-vivo daily motions of THA. Discussion: The measured patient-specific kinematics may be used as input to in vitro and computational simulations, in order to investigate how individual motion patterns affect the predicted wear or impingement.

Deep Learning Artificial Intelligence Model for Assessment of Hip Dislocation Risk Following Primary Total Hip Arthroplasty From Postoperative Radiographs

BACKGROUND

Dislocation is a common complication following total hip arthroplasty (THA), and accounts for a high percentage of subsequent revisions. The purpose of this study is to illustrate the potential of a convolutional neural network model to assess the risk of hip dislocation based on postoperative anteroposterior pelvis radiographs.

METHODS

We retrospectively evaluated radiographs for a cohort of 13,970 primary THAs with 374 dislocations over 5 years of follow-up. Overall, 1490 radiographs from dislocated and 91,094 from non-dislocated THAs were included in the analysis. A convolutional neural network object detection model (YOLO-V3) was trained to crop the images by centering on the femoral head. A ResNet18 classifier was trained to predict subsequent hip dislocation from the cropped imaging. The ResNet18 classifier was initialized with ImageNet weights and trained using FastAI (V1.0) running on PyTorch. The training was run for 15 epochs using 10-fold cross validation, data oversampling, and augmentation.

RESULTS

The hip dislocation classifier achieved the following mean performance (standard deviation): accuracy = 49.5 (4.1%), sensitivity = 89.0 (2.2%), specificity = 48.8 (4.2%), positive predictive value = 3.3 (0.3%), negative predictive value = 99.5 (0.1%), and area under the receiver operating characteristic curve = 76.7 (3.6%). Saliency maps demonstrated that the model placed the greatest emphasis on the femoral head and acetabular component.

CONCLUSION

Existing prediction methods fail to identify patients at high risk of dislocation following THA. Our radiographic classifier model has high sensitivity and negative predictive value, and can be combined with clinical risk factor information for rapid assessment of risk for dislocation following THA. The model further suggests radiographic locations which may be important in understanding the etiology of prosthesis dislocation. Importantly, our model is an illustration of the potential of automated imaging artificial intelligence models in orthopedics.

LEVEL OF EVIDENCE

Level III.