Deep Learning Predicts Total Knee Replacement from Magnetic Resonance Images

Aniket A Tolpadi,Jinhee J Lee,Valentina Pedoia,Sharmila Majumdar

doi:10.1038/s41598-020-63395-9

Abstract

Knee Osteoarthritis (OA) is a common musculoskeletal disorder in the United States. When diagnosed at early stages, lifestyle interventions such as exercise and weight loss can slow OA progression, but at later stages, only an invasive option is available: total knee replacement (TKR). Though a generally successful procedure, only 2/3 of patients who undergo the procedure report their knees feeling “normal” post-operation, and complications can arise that require revision. This necessitates a model to identify a population at higher risk of TKR, particularly at less advanced stages of OA, such that appropriate treatments can be implemented that slow OA progression and delay TKR. Here, we present a deep learning pipeline that leverages MRI images and clinical and demographic information to predict TKR with AUC 0.834 ± 0.036 (p < 0.05). Most notably, the pipeline predicts TKR with AUC 0.943 ± 0.057 (p < 0.05) for patients without OA. Furthermore, we develop occlusion maps for case-control pairs in test data and compare regions used by the model in both, thereby identifying TKR imaging biomarkers. As such, this work takes strides towards a pipeline with clinical utility, and the biomarkers identified further our understanding of OA progression and eventual TKR onset.

Highlights

Knee Osteoarthritis (OA) is one of the most common musculoskeletal disorders in the United States, with estimates of its incidence rate ranging from 14 to 30 million[1,2]
We show the increase in pipeline performance when using 3D Magnetic Resonance Imaging (MRI) images as opposed to 2D radiographs, suggesting MRI may have a role in total knee replacement (TKR) risk screening despite higher costs and more limited availability
For the X-Ray model, hyperparameter tuning steps found the following to yield the best combination of validation accuracy, sensitivity, and specificity: learning rate of 3.981 × 10−6, TKR class weight in cross-entropy loss function of 0.927 and non-TKR class weight of 0.073, dropout rate of 0.375, and only the last 2 layers fine-tuned after OA pretrain

Summary

Introduction

Knee Osteoarthritis (OA) is one of the most common musculoskeletal disorders in the United States, with estimates of its incidence rate ranging from 14 to 30 million[1,2]. It is much preferable to prolong the good health of the knee, in patients where OA has not advanced to the most severe stages, thereby delaying TKR as long as possible This necessitates a model to identify patients at higher risk of TKR such that appropriate treatment options can be pursued. A few studies have leveraged random forest regression, Cochran-Armitage tests for trend, and t-tests to identify demographic, general health, and physical examination measurements that most strongly correlate with TKR or total joint arthroplasty (TJA)[20,21] Others have taken these efforts further, using techniques such as multiple regression and multivariate risk prediction models to predict TKR outright[22,23]. The success of these works further suggests the feasibility of leveraging DL to predict TKR

Methods

Results

Conclusion