{Reference Type}: Journal Article
{Title}: Creating High Fidelity Synthetic Pelvis Radiographs Using Generative Adversarial Networks: Unlocking the Potential of Deep Learning Models Without Patient Privacy Concerns.
{Author}: Khosravi B;Rouzrokh P;Mickley JP;Faghani S;Larson AN;Garner HW;Howe BM;Erickson BJ;Taunton MJ;Wyles CC;
{Journal}: J Arthroplasty
{Volume}: 38
{Issue}: 10
{Year}: 10 2023 17
{Factor}: 4.435
{DOI}: 10.1016/j.arth.2022.12.013
{Abstract}: In this work, we applied and validated an artificial intelligence technique known as generative adversarial networks (GANs) to create large volumes of high-fidelity synthetic anteroposterior (AP) pelvis radiographs that can enable deep learning (DL)-based image analyses, while ensuring patient privacy.<BR>AP pelvis radiographs with native hips were gathered from an institutional registry between 1998 and 2018. The data was used to train a model to create 512 × 512 pixel synthetic AP pelvis images. The network was trained on 25 million images produced through augmentation. A set of 100 random images (50/50 real/synthetic) was evaluated by 3 orthopaedic surgeons and 2 radiologists to discern real versus synthetic images. Two models (joint localization and segmentation) were trained using synthetic images and tested on real images.<BR>The final model was trained on 37,640 real radiographs (16,782 patients). In a computer assessment of image fidelity, the final model achieved an "excellent" rating. In a blinded review of paired images (1 real, 1 synthetic), orthopaedic surgeon reviewers were unable to correctly identify which image was synthetic (accuracy = 55%, Kappa = 0.11), highlighting synthetic image fidelity. The synthetic and real images showed equivalent performance when they were assessed by established DL models.<BR>This work shows the ability to use a DL technique to generate a large volume of high-fidelity synthetic pelvis images not discernible from real imaging by computers or experts. These images can be used for cross-institutional sharing and model pretraining, further advancing the performance of DL models without risk to patient data safety.<BR>Level III.