THA-Net: A Deep Learning Solution for Next Generation Templating and Patient-Specific Surgical Execution

Purpose: This study introduces THA-Net, a deep learning (DL) inpainting algorithm for simulating postoperative total hip arthroplasty (THA) radiographs from a single preoperative pelvis radiograph input while being able to generate predictions either unconditionally (algorithm chooses implants) or conditionally (surgeon chooses implants). THA-Net was intended to be a next-generation THA templating tool with no to minimum inputs required from the operating surgeons.

Methods/Materials: THA-Net is a denoising diffusion probabilistic model (DDPM), which receives an input preoperative radiograph, and subsequently inpaints the target hip joint with THA implants to generate a synthetic yet realistic postoperative radiograph. We trained THA-Net on 356,305 pairs of radiographs from 14,357 patients from a single institution’s total joint registry and evaluated the validity (quality of surgical execution) and realism (ability to differentiate real and synthetic radiographs) of its outputs against both human-based and software-based criteria.

Results: The surgical validity of synthetic postoperative radiographs was significantly higher than their real counterparts (mean difference: 0.8 and 1.1 points on a 10-point Likert scale for automated and hardware-aware generations, respectively; p< 0.001). Real and synthetic radiographs were not able to be differentiated in terms of realism in blinded expert review. On average, reviewers rated the synthetic radiographs as realistic in 95% of hardware-aware generations and in 98% of automated generations. Synthetic images showed excellent validity and realism when analyzed with already-validated software. A demo video of THA-Net is available online: https://drive.google.com/file/d/1BL0u1AHWq0oBQ7QWuqUuNTX27RrnyM9q/view?usp=sharing

Conclusions: We developed a THA next-generation templating tool that can generate synthetic radiographs graded higher on ultimate surgical execution than real radiographs from training data. Further refinement of this tool may potentiate patient-specific surgical planning and enable technologies such as robotics, navigation, and augmented reality.