Generative AI enables patient-specific THA surgical templating

Sunday, November 26 | 1:00 p.m.-1:10 p.m. | S4-SSMK02-2 | Room E353C

Generative AI technology shows potential for making surgical planning for total hip arthroplasty (THA) more efficient, according to researchers from the Mayo Clinic.

Traditionally, creating THA templates has been a tedious process requiring manual measurements and 2D implant renderings of preoperative radiographs. This process is important, however, as it improves surgical efficiency and reduces complications by visualizing surgical outcomes and anticipating surgical outcomes, according to presenter Pouria Rouzrokh, MD, and colleagues.

To help, the group developed THA-Net, a deep-learning algorithm designed to simulate postoperative THA radiographs with one preoperative pelvis input and generate predictions. In testing, the algorithm produced synthetic postoperative radiographs deemed to have higher surgical validity than real postoperative radiographs. What’s more, blinded expert reviewers couldn’t tell the difference between the two types of radiographs.

“As a standalone technology, this tool enables patient-specific surgical planning and identifies the optimal postoperative target,” the researchers wrote. “Further refinement of this tool may allow it to interface with robotics, navigation, and AR/VR technologies to achieve desirable surgical execution while reducing dependence on 3D imaging data.”

To learn more, attend this scientific presentation on Sunday afternoon.