New AI technique could make minimally invasive surgeries safer and more precise
This patient-specific method, called xvr, helps doctors use X-rays for surgical navigation in fields such as orthopedics and neurosurgery.
Researchers have developed a new AI technique called xvr, which rapidly matches X-rays taken during surgery with a patient's preoperative 3D medical scan. This innovation could greatly enhance the safety and precision of minimally invasive surgeries. Traditionally, clinicians rely on real-time X-rays to guide devices like catheters and endoscopes through tiny incisions.
However, the flat nature of X-rays makes it difficult to accurately pinpoint the location and orientation of surgical tools within the patient's body, increasing the risk of complications. Clinicians often manually align X-rays with preoperative 3D images, such as CT scans or MRIs, but manual registration is slow and error-prone.
The new AI model, named xvr, overcomes these challenges by adapting to each patient in just five minutes and achieving sub-millimeter precision. By using a physics-based simulation of the X-ray process, xvr generates realistic synthetic images of a patient's anatomy, allowing it to train an AI model for accurate registration in mere seconds.
Unlike existing AI methods, xvr outperforms them by an order of magnitude, enabling faster and safer procedures for a wider range of patients, even those requiring emergency stroke interventions.
Written by urgent.news from MIT News AI's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
