Enhancing Minimally Invasive Spinal Procedures Through Computer Vision and Augmented Reality Techniques

Surgical navigation technologies have transformed the healthcare landscape, playing a key role in enhancing precision, safety, and efficiency of various medical procedures. In this paper, we present a costeffective 3D computer navigation approach that leverages augmented reality (AR) and computer vision (CV) to aid in spinal pain management procedures like radiofrequency ablation (RFA) and epidural steroid injections (ESI). We evaluate the accuracy of AR overlay of key anatomical features on the patient (obtained from MRI scans or CAD models of the patient) through simulated spinal injection experiments and assess the accuracy of the CV algorithm via optical tracking experiments. Our findings indicate that ARand CV are valuable tools for surgical guidance, offering a low-cost alternative to traditional fluoroscopy.