Cutting-edge self-drive car navigation technology is making its mark in the world of neurosurgery.
A study led by Johns Hopkins University’s Imaging for Surgery, Therapy and Radiology (I-STAR) Labs has introduced ‘augmented endoscopy’, a real-time neurosurgical guidance method that leverages advanced computer vision techniques.
Published in IEEE Transactions on Medical Robotics and Bionics, this pioneering technique aims to revolutionise neurosurgery by enhancing precision and safety.
Traditionally, invasive neurosurgery procedures have the potential to alter deep-brain anatomy and cause discrepancies between pre-operative imaging and the actual surgery.
The I-STAR Labs team sought the less invasive and more patient-friendly approach in collaboration with Medtronic and the National Institutes of Health (NIH).
Their real-time guidance system uses an endoscope, eliminating the need for additional equipment and reducing radiation exposure and scan times.
Prasad Vagdargi, a doctoral candidate at I-STAR Labs, emphasised the superiority of their method over current visualisation techniques.
Their innovative approach involves applying simultaneous localisation and mapping (SLAM), a computer vision technique used in self-driving cars.
The SLAM algorithm creates a 3D model of the patient's skull overlaid onto real-world video by tracking visual details in each frame of an endoscopic video feed.
This provides surgeons with real-time visualisation of targeted structures.
Prasad explained: ‘Think of it as a dynamic 3D map of a patient's brain that you can use to track and match deep brain deformation with preoperative imaging.’
Termed ‘augmented endoscopy’, this method has shown remarkable results, surpassing previous techniques by over 16 times while maintaining submillimetre accuracy.
- The potential benefits include:
- Reduced complications
- Shorter operation times
- Improved surgical efficiency in neurosurgery and across various endoscopic procedures
The research team is collaborating with neurosurgeons at Johns Hopkins Hospital for a clinical study to validate and refine their method for use in actual operating rooms.
They also integrate artificial intelligence and machine learning to enhance the algorithm’s speed and precision.
Prasad added: ‘We believe our findings are very important and feel that augmented endoscopy is a technology whose time has come.’
