Image-based tracking of the teeth for orthodontic augmented reality

Area of Science:

• Medical Imaging
• Computer Vision
• Orthodontics

Background:

• Current orthodontic procedures for bracket placement can be time-consuming and may lack precision.
• Augmented reality (AR) offers potential for enhancing surgical guidance and improving accuracy in medical interventions.

Purpose of the Study:

• To develop and evaluate image-based methods for tracking teeth in video images relative to CT scans for guided bracket placement in orthodontics.
• To enable a novel, lightweight augmented reality (AR) system for orthodontic applications.

Main Methods:

• Developed a tracking algorithm using CT scans to determine the position of the patient's maxilla and mandible in video images.
• Implemented two specific formulations: distance-based modulation of CT iso-surfaces to approximate the gum line and back-projection of video frames to account for placed brackets.
• Utilized a monocular AR system for image guidance via overlaying planned bracket positions onto the video image.

Main Results:

• Successfully tracked teeth in video sequences from three real patient procedures, even under challenging lighting conditions.
• Demonstrated the practical feasibility of the developed AR system through systematic evaluation.
• Achieved robustness, accuracy, and performance in the tracking algorithm despite conflicting requirements.

Conclusions:

• The presented image-based tracking method is suitable for image guidance in orthodontic correction.
• The novel AR system facilitates guided bracket placement, showing practical feasibility for real-world orthodontic procedures.
• The developed algorithm effectively addresses challenges in tracking under difficult conditions, paving the way for improved orthodontic treatments.