Background: Defects of the facial skeleton often require complex reconstruction with vascularized grafts. This trial elucidated the usability, visual perception and accuracy of a markerless augmented reality (AR)-guided navigation for harvesting iliac crest transplants.Methods: Random CT scans were used to virtually plan two common transplant configurations on 10 iliac crest models, each printed four times. The transplants were harvested using projected AR and cutting guides. The duration and accuracies of the angulation, distance and volume between the planned and executed osteotomies were measured.Results: AR was characterized by the efficient use of time and accurate rendition of preoperatively planned geometries. However, vertical osteotomies and complex anatomical settings displayed significant inferiority of AR guidance compared to cutting guides. Conclusions:This study demonstrated the usability of a markerless AR setup for harvesting iliac crest transplants. The visual perception and accuracy of the ARguided osteotomies constituted remaining weaknesses against cutting guide technology.

Reliable object tracking that is based on video data constitutes an important challenge in diverse areas, including, among others, assisted surgery. Particle filtering offers a state-of-the-art technology for this challenge. Becaise a particle filter is based on a probabilistic model, it provides explicit likelihood values; in theory, the question of whether an object is reliably tracked can be addressed based on these values, provided that the estimates are correct. In this contribution, we investigate the question of whether these likelihood values are suitable for deciding whether the tracked object has been lost. An immediate strategy uses a simple threshold value to reject settings with a likelihood that is too small. We show in an application from the medical domain—object tracking in assisted surgery in the domain of Robotic Osteotomies—that this simple threshold strategy does not provide a reliable reject option for object tracking, in particular if different settings are considered. However, it is possible to develop reliable and flexible machine learning models that predict a reject based on diverse quantities that are computed by the particle filter. Modeling the task in the form of a regression enables a flexible handling of different demands on the tracking accuracy; modeling the challenge as an ensemble of classification tasks yet surpasses the results, while offering the same flexibility.

No abstract