Abstract
PurposeElectromagnetic tracking (EMT) can partially replace X-ray guidance in minimally invasive procedures, reducing radiation in the OR. However, in this hybrid setting, EMT is disturbed by metallic distortion caused by the X-ray device. We plan to make hybrid navigation clinical reality to reduce radiation exposure for patients and surgeons, by compensating EMT error.MethodsOur online compensation strategy exploits cycle-consistent generative adversarial neural networks (CycleGAN). Positions are translated from various bedside environments to their bench equivalents, by adjusting their z-component. Domain-translated points are fine-tuned on the x–y plane to reduce error in the bench domain. We evaluate our compensation approach in a phantom experiment.ResultsSince the domain-translation approach maps distorted points to their laboratory equivalents, predictions are consistent among different C-arm environments. Error is successfully reduced in all evaluation environments. Our qualitative phantom experiment demonstrates that our approach generalizes well to an unseen C-arm environment.ConclusionAdversarial, cycle-consistent training is an explicable, consistent and thus interpretable approach for online error compensation. Qualitative assessment of EMT error compensation gives a glimpse to the potential of our method for rotational error compensation.
Highlights
In minimally invasive surgery, electromagnetic tracking (EMT) has the potential to partially replace continuous Xray navigation [9], reducing the radiation exposure to both patients and surgeons
Since the C-arm gantry is rotated to 90◦, this setup is different from anything the CycleGAN has seen during training
Comparing our domain adaptation approach to previously proposed topology-based compensation [9], we see that online compensation performance is a matter of RMSE, but needs to be assessed with interpretability in mind
Summary
Electromagnetic tracking (EMT) has the potential to partially replace continuous Xray navigation [9], reducing the radiation exposure to both patients and surgeons. Such procedures are traditionally performed under X-ray only (for example laparoscopy [1], endovascular aneurysm repair (EVAR) [2]). Our major focus is to develop an interpretable error compensation technique, which imposes two more constraints beyond mere error reduction: explicability and consistency. Compensation results could be arbitrary and still fulfill topological constraints, giving a false sense of reliability
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
