A Deep Learning Approach for Pose Estimation from Volumetric OCT Data

Tracking the pose of instruments and patients is a typical problem in many clinical scenarios, e.g., minimally invasive surgery (MIS) (Bouget et  al., 2017) or transcranial magnetic stimulation (Richter et al., 2013). Common commercially available optical and electromagnetic (EM) tracking systems reach an accuracy of 0.2 mm to 1 mm (Kral et al., 2013). For optical tracking, a mean tracking error of 0.22 mm has been achieved for clinical s etups (Elfring et al., 2010). EM tracking operates without a line of sight but generally reaches lower accuracy with a typical root mean square error (RMSE) of 1 mm (Franz et al., 2014).

Source: Medical Image Analysis - March 10, 2018 Category: Radiology Authors: Nils Gessert, Matthias Schl üter, Alexander Schlaefer Source Type: research