No abstract

Purpose Accurate estimation of the position and orientation (pose) of surgical instruments is crucial for delicate minimally invasive temporal bone surgery. Current techniques lack in accuracy and/or line-of-sight constraints (conventional tracking systems) or expose the patient to prohibitive ionizing radiation (intra-operative CT). A possible solution is to capture the instrument with a c-arm at irregular intervals and recover the pose from the image. Methods i3PosNet infers the position and orientation of instruments from images using a pose estimation network. Said framework considers localized patches and outputs pseudo-landmarks. The pose is reconstructed from pseudo-landmarks by geometric considerations. Results We show i3PosNet reaches errors $$<\,0.05$$<0.05 mm. It outperforms conventional image registration-based approaches reducing average and maximum errors by at least two thirds. i3PosNet trained on synthetic images generalizes to real X-rays without any further adaptation. Conclusion The translation of deep learning-based methods to surgical applications is difficult, because large representative datasets for training and testing are not available. This work empirically shows sub-millimeter pose estimation trained solely based on synthetic training data.

No abstract

BackgroundPhysical examination courses are an essential part of the education of medical students. The aim of this study was to ascertain the factors influencing students’ motivation and willingness to participate in a physical examination course.MethodsStudents were asked to complete a questionnaire subdivided into five domains: anthropometric data, religiousness, motivation to take part in physical examination courses, willingness to be physically examined at 11 different body regions by peers or a professional tutor and a field for free text.ResultsThe questionnaire was completed by 142 medical students. The importance of the examination course was rated 8.7 / 10 points, the score for students’ motivation was 7.8 / 10 points. Willingness to be physically examined ranged from 6 to 100% depending on body part and examiner. Female students were significantly less willing to be examined at sensitive body parts (breast, upper body, groin and the hip joint; p = .003 to < .001), depending on group composition and / or examiner. Strictly religious students showed significantly less willingness to undergo examination of any part of the body except the hand (p = .02 to < .001). Considering BMI, willingness to be examined showed comparable rates for normal weight and under- / overweight students in general (80% vs. 77%). Concerning the composition of the group for physical examination skills courses, students preferred self-assembled over mixed gender and same gender groups.ConclusionsPeer physical examination is a method to improve students’ skills. While motivation to participate in and acceptance of the physical examination course appears to be high, willingness to be examined is low for certain parts of the body, e.g. breast and groin, depending on religiousness, gender and examiner. Examination by a professional medical tutor did not lead to higher acceptance. Most students would prefer to choose their team for physical examination courses themselves rather than be assigned to a group.