Poster 23

Cone beam computed tomography (CBCT) is used intra-operatively to assess the result of surgery. Due to limitations of patient positioning and the operating theater in general, the acquisition usually cannot be performed such that the axis-aligned multiplanar reconstructions (MPR) of the volume match the anatomically oriented MPRs. This needs to be corrected manually, which is a time-consuming and complex task and requires the surgeon to interact with non-sterile equipment. To this end, this study investigates a fully-automatic solution to directly regress the standard plane parameters from a CBCT volume of the calcaneus and ankle regions. A PoseNet convolutional neural network (CNN) is adapted and trained, comparing a 6D-, Euler angle- and quaternion-based approach to represent the plane rotation [1]. In addition, a cost function is optimized to incorporate orientation constraints. The best-performing CNN - which uses the 6D representation - estimates the plane normal with a median accuracy of 5°, the in-plane rotation with a median accuracy of 6°, and the position with a median accuracy of 6 mm. The inference time is less than 0.05 s.

Postersession 2, Computer-assisted Intervention