Otomatic plane3/20/2023 The use of a combined network with shared parameters requires less memory, which is a great benefit for the implementation of an application for the surgical environment.įlat panel CT multiplanar reconstruction orthopedics plane regression.Ītesok K., et al. The reported results are in the same range as manual plane adjustments. It also improves the angle estimation for the ankle region. Conclusions: The use of a multihead approach with shared features leads to more accurate plane regression compared with the use of individual networks for each task. ![]() Thus, the achieved accuracy meets the reported interrater variance in similarly complex body regions of up to 6.3 deg for the normals and up to 9.3 mm for the plane position. The multihead approach improves the regression of the plane position from 7.4 to 6.1 mm, whereas the orientation does not benefit from this approach. Results: Using a matrix description rather than the Euler angle description, the accuracy of the regressed normals improves from 7.7 deg to 7.3 deg in the mean value for single anatomies. Then, two different MTL network architectures based on the PoseNet are compared with a single task learning network. First, various mathematical descriptions for rotation, including Euler angle, quaternion, and matrix representation, are revised. Approach: We present a detailed study of multitask learning (MTL) regression networks to estimate the parameters of the MPR planes. To speed up and ease the workflow, an automatic parameterization of these planes is needed. Thus, the multiplanar reconstructed (MPR) planes need to be adjusted manually during the review of the volume. However, the acquired volumes are typically not aligned to the anatomical regions. With mobile C-arm systems, these acquisitions can be performed intraoperatively, reducing the number of required revision surgeries. Purpose: To assess the result in orthopedic trauma surgery, usually three-dimensional volume data of the treated region is acquired.
0 Comments
Leave a Reply.AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |