Deep Learning Compatible Differentiable X-ray Projections for Inverse Rendering

Karthik Shetty, Annette Birkhold, Norbert Strobel, Bernhard Egger, Srikrishna Jaganathan, Markus Kowarschik, Andreas Maier
Friedrich-Alexander Universität Erlangen-Nürnberg, Lehrstuhl für Mustererkennung


Many minimally invasive interventional procedures still rely on 2D uoroscopic imaging. Generating a patient-specific 3D model from these X-ray projection data would allow to improve the procedural workflow, e.g. by providing assistance functions such as automatic positioning. To accomplish this, two things are required. First, a statistical human shape model of the human anatomy and second, a differentiable X-ray renderer. In this work, we propose a differentiable renderer by deriving the distance travelled by a ray inside mesh structures to generate a distance map. To demonstrate its functioning, we use it for simulating X-ray images from human shape models. Then we show its application by solving the inverse problem, namely reconstructing 3D models from real 2D uoroscopy images of the pelvis, which is an ideal anatomical structure for patient registration. This is accomplished by an iterative optimization strategy using gradient descent. With the majority of the pelvis being in the uoroscopic field of view, we achieve a mean Hausdorff distance of 30mm between the reconstructed model and the ground truth segmentation.

Postersession 3, Registration


Full Video

The author has not agreed to a public release of their video.

We use cookies to improve the usability of the website. By visiting you agree to this.