Start of funding 01.01.2024

Towards Automated Learning-based Image Quality Prediction of Cone-Beam CT - Reconstructions from few Scout Images for Metal Artifact Avoidance

Prof. Dr. Andreas Maier
Friedrich-Alexander-University of Erlangen-Nuremberg
Computer Science Department 5 - Pattern Recognition Lab

Prof. Dr. Adam Wang
Stanford University
Radiological Sciences Laboratory



The integration of Cone-Beam Computed Tomography (CBCT) with C-arm systems for image-guided surgery has become increasingly important in recent years. However, physical effects such as photon attenuation and scatter radiation, due to the interaction of X-rays with metal in the body, can impair image quality. One approach to solving this problem is to adjust the C-arm trajectory to minimize metal artifacts. One possibility for this is the development of a physics-informed model for predicting metal artifacts. This includes factors such as patient-specific absorption, equipment characteristics, and noise, which, for example, can be modeled using artificial neural networks. The goal is to integrate existing metrics and develop new criteria for improving image quality.