Bastian Bier

Papers

Total Citations

H-Index

About

Bastian Bier is a leading researcher at the intersection of medical imaging and machine learning, whose work is redefining how X-ray-based procedures are planned and executed. His primary research areas include interventional imaging, computer vision, and the simulation of image formation for procedural guidance. Bier’s most impactful contribution is his pioneering approach to bridging the gap between synthetic and real X-ray data. In his landmark 2019 paper, "Enabling machine learning in X-ray-based procedures via realistic simulation of image formation," he demonstrated how to generate high-fidelity, physically accurate simulated X-ray images. This work, which has garnered over 60 citations, provides the critical infrastructure needed to train robust deep learning models without relying on scarce, patient-specific clinical data. By enabling the development of algorithms for 3D-2D registration, pose estimation, and automatic anatomy detection, Bier’s simulations are accelerating the adoption of AI in fluoroscopy and cone-beam CT. His contributions are foundational for safer, more precise, and data-efficient image-guided interventions, making him a key figure in the future of computer-assisted radiology.