Florence Klitzner
Simulation Engineer at Inner Logic
My research and work focus on the simulation of medical imaging modalities: X-ray, CT, and ultrasound, with applications in machine learning and GPU-accelerated high-performance computing.
I graduated with an M.Sc. in Computer Science from the Technical University of Munich, after an undergraduate degree in Computer Science: Games Engineering. As a visiting student in the ARCADE Lab at Johns Hopkins University, I worked on surgical simulation and automation. Before that, I worked on ultrasound simulation for diffusion model training and 3D reconstruction in collaboration with Luma Vision and the Chair for Computer Aided Medical Procedures (CAMP).
In my free time, I sometimes explore the world of game development.
Research
Investigating Robot Control Policy Learning for Autonomous X-ray-guided Spine Procedures
We investigate imitation learning for bi-plane X-ray-guided cannula insertion, trained at scale in simulation with DeepDRR. The policy succeeds on the first attempt in 68.5% of cases and shows preliminary sim-to-real transfer on real X-rays.
Read More →FieldGPU: A GPU-based Version of Field II with Python Bindings for Large Scale Simulations and Complex Transducer Configurations
We present FieldGPU, a CUDA-accelerated reimplementation of the Field II ultrasound simulation framework, accessible as a Python package. FieldGPU achieves up to 1100 times performance increase compared to Field II for large-scale simulations with 10 million scatterers, significantly reducing simulation times while providing a modern Python interface.
Read More →