Felix Duelmer

Papers

Total Citations

H-Index

About

Felix Duelmer is at the forefront of intelligent robotic ultrasound imaging, pioneering the integration of machine learning with autonomous medical robotics. His research focuses on developing quality-aware robotic systems that can automatically acquire and interpret ultrasound data, with particular emphasis on vascular disease screening and small-vessel imaging. Duelmer’s landmark review, “Machine Learning in Robotic Ultrasound Imaging: Challenges and Perspectives” (2024, 41 citations), provides a comprehensive roadmap for the field, analyzing robotic mechanisms, control techniques, and clinical applications while identifying key challenges for future deployment. His most impactful contribution, the DopUS-Net framework (2023, 18 citations), introduces a novel quality-aware approach that leverages Doppler signals to guide robotic ultrasound imaging, enabling automatic segmentation of challenging small tubular structures like the ulnar artery—a critical capability for early vascular disease detection. This work addresses the fundamental challenge of maintaining image quality during autonomous scanning, directly advancing the clinical viability of robotic ultrasound systems. Duelmer’s research sits at the intersection of robotics, computer vision, and medical imaging, offering practical solutions that move toward radiation-free, automated screening programs.