Finn Behrendt

Papers

Total Citations

H-Index

About

Finn Behrendt is a researcher at the forefront of applying deep learning to medical imaging and surgical robotics. His work primarily focuses on enhancing the precision and safety of minimally invasive procedures through advanced computer vision and spatio-temporal modeling. A key contribution is his development of a deep learning framework for needle tracking in low-resolution 3D ultrasound volumes, a breakthrough that addresses the critical challenge of out-of-plane movement during needle insertions. This work, published in 2024, has already garnered 7 citations, highlighting its immediate relevance to improving real-time navigation in clinical settings. Behrendt has also made significant strides in vision-based force estimation for robot-assisted surgery. By leveraging spatio-temporal deep learning models to analyze 2D image sequences, he has pioneered a method to estimate forces from tissue deformation—a crucial step toward developing haptic feedback for surgical systems. This foundational work, published in 2020, has earned 2 citations and underscores his ability to bridge the gap between visual data and tactile sensing. Through these contributions, Behrendt is shaping the future of intelligent, data-driven surgical assistance.