Magdalini Paschali

Papers

Total Citations

H-Index

About

Dr. Magdalini Paschali is a leading researcher at the intersection of medical imaging, robotics, and artificial intelligence. Her primary contributions lie in developing intelligent, autonomous systems for image-guided interventions, with a particular focus on ultrasound-guided robotic navigation. In her landmark 2020 work, "Ultrasound-Guided Robotic Navigation with Deep Reinforcement Learning," Dr. Paschali pioneered the first reinforcement learning (RL) based method for robotic navigation that uses real-time ultrasound images as direct sensory input. By combining deep Q-networks (DQN) with memory buffers and a binary classifier, her approach enables a robot to autonomously navigate to a target anatomy without requiring explicit pre-operative models or human guidance. This breakthrough has garnered significant attention, with the paper accumulating over 50 citations, and has opened new avenues for safer, more efficient, and less operator-dependent procedures in minimally invasive surgery. Dr. Paschali’s work exemplifies how deep reinforcement learning can bridge the gap between perception and action in clinical robotics, making her a key figure in the future of autonomous medical interventions.