Haibo Cong

Papers

Total Citations

H-Index

About

Haibo Cong is at the forefront of medical robotics and artificial intelligence, specializing in autonomous ultrasound systems for pulmonary diagnostics. His research centers on integrating visual perception, deep learning, and robotic control to create safe, effective alternatives to manual lung ultrasound scanning—a critical need highlighted during the COVID-19 pandemic. Cong’s major contributions include developing a convolutional neural network (CNN)-based localization system that enables robots to autonomously navigate and scan lung regions, reducing clinician exposure to infectious pathogens. He further advanced this work by designing a YOLO-based detection network enhanced with channel and spatial attention mechanisms, significantly improving target identification accuracy in robotic lung ultrasound. His most-cited paper (2023, 10 citations) demonstrates a complete pipeline from visual perception to robotic scanning, while his follow-up work (4 citations) refines real-time object detection for clinical deployment. These innovations address both workflow efficiency and infection control, positioning Cong as a key figure in the intersection of robotics, computer vision, and point-of-care ultrasound. His research holds promise for transforming bedside diagnostics, especially in high-risk or resource-limited settings.