Papers
2
Total Citations
4
H-Index
2
About
Olivia Hosie is a rising leader in surgical data science and wearable sensing, whose work bridges computer vision, biomechanics, and clinical robotics. Her research centers on two key areas: **surgical phase recognition and instrument tracking** in endoscopy, and **precision hand motion capture** for medical and augmented reality applications. As a core contributor to the **PhaKIR 2024 challenge**, Hosie co-authored the landmark comparative validation study that established benchmarks for surgical phase recognition, instrument keypoint estimation, and instance segmentation—a foundational resource for the field. Her innovative **open-palm data glove design** addresses a critical limitation in motion capture technology: unlike closed-palm gloves that restrict natural movement, her device enables precise finger and wrist tracking without impeding dexterity, with direct applications in robotic surgery training and rehabilitation assessment. Though early in her career, Hosie’s work has already garnered attention, with her most-cited papers accumulating citations that underscore their immediate relevance. Her contributions are shaping how surgeons train and how machines understand human hand motion—a dual impact that positions her as a researcher to watch at the intersection of surgical AI and wearable technology.
Research Focus
Key Achievements
Top Papers
- 1
- 2