Isabella Yung

Papers

Total Citations

H-Index

About

Isabella Yung’s research lies at the intersection of computer vision and minimally invasive surgery, with a focus on enhancing surgical tool segmentation in endoscopic imagery. Her major contribution is the development of a pose-informed morphological polar transform, which leverages tool geometry and orientation to convert rigid surgical instruments into more rectangular, segmentation-friendly representations. This innovation addresses a critical bottleneck in robotic-assisted surgery: accurately identifying tool boundaries in complex, low-contrast endoscopic scenes. Her most-cited work, “Surgical Tool Segmentation with Pose-Informed Morphological Polar Transform of Endoscopic Images” (2022, 10 citations), demonstrates that while the transform is not lossless, it significantly improves segmentation consistency—a foundational step toward real-time, autonomous surgical assistance. Yung’s approach bridges classical morphological processing with modern deep learning, offering a computationally efficient alternative to purely data-driven methods. Her work has been recognized for its potential to reduce cognitive load on surgeons and improve patient outcomes, marking her as an emerging leader in surgical vision. For students and researchers, Yung’s research exemplifies how domain-informed geometric priors can unlock practical advances in medical image analysis.