Seungbum Hong
Papers
4
Total Citations
27
H-Index
3
About
Seungbum Hong is a researcher advancing the field of surgical data science, with a primary focus on **surgical workflow recognition** and **intraoperative computer vision**. His work addresses critical challenges in understanding and automating the analysis of surgical procedures, particularly in laparoscopic and robotic surgeries. Hong’s major contributions include his leadership in the **PEg TRAnsfer Workflow Recognition Challenge**, where he investigated whether multi-modal data—such as video, motion, and tool signals—improve the accuracy of recognizing surgical phases and gestures. This work, published in 2022 and 2023, has garnered a combined 17 citations and established a benchmark for the community. He also developed the **hSDB-instrument**, a specialized localization database for surgical instruments, cited 7 times. Notably, Hong pioneered a novel **image segmentation-guided intraoperative active bleeding (iAB) detection model**, which distinguishes active bleeding from similar-looking non-active blood to provide a critical statistical index for predicting patient outcomes. This work, though early in its citation history (3 citations), represents a significant step toward real-time decision support in the operating room. Through these efforts, Hong is shaping the future of context-aware, data-driven surgical assistance.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4