Papers
2
Total Citations
14
H-Index
2
About
Nazir Sirajudeen is a rising researcher at the forefront of artificial intelligence in robotic-assisted surgery, specializing in deep learning for surgical skill assessment and error detection. His work addresses a critical bottleneck in minimally invasive surgery: the need for automated, objective evaluation of surgical performance. Sirajudeen’s most cited paper, “Deep learning prediction of error and skill in robotic prostatectomy suturing” (2024, 8 citations), demonstrates how neural networks can predict surgical expertise and identify errors from video data, offering a scalable alternative to subjective manual assessment. Building on this, his innovative “SEDMamba” framework (2024, 6 citations) introduces a hierarchical architecture combining selective state space modeling with a bottleneck mechanism and fine-to-coarse temporal fusion, enabling efficient long-term dependency capture for real-time error detection. This work directly addresses the computational challenges of processing complex surgical video streams. Sirajudeen’s contributions are pivotal for advancing patient safety and surgical training, providing tools that could transform how surgeons learn and operate. His research, though early in its trajectory, has already garnered attention for its practical impact on automating quality assurance in robot-assisted procedures.
Research Focus
Key Achievements
Top Papers
- 1
- 2