S. M. Kamrul Hasan
Papers
4
Total Citations
108
H-Index
3
About
S. M. Kamrul Hasan is a leading researcher in computer vision for robot-assisted surgery, focusing on the critical challenge of surgical tool detection and scene understanding in minimally invasive procedures. His major contributions center on developing deep learning architectures for semantic and instance segmentation of surgical instruments from laparoscopic and endoscopic video. Hasan’s most influential work, the U-NetPlus architecture (2019, 79 citations), introduces a modified encoder-decoder U-Net that significantly improves the accuracy of tracking surgical tools in cluttered, narrow field-of-view surgical scenes—a problem that directly impacts patient safety by reducing the risk of tissue injury. He has further advanced the field by pioneering methods for segmenting and removing surgical instruments to reconstruct background scenes (2021, 9 citations) and inpainting occluded regions in laparoscopic video (2023), enabling clearer visualization for surgeons during robot-assisted interventions. With over 100 total citations, Hasan’s research bridges the gap between artificial intelligence and practical surgical needs, offering solutions that enhance dexterity control and intra-operative decision-making. His work is essential reading for anyone interested in the intersection of medical robotics, deep learning, and real-time surgical assistance.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4