Haorui Huang
Papers
1
Total Citations
15
H-Index
1
About
Haorui Huang is a rising researcher in medical image analysis, with a primary focus on deep learning architectures for ultrasound image segmentation. His most influential work introduces MM-UKAN++, a novel U-shaped network grounded in Kolmogorov–Arnold Network theory, designed to address the persistent challenges of low contrast and boundary fuzziness in ultrasound imaging. This architecture achieves both high accuracy and computational efficiency, making it well-suited for real-time clinical and robot-assisted diagnosis. Since its publication in 2025, the paper has already garnered 15 citations, reflecting its immediate impact on the field. Huang’s contributions are particularly notable for bridging theoretical advances in neural network design with practical medical imaging needs, offering a robust solution for segmenting regions of interest in noisy, low-quality ultrasound data. His work stands out for its innovative integration of KAN layers into a U-shaped framework, setting a new benchmark for segmentation tasks in challenging imaging modalities. As an early-career researcher, Huang is establishing himself at the forefront of AI-driven medical diagnostics, with his methods poised to influence both future research and clinical workflows.
Research Focus
Key Achievements
Top Papers
- 1