Baiying Lei
Papers
3
Total Citations
18
H-Index
2
About
Baiying Lei is a leading researcher in medical image analysis and 3D shape reconstruction, with a focus on advancing surgical navigation and brain imaging. Her work centers on developing novel deep learning architectures for reconstructing 3D anatomical structures from limited or incomplete 2D data—a critical challenge in minimally-invasive and robot-guided surgeries. Lei’s major contributions include pioneering point cloud generative models using tree-structured graph convolutions for 3D brain shape reconstruction, enabling the fusion of medical images with 3D shape representations to provide complementary microstructure details. This approach significantly improves operational performance and accuracy in brain surgery. She also introduced hierarchical shape-perception networks capable of reconstructing complete 3D brain shapes from single incomplete images, addressing a key limitation in surgical environments with indirect and narrow operating fields. Her work has garnered substantial attention, with her most cited papers accumulating over 14 citations, reflecting their impact on both computer vision and clinical practice. Lei’s innovative methods are paving the way for more precise, automated surgical guidance systems, making her a notable figure at the intersection of AI and healthcare.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3