Papers
1
Total Citations
2
H-Index
1
About
Yueyue Xiao is a researcher at the forefront of medical image analysis, with a primary focus on 2D/3D image registration—a critical technique for aligning preoperative 3D scans with intraoperative 2D X-rays in image-guided interventions. Her most notable contribution, the 2025 paper "Parametric Bi-invariant Learning for Improved Precision in 2D/3D Image Registration," introduces a novel parametric framework that leverages bi-invariant transformations to enhance registration accuracy and robustness. This work addresses a longstanding challenge in the field: achieving submillimeter precision despite variations in patient positioning and imaging geometry. While still early in her career, Xiao’s approach has already garnered attention, earning 2 citations and signaling its potential impact on surgical navigation and radiotherapy planning. By integrating geometric deep learning with classical registration methods, she offers a pathway to more reliable, real-time alignment in clinical settings. Her research bridges the gap between theoretical invariance and practical deployment, making her a promising voice in computational medical imaging. For students and researchers exploring registration techniques, Xiao’s work exemplifies how principled mathematical design can drive tangible improvements in precision medicine.
Research Focus
Key Achievements
Top Papers
- 1