Research team
Expertise
I am a biomedical engineer specialised in artificial intelligence for medical imaging, with a primary focus on endoscopic image analysis. My research develops computer vision and deep learning methods for detection, classification, depth estimation, and 3D scene understanding in endoscopy. I work on synthetic data generation, physics-based modelling, and multimodal learning strategies to improve robustness across devices, acquisition settings, and limited annotated data. Currently, I am expanding this expertise to CT and X-ray imaging, with a focus on 2D–3D registration. I develop pose-based learning frameworks to align 2D radiographs with 3D CT volumes, combining geometric modelling of X-ray projection physics with data-driven feature learning. This includes estimating imaging geometry, generating digitally reconstructed radiographs, and designing end-to-end models for accurate source and detector pose estimation. My work integrates computer vision, 3D modelling, and cross-modal representation learning for image-guided procedures.