Our research focuses on the development of biomedical image analysis algorithms, with an emphasis on the combination with computational models, and applications on cardiac and pulmonary medicine.

We conduct advanced research on Machine Learning (ML) and Artificial Intelligence (AI) to develop the next generation of methods for medical image analysis. We push the boundaries of this technology to create more accurate, reliable and explainable methods. Our aim is to enable safe use of ML/AI in healthcare, and use the technology to tackle any challenging clinical question towards improving diagnosis and treatment.

Our research focuses on machine learning applied to fetal ultrasound analysis. We are measuring at scale how operators scan, by recording eye and probe tracking, ultrasound video and audio in the clinic. This enables us to develop machine learning models to characterise operator skill, and to build multi-modal ultrasound assistive technologies to support non-experts to scan. We are also developing low-cost ultrasound technologies empowered by deep learning based algorithms for pregnancy risk assessment in collaboration with partners in Africa and India.

Motion is a massive barrier in cancer imaging hampering developments in cancer research and treatment. My research work has comprised the development of accurate, thus complex and realistic but still computationally efficient, models of organ motion, and has established a solid foundation to reliable quantitative cancer image analysis.

The aim of our research is to enhance our understanding of complex biological processes through the analysis of image data that has been acquired at the microscopic scale. We develop algorithms and methods that enable the quantification of a broad range of phenotypical alterations, the precise localisation of signalling events, and the ability to correlate such events in the context of the biological specimen.

Our work is primarily focused on Multimodal Reconstruction and Analysis of Digital Anatomy for Real-Time Clinical Interventions; in particular Segmentation, Landmark Detection, Tracking, Motion Modelling, Reconstruction, Registration, and Fusion of 2D/3D/3D+t Anatomical Structures and Physiological information from Multi-Modality including X-ray, Angiography, MRI, CT, US, etc.