Artificial intelligence for aiding cardiac diagnosis and treatment

Medical imaging, including computed tomography (CT) and magnetic resonance imaging (MRI), has revolutionised modern medicine and healthcare by enabling non-invasive qualitative and quantitative assessments of cardiac anatomical structures and functions and providing support for clinical treatment. In current clinical practice, these medical images are eyeball-checked to make decisions that are subjective and prone to errors. Furthermore,  3D virtual hearts are not widely used in clinics to guide treatment. 

In this project, we aim to develop a robust, automatic clinical software program for creating 3D reconstructions of cardiac chambers, providing patient-specific key structural factors from clinical CT/MRI to guide diagnosis, disease monitoring, treatment planning and prognosis of atrial fibrillation. This study is made possible through extensive collaboration with overseas clinical centres to utilise the world’s largest set of high-quality cardiac CT/MRIs. This large-scale imaging dataset will provide an ideal testing bed for our approach development.

• Machine learning
• Medical images
  

HRC