Assessment of coronary physiology and plaque vulnerability is crucial in the decision-making of optimal treatment strategy for patients with coronary artery disease. Over the past decades several intracoronary devices including fractional flow reserve, intravascular ultrasound, and optical coherence tomography have been developed to address this clinical need. However, the clinical adoption of these invasive devices is limited in several countries. We have developed several novel computational methods to assess coronary physiology and plaque vulnerability from imaging data. Empowered by artificial intelligence, the ease of use has been greatly improved, resulting in higher feasibility and reproducibility. Some of these methods have been used in many hospitals worldwide. In this talk, I will present our development and validation of these novel techniques.