RSNA News covered our work on automatic calcium scoring in an interview with Ivana Išgum.

The work is described in our paper ‘Deep Learning for Automatic Calcium Scoring in CT: Validation Using Multiple Cardiac CT and Chest CT Protocols’ by van Velzen et al. that has been published in Radiology. In this paper, we described an AI-based method that performs automatic calcium scoring in the coronary arteries and aorta in CT scans that visualize the heart.

Unlike most automatic methods that require a specific type of input image, our aim was to develop a method that is robust to substantial differences in CT protocols and variations in subject population. This eliminates the need to train a specific algorithm for each type of CT scan and enables use of a single method that quantifies calcium in various types of CT scans. This means the method should be easy to implement in the clinic and for screening using CT scans made for various purposes. Consequently, the method could help identify people at increased risk of cardiovascular events.