Embodiments relate to detecting coronary stenosis through spatio-temporal tracking. Aspects include extracting a coronary artery tree from each of a sequence of angiogram images, creating a mean artery tree from the extracted coronary artery trees, and projecting the mean artery tree back onto each of the sequence of angiogram images to recover a complete coronary artery tree for each of the sequence of angiogram images. Aspects also include extracting one or more tubular sections from each of the sequence of angiogram images, estimating an arterial width for each of the one or more tubular sections from each of the sequence of angiogram images, and creating a spatio-temporal surface from the arterial widths of the one or more tubular sections over a time spanned by the sequence of angiogram images. Aspects further include detecting a minimum in the spatio-temporal surface and determining if the minimum is indicative of stenosis.
