Angiography is one of the methods used by radiologists to examine the structure and health of blood vessels. To obtain an angiogram, a radiologist injects an x-ray opaque contrast agent into a vessel, and takes an x-ray image of the vessel. The diameter of a vessel everywhere along its length can be measured in these images. This information reveals constrictions caused by blood clots, cholesterol build-up, or injury. Treatment of these conditions involves inserting a catheter with a scraping tool mounted at its tip into the vessel to remove the obstruction.
The work presented here automatically detects and measures vessels within a single x-ray image. The algorithms will be a basis for further work in using images taken at different angles around the vessel to reconstruct its three-dimensional shape. With such information, a computer could aid treatment planning by simulating what a catheter would encounter in the branching vascular network. Some earlier work related to this project is presented in .