The segmentation method of degree-based fusion algorithm for coronary angiograms

In allusion to the low contrast of the image between the backdrop and the small blood vessels, the blurred and fuzzy background of coronary artery image, a new blood vessel extraction method based on degree is proposed. First of all, two enhanced coronary angiograms are obtained from the original image by using two different image enhancement methods. Secondly, coronary arteries are extracted from two enhanced coronary angiograms through using the transition region extraction method based on degree, and then two extracted coronary artery images are acquired. At last, two extracted blood vessel images are fused, and the result of the fusion is the final segmentation image. The experimental results show that the backdrop can be eliminated and the small vessels can be remained effectively.