Segmentation of linear structures from medical images

In this paper, an algorithm for the extraction of linear structures from medical images is implemented. Blood vessels in angiographic images have linear patterns. Hence, these features can be extracted easily using morphological operations. Blood vessels can be separated out as they have a specific Gaussian-like profile whose curvature varies smoothly along the vessel. In order to differentiate vessels from analogous background patterns, edge detection is performed and the application of linear filters like top-hat transformations can eliminate the background noise, thereby segmenting the entire blood vessels in the angiographic image. Such vessel extraction could help physicians in the computation of parameters related to blood flow.