Cerebrovascular image segmentation method based on statistical model and multi-scale filtering

The invention provides a cerebrovascular image segmentation method based on a statistical model and multi-scale filtering, and belongs to the technical field of medical calculation and image processing. The segmentation method combines a statistical model and multi-scale filtering so as to combine a high-level model and a low-level model to extract a cerebrovascular image and segment the cerebrovascular image, and comprises the following steps: S1, preprocessing data to obtain a denoised brain region image; s2, fitting a Gaussian model of an image background and a blood vessel class in the S1, and building an FMM; s3, setting an FMM initial value, estimating parameters and calculating a low-layer energy function; s4, segmenting the image; and S5, screening the seed points in combination with ridge line properties, extracting a blood vessel center line in a 3D space, performing expansion along the far-end blood vessel center line, and supplementing the low-layer model. According to the method, the segmentation precision of the far-end blood vessel image is improved, and accurate blood vessel center line extraction can be achieved under a rough blood vessel image segmentation result.