Carotid artery extraction method based on convolutional neural network

Abstract

The invention discloses a carotid artery extraction method based on a convolutional neural network, and relates to the technical field of medical image processing. The method comprises the steps that patch blocks are extracted from all three-dimensional carotid artery CTA images in an original data set and segmentation tags corresponding to the three-dimensional carotid artery CTA images respectively; constructing a training data set; establishing and training a carotid artery central path prediction model; determining and training a carotid artery segmentation model; inputting a three-dimensional carotid artery CTA image of a carotid artery to be predicted and a given seed point; extracting patch blocks taking the seed points as centers based on the seed points; and loading the pre-trained carotid artery central path prediction model and the pre-trained carotid artery segmentation model, performing iterative tracking of the carotid artery central path based on the patch block taking the seed point as the center and the pre-trained carotid artery central path prediction model, and completing carotid artery segmentation in the carotid artery central path tracking process. According to the method, the carotid artery segmentation is completed while the carotid artery central path is tracked for the first time.

Description

Technical field [0001] The present invention relates to the field of medical image processing technology, specifically to a carotid artery extraction method based on a convolutional neural network. Background [0002] Cerebrovascular diseases seriously threaten human health and are characterized by high prevalence, disability and mortality. Because of its rapid, non-invasive, clear image and economical characteristics, enhanced CT scan has become the primary means of examination for vascular diseases in clinical practice. The extraction of blood vessels in carotid CTA (Computed Tomography Angiography) images, mainly including the extraction of the central path of the carotid artery and the segmentation of the carotid artery, is a key step in accurately displaying and quantifying the carotid artery from a complex data set, and is also a prerequisite for cerebrovascular diseases such as stenosis, plaque, aneurysm diagnosis and surgical planning, which is crucial for the evaluation ...

AI Technical Summary

Problems solved by technology

[0004] Although many traditional automatic and semi-automatic blood vessel extraction methods have been proposed in the past few years, there are still many deficiencies that cannot meet the growing clinical needs.

For example, in the filter-based method, the blood vessel extraction effect is greatly affected by the shape of the blood vessel and the image quality; the model-based method requires strong constraint criteria and relies heavily on prior knowledge; the centerline method cannot directly segment the blood vessel contour, and needs to be combined with Vascular Appearance and Geometry Information

Images