Intracranial vascular lesion identification method based on transfer learning

Abstract

The invention discloses an intracranial vascular lesion identification method based on transfer learning. The method comprises the following steps: acquiring a bright blood image group, a black blood image group and an enhanced black blood image group; preprocessing to obtain a first bright blood image and a first black blood image; for each first bright blood image, taking the corresponding first black blood image as a reference, and obtaining a registered bright blood image group by using a mutual information and image pyramid registration method based on Gaussian distribution sampling; empty flow artifacts are eliminated to obtain an artifact-eliminated enhanced black blood image group; subtracting corresponding images in the artifact elimination enhanced black blood image group and the black blood image group to obtain K contrast enhanced images; and establishing a blood three-dimensional model by using the registered bright blood image group and adopting a transfer learning method, and establishing a blood vessel three-dimensional model for blood boundary expansion by using the registered bright blood image group. According to the method, the focus area of the intracranial blood vessel can be clinically, conveniently, quickly and intuitively identified.

Description

technical field [0001] The invention belongs to the field of image processing, and in particular relates to a method for identifying intracranial vascular lesions based on migration learning. Background technique [0002] With the rapid development of my country's national economy, people pay more and more attention to health issues. A paper published by "Lancet" in June 2019 analyzed the causes of death of residents in 34 provinces in China (including Hong Kong, Macao and Taiwan) from 1990 to 2017, and found that the number one cause of death among Chinese was stroke. Stroke is the rupture, stenosis or blockage of intracranial blood vessels that causes brain tissue necrosis, resulting in a series of symptoms, including cerebral hemorrhage, cerebral infarction, etc. If the treatment is not timely, the patient may die; disabled. [0003] At present, methods based on lumen imaging are usually used to evaluate the degree of intracranial vascular lesions and vascular stenosis ...

AI Technical Summary

Problems solved by technology

However, two-dimensional images have limitations, which is not conducive to obtaining real information of intracranial blood vessels easily and quickly.

Moreover, from the images obtained by the above-mentioned imaging methods, it is impossible to intuitively and quickly obtain analysis data on the degree of intracranial vascular stenosis, which is not conducive to the clinical positioning and analysis of intracranial vascular lesion regions.

Images