Vascular plaque composition recognition method based on multi-contrast magnetic resonance image

Abstract

The invention provides a vascular plaque composition recognition method (300) based on a multi-contrast magnetic resonance image. The method comprises the following steps: implementing composition labeling (S310) on the to-be-trained multi-contrast vascular plaque magnetic resonance image; inputting the labeled multi-contrast vascular plaque magnetic resonance image into a convolutional neural network and implementing network model training (S320); and inputting the to-be-recognized multi-contrast vascular plaque magnetic resonance image into a trained network model and predicting the image, so as to output a vascular plaque composition recognition result (S330). According to the vascular plaque composition recognition method, the multi-contrast vascular plaque magnetic resonance image undergoes learning and modeling via the convolutional neural network, so that a new sample can be effectively recognized to assist a doctor in a diagnosis process, and working efficiency of the doctor can be greatly improved. The technical scheme can be conveniently promoted to magnetic resonance image assisted diagnosis processes of other organs.

Description

Technical field [0001] The invention relates to magnetic resonance imaging, and more particularly to a method for identifying components of vascular plaques based on multi-contrast magnetic resonance images. Background technique [0002] Cardiovascular and cerebrovascular diseases caused by high-risk plaques in blood vessels have become the number one killer of human health. The monitoring of vascular plaque based on imaging methods is of great significance for the prediction, staging and prognosis evaluation of cardiovascular and cerebrovascular diseases. Magnetic resonance vascular wall imaging technology is based on the physical principles of magnetic resonance. It is a method to obtain static tissue information such as the vascular wall by inhibiting the signal of blood flowing in the blood vessel, and can evaluate the composition of vascular plaque. [0003] Multi-contrast magnetic resonance imaging technology uses QIR-T1W (Quadruple Inversion Recovery T1-Weighted Image, T1-w...

AI Technical Summary

Problems solved by technology

[0007] a. Due to the limited modeling ability of traditional machine learning, complex feature engineering is required manually. This process requires the participation of a large number of experienced personnel, while the number of professional physicians is scarce, and it is difficult to effectively collaborate with technical personnel;

[0008] b. Feature engineering will inevitably cause the loss of the original multi-contrast vascular plaque magnetic resonance image signal, thereby reducing the accuracy of recognition;

[0009] c. The model has poor portability and is not universal, and cannot be easily applied to MRI image recognition scenarios of other organs

Images