Head and neck combined imaging method and device based on deep priori learning

Abstract

The invention provides a head and neck joint imaging method and device based on deep priori learning, and the method comprises the steps: obtaining a magnetic resonance image of a head and neck jointto be reconstructed; Inputting the head and neck combined magnetic resonance image to be reconstructed into a plurality of pre-established convolutional neural network models, and setting a pluralityof residual error blocks in the plurality of convolutional neural network models; And reconstructing the head and neck combined magnetic resonance image to be reconstructed through the plurality of convolutional neural network models to obtain an artifact-free high-resolution head and neck combined image. By means of the scheme, the problem that the imaging precision and the imaging time requirement cannot be guaranteed at the same time in existing head and neck combined imaging is solved, and the technical effect that the imaging time can be effectively shortened under the condition that theimaging precision is guaranteed is achieved.

Description

Technical field [0001] This application belongs to the field of image processing technology, and in particular relates to a head and neck joint imaging method and device based on deep prior learning. Background technique [0002] Fast imaging has always been a research hotspot in magnetic resonance imaging, and magnetic resonance scanning of the head and neck is a very important aspect in the field of magnetic resonance imaging. The main difficulty of head-neck MRI vascular wall imaging is the intracranial part. In general, intracranial imaging is basically two-dimensional imaging technology. Two-dimensional imaging technology can only observe a certain section of the cross-sectional image. The layer thickness is generally too large and not all The items are of the same nature and cannot meet actual application requirements. However, intracranial three-dimensional vascular wall imaging can obtain blood flow and bleeding signals at the same time, which is conducive to the quantit...

AI Technical Summary

Problems solved by technology

The difficulty of combined head-neck magnetic resonance vessel wall imaging is mainly the intracranial part. Generally, intracranial imaging is basically a two-dimensional imaging technology. Item homogeneity, unable to meet actual application requirements

However, intracranial three-dimensional vessel wall imaging can simultaneously obtain blood flow and bleeding signals, which is beneficial to the quantitative detection of plaque hemorrhage, but there are problems such as low spatial resolution, long imaging time, and insufficient contrast between vessel wall and cerebrospinal fluid.

[0003] The current head and neck joint imaging technology generally adopts T1-weighted three-dimensional fast spin echo technology. This technology uses head and neck integrated imaging with a maximum field of view of 250mm. It uses flip-down preparation pulses to uniformly suppress cerebrospinal fluid signals, and uses DANTE modules to effectively suppress blood flow. The signal has better contrast and isotropic resolution of 0.5mm in the whole brain. However, due to the increase of the scanning field of view, the imaging time is longer. If the carotid artery examination is added, the time will be longer and it is even more unsatisfactory. actual application needs

[0004] Aiming at the problem that the existing head and neck joint imaging cannot meet the requirements of imaging accuracy and imaging time at the same time, no effective solution has been proposed yet

Images