A magnetic resonance parallel imaging method and device
An imaging method and magnetic resonance technology, applied in image enhancement, image analysis, image data processing, etc., can solve the problems of slow reconstruction speed, poor reconstruction uniformity, low signal-to-noise ratio, etc., and achieve fast image reconstruction speed and high uniformity and the effect of the signal-to-noise ratio
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment approach 1
[0070] In Embodiment 1, in order to increase the data scanning rate, multiple contrasts share one data convolution kernel. In order to make multiple contrasts share one data convolution kernel, the scanning geometric information of the multiple contrasts in Embodiment 1 of the present application is the same.
[0071] figure 2 It is a schematic flowchart of the magnetic resonance parallel imaging method provided in Embodiment 1 of the present application. Such as figure 2 As shown, the method includes a k-space data acquisition process and an image reconstruction process. Wherein, the k-space data collection process includes step S201 and step S202. Wherein, step S201 is used to collect training data for training the convolution kernel of virtual channel data, and step S202 is used to collect imaging data of magnetic resonance parallel imaging. The image reconstruction process includes step S203 to step S205.
[0072] S201: Use the general coil to collect at least once ...
Embodiment approach 2
[0118] image 3 It is a schematic flowchart of the magnetic resonance parallel imaging method provided in Embodiment 2 of the present application. Such as image 3 As shown, this method is similar to Embodiment 1, and it also includes a data acquisition process and an image reconstruction process. Among them, the data collection process includes the following steps:
[0119] S301: Using the general coil to collect data in the central area of k-space of each channel with a preset contrast at least once through a full sampling method to obtain general coil data, and using a multi-channel coil to collect data in the central area of each channel k-space with a preset contrast through a full sampling method data to get multi-channel coil data.
[0120] The collection process of step S301 is the same as that of S201. The difference is that in the second embodiment of the present application, the general coil data is not directly used as training output data, and the multi-cha...
Embodiment approach 3
[0186] It should be noted that the third embodiment is improved on the basis of the first embodiment. The difference between the two is that the acquisition acceleration factor A of the imaging data in the first embodiment is an integer, while the acceleration factor A of the imaging data acquisition in the third embodiment is a non-integer.
[0187] Figure 5 It is a schematic flowchart of the magnetic resonance parallel imaging method provided in Embodiment 3 of the present application. Such as Figure 5 As shown, the magnetic resonance parallel imaging method also includes a k-space data acquisition process and an image reconstruction process.
[0188] Wherein, the data collection process is the same as the data collection process in the first embodiment. It specifically includes:
[0189] S501: Using the general coil to collect data in the central area of k-space of each channel with a preset contrast through a full sampling method to obtain general coil data, and us...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More