Magnetic resonance imaging method, device, system and storage medium
A magnetic resonance imaging and magnetic resonance image technology, applied in the field of medical imaging, can solve the problem that the network model does not fully utilize the information between different channels, and achieve the effect of low model training cost and small amount of data collection
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0031] figure 1 This is a flowchart of the magnetic resonance imaging method provided in Embodiment 1 of the present invention. The technical solution of this embodiment is applicable to the situation in which the corresponding target magnetic resonance image is determined according to the undersampled K-space data by using the trained preset neural network model. The method may be performed by the magnetic resonance imaging apparatus provided in the embodiment of the present invention, and the apparatus may be implemented in software and / or hardware, and configured to be applied in a processor. like figure 1 As shown, the method specifically includes the following steps:
[0032] S101. Acquire the under-mined K-space data of the target scanning part collected based on the time-interleaved under-mining method.
[0033] Figure 2A A schematic diagram showing the time-interleaved under-mining mode, the graph k y The acquisition channel of the direction is spread along the t...
Embodiment 2
[0047] Figure 4 This is a flowchart of the magnetic resonance imaging method provided by the second embodiment of the present invention. The embodiments of the present invention describe the training process of the preset neural network in detail on the basis of the above-mentioned embodiments. like Figure 4 shown, including:
[0048] S201, constructing a training sample.
[0049] After the under-coded k-space data and fully-coded images are obtained, training samples can be constructed. like Figure 5 As shown, the training sample includes at least two under-encoded K-space data of the input image and a fully encoded image corresponding to the input image as the output image.
[0050] The under-sampling multiple of the under-coded K-space data can be determined by the extraction matrix determined by the user according to actual needs.
[0051] Exemplarily, if the extraction matrix of the under-encoded k-space data whose under-sampling multiple is three times is determ...
Embodiment 3
[0060] Figure 6A This is a structural block diagram of the magnetic resonance imaging apparatus provided by the third embodiment of the present invention. The apparatus is used to execute the magnetic resonance imaging method provided in any of the foregoing embodiments, and the apparatus can be optionally implemented in software or hardware.
[0061] The device includes:
[0062] The acquisition module 31 is used for acquiring the under-mined K-space data of the target scanning position collected based on the time-interleaved under-mining method;
[0063] The output module 32 is used to input the under-mined K-space data into the trained preset neural network model to obtain the target magnetic resonance image; wherein, the target magnetic resonance image is a fully encoded image, and the trained preset neural network model is being trained In the process, the corresponding relationship between the under-encoded k-space data and the fully-encoded image is determined by det...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More