Automated adjustment of the undersampling factor

1. A system, comprising:

a memory, wherein the memory is configured to store machine executable instructions, wherein the memory further stores a neural network, wherein the neural network is configured to output a predicted undersampling factor for magnetic resonance imaging in response to receiving magnetic resonance scan parameters, wherein the magnetic resonance scan parameters are descriptive of a configuration of a magnetic resonance imaging system; and

a computational system, wherein the computational system is configured to control the magnetic resonance imaging system, wherein execution of the machine executable instructions causes the computational system to:

receive pulse sequence commands, wherein the pulse sequence commands are configured to control the magnetic resonance imaging system to acquire k-space data according to a Compressed Sensing magnetic resonance imaging protocol;

receive the magnetic resonance scan parameters;

receive the predicted undersampling factor in response to inputting the magnetic resonance scan parameters into the neural network and prior to the acquisition of k-space data;

adjust the pulse sequence commands to select or modify sampling of the k-space data based on the predicted undersampling factor; and

store the adjusted pulse sequence commands in the memory.

2. A method of operating a system which includes a computational system, the method comprising:

the computational system receiving pulse sequence commands, wherein the pulse sequence commands are configured to control a magnetic resonance imaging system to acquire k-space data according to a Compressed Sensing magnetic resonance imaging protocol;

the computational system receiving magnetic resonance scan parameters, wherein the magnetic resonance scan parameters are descriptive of a configuration of the pulse sequence commands and a configuration of the magnetic resonance imaging system;

the computational system receiving a predicted undersampling factor in response to inputting the magnetic resonance scan parameters into a neural network; and

the computational system adjusting the pulse sequence commands to select or modify sampling of the k-space data based on the predicted undersampling factor; and

the computational system storing the adjusted pulse sequence commands in a memory,

wherein the neural network is configured to output the undersampling factor in response to receiving the magnetic resonance scan parameters and prior to the acquisition of the k-space data.

3. A non-transitory computer-readable medium having stored thereon a computer program comprising machine executable instructions for execution by a computational system configured to control a system, wherein execution of the machine executable instructions causes the computational system to:

receive pulse sequence commands, wherein the pulse sequence commands are configured to control a magnetic resonance imaging system to acquire k-space data according to a Compressed Sensing magnetic resonance imaging protocol;

receive magnetic resonance scan parameters, wherein the magnetic resonance scan parameters are descriptive of a configuration of the pulse sequence commands and a configuration of the magnetic resonance imaging system;

receive an undersampling factor in response to inputting the magnetic resonance scan parameters into a neural network; and

adjust the pulse sequence commands to select or modify sampling of the k-space data based on the undersampling factor; and

store the adjusted pulse sequence commands in a memory,

wherein the neural network is configured to output a predicted undersampling factor in response to receiving the magnetic resonance scan parameters and prior to the acquisition of k-space data.

4. The system of claim 1 , wherein the magnetic resonance scan parameters comprise at least one of: a radio-frequency coil configuration, a scan mode specifying a two-dimensional or three-dimensional scan, a sequence type specifying a contrast of the pulse sequence commands, an echo time, a pulse repetition time, a voxel size or three-dimensional spatial resolution, a three dimensional field of view, or a radio frequency bandwidth during k-space sampling.

5. The system of claim 1 , wherein execution of the machine executable instructions further causes the computational system to:

retrieve archived scan parameter data from a magnetic resonance scan parameter database;

construct archived training data from the archived scan parameter data; and

train the neural network using the archived training data.

6. The system of claim 1 , wherein execution of the machine executable instructions further causes the computational system to:

retrieve archived training data remotely; and

train the neural network using the archived training data.

7. The system of claim 1 , wherein the system further comprises the magnetic resonance imaging system, wherein execution of the machine executable instructions further causes the computational system to:

acquire the k-space data by controlling the magnetic resonance imaging system with the adjusted pulse sequence commands;

reconstruct magnetic resonance image data from the k-space data; and

store the reconstructed magnetic resonance image data in the memory.

8. The system of claim 1 , comprising a user interface, wherein execution of the machine executable instructions further causes the computation system to:

display the predicted undersampling factor and at least a portion of the magnetic resonance scan parameters on the user interface before adjusting the pulse sequence commands; and

receive an undersampling factor from the user interface in response to displaying the predicted undersampling factor, wherein the pulse sequence commands are adjusted using the undersampling factor received from the user interface.

9. The system of claim 1 , wherein the magnetic resonance imaging protocol is a parallel imaging magnetic resonance imaging protocol.

10. The system of claim 1 , wherein the neural network is a muti-layer neural network.

11. The method of claim 2 , further comprising:

acquiring the k-space data by controlling the magnetic resonance imaging system with the adjusted pulse sequence commands;

reconstructing magnetic resonance image data from the k-space data; and

storing the reconstructed magnetic resonance image data in the memory.

12. The method of claim 2 , further comprising:

displaying the predicted undersampling factor and at least a portion of the magnetic resonance scan parameters on a user interface before adjusting the pulse sequence commands; and

receiving an undersampling factor from the user interface in response to displaying the predicted undersampling factor, wherein the pulse sequence commands are adjusted using the undersampling factor received from the user interface.

13. The method of claim 2 , further comprising:

retrieving archived scan parameter data from a magnetic resonance scan parameter database;

constructing archived training data from the archived scan parameter data; and

training the neural network using the archived training data.

14. The method of claim 2 , further comprising:

retrieving archived training data is retrieved remotely; and

training the neural network using the archived training data.

15. The method of claim 2 , wherein the magnetic resonance scan parameters comprise at least one of: a radio-frequency coil configuration, a scan mode specifying a two-dimensional or three-dimensional scan, a sequence type specifying a contrast of the pulse sequence commands, an echo time, a pulse repetition time, a voxel size or three-dimensional spatial resolution, a three dimensional field of view, or a radio frequency bandwidth during k-space sampling.

16. The system of claim 4 , wherein the magnetic resonance scan parameters further comprise at least one of: a type of fat suppression protocol being used, a flip angle, a scan time, an orientation of the field of view, a foldover direction, a number of dynamic scans, a type of contrast agent used, or a number of signal averages.

17. The system of claim 6 , wherein the archived training data is retrieved remotely through a network connection.

18. The system of claim 8 , wherein execution of the machine executable instructions further causes the computational system to:

construct user specific training data from the magnetic resonance scan parameters and the predicted undersampling factor; and

train the neural network using the user specific training data.

19. The system of claim 10 , wherein the multi-layer neural network comprises at least 6 layers, and wherein each of the at least 6 layers is fully connected to adjacent layers.

20. The system of claim 16 , wherein the magnetic resonance scan parameters further comprise at least one of: a reconstruction voxel size or reconstruction matrix size, a type of pre-pulse used, an implementation of partial Fourier half scan protocol, an anatomical portion being examined, a shot typed used, a k-space profile order, a k-space trajectory, a physiological synchronization, a diffusion encoding technique type, a k-space segmentation factor, or a number of echoes used to acquire the same k-space line.