Magnetic resonance image processing method and apparatus using scan parameters
According to an embodiment of the present invention, there is provided a magnetic resonance image processing method including: acquiring a low-quality training image, a first parameter group including at least one scan parameter applied when the training image is acquired, a high-quality label image, and a second parameter group including at least one scan parameter applied when the label image is acquired; and training an artificial neural network model by using the training image, the first parameter group, the label image, and the second parameter group.
1. A magnetic resonance image processing method performed by a magnetic resonance image processing apparatus, the method comprising:
acquiring a low-quality training image, a first parameter group including at least one scan parameter applied, which is an environmental variable applied to a medical imaging device that captures the training image, when the training image is acquired, a high-quality label image, and a second parameter group including at least one scan parameter applied, which is an environmental variable applied to the medical imaging device that captures the label image, when the label image is acquired; and
training an artificial neural network model by using the training image, the first parameter group, the label image, and the second parameter group,
wherein the first parameter group and the second parameter group are one-dimensional data in which values of at least one scan parameter are listed, and
wherein the first parameter group and the second parameter group are transformed and input to the artificial neural network model.
2. The magnetic resonance image processing method of claim 1 , wherein the scan parameter includes at least one of:
a number of excitations, which is a number of repetitions when lines of first k-space data of a magnetic resonance signal are repeatedly acquired; a phase resolution, which is a value obtained by dividing a number of lines sampled in a phase encoding direction of the first k-space data by a preset reference value; and an acceleration factor, which refers to a value obtained by dividing a number of fully sampled signal lines of the first k-space data by a number of sub-sampled signal lines.
3. The magnetic resonance image processing method of claim 1 , wherein:
the training image is acquired by sub-sampling a magnetic resonance signal; and
the label image is acquired by fully sampling the magnetic resonance signal.
4. The magnetic resonance image processing method of claim 1 , wherein a number of excitations of the training image is smaller than a number of excitations of the label image.
5. The magnetic resonance image processing method of claim 1 , wherein a phase resolution of the training image is lower than a phase resolution of the label image.
6. The magnetic resonance image processing method of claim 1 , wherein training the artificial neural network model comprises performing pre-processing so that a size of the first parameter group and a size of the second parameter group correspond to a number of channels of the artificial neural network model.
7. The magnetic resonance image processing method of claim 6 , wherein:
performing the pre-processing comprises generating first attention data and second attention data by inputting the first parameter group and the second parameter group to a pre-processing artificial neural network model; and
training the artificial neural network model comprises inputting the first attention data and the second attention data to the artificial neural network model.
8. The magnetic resonance image processing method of claim 7 , wherein the pre-processing artificial neural network model includes a fully connected layer.
9. The magnetic resonance image processing method of claim 1 , further comprising generating a reconstructed image by inputting an input image and a third parameter group, including at least one scan parameter applied when the input image is acquired, to the artificial neural network model.
10. A non-transitory computer-readable storage medium in which a program for performing the method of claim 1 is stored.
11. A magnetic resonance image processing method performed by a magnetic resonance image processing apparatus, the method comprising:
inputting an input image and a third parameter group, including at least one scan parameter applied, which is an environmental variable applied to a medical imaging device that captures the input image, when the input image is acquired, to an artificial neural network model trained using a low-quality training image, a first parameter group including at least one scan parameter applied, which is an environmental variable applied to a medical imaging device that captures the training image, when the training image is acquired, a high-quality label image, and a second parameter group including at least one scan parameter applied, which is an environmental variable applied to the medical imaging device that captures the label image, when the label image is acquired; and
outputting a reconstructed image from the artificial neural network model,
wherein the first parameter group, the second parameter group and the third parameter group are one-dimensional data in which values of at least one scan parameter are listed,
wherein the first parameter group and the second parameter group are transformed and input to the artificial neural network model.
12. A magnetic resonance image processing apparatus for performing a magnetic resonance image processing method, the magnetic resonance image processing apparatus comprising:
memory configured to store a magnetic resonance image processing program; and
a processor configured to execute the program,
wherein the processor trains an artificial neural network model by using a low-quality training image, a first parameter group including at least one scan parameter applied, which is an environmental variable applied to a medical imaging device that captures the training image, when the training image is acquired, a high-quality label image, and a second parameter group including at least one scan parameter applied, which is an environmental variable applied to the medical imaging device that captures the label image, when the label image is acquired,
wherein the first parameter group and the second parameter group are one dimensional data in which values of at least one scan parameter are listed,
wherein the first parameter group and the second parameter group are transformed and input to the artificial neural network model.