Medical data processing apparatus, magnetic resonance imaging apparatus, and learned model generating method

1. A medical data processing apparatus comprising:

a memory configured to store a learned model including

an input layer to which first MR data and second MR data are inputted in parallel, the second MR data relating to an imaging target the same as the first MR data and an imaging parameter different from the first MR data,

an output layer from which third MR data is output with a missing portion of the first MR data restored, and

at least one intermediate layer arranged between the input layer and the output layer; and

processing circuitry configured to generate the third MR data relating to a subject in accordance with the learned model from the first MR data serving as a process target and relating to the subject and the second MR data relating to the subject and acquired by an imaging parameter different from the first MR data serving as the process target, wherein

the imaging parameter includes at least one of a slice position, an acquisition time, an acquisition sequence, a k-space trajectory, and a temporal resolution, and

for every one signal of the first MR data and at least one signal of the second MR data that are input into the input layer in parallel, the output layer outputs one signal of the third MR data.

2. The medical data processing apparatus according to claim 1 , wherein the first MR data and the second MR data are k-space data or MR image data generated by performing a restoration process on the k-space data.

3. The medical data processing apparatus according to claim 2 , wherein the restoration process includes denoising restoration or data error feedback restoration.

4. The medical data processing apparatus according to claim 1 , wherein an amount of under-sampled data is larger in the first MR data than in the second MR data.

5. The medical data processing apparatus according to claim 1 , wherein each of the first MR data and the second MR data is inputted as a single input vector to the learned model.

6. The medical data processing apparatus according to claim 5 , wherein

the first MR data is assigned to a first region of the input vector,

the second MR data is assigned to a second region of the input vector, and

positions of the first region and the second region are fixed.

7. The medical data processing apparatus according to claim 6 , wherein

the second MR data includes a plurality of sets of MR data having different imaging parameters, and

each of the sets of second MR data is assigned to a fixed region of the second region of the input vector.

8. The medical data processing apparatus according to claim 1 , the apparatus further comprising training circuitry configured to generate estimated output data by applying the first MR data and the second MR data to a parameter-added composite function obtained by combining a plurality of functions and to generate the learned model by updating parameters of the parameter-added composite function such that the estimated output data and true output data approximate each other.

9. The medical data processing apparatus according to claim 1 , wherein the processing circuitry is configured to:

select an imaging body part in accordance with user's instructions; and

switch learned models in accordance with the selected imaging body part.

10. The medical data processing apparatus according to claim 1 , wherein

the imaging parameter includes a first parameter and a second parameter,

the first MR data and the second MR data share the first parameter and have different second parameters,

the first MR data and the third MR data share the first parameter and the second parameter,

the second MR data and the third MR data share the first parameter and have different second parameters, and

the third MR data includes less data deficit or higher image quality than the first MR data.

11. The medical data processing apparatus according to claim 10 , wherein

the first parameter represents a slice position, and

the second parameter represents an acquisition time, an acquisition sequence, a k-space trajectory, and a temporal resolution.

12. The medical data processing apparatus according to claim 10 , wherein

the first parameter represents at least one of an acquisition sequence, a k-space trajectory, and a temporal resolution, and

the second parameter represents a slice position.

13. The medical data processing apparatus according to claim 10 , wherein

the first parameter represents a slice position and an EPI acquisition sequence, and

the second parameter represents a value b of the acquisition sequence.

14. A magnetic resonance imaging apparatus comprising:

a memory configured to store a learned model including

an input layer to which first k-space data or MR image data and second k-space data or MR image data are inputted in parallel, the second k-space data or MR image data relating to an imaging target the same as the first k-space data or MR image data and an imaging parameter different from the first k-space data or MR image data,

an output layer from which third k-space data or MR image data having a missing portion of the first k-space data or MR image data restored is output, and

at least one intermediate layer arranged between the input layer and the output layer, and

processing circuitry configured to:

acquire first k-space data relating to a first imaging parameter and second k-space data relating to a second imaging parameter that is different from the first imaging parameter by performing MR imaging on a subject, and

generate third k-space data or MR image data relating to the subject in accordance with the learned model from the acquired k-space data or the MR image data based on the acquired k-space data and the acquired second k-space data or the MR image data based on the acquired k-space data, wherein

the imaging parameter includes at least one of a slice position, an acquisition time, an acquisition sequence, a k-space trajectory, and a temporal resolution, and

for every one signal of the first k-space data or MR image data and at least one signal of the second k-space data or MR image data that are input into the input layer in parallel, the output layer outputs one signal of the third k-space data or MR image data.

15. The magnetic resonance imaging apparatus according to claim 14 , wherein the processing circuitry is configured to:

acquire k-space data of time-series frames; and

select k-space data of one first frame as the first k-space data and k-space data of one or more second frames as the second k-space data from the k-space data of the frames.

16. The magnetic resonance imaging apparatus according to claim 15 , wherein the first k-space data is included in the second k-space data.

17. The magnetic resonance imaging apparatus according to claim 14 , wherein the processing circuitry is configured to:

acquire k-space data of time-series frames including the first k-space data and the second k-space data;

select k-space data of one first frame as the first k-space data from the k-space data of the frames,

generate k-space data of a plurality of second frames having a different acquisition time and/or temporal resolution based on the k-space data of the frames; and

select the k-space data of the second frames as the second k-space data.

18. The magnetic resonance imaging apparatus according to claim 17 , wherein the processing circuitry is configured to:

generate input MR image data of the first frame based on the k-space data of the first frame, k-space data of the second frames based on the k-space data of the frames, input MR image data of the second frames based on the k-space data of the second frames; and

generate output MR image data of the first frame as the third MR data from the input MR image data of the first frame and the input MR image data of the second frames in accordance with the learned model.

19. The magnetic resonance imaging apparatus according to claim 17 , wherein

the frames and the first frame have a first temporal resolution level, and

the second frames have a second temporal resolution level lower than the first temporal resolution level.

20. The magnetic resonance imaging apparatus according to claim 19 , wherein

the first temporal resolution level has a temporal resolution corresponding to one imaging frame,

the second temporal resolution level has a temporal resolution corresponding to two imaging frames or more,

the second frames include N(N+1)/2 frames, and

the second frames in each n-th temporal resolution level from a temporal resolution level corresponding to N imaging frames to a temporal resolution level corresponding to two imaging frames include (N+1−n) frames.

21. A learned model generating method comprising:

generating estimated output data by applying first MR data and second MR data in parallel to a parameter-added composite function obtained by combining a plurality of functions, the second MR data relating to an imaging target the same as the first MR data and an imaging parameter different from the first MR data; and

generating a learned model by updating the parameter of the parameter-added composite function such that the estimated output data and true output data having a missing portion of the first MR data restored approximate each other, wherein

the imaging parameter includes at least one of a slice position, an acquisition time, an acquisition sequence, a k-space trajectory, and a temporal resolution, and

for every one signal of the first MR data and at least one signal of the second MR data that are input into the parameter-added composite function in parallel, one signal of the third MR data is output.