Medical information processing apparatus and medical information processing method
According to one embodiment, a medical information processing apparatus has processing circuitry. The processing circuitry acquires medical data on a subject, acquires numerical data obtained by digitizing an acquisition condition of the medical data, and applies a machine learning model to input data including the numerical data and the medical data, thereby generating output data based on the medical data.
1. A medical information processing apparatus comprising a processing circuitry,
the processing circuitry being configured to
acquire numerical data obtained by digitizing an acquisition condition of medical data of the subject, wherein the acquisition condition includes at least one of a type of pulse sequence, a frame number, a type of k-space filling trajectory, a number of times of repetition of repetition operation or an acceleration factor of parallel imaging,
acquire, as the medical data, raw data acquired by medical imaging according to the acquisition condition,
apply a machine learning model to input data including (1) the numerical data and (2a) the medical data or (2b) a medical image based on the medical data to generate output data based on the medical data or the medical image, and
output as the output data at least one of de-noised medical data, segmented image data, or super resolution data.
2. The medical information processing apparatus according to claim 1 , wherein the machine learning model receives inputs of the numerical data and the medical data and learns using teacher data.
3. The medical information processing apparatus according to claim 1 , wherein
the numerical data includes an element having two or more finite number of elements,
the number of the elements corresponds to a number of a plurality of candidate conditions corresponding to the acquisition condition, and
the value of the element corresponds to a numerical value according to whether or not the acquisition condition is adopted for the candidate conditions and/or a value.
4. The medical information processing apparatus according to claim 3 , wherein the value of the element has one of a first value indicating that the acquisition condition is adopted and a second value indicating that the acquisition condition is not adopted.
5. The medical information processing apparatus according to claim 3 , wherein
the numerical data includes an element having two or more finite number of elements, and
the elements by the number of the elements include a first element corresponding to the candidate conditions and a second element corresponding to none of the candidates.
6. The medical information processing apparatus according to claim 1 , wherein the processing circuitry generates data to be provided for medical diagnosis on the subject as the output data.
7. The medical information processing apparatus according to claim 1 , wherein the machine learning model is configured to multiply each of the numerical data and the medical data by weight different and add a product for each channel.
8. The medical information processing apparatus according to claim 1 , wherein the processing circuit performs reconstruction processing on the input data including the numerical data and the raw data using the machine learning model to generate the image data on the subject.
9. The medical information processing apparatus according to claim 1 , wherein
the acquisition condition is a number of times of acquisition and/or a direction of acquisition for each data acquisition trajectory, and
the numerical data is mask data in which a numerical value corresponding to the number of times of acquisition and/or the direction of acquisition in target imaging is assigned to a plurality of data acquisition trajectory candidates having a finite number of elements.
10. The medical information processing apparatus according to claim 9 , wherein the processing circuitry determines the number of times of acquisition and/or the direction of acquisition for the data acquisition trajectory candidates according to a user's instruction or automatically.
11. The medical information processing apparatus according to claim 9 , wherein the processing circuitry determines the number of times of acquisition and/or the direction of acquisition for the data acquisition trajectory candidates according to a predetermined rule based on an imaging time in the medical imaging.
12. The medical information processing apparatus according to claim 9 , wherein the numerical value includes a first numerical value indicating that data acquisition is to be performed and a second numerical value indicating that data acquisition is not to be performed.
13. The medical information processing apparatus according to claim 9 , wherein each of the data acquisition trajectory candidates is a data acquisition trajectory in k-space related to a radial method, and linearly passes substantially a center of the k-space.
14. The medical information processing apparatus according to claim 13 , wherein an angular interval between the data acquisition trajectory candidates is set to a predetermined angle.
15. The medical information processing apparatus according to claim 13 , wherein the data acquisition trajectory candidates are arranged at substantially equal intervals at an angle based on an angle obtained by dividing 360 degrees by the number of the elements.
16. The medical information processing apparatus according to claim 9 , wherein each of the data acquisition trajectory candidates is a data acquisition trajectory in k-space related to a spiral method, and spirally passes through the k-space.
17. The medical information processing apparatus according to claim 9 , wherein the processing circuitry applies the machine learning model to the mask data and the raw data, generates de-noised raw data as the output data, and performs Fourier transformation on the de-noised raw data to generate the medical image.
18. The medical information processing apparatus according to claim 9 , wherein the processing circuitry performs Fourier transformation on the raw data to generate a provisional medical image, and applies the machine learning model to the mask data and the provisional medical image.
19. The medical information processing apparatus according to claim 1 , further comprising an imaging apparatus configured to perform magnetic resonance imaging on the subject and acquire k-space data as the medical data.
20. A medical information processing method comprising:
acquiring numerical data obtained by digitizing an acquisition condition medical data of the subject, wherein the acquisition condition includes at least one of a type of pulse sequence, a frame number, a type of k-space filling trajectory, a number of times of repetition of repetition operation or an acceleration factor of parallel imaging;
acquiring, as the medical data, raw data acquired by medical imaging according to the acquisition condition,
applying a machine learning model to input data including (1) the numerical data and (2a) the medical data or (2b) a medical image based on the medical data to generate output data based on the medical data or the medical image; and
outputting as the output data at least one of de-noised medical data, segmented image data, or super resolution data.