Information processing method, medical image diagnostic apparatus, and information processing system

1. An information processing method of information acquired by imaging performed by a medical image diagnostic apparatus, the information processing method comprising:

based on first subject data acquired by the imaging performed by the medical image diagnostic apparatus, acquiring noise data in the first subject data;

based on second subject data acquired by the imaging performed by a medical image diagnostic modality of a same kind as the medical image diagnostic apparatus and based on the acquired noise data, acquiring synthesized subject data in which noise based on the acquired noise data is added to the second subject data; and

acquiring a noise reduction processing model by machine learning using the synthesized subject data and third subject data acquired by the imaging performed by the medical image diagnostic modality.

2. The information processing method according to claim 1 , wherein the second subject data is acquired by the imaging performed by the medical image diagnostic apparatus.

3. The information processing method according to claim 1 , wherein the second subject data is acquired by imaging performed by another medical image diagnostic apparatus, which is a same kind as the medical image diagnostic apparatus and is not the medical image diagnostic apparatus.

4. The information processing method according to claim 1 , wherein the second subject data is acquired by imaging performed by another medical image diagnostic apparatus, which is a same imaging system as the medical image diagnostic apparatus and is not the medical image diagnostic apparatus.

5. The information processing method according to claim 1 , wherein the third subject data is data acquired by imaging a subject that is a same subject used to obtain the second subject data.

6. The information processing method according to claim 1 , wherein the noise data is data indicating a noise intensity of the first subject data in image space or projection data space.

7. The information processing method according to claim 1 , wherein the noise reduction processing model is acquired by training the model by deep learning, wherein an input of the model is the synthesized subject data and a target of the model is the third subject data acquired by the imaging performed by the medical image diagnostic apparatus.

8. The information processing method according to claim 1 , wherein the step of acquiring the noise data further comprises extracting the noise data based on a first reconstructed image and a second reconstructed image acquired by reconstructing a first subset of the first subject data and a second subset of the first subject data, respectively.

9. The information processing method according to claim 8 , wherein the extracting step further comprises extracting the noise data by performing difference processing between the first reconstructed image and the second reconstructed image.

10. The information processing method according to claim 1 , further comprising acquiring the second subject data from a subject different from the first subject data, or at a date and time different from the first subject data.

11. The information processing method according to claim 1 , further comprising:

acquiring the second subject data based on a first subset of fourth subject data acquired by the imaging performed by the medical image diagnostic apparatus, and

acquiring the third subject data based on a second subset of the fourth subject data, which is different from the first subset.

12. The information processing method according to claim 1 , further comprising:

acquiring the second subject data as a reconstructed image acquired by reconstructing the fourth subject data acquired by the imaging performed by the medical image diagnostic apparatus, by a first reconstruction method, and

acquiring the third subject data as a reconstructed image acquired by reconstructing the fourth subject data by a second reconstruction method with higher accuracy than the first reconstruction method.

13. The information processing method according to claim 1 , further comprising acquiring the third subject data as a reconstructed image acquired by reconstructing the fourth subject data acquired by the imaging performed by the medical image diagnostic apparatus, by an FBP method.

14. The information processing method according to claim 1 , further comprising acquiring the second subject data and the third subject data by low-dose imaging.

15. A medical image diagnostic apparatus, comprising:

processing circuitry configured to

acquire input subject data by imaging a subject,

acquire denoised data by reducing noise in the input subject data by a noise reduction processing model acquired by training a model by machine learning using synthesized subject data and third subject data, the synthesized subject data being acquired based on second subject data and noise data in first subject data acquired by imaging performed by the medical image diagnosis apparatus, and

output an image of the subject based on the denoised data.

16. The medical image diagnostic apparatus according to claim 15 , wherein the processing circuitry is further configured to:

acquire the noise data in the first subject data based on the first subject data acquired by the imaging performed by the medical image diagnostic apparatus,

acquire synthesized subject data, in which noise based on the noise data is added to the second subject data, based on the second subject data and the noise data, the second subject data being acquired by the imaging performed by the medical image diagnostic apparatus, and

acquire the noise reduction processing model by machine learning using the synthesized subject data and the third subject data, which is acquired by the imaging performed by the medical image diagnostic apparatus.

17. An information processing system, comprising:

processing circuitry configured to

acquire input subject data by imaging a subject,

acquire denoised data by reducing noise in the input subject data by a noise reduction processing model acquired by training a model by machine learning using synthesized subject data and third subject data, the synthesized subject data being acquired based on second subject data and noise data in first subject data acquired by imaging performed by the medical image diagnosis apparatus, and

output an image of the subject based on the denoised data.

18. The information processing system according to claim 17 , wherein the processing circuitry is further configured to:

acquire the noise data in the first subject data based on the first subject data acquired by the imaging performed by a medical image diagnostic apparatus,

acquire synthesized subject data, in which noise based on the noise data is added to the second subject data, based on the second subject data and the noise data, the second subject data being acquired by the imaging performed by the medical image diagnostic apparatus, and

acquire the noise reduction processing model by machine learning using the synthesized subject data and the third subject data acquired by the imaging performed by the medical image diagnostic apparatus.

19. An information processing method of processing information acquired by imaging performed by a medical image diagnostic modality, the information processing method comprising:

based on first subject data acquired by the imaging performed by a medical image diagnostic apparatus, acquiring noise data in the first subject data;

based on subject data of a subject acquired by the imaging performed by a medical image diagnostic modality of a same kind as the medical image diagnostic apparatus, generating second subject data corresponding to a first subset of the subject data, and third subject data corresponding to a second subset of the subject data, which is different from the first subset;

generating synthesized subject data by synthesizing the second subject data and the acquired noise data; and

acquiring a noise reduction processing model by machine learning, wherein an input of the model is the synthesized subject data and a target of the model is the third subject data.

20. An information processing method of information acquired by imaging performed by a medical image diagnostic apparatus, the information processing method comprising:

based on first subject data acquired by the imaging performed by the medical image diagnostic apparatus, acquiring noise data in the first subject data;

based on second subject data acquired by the imaging performed by a medical image diagnostic modality of a same kind as the medical image diagnostic apparatus and based on the acquired noise data, acquiring synthesized subject data in which noise based on the acquired noise data is added to the second subject data; and

acquiring a noise reduction processing model by machine learning using the synthesized subject data and third subject data acquired by the imaging performed by the medical image diagnostic modality,

wherein the step of acquiring the noise data further comprises extracting the noise data based on a first reconstructed image and a second reconstructed image acquired by reconstructing a first subset of the first subject data and a second subset of the first subject data different from the first subset, respectively.

21. The information processing method according to claim 1 , wherein the first subject data, the second subject data, and the third subject data are acquired by imaging a human body.