Magnetic resonance imaging system and method, and computer-readable storage medium
Provided in the present invention are a magnetic resonance imaging system and method, and a computer-readable storage medium. The method comprises: performing a medical scan of a subject and acquiring a first medical image having a first noise interference artifact, and performing an additional scan of the subject to acquire a second medical image, wherein the second medical image has a second noise interference artifact, and the location mapping of the second noise interference artifact in the first medical image is symmetrical to the location of the first noise interference artifact relative to a pixel center of the first medical image; and performing synthesis-related processing on the first medical image and the second medical image to acquire a post-processed image with reduced noise interference artifacts.
1. A magnetic resonance imaging method, comprising:
performing a medical scan of a subject and acquiring a first medical image having a first noise interference artifact, and performing an additional scan of the subject to acquire a second medical image, wherein the second medical image has a second noise interference artifact, and the location mapping of the second noise interference artifact in the first medical image is symmetrical to the location of the first noise interference artifact relative to a pixel center of the first medical image; and
performing synthesis-related processing on the first medical image and the second medical image to acquire a post-processed image with reduced noise interference artifacts.
2. The method according to claim 1 , wherein frequency encoding directions used in the additional scan and in the medical scan are opposite.
3. The method according to claim 2 , wherein the second medical image has a lower resolution than the first medical image.
4. The method according to claim 3 , wherein a central region passing through a center frequency line in k-space is sampled when the additional scan is performed, and data outside the central region are filled with 0.
5. The method according to claim 1 , wherein the step of performing synthesis-related processing on the first medical image and the second medical image comprises:
inputting the first medical image and the second medical image into a trained first deep learning network for deep learning to acquire the post-processed image.
6. The method according to claim 5 , wherein the first deep learning network comprises:
a pre-processing module used to pre-process the first medical image and the second medical image respectively and to perform data fusion of the pre-processed first medical image and the pre-processed second medical image; and,
a processing module used to process a result of the data fusion to output the post-processed image.
7. The method according to claim 6 , wherein the data fusion comprises: performing a fusion operation on corresponding pixel values of the pre-processed first medical image and the pre-processed second medical image.
8. The method according to claim 5 , wherein the step of performing synthesis-related processing on the first medical image and the second medical image comprises:
performing fusion processing on the first medical image and the second medical image to acquire the post-processed image.
9. The method according to claim 1 , further comprising:
acquiring a prior-scan image of the subject prior to performing the medical scan;
determining whether noise interference artifacts are present in the prior-scan image, and if so, performing the additional scan of the subject to acquire the second medical image.
10. The method according to claim 9 , wherein the prior-scan image comprises a pre-scan image acquired by pre-scanning the subject.
11. The method according to claim 10 , wherein the pre-scan image comprises a shimming image.
12. The method according to claim 9 , wherein the prior-scan image comprises a positioning image.
13. The method according to claim 9 , wherein the presence or absence of noise interference artifacts in the prior-scan image is determined based on a trained second deep learning network.
14. A non-transitory computer-readable storage medium, comprising a stored computer program, wherein the method of claim 1 is executed when the computer program is run.
15. A magnetic resonance imaging system, comprising:
a scanner;
a processing system programmed to control the scanner to perform a magnetic resonance scan, the magnetic resonance scan comprising:
performing a medical scan of a subject and acquiring a first medical image, wherein the first medical image has a first noise interference artifact; and
performing an additional scan of the subject to acquire a second medical image, wherein the second medical image has a second noise interference artifact, and the location mapping of the second noise interference artifact in the first medical image is symmetrical to the location of the first noise interference artifact relative to a pixel center of the first medical image; and,
an image processor used to perform synthesis-related processing on the first medical image and the second medical image to acquire a post-processed image with reduced noise interference artifacts.
16. The system according to claim 15 , wherein the processing system is programmed to control the scanner to use opposite frequency encoding directions when performing the additional scan and the medical scan.
17. The system according to claim 16 , wherein the second medical image has a lower resolution than the first medical image.
18. The system according to claim 15 , wherein the image processor comprises a trained first deep learning network used to perform deep learning on the first medical image and the second medical image to output the post-processed image.
19. The system according to claim 18 , wherein the first deep learning network comprises a pre-processing module and a processing module, wherein the pre-processing module is used to pre-process the first medical image and the second medical image respectively and to perform data fusion of the pre-processed first medical image and the pre-processed second medical image, and the processing module is used to process a result of the data fusion to output the post-processed image.
20. The system according to claim 15 , wherein the processing system is further programmed to control the scanner to acquire a prior-scan image of the subject prior to performing the medical scan, and the magnetic resonance imaging system further comprises a determination module used to determine whether noise interference artifacts are present in the prior-scan image, and if so, the controller controls the scanner to perform the additional scan of the subject to acquire the second medical image.