Medical imaging method and system and non-transitory computer-readable storage medium
The present application provides a medical imaging method and system and a non-transitory computer-readable storage medium. The medical imaging method comprises identifying an image quality type of a medical image based on a trained learning network, and generating, based on the identified image quality type, a corresponding control signal for controlling a medical imaging system.
1. A medical imaging method, comprising:
identifying an image quality type of a medical image based on a trained learning network;
generating, based on the identified image quality type, a corresponding control signal for controlling a medical imaging system;
wherein the image quality type comprises one or a plurality of artifact types; and
wherein when the medical image is identified as an acceleration artifact in a magnetic resonance image, a first control signal is generated to control the medical imaging system to send a warning signal for adjusting an acceleration factor.
2. The method according to claim 1 , wherein before the identifying an image quality type of a medical image, the method further comprises receiving, based on an instruction of a user, the medical image generated by the medical imaging system.
3. The method according to claim 1 , wherein the learning network is obtained by training based on a data set of sample images and corresponding image quality types thereof.
4. The method according to claim 1 , wherein the image quality type comprises one or a plurality of non-artifact types.
5. The method according to claim 1 , wherein the identifying an image quality type of a medical image comprises analyzing a matching degree of an artifact in the medical image with the one or plurality of artifact types.
6. The method according to claim 5 , wherein the identifying an image quality type of a medical image further comprises outputting an artifact type whose matching degree with the medical image is greater than a preset value or is on a preset ranking.
7. The method according to claim 1 , wherein when the medical image is identified as a motion artifact in a magnetic resonance image, a second control signal is generated to control the medical imaging system to send a warning signal about motion of a detected object.
8. The method according to claim 1 , wherein when the medical image is identified as a Nyquist artifact in a magnetic resonance image, a third control signal is generated to control the medical imaging system to start a calibration mode.
9. The method according to claim 5 , wherein when the medical image is identified as a Nyquist artifact in a magnetic resonance image, and the matching degree exceeds a preset threshold, a third control signal is generated to control the medical imaging system to start a calibration mode.
10. A medical imaging system, comprising:
an identification module, configured to identify, based on a trained learning network, an image quality type of a medical image generated by the medical imaging system;
a control module, configured to generate, based on the identified image quality type, a corresponding control signal for controlling the medical imaging system;
wherein the image quality type comprises one or a plurality of artifact types; and
wherein the control module comprises a first control unit configured to generate a first control signal based on an acceleration artifact type in a magnetic resonance image outputted by the identification module, so as to control the medical imaging system to send a warning signal for adjusting an acceleration factor.
11. The system according to claim 10 , further comprising:
a training module, configured to train the learning network based on a data set of sample images and corresponding image quality types thereof.
12. The system according to claim 10 , wherein the image quality type comprises one or a plurality of non-artifact types.
13. The system according to claim 10 , wherein the identification module outputs an artifact in the medical image and a matching degree of the artifact with the one or plurality of artifact types.
14. The system according to claim 10 , wherein the control module comprises a second control unit configured to generate a second control signal based on a motion artifact in a magnetic resonance image outputted by the identification module, so as to control the medical imaging system to send a warning signal about motion of a detected object.
15. The system according to claim 10 , wherein the control module comprises a third control unit configured to generate a third control signal based on a Nyquist artifact in a magnetic resonance image outputted by the identification module, so as to control the medical imaging system to start a calibration mode.
16. The system according to claim 15 , wherein the control module further comprises a matching degree comparison unit connected to the third control unit and configured to compare the matching degree outputted by the identification module with a preset threshold, and the third control unit generates the third control signal based on the Nyquist artifact outputted by the identification module and a result of the comparison.
17. The medical imaging method, comprising:
identifying an image quality type of a medical image based on a trained learning network;
generating, based on the identified image quality type, a corresponding control signal for controlling a medical imaging system;
wherein the image quality type comprises one or a plurality of artifact types; and
wherein the medical image is identified as a Nyquist artifact in a magnetic resonance image, a second control signal is generated to control the medical imaging system to start a calibration mode.