System, method and computer-accessible medium for learning an optimized variational network for medical image reconstruction
An exemplary system, method and computer accessible medium for generating an image(s) of a portion(s) of a patient can be provided, which can include, for example, receiving first imaging information related to the portion(s), receiving second information related to modelling information of a further portion(s) of a further patient(s), where the modelling information includes (i) an under sampling procedure, and/or (ii) a learning-based procedure, and generating the image(s) using the first information and the second information. The modelling information can include artifacts present in a further image of the further portion(s). The image(s) can be generated by reducing or minimizing the artifacts. The second information can be generated, for example using a variational network(s).
1. A non-transitory computer-accessible medium having stored thereon computer-executable instructions for generating at least one image of at least one portion of a patient, wherein, when a computer arrangement executes the instructions, the computer arrangement is configured to perform procedures comprising:
receiving first imaging information related to the at least one portion;
receiving second information related to modelling information of at least one further portion of at least one further patient, wherein the modelling information includes at least one of (i) an under sampling procedure, or (ii) a learning-based procedure;
removing errors in the first imaging information using the second information; and
automatically generating the at least one image using the first information and the second information.
2. The computer-accessible medium of claim 1 , wherein the modelling information includes artifacts present in a further image of the at least one further portion.
3. The computer-accessible medium of claim 2 , wherein the computer arrangement is configured to generate the at least one image by reducing or minimizing the artifacts.
4. The computer-accessible medium of claim 1 , wherein the computer arrangement is further configured to generate the second information.
5. The computer-accessible medium of claim 4 , wherein the computer-arrangement is configured to generate the second information using at least one variational network.
6. The computer-accessible medium of claim 5 , wherein the at least one variational network is based on at least one gradient descent procedure.
7. The computer-accessible medium of claim 5 , wherein the at least one variational network is based on a loss function.
8. The computer-accessible medium of claim 7 , wherein the computer arrangement is configured to minimize the loss function over a set of training images of the at least one further portion.
9. The computer-accessible medium of claim 5 , wherein the at least one of (i) the under sampling procedure, or (ii) the learning-based procedure includes filter kernels and corresponding influence functions of the at least one variational network.
10. The computer-accessible medium of claim 9 , wherein the computer arrangement is further configured to automatically learn the filter kernels and influence functions by optimizing a loss function that compares under sampled, aliased, images to artifact-free reference reconstructions of the at least one portion.
11. The computer-accessible medium of claim 5 , wherein the at least one variational network includes convolutional filters in at least one of a real plane or an imaginary plane.
12. The computer-accessible medium of claim 1 , wherein the computer arrangement is further configured automatically generate the at least one image by applying the second imaging information to the first imaging information.
13. The computer-accessible medium of claim 1 , wherein the computer arrangement is further configured to automatically generate the at least one of (i) the under sampling procedure, or (ii) the learning-based procedure.
14. The computer-accessible medium of claim 13 , wherein the computer arrangement is configured to generate the at least one of (i) the under sampling procedure, or (ii) the learning-based procedure by using information about a pattern in k-space in the second imaging information to discriminate aliasing artifacts.
15. The computer-accessible medium of claim 14 , wherein the aliasing artifacts are based on under sampling from true anatomical structures.
16. The computer-accessible medium of claim 13 , wherein the computer arrangement is configured to automatically generate the at least one of (i) the under sampling procedure, or (ii) the learning-based procedure based on coil sensitivities and raw k-space measurements.
17. The computer-accessible medium of claim 1 , wherein at least one of the first imaging information or the second imaging information includes at least one of (i) magnetic resonance imaging information, (ii) computed tomography imaging information, (iii) positron emission tomography imaging information, or (iv) optical imaging information.
18. A system for generating at least one image of at least one portion of a patient, comprising:
at least one computer hardware arrangement configured to:
receive first imaging information related to the at least one portion;
receive second information related to modelling information of at least one further portion of at least one further patient, wherein the modelling information includes at least one of (i) an under sampling procedure, or (ii) a learning-based procedure;
remove errors in the first imaging information using the second information; and
generate the at least one image using the first information and the second information.
19. The system of claim 18 , wherein the modelling information includes artifacts present in a further image of the at least one further portion.
20. The system of claim 19 , wherein the computer hardware arrangement is configured to generate the at least one image by reducing or minimizing the artifacts.
21. The system of claim 18 , wherein the computer arrangement is further configured automatically generate the at least one image by applying the second imaging information to the first imaging information.
22. A method for generating at least one image of at least one portion of a patient, comprising:
receiving first imaging information related to the at least one portion;
receiving second information related to modelling information of at least one further portion of at least one further patient, wherein the modelling information includes at least one of (i) an under sampling procedure, or (ii) a learning-based procedure;
removing errors in the first imaging information using the second information; and
using a computer hardware arrangement, generating the at least one image using the first information and the second information.
23. The method of claim 22 , wherein the modelling information includes artifacts present in a further image of the at least one further portion.
24. The method of claim 23 , wherein the generating the at least one image using the first information and the second information includes reducing or minimizing the artifacts.
25. The method of claim 22 , wherein the generating the at least one image includes applying the second imaging information to the first imaging information.
26. A non-transitory computer-accessible medium having stored thereon computer-executable instructions for generating at least one image of at least one portion of a patient, wherein, when a computer arrangement executes the instructions, the computer arrangement is configured to perform procedures comprising:
receiving first imaging information related to the at least one portion;
receiving second information related to modelling information of at least one further portion of at least one further patient, wherein the modelling information includes artifacts present in a further image of the at least one further portion, and at least one of (i) an under sampling procedure, or (ii) a learning-based procedure; and
automatically generating the at least one image using the first information and the second information.
27. The computer-accessible medium of claim 26 , wherein the computer arrangement is configured to generate the at least one image by reducing or minimizing the artifacts.
28. The computer-accessible medium of claim 26 , wherein the computer arrangement is further configured automatically generate the at least one image by applying the second imaging information to the first imaging information.
29. A system for generating at least one image of at least one portion of a patient, comprising:
at least one computer hardware arrangement configured to:
receive first imaging information related to the at least one portion;
receive second information related to modelling information of at least one further portion of at least one further patient, wherein the modelling information includes artifacts present in a further image of the at least one further portion, and at least one of (i) an under sampling procedure, or (ii) a learning-based procedure; and
generate the at least one image using the first information and the second information.
30. The system of claim 29 , wherein the computer hardware arrangement is configured to generate the at least one image by reducing or minimizing the artifacts.
31. The computer-accessible medium of claim 29 , wherein the computer hardware arrangement is further configured automatically generate the at least one image by applying the second imaging information to the first imaging information.
32. A method for generating at least one image of at least one portion of a patient, comprising:
receiving first imaging information related to the at least one portion;
receiving second information related to modelling information of at least one further portion of at least one further patient, wherein the modelling information includes artifacts present in a further image of the at least one further portion, and at least one of (i) an under sampling procedure, or (ii) a learning-based procedure; and
using a computer hardware arrangement, generating the at least one image using the first information and the second information.
33. The method of claim 32 , wherein the generating the at least one image using the first information and the second information includes reducing or minimizing the artifacts.
34. The method of claim 32 , wherein the generating the at least one image using the first information and the second information includes applying the second imaging information to the first imaging information.