Region-optimzed virtual (ROVir) coils
Systems and methods of image reconstruction are provided. A system may have a memory and a processor to receive data corresponding to magnetic resonance imaging coils and data corresponding to a region of interest within a field of view of the magnetic resonance imaging machine. By determining different weights to associate with virtualized magnetic resonance imaging coils, images may be reconstructed to favor signals associated with a region of interest and to disfavor interference associated with areas outside the region of interest.
1 . An image reconstruction system, comprising:
a memory configured to store image data or k-space data; and
a processor coupled to the memory and configured to:
determine a region of interest of the image data or the k-space data,
determine a region of non-interest of the image data or the k-space data;
determine coil combination weights that optimize a signal-to-interference ratio of the image data or the k-space data based on the region of interest and the region of non-interest, and
generate or reconstruct a magnetic resonance imaging (MRI) image or k-space data based on the image data or the k-space data and using the coil combination weights.
2 . The image reconstruction system of claim 1 , further comprising:
a display configured to render the generated or reconstructed MRI image, wherein the processor is configured to output the generated or reconstructed MRI image on the display.
3 . The image reconstruction system of claim 1 , wherein the generated or reconstructed MRI image is generated faster than a second generated or reconstructed MRI image generated from an entire k-space data and with a same resolution.
4 . The image reconstruction system of claim 1 , wherein the generated or reconstructed MRI image is generated with greater resolution and during a same period of time than a second generated or reconstructed MRI image generated from an entire k-space data and with less resolution.
5 . The image reconstruction system of claim 1 , wherein the generated or reconstructed MRI image is generated with fewer artifacts than a second generated or reconstructed MRI image generated from an entire k-space data.
6 . The image reconstruction system of claim 1 , wherein the processor is further configured to:
filter, remove, or attenuate the region of non-interest of the image data or the k-space data from the image data or the k-space data; and
exclude or suppress the region of non-interest of the image data or the k-space data when generating or reconstructing the MRI image.
7 . The image reconstruction system of claim 1 , wherein the processor is further configured to:
obtain one or more scout scan images;
determine a signal region within the one or more scout scan images;
determine an interference region within the one or more scout scan images; and
determine the coil combination weights based on the signal region and the interference region within the one or more scout scan images.
8 . The image reconstruction system of claim 7 ,
wherein the processor is further configured to:
obtain user input that indicates the signal region or the interference region within the one or more scout scan images; or
apply artificial intelligence to determine the signal region or the interference region within the one or more scout scan images, and
wherein the processor is further configured to:
determine the signal region within the one or more scout scan images based on the user input or using the applied artificial intelligence.
9 . The image reconstruction system of claim 7 , wherein the coil combination weights prioritize the signal region over the interference region.
10 . The image reconstruction system of claim 7 , wherein to determine the coil combination weights the processor is further configured to:
form a signal matrix based on the signal region;
form an interference matrix based on the interference region; and
determine the coil combination weights based on the signal matrix and the interference matrix using a generalized eigen decomposition function.
11 . An image reconstruction system, comprising:
a memory configured to store image data or k-space data; and
a processor coupled to the memory and configured to:
determine a region of interest of the image data or the k-space data;
determine a region of non-interest of the image data or the k-space data;
determine coil combination weights that optimize a signal-to-interference ratio (SIR) of the image data or the k-space data based on the region of interest and the region of non-interest;
generate or reconstruct a magnetic resonance imaging (MRI) image based on the region of interest of the image data or the k-space data; and
transmit the generated or reconstructed MRI image for display.
12 . The image reconstruction system of claim 11 , further comprising a display configured to render the generated or reconstructed MRI image.
13 . The image reconstruction system of claim 11 , wherein the processor is further configured to:
filter, remove, or attenuate the region of non-interest of the image data or the k-space data from the image data or the k-space data; and
exclude or suppress the region of non-interest of the image data or the k-space data when generating or reconstructing the MRI image.
14 . The image reconstruction system of claim 11 , wherein the processor is further configured to:
obtain one or more scout scan images;
determine a signal region within the one or more scout scan images;
determine an interference region within the one or more scout scan images; and
determine the coil combination weights based on the signal region and the interference region within the one or more scout scan images.
15 . The image reconstruction system of claim 14 , wherein the processor is further configured to:
obtain user input that indicates the signal region or the interference region within the one or more scout scan images,
wherein the processor is further configured to determine the signal region within the one or more scout scan images based on the user input.
16 . The image reconstruction system of claim 11 , further comprising:
a magnetic resonance imaging (MRI) scanner configured to obtain the image data or the k-space data,
wherein the image data or the k-space data is representative of data related to a human body.
17 . The image reconstruction system of claim 16 , wherein the data related to the human body includes biological, anatomical, neurological, functional, microstructural, or physiological data of the human body.
18 . A method of generating a magnetic resonance imaging (MRI) image, comprising:
obtaining, by a processor, image data or k-space data;
determining, by the processor, a region of interest of the image data or the k-space data;
determining, by the processor, a region of non-interest of the image data or the k-space data;
determining, by the processor, coil combination weights that optimize a signal-to-interference ratio of the image data or the k-space data based on the region of interest and the region of non-interest; and
generating or reconstructing, by the processor, the MRI image based on the image data or the k-space data using the coil combination weights.