System and method for enhancing propeller image quality by denoising blades
A system and method for improving image quality of periodically rotated overlapping parallel lines with enhanced reconstruction (PROPELLER) imaging include acquiring a plurality of blades of k-space data of a region of interest in a rotational manner around a center of k-space via a magnetic resonance imaging (MRI) scanner from a coil during a PROPELLER sequence, wherein each blade of the plurality of blades of k-space data includes a plurality of parallel phase encoding lines sampled in a phase encoding order. The system and method also include utilizing a deep learning-based denoising network to denoise each blade of the plurality of blades of k-space data to generate a plurality of denoised blades. The system and method further include utilizing a PROPELLER reconstruction algorithm to generate a complex image from the plurality of denoised blades.
1 . A computer-implemented method for improving image quality of periodically rotated overlapping parallel lines with enhanced reconstruction (PROPELLER) imaging, comprising:
acquiring, via a processor, a plurality of blades of k-space data of a region of interest in a rotational manner around a center of k-space via a magnetic resonance imaging (MRI) scanner from a coil during a PROPELLER sequence, wherein each blade of the plurality of blades of k-space data comprises a plurality of parallel phase encoding lines sampled in a phase encoding order;
utilizing, via the processor, a deep learning-based denoising network to individually denoise each blade of the plurality of blades of k-space data to generate a plurality of denoised blades of k-space data, wherein the denoising occurs in a k-space domain; and
utilizing, via the processor, a PROPELLER reconstruction algorithm to generate a complex image from the plurality of denoised blades of k-space data.
2 . The computer-implemented method of claim 1 , wherein the plurality of blades of k-space data is acquired from a single channel of the coil.
3 . The computer-implemented method of claim 1 , wherein the plurality of blades of k-space data is acquired from a plurality of channels of the coil.
4 . The computer-implemented method of claim 3 , further comprising combining, via the processor, corresponding blades of k-space data acquired from the plurality of channels to generate the plurality of blades of k-space data prior to utilizing the deep learning-based denoising network to individually denoise each blade of the plurality of blades of k-space data.
5 . The computer-implemented method of claim 1 , further comprising utilizing, via the processor, a deep learning-based de-streaking network on the complex image to remove streaks.
6 . The computer-implemented method of claim 1 , further comprising training, via the processor, the deep learning-based denoising network on input-output data pairs utilizing supervised learning, wherein the input-output data pairs comprise near perfect and conventional MR images simulated from natural images, and wherein the deep learning-based denoising network is trained to predict noise in Cartesian acquired images.
7 . The computer-implemented method of claim 6 , wherein at least some pairs of simulated images comprise skewed aspect ratios.
8 . A system for improving image quality of periodically rotated overlapping parallel lines with enhanced reconstruction (PROPELLER) imaging, comprising:
a memory encoding processor-executable routines; and
a processor configured to access the memory and to execute the processor-executable routines, wherein the routines, when executed by the processor, cause the processor to:
acquire a plurality of blades of k-space data of a region of interest in a rotational manner around a center of k-space via a magnetic resonance imaging (MRI) scanner from a coil during a PROPELLER sequence, wherein each blade of the plurality of blades of k-space data comprises a plurality of parallel phase encoding lines sampled in a phase encoding order;
utilize a deep learning-based denoising network to individually denoise each blade of the plurality of blades of k-space data to generate a plurality of denoised blades of k-space data, wherein the denoising occurs in a k-space domain; and
utilize a PROPELLER reconstruction algorithm to generate a complex image from the plurality of denoised blades of k-space data.
9 . The system of claim 8 , wherein the plurality of blades of k-space data is acquired from a single channel of the coil.
10 . The system of claim 8 , wherein the plurality of blades of k-space data is acquired from a plurality of channels of the coil.
11 . The system of claim 10 , wherein the routines, when executed by the processor, further cause the processor to combine corresponding blades of k-space data acquired from the plurality of channels to generate the plurality of blades of k-space data prior to utilizing the deep learning-based denoising network to individually denoise each blade of the plurality of blades of k-space data.
12 . The system of claim 8 , further comprising wherein the routines, when executed by the processor, further cause the processor to utilize a deep learning-based de-streaking network on the complex image to remove streaks.
13 . The system of claim 8 , wherein the routines, when executed by the processor, further cause the processor to train the deep learning-based denoising network on input-output data pairs utilizing supervised learning, wherein the input-output data pairs comprise near perfect and conventional MR images simulated from natural images, and wherein the deep learning-based denoising network is trained to predict noise in Cartesian acquired images.
14 . The system of claim 13 , wherein at least some pairs of simulated images comprise skewed aspect ratios.
15 . A non-transitory computer-readable medium, the computer-readable medium comprising processor-executable code that when executed by a processor, causes the processor to:
acquire a plurality of blades of k-space data of a region of interest in a rotational manner around a center of k-space via a magnetic resonance imaging (MRI) scanner from a coil during a periodically rotated overlapping parallel lines with enhanced reconstruction (PROPELLER) sequence, wherein each blade of the plurality of blades of k-space data comprises a plurality of parallel phase encoding lines sampled in a phase encoding order;
utilize a deep learning-based denoising network to individually denoise each blade of the plurality of blades of k-space data to generate a plurality of denoised blades of k-space data, wherein the denoising occurs in a k-space domain; and
utilize a PROPELLER reconstruction algorithm to generate a complex image from the plurality of denoised blades of k-space data.
16 . The computer-readable medium of claim 15 , wherein the plurality of blades of k-space data is acquired from a single channel of the coil.
17 . The computer-readable medium of claim 15 , wherein the plurality of blades of k-space data is acquired from a plurality of channels of the coil and wherein the processor-executable code, when executed by the processor, further causes the processor to combine corresponding blades of k-space data acquired from the plurality of channels to generate the plurality of blades of k-space data prior to utilizing the deep learning-based denoising network to individually denoise each blade of the plurality of blades of k-space data.
18 . The computer-readable medium of claim 15 , wherein the processor-executable code, when executed by the processor, further causes the processor to utilize a deep learning-based de-streaking network on the complex image to remove streaks.
19 . The computer-readable medium of claim 15 , wherein the processor-executable code, when executed by the processor, further causes the processor to train the deep learning-based denoising network on input-output data pairs utilizing supervised learning, wherein the input-output data pairs near perfect and conventional MR images simulated from natural images, and wherein the deep learning-based denoising network is trained to predict noise in Cartesian acquired images.
20 . The computer-readable medium of claim 19 , wherein at least some pairs of simulated images comprise skewed aspect ratios.