Diffusion dictionary imaging (DDI) of microstructure and inflammation
A computing device for diffusion dictionary imaging (DDI) of microstructure and inflammation of a patient is provided. The DDI computing device is connected to other computing devices, such as a magnetic resonance imaging (MRI) scanner. The DDI computing device receives magnetic resonance (MR) signals from the MRI scanner. Once received, the DDI computing device records the one or more MR signals to a memory device. The DDI computing device computationally processes the one or more MR signals to reconstruct a diffusion MRI image using diffusion dictionary data. The MR signals include values that are used as input to algorithms of the DDI data to reconstruct the diffusion MRI image. A database is used to store DDI data, artificial intelligence (AI) data, diffusion dictionary data, and MR data.
1 . A diffusion dictionary imaging (DDI) computing device for inflammation imaging, the DDI computing device comprising at least one processor in communication with at least one memory device, wherein the at least one processor is programmed to:
receive, from at least one user device, one or more magnetic resonance (MR) signals;
record the one or more MR signals to the at least one memory device;
retrieve one or more DDI algorithms from the at least one memory device, the DDI algorithms including extraction of neuroinflammation signals;
retrieve, from a diffusion dictionary, one or more microstructural component diffusion patterns;
process the one or more MR signals to reconstruct a diffusion MRI image using the retrieved one or more DDI algorithms and the one or more microstructural component diffusion patterns; and
output the reconstructed diffusion MRI image.
2 . The DDI computing device of claim 1 , wherein the one or more MR signals are detected by a clinical MRI scanner configured to provide longitudinal imaging.
3 . The DDI computing device of claim 1 , wherein to process the one or more MR signals, the at least one processor is further programmed to:
extract one or more values from the one or more MR signals; and
input the one or more values into the one or more DDI algorithms to reconstruct the diffusion MRI image.
4 . The DDI computing device of claim 1 , wherein the at least one processor is further programmed to:
define a weighted apparent diffusion coefficient (wADC); and
capture one or more microstructure hallmarks of the diffusion MRI image, wherein the one or more microstructure hallmarks is associated with immune cell activation during an inflammation process;
wherein the wADC is based at least in part on a computation of the DDI computing device.
5 . The DDI computing device of claim 1 , wherein the at least one processor is further configured to:
detect one or more microstructural features of the diffusion MRI image; and
associate the one or more microstructural features with at least one immune response.
6 . The DDI computing device of claim 1 , wherein the at least one processor is programmed to determine a DDI neuroinflammation index based at least in part on the reconstructed diffusion MRI image.
7 . The DDI computing device of claim 1 , wherein the at least one processor is programmed to compute one or more microstructural spectrum by projecting the one or more MR signals onto the diffusion dictionary through a regularized compressed sensing (CS) inverse computation.
8 . The DDI computing device of claim 7 , wherein the diffusion dictionary comprises an overcomplete dictionary.
9 . A non-transitory computer readable medium comprising instructions for inflammation imaging, the instructions, when executed by at least one processor, implement:
receiving one or more magnetic resonance (MR) signals;
recording the one or more MR signals to at least one memory device;
retrieving one or more DDI algorithms from the at least one memory device;
retrieving, from a diffusion dictionary, one or more microstructural component diffusion patterns;
reconstructing a diffusion MRI image based on the one or more MR signals using the retrieved one or more DDI algorithms and the one or more microstructural component diffusion patterns, the DDI algorithms including extraction of neuroinflammation signals;
detecting one or more microstructural features of the reconstructed diffusion MRI image; and
associating the one or more microstructural features with at least one immune response.
10 . The non-transitory computer readable medium of claim 9 , wherein the one or more MR signals are detected by a clinical MRI scanner configured to provide longitudinal imaging.
11 . The non-transitory computer readable medium of claim 9 , wherein the instructions, when executed by at least one processor, further implement:
extracting one or more values from the one or more MR signals; and
inputting the one or more values into the one or more DDI algorithms to reconstruct the diffusion MRI image.
12 . The non-transitory computer readable medium of claim 9 , wherein the instructions, when executed by at least one processor, further implement:
defining a weighted apparent diffusion coefficient (wADC); and
capturing one or more microstructure hallmarks of the diffusion MRI image, wherein the one or more microstructure hallmarks is associated with immune cell activation during an inflammation process;
wherein the wADC is based at least in part on a computation of the DDI computing device.
13 . The non-transitory computer readable medium of claim 9 , wherein the instructions, when executed by at least one processor, further implement computing one or more microstructural spectrum by projecting the one or more MR signals onto the diffusion dictionary through a regularized compressed sensing (CS) inverse computation.
14 . A system, comprising:
at least one MRI scanner coupled to a network, wherein the at least one MRI scanner configured to:
detect one or more MRI signals; and
transmit the one or more MRI signals over a network;
a diffusion dictionary imaging (DDI) computing device, the DDI computing device including at least one memory and a processor, wherein the DDI computing device is coupled to the network and is configured to:
receive the one or more MR signals from the at least one MRI scanner via the network;
record the one or more MR signals to the at least one memory device;
retrieve one or more DDI algorithms from the at least one memory device;
retrieving, from a diffusion dictionary, one or more microstructural component diffusion patterns;
reconstruct a diffusion MRI image based on the one or more MR signals using the retrieved one or more DDI algorithms and the one or more microstructural component diffusion patterns, the DDI algorithms including extraction of neuroinflammation signals;
detect one or more microstructural features of the reconstructed diffusion MRI image; and
associate the one or more microstructural features with at least one immune response.
15 . The system of claim 14 , wherein the MRI scanner is a clinical MRI scanner configured to provide longitudinal imaging.
16 . The system of claim 14 , wherein the DDI computing device is further configured to:
extract one or more values from the one or more MR signals; and
input the one or more values into the one or more DDI algorithms when reconstructing the diffusion MRI image.
17 . The system of claim 16 , wherein the one or more values are extracted using artificial intelligence, machine learning, or both.
18 . The system of claim 14 , wherein the DDI computing device is further configured to:
define a weighted apparent diffusion coefficient (wADC); and
capture one or more microstructure hallmarks of the diffusion MRI image, wherein the one or more microstructure hallmarks is associated with immune cell activation during an inflammation process;
wherein the wADC is based at least in part on a computation of the DDI computing device.
19 . The system of claim 18 , wherein the DDI computing device is further configured to:
associate the one or more microstructural features with at least one immune response.
20 . The system of claim 18 , wherein the DDI computing device is further configured to compute one or more microstructural spectrum by projecting the one or more MR signals onto the diffusion dictionary through a regularized compressed sensing (CS) inverse computation.