Artificial intelligence based reconstruction for phase contrast magnetic resonance imaging
A method for phase-contrast magnetic resonance imaging (PC-MRI) acquires undersampled PC-MRI data using a magnetic resonance imaging scanner and reconstructs MRI images from the undersampled PC-MRI data by reconstructing a first flow-encoded image using a first convolutional neural network, reconstructing a complex difference image using a second convolutional neural network, combining the complex difference image and the first flow-encoded image to obtain a second flow-encoded image, and generating a velocity encoded image from the first flow-encoded image and second flow-encoded image using phase difference processing.
1. A method for phase-contrast magnetic resonance imaging (PC-MRI), the method comprising:
(a) acquiring undersampled PC-MRI data using a magnetic resonance imaging scanner; and
(b) reconstructing MRI images from the undersampled PC-MRI data by
i. reconstructing a first flow-encoded image using a first convolutional neural network;
ii. reconstructing a complex difference image using a second convolutional neural network;
iii. combining the complex difference image and the first flow-encoded image to obtain a second flow-encoded image; and
iv. generating a velocity encoded image from the first flow-encoded image and second flow-encoded image using phase difference processing.
2. The method of claim 1 wherein acquiring the undersampled PC-MRI data using the magnetic resonance imaging scanner comprises acquiring multidimensional (2D or 4D PC-MRI) data.
3. The method of claim 1 wherein the first convolutional neural network is an unrolled convolutional neural network.
4. The method of claim 1 wherein the first convolutional neural network is a DL-ESPIRiT network modified for PC-MRI data.
5. The method of claim 1 wherein the second convolutional neural network is an unrolled convolutional neural network.
6. The method of claim 1 wherein the second convolutional neural network is a DL-ESPIRiT network trained with CD PC-MRI data.
7. The method of claim 1 wherein reconstructing the complex difference image using the second convolutional neural network comprises inputting to the second convolutional neural network a difference of two portions of the undersampled PC-MRI data having different velocity encodings.