Semi-supervised ML-synthesis for time-resolved imaging
AssigneeThe Board of Trustees of the Leland Stanford Junior University
InventorsKawin Setsompop, Congyu Liao, Cagan Alkan, Mahmut Yurt
Life of this patent
Estimating the term…
Abstract
A method for magnetic resonance imaging acquires time-resolved k-space data by a magnetic resonance imaging apparatus, and generates contrast-weighted images by a multi-task generator G from the time-resolved k-space data. The multi-task generator G comprises a deep learning neural network trained using prospectively under-sampled ground truth images acquired using an acceleration factor of at least 8 without any fully-sampled ground truth images. The multi-task generator G is also trained using a physics guidance model and a semi-supervised loss function.
Claims9
A method for magnetic resonance imaging comprising:
- a) acquiring time-resolved k-space data by a magnetic resonance imaging apparatus;
- b) generating contrast-weighted images by a multi-task generator G from the time-resolved k-space data;
- wherein the multi-task generator G comprises a deep learning neural network trained using prospectively under-sampled ground truth images acquired using an acceleration factor of at least 8 without any fully-sampled ground truth images, wherein the multi-task generator G is trained using a physics guidance model and a semi-supervised loss function.
Dependencies are inferred from the claim text.