Systems and methods for a stationary CT imaging system

A stationary computed tomography (CT) system, comprising:

• an imaging unit comprising:
• one or more stationary distributed x-ray source units each comprising a plurality of emitters positioned to emit x-ray beams through an imaging volume, where the one or more x-ray source units do not rotate around the imaging volume;
• and
• one or more detector arrays extending around at least a portion of the imaging volume, each detector array comprising a plurality of detector elements;
• and
• one or more computing devices configured to, during a scan of an object within the imaging volume:
• translate the imaging unit vertically along the object;
• activate each plurality of emitters;
• sample each plurality of detector elements to obtain a projection dataset;
• and
• reconstruct one or more images from the projection dataset using sparse view reconstruction method.

A method for a stationary computed tomography (CT) system, comprising:

• generating a sparse view projection dataset by activating a plurality of emitters of a stationary distributed x-ray source unit to emit x-ray beams toward an object within an imaging volume, where the x-ray source unit does not rotate around the imaging volume, and receiving attenuated x-ray beams with one or more detector arrays, the sparse view projection dataset differing from a dense view projection dataset in one or more of a total number of views, a spacing of views, a view angle range, and a field of view;
• and
• reconstructing an image from the sparse view projection dataset using a sparse view reconstruction method that includes a deep learning network trained with training data that includes:
• the dense view projection dataset and/or one or more training images generated from the dense view projection dataset, and
• a pseudo sparse view projection dataset generated from the dense view projection dataset and/or one more training images generated from the pseudo sparse view projection dataset, where the pseudo sparse view projection dataset is generated by discarding a plurality of views of the dense view projection dataset so that a total number of views, a spacing of views, a view angle range, and a field of view of the pseudo sparse view dataset matches the total number of views, the spacing of views, the view angle range, and the field of view of the sparse view projection dataset.