System and methods for reconstructing medical images using deep neural networks and recursive decimation of measurement data

A method comprising:

• receiving measurement data acquired by an imaging device;
• flattening the measurement data;
• selecting a decimation strategy based on a size of the measurement data;
• producing a reconstructed image from the flattened measurement data using the decimation strategy and a plurality deep neural networks, where the selection is further based a size of an input layer of the plurality of deep neural networks;
• decimating the measurement data according to the decimation strategy to produce at least a first decimated measurement data array and a second decimated measurement data array;
• mapping the first decimated measurement data array to a first decimated image data array using a first deep neural network;
• mapping the second decimated measurement data array to a second decimated image data array using a second deep neural network;
• aggregating the first decimated image data array and the second decimated image data array using an aggregation network to produce an image data array;
• reshaping the image data array to produce the reconstructed image;
• and
• displaying the reconstructed image via a display device.