Ultrasound system with a neural network for producing images from undersampled ultrasound data

A system for generating ultrasound images, the system comprising:

• at least one storage device;
• at least one processor operatively coupled to the storage device;
• and
• at least one non-transitory computer readable storage medium storing instructions thereon, that, when executed by the at least one processor, cause the processor to:
• receive undersampled ultrasound data corresponding to ultrasound images acquired during cardiac imaging;
• produce modified ultrasound data by modifying, using a neural network, the undersampled ultrasound data to represent sufficiently-sampled ultrasound data, the neural network trained by:
• providing a first ultrasound data set comprising sufficiently-sampled ultrasound data corresponding to previously-acquired ultrasound cardiac images;
• producing a second ultrasound data set with missing data by reducing spatial and temporal sampling of the first ultrasound data set to mimic undersampling caused by low frame rate acquisition as applied to the cardiac imaging over at least one cardiac cycle;
• coupling the second ultrasound data set to one or more neural networks including the neural network to generate new data estimated to represent the missing data;
• producing a third ultrasound data set by modifying the second ultrasound data set to include the new data;
• classifying, by the one or more neural networks, the third ultrasound data set as either real or fake;
• and
• adjusting activation rules for one or more nodes of the one or more neural networks based on an accuracy of the classifying;
• and
• generate an ultrasound image based on the modified ultrasound data.