Generalizable image-based training framework for artificial intelligence-based noise and artifact reduction in medical images

A method for reducing noise and artifacts in previously reconstructed medical images, the method comprising:

• (a) accessing patient medical image data with a computer system, wherein the patient medical image data comprise one or more medical images acquired with a medical imaging system and depicting a patient;
• (b) accessing a trained neural network with the computer system, wherein the trained neural network has been trained on training data comprising augmented image data and ground truth data, wherein the augmented image data comprise at least one of noise-augmented image data or artifact-augmented image data;
• and
• (c) inputting the patient medical image data to the trained neural network using the computer system, generating output as uncorrupted patient medical image data, wherein the uncorrupted patient medical image data comprise one or more medical images depicting the patient and having reduced noise and artifacts relative to the patient medical image data,
• wherein the noise-augmented image data are generated by combining image data with noise-only image data generated from medical image data acquired with the medical imaging system by separating noise and artifact image content of the medical image data from signal components of the medical image data.