Feature-based image processing using feature images extracted from different iterations

A non-transitory storage medium storing instructions readable and executable by a computer to perform an image processing method comprising:

• performing iterative image reconstruction on projection or k-space imaging data to generate a series of update images ending in an iteratively reconstructed image;
• generating a difference image between a first update image and a second update image of the series of update images;
• transforming the difference image into a feature image by transformation operations including at least scaling or weighting pixels or voxels of the difference image;
• and
• using the feature image in the iterative image reconstruction or in post-processing performed on the iteratively reconstructed image.

An image processing method comprising:

• performing a first image reconstruction on projection or k-space imaging data to generate a first reconstructed image;
• performing a second image reconstruction on the projection or k-space imaging data to generate a second reconstructed image;
• generating a difference image between two images each selected from the group consisting of the first reconstructed image, an update image of the first image reconstruction, the second reconstructed image, and an update image of the second image reconstruction;
• and
• generating a final reconstructed image that combines the first reconstructed image and the second reconstructed image using the difference image.