Systems and methods for motion detection in medical images

An imaging system, comprising:

• an x-ray source configured to emit x-rays towards a subject;
• a detector array comprising a plurality of detector elements configured to detect x-rays attenuated by the subject;
• a computing device communicatively coupled to the x-ray source and the detector array, the computing device configured with instructions in non-transitory memory that when executed cause the computing device to:
• control the x-ray source and the detector array to scan the subject and acquire raw projection data;
• reconstruct a first image corresponding to a location of the subject from a subset of the raw projection data using a first reconstruction technique and reconstruct a second image corresponding to the same location of the subject from the subset of raw projection data using a second reconstruction technique, different than the first reconstruction technique;
• calculate an inconsistency metric quantifying temporal inconsistencies between the first image and the second image due to motion of the subject, wherein calculating the inconsistency metric comprises calculating the inconsistency metric in image space and spatial frequency space based on the motion, and wherein the inconsistency metric is calculated in image space when the motion is localized to a small area;
• responsive to the inconsistency metric not being greater than a threshold, generate a final image of the subset of raw projection data without applying a motion artifact correction technique;
• and
• responsive to the inconsistency metric being greater than the threshold, generate the final image of the subset of raw projection data with a motion artifact correction technique.

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

• obtaining raw projection data of an imaging subject with the CT imaging system;
• reconstructing a first image from the raw projection data using a first temporal range of the projection data;
• reconstructing a second image from the raw projection data using a second, different temporal range of the projection data;
• calculating an inconsistency metric quantifying temporal inconsistencies between the first image and the second image due to involuntary motion of the imaging subject;
• and
• taking an action based on the inconsistency metric, wherein the first image has a different magnitude of motion-related artifact than the second image.