Detecting artifacts in medical images

1 . A computer-implemented method, the method comprising:

obtaining input data associated with acquiring at least one image by a medical imaging system, wherein the input data comprises or more of,

at least part of at least one of raw measurement data or processed measurement data acquired by the medical imaging system for generating the at least one image,

at least part of image data of the at least one image, and

metadata of the medical imaging system associated with the acquiring of the at least one image;

applying a machine-learning model to the input data to determine information about an image artefact in the at least one image;

providing the information about the image artefact, wherein the information about the image artefact comprises a root cause component associated with the image artefact;

in response to determining the information about the image artefact, obtaining a position of at least one detector of the medical imaging system and used for acquiring the at least one image; and

estimating, based on the position of each of the at least one detector and the information about the image artefact, at least one location of a defect causing the image artefact in the medical imaging system.

2 . The computer-implemented method of claim 1 , wherein the artefact is caused by one or more of:

a hardware defect of the medical imaging system,

a software defect of the medical imaging system, or

a hardware component in an environment surrounding the medical imaging system.

3 . The computer-implemented method of claim 1 , wherein the obtaining the input data comprises:

extracting the at least one image from a plurality of medical images acquired using the medical imaging system when executing a diagnostic protocol associated with a diseased region of interest.

4 . The computer-implemented method of claim 1 , wherein the information about the image artefact comprises a classification of the image artefact.

5 . The computer-implemented method of claim 4 , wherein the classification comprises multiple hierarchies of classes.

6 . The computer-implemented method of claim 1 , wherein the applying the machine-learning model to the input data comprises:

determining multiple components of at least one of the medical imaging system or near the medical imaging system that are affected by a defect causing the image artefact,

determining the root-cause component of the image artefact included in the multiple components that are affected by the defect.

7 . The computer-implemented method of claim 1 , wherein the applying the machine-learning model to the input data comprises:

determining a probability of a component at least one of the medical imaging system or near the medical imaging system being affected by a defect causing the image artefact, wherein the information about the image artefact comprises the probability.

8 . The computer-implemented method of claim 1 , wherein the applying the machine-learning model to the input data comprises:

determining a worklist, the worklist comprising a plurality of control commands for the medical imaging system to acquire additional data for obtaining additional information on the image artefact, and the information about the image artefact comprises the worklist.

9 . The computer-implemented method of claim 1 , further comprising:

simulating, based on the position of each of the at least one detector, detector signals for multiple candidate locations of the defect; and

comparing measured detector signals of the at least one detector with the simulated detector signals,

wherein the at least one location of the defect is estimated based on the comparing.

10 . The computer-implemented method of claim 1 , wherein the applying the machine-learning model to the input data comprises:

determining a confidence or severity value for the information about the image artefact.

11 . A computing device comprising:

a processor; and

memory, the memory comprising instructions executable by the processor that, when executed by the processor, cause the computing device to perform the computer-implemented method of claim 1 .

12 . A medical imaging system comprising:

at least one of the computing device according to claim 11 .

13 . A non-transitory computer-readable storage medium for use in conjunction with an electronic device, the computer-readable storage medium storing program instructions that, when executed by the electronic device, cause the electronic device to perform the computer-implemented method of claim 1 .

14 . The computer-implemented method of claim 1 , wherein the artefact is caused by one or more of:

a hardware defect of the medical imaging system,

a software defect of the medical imaging system, or

a hardware component in an environment surrounding the medical imaging system.

15 . The computer-implemented method of claim 14 , wherein the obtaining the input data comprises:

extracting the at least one image from a plurality of medical images acquired using the medical imaging system when executing a diagnostic protocol associated with a diseased region of interest.

16 . The computer-implemented method of claim 15 , wherein the information about the image artefact comprises a classification of the image artefact.

17 . The computer-implemented method of claim 16 , wherein the classification comprises multiple hierarchies of classes.

18 . The computer-implemented method of claim 17 , wherein the applying the machine-learning model to the input data comprises:

determining multiple components of at least one of the medical imaging system or near the medical imaging system that are affected by a defect causing the image artefact,

determining a root-cause component of the image artefact included in the multiple components that are affected by the defect, wherein the information about the image artefact comprises the root-cause component associated with the image artefact.