X-ray image quality control system

1. An X-ray image quality control system comprising:

an image acquisition unit configured to acquire Drill a digital X-ray image of a patient anatomy under control of a technician, to determine which body part is captured in the imaged patient anatomy, and to determine the type of the projection mode used to capture the imaged patient anatomy including a projection direction of the X-ray projection relative to the patient anatomy; and

a quality detection unit configured to detect an image defect in the X-ray image of the patient anatomy with regard to the body part that is captured therein and with regard to the direction of the X-ray projection relative to the patient anatomy;

the quality detection unit further configured to use a first detection parameter to detect a defect in the imaged patient anatomy in response to the image acquisition unit determining that the imaged patient anatomy is a first body part and that the projection mode used to capture the imaged patient anatomy included a first projection direction, the quality detection unit further configured to use a second detection parameter different from the first detection parameter to detect a defect in the imaged patient anatomy in response to the image acquisition unit determining that the imaged patient anatomy is a second body part different from the first body part and that the projection mode used to capture the imaged patient anatomy included a second projection direction different from the first projection direction.

2. The control system according to claim 1 , further comprising:

a quality feedback unit, configured to feed back the detected image defect to the image acquisition side for use by the technician to correct an image capture configuration.

3. The control system according to claim 1 , wherein the quality detection unit is configured to:

extract a feature set of the location and orientation for a bone structure and/or a soft tissue structure of the imaged patient anatomy; and

locate or segment a region of interest of the imaged patient anatomy based on the extracted feature set.

4. The control system according to claim 2 , wherein the quality detection unit is configured to be trained using a machine learning algorithm to determine and/or adjust at least the first detection parameter.

5. The control system according to claim 4 , wherein the quality detection unit is configured to:

for a first combination of the type of the captured body part and the type of the projection mode, detect a region of interest based on the first detection parameter; and

for a second combination of the type of the captured body part and the type of the projection mode, detect the region of interest based on a second detection parameter different from the first detection parameter.

6. The control system according to claim 2 , wherein the quality detection unit is further configured to detect a region of interest associated with a first image defect type by using a histogram analysis algorithm.

7. The control system according to claim 2 , wherein the image acquisition unit is further configured to perform pre-processing on the acquired X-ray image of the patient anatomy, the pre-processing comprises dividing the acquired X-ray image into a bone structure region, a soft tissue region and a background region.

8. The control system according to claim 2 , wherein the quality feedback unit is further configured to select the image defect and mark the image defect for use by the technician.

9. The control system according to claim 1 , wherein the image acquisition unit is further configured to receive the X-ray image of the patient anatomy from an external image data source.

10. The control system according to claim 1 , wherein the image acquisition unit comprises an image acquisition device configured to acquire the X-ray image.

11. A computer implemented X-ray image quality detection method, the method comprising:

receiving a digital X-ray image of a part of a body;

determining what body part is captured in the X-ray image and the direction of the X-ray projection, relative to the body, used to capture the X-ray image; and

detecting an image defect of the X-ray image using a first detection parameter in response to determining that the X-ray image captured a first body part and that the direction of the X-ray projection used to capture the X-ray image included a first projection direction, or detecting an image defect of the X-ray image using a second detection parameter in response to determining that the X-ray image captured a second body part different from the first body part and that the direction of the X-ray projection used to capture the X-ray image included a second projection direction different from the first projection direction.

12. The method of claim 11 , further comprising:

feeding the detected image defect back to an X-ray image acquisition side.

13. The method of claim 11 , wherein detecting the image defect of the X-ray image comprises:

extracting a feature set of a location and orientation for a bone structure and/or a soft tissue structure of the captured body part; and

locating or segmenting a region of interest of the captured body part based on the extracted feature set.

14. The method of claim 13 , wherein detecting the image defect of the X-ray image further comprises:

for a first combination of the captured body part and the direction of the X-ray projection, detecting the region of interest based on the first detection parameter;

for a second combination of the captured body part and the direction of the X-ray projection, detecting the region of interest based on a second detection parameter different from the first detection parameter; and

wherein the first detection parameter and the second detection parameter are determined by using a machine learning algorithm.

15. The method of claim 11 , wherein detecting the image defect of the X-ray image further comprises detecting a region of interest associated with a first image defect type by using a histogram analysis algorithm.

16. The method of claim 11 , further comprising:

performing pre-processing on the X-ray image, wherein the pre-processing comprises dividing the X-ray image into a bone structure region, a soft tissue region and a background region.

17. A computer-readable storage medium having stored thereon non-transitory machine-executable instructions, wherein the non-transitory machine-executable instructions, when executed by a processor, implement the method of claim 11 .

18. The control system according to claim 8 , wherein the quality feedback unit is further configured to mark the image defect as a box.