System and method for adjustment of imaging components based on object detection

1 . An imaging apparatus, comprising:

processing circuitry configured to

obtain a first medical image, the first medical image being acquired by performing a scan using a first set of scan parameters,

analyze the first medical image to detect a plurality of objects in the first medical image and corresponding features of the detected plurality of objects,

determine an action corresponding to a combination of a first object and a first object feature, which has a relatively high priority among a plurality of combinations of objects and object features detected in the first medical image,

determine an updated set of scan parameters based on the determined action, and

control the imaging apparatus based on the updated set of scan parameters.

2 . The imaging apparatus of claim 1 , wherein the processing circuitry is further configured to:

receive information of a known object and a corresponding known feature of the known object, and

determine the action based on a combination of the received information and the detection result.

3 . The imaging apparatus of claim 1 , wherein the processing circuitry is further configured to:

obtain a second medical image, the second medical image being acquired by performing a scan using a second set of scan parameters,

analyze the second medical image to detect the first object and the first object feature in the second medical image,

determine whether there is a difference in the first object feature between the first medical image and the second medical image,

upon determining that there is a difference in the first object feature between the first medical image and the second medical image, generate an updated first object feature, and

determine an updated action corresponding to the first object and the updated first object feature from a database.

4 . The imaging apparatus of claim 3 , wherein the processing circuitry is further configured to:

determine a second updated set of scan parameters based on the determined updated action, and

control the imaging apparatus based on the second updated set of scan parameters.

5 . The imaging apparatus of claim 1 , wherein the first object and the first object feature are identified using machine vision.

6 . The imaging apparatus of claim 2 , wherein the processing circuitry is further configured to determine the action corresponding to the first object and the first object feature by applying information of the first object and the first object feature to a trained machine learning model.

7 . The imaging apparatus of claim 6 , wherein the trained machine learning model includes a neural network trained on reference known objects, reference known object features, and corresponding reference actions corresponding to the reference known objects and the reference known object features.

8 . The imaging apparatus of claim 2 , wherein the received information received by the processing circuitry is examination settings for the scan.

9 . The imaging apparatus of claim 1 , wherein the processing circuitry is further configured to train a neural network to directly determine the action corresponding to the first object and the first object feature based on input of the first medical image to the neural network.

10 . The imaging apparatus of claim 1 , wherein, in performing the analyzing of the first medical image to detect objects in the first medical image, the processing circuitry is further configured to use a trained neural network to segment the first medical image and detect the objects in the first medical image and the corresponding first object feature.

11 . The imaging apparatus of claim 1 , wherein

the imaging apparatus further comprises a table, an X-ray source configured to generate X-rays, an X-ray detector configured to detect the X-rays, an arm configured to hold the X-ray source and the X-ray detector, and an optical camera configured to obtain video data of the table, the X-ray source, the X-ray detector, and the arm, and

the processing circuitry is further configured to adjust at least two of the table, the X-ray source, the X-ray detector, and the arm simultaneously based on the updated set of scan parameters and the obtained video data, the at least two of the table, the X-ray source, the X-ray detector, and the arm avoiding a collision by the simultaneous adjustment based on the obtained video data.

12 . A method of adjusting components in an imaging apparatus, comprising:

obtaining a first medical image, the first medical image being acquired by performing a scan using a first set of scan parameters;

analyzing the first medical image to detect a plurality of objects in the first medical image and corresponding features of the detected plurality of objects;

determining an action corresponding to a combination of a first object and a first object feature, which has a relatively high priority among a plurality of combinations of objects and object features detected in the first medical image;

determining an updated set of scan parameters based on the determined action; and

controlling the imaging apparatus based on the updated set of scan parameters.

13 . The method of claim 12 , further comprising:

receiving information of a known object and a corresponding known feature of the known object; and

determining the action based on a combination of the received information and the detection result.

14 . The method of claim 12 , further comprising:

obtaining a second medical image, the second medical image being acquired by performing a scan using a second set of scan parameters;

analyzing the second medical image to detect the first object and the first object feature in the second medical image;

determining whether there is a difference in the first object feature between the first medical image and the second medical image;

upon determining that there is a difference in the first object feature between the first medical image and the second medical image, generating an updated first object feature; and

determining an updated action corresponding to the first object and the updated first object feature from a database.

15 . The method of claim 14 , further comprising:

determining a second updated set of scan parameters based on the determined updated action; and

controlling the imaging apparatus based on the second updated set of scan parameters.

16 . The method of claim 12 , wherein the first object and the first object feature are identified using machine vision.

17 . The method of claim 13 , further comprising determining the action corresponding to the first object and the first object feature by applying information of the first object and the first object feature to a trained machine learning model.

18 . The method of claim 17 , wherein the trained machine learning model includes a neural network trained on reference known objects, reference known object features, and corresponding reference actions corresponding to the reference known objects and the reference known object features.

19 . The method of claim 12 , wherein

the imaging apparatus further includes a table, an X-ray source configured to generate X-rays, an X-ray detector configured to detect the X-rays, an arm configured to hold the X-ray source and the X-ray detector, and an optical camera configured to obtain video data of the table, the X-ray source, the X-ray detector, and the arm, and

the method further comprises adjusting at least two of the table, the X-ray source, the X-ray detector, and the arm simultaneously based on the updated set of scan parameters and the obtained video data, the at least two of the table, the X-ray source, the X-ray detector, and the arm avoiding a collision by the simultaneous adjustment based on the obtained video data.

20 . A non-transitory computer-readable storage medium including executable instructions, which when executed by circuitry, cause the circuitry to perform a method of adjusting components in an imaging apparatus, comprising:

obtaining a first medical image, the first medical image being acquired by performing a scan using a first set of scan parameters;

analyzing the first medical image to detect a plurality of objects in the first medical image and corresponding features of the detected plurality of objects;

determining an action corresponding to a combination of a first object and a first object feature, which has a relatively high priority among a plurality of combinations of objects and object features detected in the first medical image;

determining an updated set of scan parameters based on the determined action; and

controlling the imaging apparatus based on the updated set of scan parameters.