Methods for providing second key elements of the examination region in an x-ray image

1 . A computer-implemented method for providing second key elements of an examination region of a patient in an X-ray image, comprising:

receiving first input data, the first input data being an optical image of the examination region;

applying a first trained function to the first input data to generate first output data, the first output data including detected first key elements in the optical image, a first collimation region being determined based on the first key elements;

receiving second input data, the second input data being an X-ray image of the examination region acquired using the first collimation region;

applying a second trained function to the second input data to generate second output data, the second output data including detected second key elements in the X-ray image;

providing the second output data, the second output data including second key elements of the examination region; and

checking the second key elements for completeness, and in response to incomplete second key elements

receiving third input data, the third input data being the X-ray image of the examination region acquired using the first collimation region, the third input data further comprising the second key elements, and

applying a third trained function to the third input data to generate third output data, the third output data including at least one estimated third key element to complete the second key elements.

2 . A computer-implemented method for providing a first trained function, comprising:

receiving first input training data, the first input training data including an optical image of an examination region of a patient;

receiving first output training data, the first output training data being related to the first input training data, and the first output training data including second key elements determined based on an X-ray image of the examination region;

training a first function based on the first input training data and the first output training data;

providing the first trained function;

receiving second input training data, the second input training data including a first X-ray image;

receiving second output training data, the second output training data being related to the second input training data, the second output training data including at least one estimated third key element;

training a second trained function based on the second input training data and the second output training data;

providing the second trained function; and

retraining the first trained function based on a first collimation region determined from first key elements of the optical image and a second collimation region determined from the second key elements.

3 . The method of claim 2 , wherein the first collimation region determined based on the first key elements and the second collimation region determined based on the second key elements are substantially identical, and at least one of the first key elements differs from a corresponding second key element of the second key elements.

4 . The method of claim 2 , wherein the first collimation region determined based on the first key elements is larger than the second collimation region determined based on the second key elements.

5 . The method of claim 4 , further comprising:

applying a weight to reinforce an optimization of a size of the first collimation region with respect to the examination region.

6 . The method according to claim 1 , wherein the first trained function is provided by

receiving first input training data, the first input training data including an optical image of an examination region;

receiving first output training data, the first output training data being related to the first input training data, and the first output training data including second key elements determined based on an X-ray image of the examination region; and

training a first function based on the first input training data and the first output training data.

7 . A providing system, comprising:

a first interface configured to receive first input data, the first input data being an optical image of an examination region of a patient;

a first computation unit configured to apply a first trained function to the first input data to generate first output data, the first output data including detected first key elements and a first collimation region is determined based on the first key elements;

a second interface configured to receive second input data, the second input data being an X-ray image of the examination region acquired using the first collimation region;

a second computation unit configured to apply a second trained function to the second input data to generate second output data, the second output data including detected second key elements; and

a third interface configured to provide the second output data, the second output data including second key element data of the examination region, wherein the providing system is further configured to

check the second key elements for completeness, and in response to incomplete second key elements,

receive third input data, the third input data being a second x-ray image of the examination region acquired using the first collimation region, the third input data further comprising the second key elements, and

apply a third trained function to the third input data to generate third output data, the third output data including at least one estimated third key element to complete the second key elements.

8 . A non-transitory computer-readable medium comprising instructions which, when executed by a providing system, cause the providing system to perform the method of claim 1 .

9 . A training system, comprising:

a first training interface configured to receive first input training data and second input training data, the first input training data including an optical image of an examination region of a patient and the second input training data including a first X-ray image;

a second training interface configured to receive first output training data and second output training data, the first input training data being related to the first output training data, the first output training data including second key elements determined based on an X-ray image of the examination region and the second output training data being related to the second input training data, the second output training data including at least one estimated third key element;

a training computation unit configured to train a first trained function based on the first input training data and the first output training data and configured to train a third trained function based on the second input training data and the second output training data; and

a third training interface configured to provide the first trained function and the third trained function,

wherein the first trained function is retrained based on a first collimation region determined from first key elements of the optical image and a second collimation region determined from the second key elements.

10 . A non-transitory computer-readable medium comprising instructions which, when executed by a providing system, cause the providing system to perform the method of claim 2 .

11 . An X-ray system comprising the providing system of claim 7 .

12 . The method of claim 1 , wherein the at least one estimated third key element and the second output data form a complete set of second key elements.

13 . The method of claim 12 , further comprising:

determining a second collimation region based on the complete set of second key elements.

14 . The method of claim 1 , further comprising: mapping the X-ray image to the optical image to register the X-ray image with the optical image.