Image generation device, medical device, and storage medium

1 . An image generation device including one or a plurality of processors that perform operations comprising:

reconstructing a virtual monochromatic X-ray image of a first energy and a virtual monochromatic X-ray image of a second energy based on data collected from an imaging subject;

inputting an input image created based on the reconstructed virtual monochromatic X-ray image of the second energy into a trained model;

inferring the virtual monochromatic X-ray image of the first energy using the trained model; and

generating a corrected virtual monochromatic X-ray image of the first energy based on the reconstructed virtual monochromatic X-ray image of the first energy and the inferred virtual monochromatic X-ray image of the first energy, wherein generating the corrected virtual monochromatic X-ray image of the first energy includes:

weighting CT values of each pixel of the reconstructed virtual monochromatic X-ray image of the first energy;

weighting the CT values of each pixel of the inferred virtual monochromatic X-ray image of the first energy; and

generating a corrected virtual monochromatic X-ray image of the first energy based on the weighted reconstructed virtual monochromatic X-ray image of the first energy and weighted inferred virtual monochromatic X-ray image of the first energy; and

identifying, from a virtual monochromatic X-ray image of a first of the reconstructed virtual monochromatic X-ray image and inferred virtual monochromatic X-ray image, a first region including pixels with CT values in a first range and a second region including pixels with CT values in a second range;

identifying, from a virtual monochromatic X-ray image of a second of the reconstructed virtual monochromatic X-ray image and inferred virtual monochromatic X-ray image, a third region corresponding to the first region and a fourth region corresponding to the second region;

determining a first weighting coefficient for weighting the CT values of the pixels in the first region, a second weighting coefficient for weighting the CT values of the pixels in the second region, a third weighting coefficient for weighting the CT values of the pixels in the third region, and a fourth weighting coefficient for weighting the CT values of the pixels in the fourth region;

weighting a first virtual monochromatic X-ray image with the first weighting coefficient and second weighting coefficient;

weighting a second virtual monochromatic X-ray image with the third weighting coefficient and fourth weighting coefficient; and

generating a corrected virtual monochromatic X-ray image of the first energy based on the first virtual monochromatic X-ray image weighted by the first weighting coefficient and second weighting coefficient and the second virtual monochromatic X-ray image weighted by the third weighting coefficient and fourth weighting coefficient.

2 . The image generation device according to claim 1 , wherein the first virtual monochromatic X-ray image is the reconstructed virtual monochromatic X-ray image and the second virtual monochromatic X-ray image is the inferred virtual monochromatic X-ray image.

3 . The image generation device according to claim 1 , wherein the first range represents the range of CT values of soft tissue.

4 . The image generation device according to claim 3 , wherein the first range is a range between a first threshold representing a lower limit of the CT values of soft tissue and a second threshold representing an upper limit of CT values of soft tissue.

5 . The image generation device according to claim 4 , wherein the first threshold is a negative value and the second threshold is a positive value.

6 . The image generation device according to claim 1 , wherein the one or a plurality of processors perform operations including:

filtering the reconstructed virtual monochromatic X-ray image of the first energy and/or the inferred virtual monochromatic X-ray image of the first energy; and

determining a first weighting coefficient and a second weighting coefficient for weighting the CT values of pixels in the reconstructed virtual monochromatic X-ray image of the first energy, and determining a third weighting coefficient and a fourth weighting coefficient for weighting the CT values of pixels in the inferred virtual monochromatic X-ray image of the first energy, based on the filtered virtual monochromatic X-ray image.

7 . The image generation device according to claim 1 , wherein generating the corrected virtual monochromatic X-ray image of the first energy includes:

generating a difference image between the reconstructed virtual monochromatic X-ray image of the first energy and the inferred virtual monochromatic X-ray image of the first energy; and

generating a corrected virtual monochromatic X-ray image of the first energy based on the difference image.

8 . The image generation device according to claim 7 , wherein generating the corrected virtual monochromatic X-ray image of the first energy based on the difference image includes:

identifying a pixel with the largest difference value from among a plurality of pixels in the difference image;

identifying a first pixel corresponding to the identified pixel among the plurality of pixels in the reconstructed virtual monochromatic X-ray image of the first energy;

identifying a second pixel corresponding to the identified pixel among the plurality of pixels in the inferred virtual monochromatic X-ray image of the first energy; and

correcting the inferred virtual monochromatic X-ray image of the first energy based on CT values of the first pixel and the CT values of the second pixel.

9 . The image generation device according to claim 8 , wherein correcting the inferred virtual monochromatic X-ray image of the first energy includes:

gamma-correcting the inferred virtual monochromatic X-ray image of the first energy based on the CT values of the first pixel and the CT values of the second pixel.

10 . The image generation device according to claim 1 , wherein the trained model is generated by training a neural network with training data that includes images obtained by pre-processing virtual monochromatic X-ray images of the first energy and pre-processing virtual monochromatic X-ray images of the second energy.

11 . The image generation device according to claim 1 , wherein the first energy is lower than the second energy.

12 . A medical device including one or a plurality of processors capable of performing operations including:

reconstructing a virtual monochromatic X-ray image of a first energy and a virtual monochromatic X-ray image of a second energy based on data collected from an imaging subject;

inputting an input image created based on the reconstructed virtual monochromatic X-ray image of the second energy into a trained model;

inferring the virtual monochromatic X-ray image of the first energy using the trained model; and

generating a corrected virtual monochromatic X-ray image of the first energy based on the reconstructed virtual monochromatic X-ray image of the first energy and the inferred virtual monochromatic X-ray image of the first energy, wherein generating the corrected virtual monochromatic X-ray image of the first energy includes:

weighting CT values of each pixel of the reconstructed virtual monochromatic X-ray image of the first energy;

weighting the CT values of each pixel of the inferred virtual monochromatic X-ray image of the first energy; and

generating a corrected virtual monochromatic X-ray image of the first energy based on the weighted reconstructed virtual monochromatic X-ray image of the first energy and weighted inferred virtual monochromatic X-ray image of the first energy; and

identifying, from a virtual monochromatic X-ray image of a first of the reconstructed virtual monochromatic X-ray image and inferred virtual monochromatic X-ray image, a first region including pixels with CT values in a first range and a second region including pixels with CT values in a second range;

identifying, from a virtual monochromatic X-ray image of a second of the reconstructed virtual monochromatic X-ray image and inferred virtual monochromatic X-ray image, a third region corresponding to the first region and a fourth region corresponding to the second region;

determining a first weighting coefficient for weighting the CT values of the pixels in the first region, a second weighting coefficient for weighting the CT values of the pixels in the second region, a third weighting coefficient for weighting the CT values of the pixels in the third region, and a fourth weighting coefficient for weighting the CT values of the pixels in the fourth region;

weighting a first virtual monochromatic X-ray image with the first weighting coefficient and second weighting coefficient;

weighting a second virtual monochromatic X-ray image with the third weighting coefficient and fourth weighting coefficient; and

generating a corrected virtual monochromatic X-ray image of the first energy based on the first virtual monochromatic X-ray image weighted by the first weighting coefficient and second weighting coefficient and the second virtual monochromatic X-ray image weighted by the third weighting coefficient and fourth weighting coefficient.

13 . A storage medium readable by a computer and non-transitory containing one or more instructions executable by one or more processors, wherein

the one or more instructions instruct the one or more processors to perform operations including:

reconstructing a virtual monochromatic X-ray image of a first energy and a virtual monochromatic X-ray image of a second energy based on data collected from an imaging subject;

creating an input image based on the reconstructed virtual monochromatic X-ray image of the second energy;

inputting the input image to a trained model and use the trained model to infer a virtual monochromatic X-ray image of the first energy; and

generating a corrected virtual monochromatic X-ray image of the first energy based on the reconstructed virtual monochromatic X-ray image of the first energy and the inferred virtual monochromatic X-ray image of the first energy, wherein generating the corrected virtual monochromatic X-ray image of the first energy includes:

weighting CT values of each pixel of the reconstructed virtual monochromatic X-ray image of the first energy;

weighting the CT values of each pixel of the inferred virtual monochromatic X-ray image of the first energy; and

generating a corrected virtual monochromatic X-ray image of the first energy based on the weighted reconstructed virtual monochromatic X-ray image of the first energy and weighted inferred virtual monochromatic X-ray image of the first energy; and

identifying, from a virtual monochromatic X-ray image of a first of the reconstructed virtual monochromatic X-ray image and inferred virtual monochromatic X-ray image, a first region including pixels with CT values in a first range and a second region including pixels with CT values in a second range;

identifying, from a virtual monochromatic X-ray image of a second of the reconstructed virtual monochromatic X-ray image and inferred virtual monochromatic X-ray image, a third region corresponding to the first region and a fourth region corresponding to the second region;

determining a first weighting coefficient for weighting the CT values of the pixels in the first region, a second weighting coefficient for weighting the CT values of the pixels in the second region, a third weighting coefficient for weighting the CT values of the pixels in the third region, and a fourth weighting coefficient for weighting the CT values of the pixels in the fourth region;

weighting a first virtual monochromatic X-ray image with the first weighting coefficient and second weighting coefficient;

weighting a second virtual monochromatic X-ray image with the third weighting coefficient and fourth weighting coefficient; and

generating a corrected virtual monochromatic X-ray image of the first energy based on the first virtual monochromatic X-ray image weighted by the first weighting coefficient and second weighting coefficient and the second virtual monochromatic X-ray image weighted by the third weighting coefficient and fourth weighting coefficient.