Image creation device
An image generating device for generating an image which is an X-ray image of an area including a bone portion of a subject with the bone portion removed has a control unit 70 including: a DRR imager 81 configured to generate a first DRR image of an area including a bone portion and a second DRR image showing the bone portion, by performing, for a set of CT image data of an area including the bone portion of a subject, a virtual fluoroscopic projection simulating a geometric fluoroscopy condition of an X-ray irradiator and an X-ray detector for the subject; a training section 82 configured to generate a machine learning model for recognizing the bone portion, by performing machine learning using the first DRR image and the second DRR image serving as a training image; an image converter 83 configured to perform conversion of the X-ray image of the area including the bone portion of the subject, using the machine learning model trained in the training section 82 , to generate an image showing the bone portion; and a bone portion subtractor 84 configured to subtract the image showing the bone portion from the X-ray image of the area including the bone portion of the subject.
1. An image generating device, comprising:
a DRR imager configured to generate a first DRR image showing a first region and a second region of a subject and a second DRR image showing the first region, by performing, for a set of CT image data of the area including the first region of the subject, a virtual fluoroscopic projection simulating a geometric fluoroscopy condition of an X-ray irradiator and an X-ray detector for the subject; and
an image converter configured to perform conversion of an X-ray image showing the first region and the second region of the subject into an image showing the first region, using a machine learning model that has undergone machine learning using the first DRR image for an input image and the second DRR image for a training image.
2. The image generating device according to claim 1 , wherein:
the first region is a bone portion; and
the image generating device further comprises a bone portion subtractor configured to subtract an image showing the bone portion from the X-ray image.
3. The image generating device according to claim 1 , wherein:
the first region is all regions except the bone portion of the subject.
4. The image generating device according to claim 1 , wherein:
the first region is a blood vessel with a contrast dye injected.
5. The image generating device according to claim 4 , wherein:
the first DRR image is a DRR image obtained by removing the dye-injected blood vessel from a DRR image including the dye-injected blood vessel, while the X-ray image is an X-ray image with no contrast dye injected; and
the image generating device further comprises a blood vessel adder configured to add an image showing the dye-injected blood vessel to the X-ray image.
6. The image generating device according to claim 1 , wherein:
the first region is a stent placed in a body of the subject; and
the image generating device further comprises a stent adder configured to add an image showing the stent to the X-ray image.
7. A method for generating a machine learning model, comprising:
generating a first DRR image showing a first region and a second region of a subject and a second DRR image showing the first region, by performing, for a set of CT image data of the area including the first region of the subject, a virtual fluoroscopic projection simulating a geometric fluoroscopy condition of an X-ray irradiator and an X-ray detector for the subject; and
generating a machine learning model for performing conversion of an X-ray image showing the first region and the second region of the subject into an image showing the first region, by performing machine learning using the first DRR image for an input image and the second DRR image for a training image.