X-ray diagnostic apparatus and image processing method

Patent metadata

Field	Value
Publication number	US-12569211-B2
Application number	US-202318534886-A
Country	US
Kind code	B2
Filing date	Dec 11, 2023
Priority date	Dec 16, 2022
Publication date	Mar 10, 2026
Grant date	Mar 10, 2026

Abstract

In one embodiment, an X-ray diagnostic apparatus comprising: an X-ray tube configured to irradiate an imaging part of an object with X-rays; an X-ray detector configured to detect the X-rays; an image sensor configured to image the object; and processing circuitry configured to acquire: a human body model; image data from the image sensor; and imaging geometry information, detect positioning of the object from the image data, set the human body model based on detected positioning of the object, generate a predicted X-ray image that is predicted to be detected by the X-ray detector, by using the set human body model and the imaging geometry information, and display the predicted X-ray image.

First claim

What is claimed is:

1 . An X-ray diagnostic apparatus, comprising:
an X-ray tube configured to irradiate an imaging part of an object with X-rays; an X-ray detector configured to detect the X-rays; an image sensor configured to image the object; and processing circuitry configured to
acquire a human body model, image data from the image sensor, and imaging geometry information,
detect positioning of the object from the image data,
set the acquired human body model based on the detected positioning of the object,
generate a predicted X-ray image that is predicted to be detected by the X-ray detector, by using the set human body model and the acquired imaging geometry information,
set body parts of the acquired human body model in such a manner that the positioning of the object matches a desired positioning;
generate a pseudo X-ray image from the human body model that has been subjected to the setting; and
display at least one of the predicted X-ray image and the pseudo X-ray image.

2 . The X-ray diagnostic apparatus according to claim 1 , wherein the predicted X-ray image is a predicted X-ray image subjected to virtual positioning by having the body parts of the human body model set to match an actual positioning of the detected object.

3 . The X-ray diagnostic apparatus according to claim 1 , wherein the predicted X-ray image displayed by the processing circuitry is one of:
an image that depicts only bones; an image in which at least one of an organ, a muscle, and a blood vessel is depicted together with a bone; an image that depicts translucent bones; and an image that depicts only an outline of bones.

4 . The X-ray diagnostic apparatus according to claim 1 , wherein the processing circuitry is further configured to:
acquire a plurality of human body models; and select a particular human body model close to a skeleton or a physique of the object from the acquired plurality of human body models.

5 . The X-ray diagnostic apparatus according to claim 4 , wherein the plurality of human body models is one of:
models with standard body shapes for each gender and each age; models with characterized body shapes in terms of a skeleton or a physique; and models generated from medical diagnostic images that were previously acquired.

6 . The X-ray diagnostic apparatus according to claim 1 , wherein the image sensor is attached to a tube holder configured to hold the X-ray tube in such a manner that the image sensor can image the object in a same direction as an X-ray irradiation direction.

7 . The X-ray diagnostic apparatus according to claim 1 , wherein the human body model is a three-dimensional human body model configured in such a manner that body parts can be set in accordance with the detected positioning of the object.

8 . The X-ray diagnostic apparatus according to claim 7 , wherein the processing circuitry is further configured to determine whether or not the predicted X-ray image and the pseudo X-ray image are equivalent to each other.

9 . The X-ray diagnostic apparatus according to claim 7 , wherein the processing circuitry is further configured to:
use the pseudo X-ray image to generate a virtual visible image or a virtual camera image, each of which supports positioning of an imaging part of the object; and display the virtual visible image or the virtual camera image.

10 . The X-ray diagnostic apparatus according to claim 1 , wherein the acquired human body model is generated by generative AI from a camera image that is generated by the image sensor.

11 . An image processing method, comprising:
acquiring a human body model, image data obtained by imaging an object using an image sensor, and imaging geometry information; detecting positioning of the object from the image data, setting the acquired human body model based on the detected positioning of the object; generating a predicted X-ray image that is predicted to be detected by an X-ray detector, by using the human body model and the acquired imaging geometry information; setting body parts of the acquired human body model in such a manner that the positioning of the object matches a desired positioning; generating a pseudo X-ray image from the human body model that has been subjected to the setting; and displaying at least one of the predicted X-ray image and the pseudo X-ray image.

12 . The image processing method according to claim 11 , wherein the predicted X-ray image is a predicted X-ray image subjected to virtual positioning by having the body parts of the human body model set to match an actual positioning of the detected object.

13 . The image processing method according to claim 11 , wherein the predicted X-ray image is one of:
an image that depicts only bones; an image in which at least one of an organ, a muscle, and a blood vessel is depicted together with a bone; an image that depicts translucent bones; and an image that depicts only an outline of bones.

14 . The image processing method according to claim 11 , further comprising:
acquiring a plurality of human body models; and selecting a particular human body model close to a skeleton or a physique of the object from the acquired plurality of human body models.

15 . The image processing method according to claim 14 , wherein the plurality of human body models is one of:
models with standard body shapes for each gender and each age; models with characterized body shapes in terms of a skeleton or a physique; and models generated from medical diagnostic images that were previously acquired.

16 . The image processing method according to claim 11 , wherein the image sensor is attached to a tube holder configured to hold an X-ray tube in such a manner that the image sensor is configured to image the object in a same direction as an X-ray irradiation direction.

17 . The image processing method according to claim 11 , wherein the human body model is a three-dimensional human body model configured in such a manner that body parts can be set in accordance with the detected positioning of the object.

18 . The image processing method according to claim 17 , further comprising determining whether or not the predicted X-ray image and the pseudo X-ray image are equivalent to each other.

19 . The image processing method according to claim 17 , further comprising:
using the pseudo X-ray image to generate a virtual visible image or a virtual camera image, each of which supports positioning of an imaging part of the object; and displaying the virtual visible image or the virtual camera image.

20 . The image processing method according to claim 11 , wherein the acquired human body model is generated by generative AI from a camera image that is generated by an image sensor.

Assignees

• Canon Medical Systems Corp

Inventors

• Sato Daisuke
• Kobayashi Yoshimasa
• Takahashi Katsuo
• Saito Suzuna
• Tanaka Takahiro
• Kojima Katsunori

Classifications

• G06T7/0012

  Biomedical image inspection · CPC title

• A61B6/463

  characterised by displaying multiple images or images and diagnostic data on one display · CPC title

• A61B6/4208

  characterised by using a particular type of detector · CPC title

• A61B6/0487

  Motor-assisted positioning · CPC title

• A61B6/505

  for diagnosis of bone · CPC title