Medical image processing apparatus, learning method, X-ray diagnostic apparatus, and medical image processing method

Patent metadata

Field	Value
Publication number	US-11615270-B2
Application number	US-202016809673-A
Country	US
Kind code	B2
Filing date	Mar 5, 2020
Priority date	Mar 6, 2019
Publication date	Mar 28, 2023
Grant date	Mar 28, 2023

Abstract

A medical image processing apparatus of an embodiment includes processing circuitry. The processing circuitry is configured to acquire medical image data on the basis of tomosynthesis imaging of a test object, and input the acquired medical image data of the test object to a trained model to acquire a two-dimensional image data, the trained model being generated by learning of two-dimensional image data on the basis of X-ray imaging of a person and image data on the basis of tomosynthesis imaging of the person who is subjected to the X-ray imaging.

First claim

What is claimed is:

1. A medical image processing apparatus comprising:
processing circuitry configured to
acquire medical image data on the basis of tomosynthesis imaging of a breast of a test object, and
input the acquired medical image data of the test object to a trained model to acquire mammography image data of the test object, the trained model being generated by learning of mammography image data on the basis of mammography imaging of a breast of a person and image data on the basis of tomosynthesis imaging of the breast of the person who is subjected to the mammography imaging,
wherein
the processing circuitry is further configured to
extract, from the medical image data acquired through the tomosynthesis imaging, projection data or reconstructed data of the projection data, an angle of which corresponds to an angle of the mammography imaging of the test object, and
input both the extracted projection data or reconstructed data and the acquired medical image data to the trained model to acquire the mammography image data of the test object.

2. The medical image processing apparatus according to claim 1 , wherein
the processing circuitry is further configured to
extract a region of interest included in the acquired medical image data on the basis of the tomosynthesis imaging, and
emphasize a region associated with the extracted region of interest in the acquired mammography image data.

3. The medical image processing apparatus according to claim 2 , wherein
the processing circuitry is configured to extract a lesion on the basis of a result of computer aided detection (CAD) as the region of interest.

4. The medical image processing apparatus according to claim 1 , wherein
the processing circuitry is further configured to blend tomographic image data included in the medical image data on the basis of the tomosynthesis imaging with the mammography image data of the test object at a predetermined ratio to generate image data.

5. A learning method comprising:
generating a trained model which generates mammography image data from medical image data on the basis of tomosynthesis imaging of a breast of a test object, using a data set including a pair of mammography medical image data on the basis of mammography imaging of a breast of a person and medical image data on the basis of the tomosynthesis imaging of the breast of the person who is subjected to the mammography imaging,
wherein
outputting the mammography image data of the test object from the trained model when both projection data or reconstructed data of the projection data and the medical image data are input, the projection data or reconstructed data being extracted from the medical image data acquired through the tomosynthesis imaging are input, an angle of the projection data or reconstructed data corresponding to an angle of the mammography imaging of the test object.

6. An X-ray diagnostic apparatus comprising:
an imager configured to perform tomosynthesis imaging on a test object by radiating the test object with X-rays at a plurality of angles; and
a medical image processing apparatus according to claim 1 .

7. A medical image processing method, using a computer, comprising:
acquiring medical image data on the basis of tomosynthesis imaging of a breast of a test object, and
inputting the medical image data of the test object to a trained model to acquire mammography image data of the test object, the trained model being generated by learning of mammography image data on the basis of mammography imaging of a breast of a person and image data on the basis of tomosynthesis imaging of the breast of the person who is subjected to the mammography imaging,
wherein
the medical image processing method further comprises
extracting, from the medical image data acquired through the tomosynthesis imaging, projection data or reconstructed data of the projection data, an angle of which corresponds to an angle of the mammography imaging of the test object, and
inputting both the extracted projection data or reconstructed data and the acquired medical image data to the trained model to acquire the mammography image data of the test object.

Assignees

• Canon Medical Systems Corp

Inventors

• Kobayashi Yoshimasa

Classifications

• G06T12/30

  Image post-processing, e.g. metal artefact correction · CPC title

• G06T12/10

  Image preprocessing, e.g. calibration, positioning of sources or scatter correction · CPC title

• A61B6/502

  for diagnosis of breast, i.e. mammography · CPC title

• G06V10/774

  Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting · CPC title

• A61B6/025 Primary

  Tomosynthesis · CPC title