Medical image processing apparatus, x-ray CT apparatus, method of medical image processing, and computer program product
A medical image processing apparatus according to an embodiment includes processing circuitry. The processing circuitry is configured to acquire first medical image data. The processing circuitry is configured to identify a region of interest in the first medical image data based on a learned model and the first medical image data. The learned model is trained based on second medical image data corresponding to the first medical image data and third medical image data different from the first medical image data in type and related to the same subject as a subject of the second medical image data. At least part of the third medical image data is higher in imaging sensitivity for a region of the subject corresponding to the region of interest than the second medical image data.
1. A medical image processing apparatus comprising processing circuitry configured to
acquire first medical image data and
identify a region of interest in the first medical image data based on a learned model and the first medical image data, wherein
the learned model is trained based on
second medical image data corresponding to the first medical image data and
third medical image data different from the first medical image data in type and related to the same subject as a subject of the second medical image data, and
at least part of the third medical image data is higher in imaging sensitivity for a region of the subject corresponding to the region of interest than the second medical image data.
2. The medical image processing apparatus according to claim 1 , wherein the first medical image data and the second medical image data are data obtained by the same type of medical image diagnostic apparatus.
3. The medical image processing apparatus according to claim 1 , wherein the second medical image data and the third medical image data differ from each other in at least one of a medical image diagnostic apparatus used for imaging, a scan condition during imaging, an applied reconstruction condition, and applied image processing.
4. The medical image processing apparatus according to claim 2 , wherein the second medical image data and the third medical image data differ from each other in at least one of a medical image diagnostic apparatus used for imaging, a scan condition during imaging, an applied reconstruction condition, and applied image processing.
5. The medical image processing apparatus according to claim 1 , wherein the first medical image data is projection data or reconstructed image data generated by image reconstruction based on the projection data.
6. The medical image processing apparatus according to claim 1 , wherein
the first medical image data is reconstructed image data, and
the processing circuitry is configured to generate a display image in which the region of interest identified on an image of a reconstructed image indicated by the reconstructed image data is highlighted.
7. The medical image processing apparatus according to claim 1 , wherein
the first medical image data is projection data, and
the processing circuitry is configured to generate a display image in which the region of interest identified on an image of a reconstructed image obtained by image reconstruction based on the projection data is highlighted.
8. The medical image processing apparatus according to claim 1 , wherein
the first medical image data is projection data and reconstructed image data generated by image reconstruction based on the projection data, and
the processing circuitry is configured to
identify a first region of interest in the projection data based on the learned model and the projection data,
identify a second region of interest in the reconstructed image data based on the learned model and the reconstructed image data, and
identify a logical sum of the first region of interest and the second region of interest as the region of interest.
9. The medical image processing apparatus according to claim 1 , wherein
the second medical image data and the third medical image data are each projection data or reconstructed image data generated by image reconstruction based on the projection data, and
the processing circuitry is configured to
identify a region of interest on an image of a reconstructed image corresponding to the third medical image data,
generate a mask image in which a CT value of another region than a region corresponding to the region of interest identified on the image of the reconstructed image in the second medical image data is deleted, and
generate data for learning the model using mask image data indicating the mask image.
10. An X-ray computed tomography (CT) apparatus comprising:
an X-ray tube generating X-rays;
an X-ray detector detecting X-rays from the X-ray tube having passed through a subject; and
processing circuitry configured to, based on a learned model and first medical image data, which is projection data based on output of the X-ray detector or reconstructed image data image-reconstructed based on the projection data, identify a region of interest in the first medical image data, wherein
the learned model is trained based on second medical image data corresponding to the first medical image data and third medical image data different from the first medical image data in type and related to the same subject as a subject of the second medical image data, and
at least part of the third medical image data is higher in imaging sensitivity for a region of the subject corresponding to the region of interest than the second medical image data.
11. A method of medical image processing comprising:
acquiring first medical image data; and
identifying a region of interest in the first medical image data based on a learned model and the first medical image data, wherein
the learned model is trained based on second medical image data corresponding to the first medical image data and third medical image data different from the first medical image data in type and related to the same subject as a subject of the second medical image data, and
at least part of the third medical image data is higher in imaging sensitivity for a region of the subject corresponding to the region of interest than the second medical image data.
12. A computer program product storing a program executed by a computer, the program causing the computer to execute:
acquiring first medical image data; and
identifying a region of interest in the first medical image data based on a learned model and the first medical image data, wherein
the learned model is trained based on second medical image data corresponding to the first medical image data and third medical image data different from the first medical image data in type and related to the same subject as a subject of the second medical image data, and
at least part of the third medical image data is higher in imaging sensitivity for a region of the subject corresponding to the region of interest than the second medical image data.