Time phase determination apparatus and time phase determination method
A time phase determination apparatus according to an embodiment is a time phase determination apparatus for determining the range of a particular time phase in a contrast-enhanced image, and includes processing circuitry. The processing circuitry acquires medical images at a plurality of different timings. The processing circuitry extracts a plurality of regions of interest on the basis of the medical images at the different timings. The processing circuitry generates a plurality of time intensity curves that are time intensity curves corresponding to the respective regions of interest. The processing circuitry determines the range of the particular time phase on the basis of the time intensity curves.
1 . An image processing apparatus, comprising:
processing circuitry configured to
acquire a plurality of medical images, each of which corresponds to a different one of a plurality of timings;
extract a first region of interest in each of the plurality of medical images;
extract a second region of interest in each of the plurality of medical images, a timing when the second region of interest is enhanced by a contrast agent being earlier than a timing when the first region of interest is enhanced by the contrast agent;
generate a first time intensity curve corresponding to a pixel value in the first region of interest at the plurality of timings;
generate a second time intensity curve corresponding to a pixel value in the second region of interest at the plurality of timings; and
determine a range of a time phase corresponding to a period before a first time phase and after a second time phase, the first time phase being a time phase when the first time intensity curve reaches a predetermined value from a value less than the predetermined value, the second time phase being determined based on a gradient of the second time intensity curve.
2 . The image processing apparatus according to claim 1 , wherein the processing circuitry is further configured to extract the first region of interest, which corresponds to a liver area and extract the second region of interest, which corresponds to an abdominal aorta area.
3 . The image processing apparatus according to claim 1 , wherein the processing circuitry is further configured to extract at least one region of interest among the first region of interest and the second region of interest by:
tracking a rigid body motion of an entire area of the region of interest, based on the plurality of medical images; and
calculating displacement of the region of interest relative to the entire area for each of the plurality of medical images.
4 . The image processing apparatus according to claim 3 , wherein the processing circuitry is further configured to:
in the tracking, track the rigid body motion of the entire area by extracting the entire area from one medical image, creating a binary template of a local target in the entire area, and obtaining a displacement quantity of the local target by performing template matching with the binary template in another medical image, and
in the calculating of the displacement, calculate the displacement of the region of interest relative to the entire area by extracting a plurality of local targets in the entire area and predicting the displacement of each of the local targets using a regression model.
5 . The image processing apparatus according to claim 1 , wherein the processing circuitry is further configured to select a region of interest to be extracted, based on an image resolution of the plurality of medical images.
6 . The image processing apparatus according to claim 1 , wherein the processing circuitry is further configured to reconstruct a medical image that has image resolution higher than an image resolution of the plurality of medical images, the medical image being within the determined range of the time phase.
7 . The image processing apparatus according to claim 1 , wherein the processing circuitry is further configured to reconstruct a medical image that has image resolution higher than an image resolution of the plurality of medical images, the medical image corresponding to a time phase determined based on the determined range of the time phase.
8 . The image processing apparatus according to claim 1 , wherein the second time phase is a time phase when the gradient of the second time intensity curve is maximum.
9 . An image processing apparatus, comprising:
processing circuitry configured to
acquire a plurality of medical images, each of which corresponds to a different one of a plurality of timings;
extract a first region of interest in each of the plurality of medical images;
extract a second region of interest in each of the plurality of medical images, a timing when the second region of interest is enhanced by a contrast agent being earlier than a timing when the first region of interest is enhanced by the contrast agent;
generate a first time intensity curve corresponding to a pixel value in the first region of interest at the plurality of timings;
generate a second time intensity curve corresponding to a pixel value in the second region of interest at the plurality of timings; and
determine a range of a time phase corresponding to a period before a first time phase and after a second time phase, the first time phase being a time phase when the first time intensity curve reaches a first predetermined value from a value less than the first predetermined value, the second time phase being a time phase when the second time intensity curve reaches a second predetermined value from a value less than the second predetermined value.
10 . The image processing apparatus according to claim 9 , wherein the first region of interest corresponds to a liver area and the second region of interest corresponds to an abdominal aorta area.
11 . The image processing apparatus according to claim 9 , wherein the processing circuitry is further configured to extract at least one region of interest among the first region of interest and the second region of interest by:
tracking a rigid body motion of an entire area of the region of interest, based on the plurality of medical images; and
calculating displacement of the region of interest relative to the entire area for each of the plurality of medical images.
12 . The image processing apparatus according to claim 11 , wherein the processing circuitry is further configured to:
in the tracking, track the rigid body motion of the entire area by extracting the entire area from one medical image, creating a binary template of a local target in the entire area, and obtaining a displacement quantity of the local target by performing template matching with the binary template in another medical image, and
in the calculating of the displacement, calculate the displacement of the region of interest relative to the entire area by extracting a plurality of local targets in the entire area and predicting the displacement of each of the local targets using a regression model.
13 . The image processing apparatus according to claim 9 , wherein the processing circuitry is further configured to select a region of interest to be extracted, based on an image resolution of the plurality of medical images.
14 . The image processing apparatus according to claim 9 , wherein the processing circuitry is further configured to reconstruct a medical image that has an image resolution higher than an image resolution of the plurality of medical images, the medical image being within the determined range of the time phase.
15 . The image processing apparatus according to claim 9 , wherein the processing circuitry is further configured to reconstruct a medical image that has an image resolution higher than an image resolution of the plurality of medical images, the medical image corresponding to a time phase determined based on the determined range of the time phase.