Medical imaging apparatus, method, and storage medium
A medical imaging apparatus for generating a three-dimensional image of a vessel includes a catheter including a probe and insertable into the vessel, the catheter being configured to generate cross-sectional images of the vessel from ultrasonic signals emitted from the probe and received by the probe, and a processor configured to: control the catheter to emit the signals and acquire a series of cross-sectional images of the vessel therefrom, calculate a series of feature values of the vessel corresponding to the series of cross-sectional images, determine local maximums of variations in the series of feature values, select two or more of the cross-sectional images corresponding to the local maximums, and generate a three-dimensional image of the vessel using the selected images.
1 . A medical imaging apparatus for generating a three-dimensional image of a vessel, comprising:
a catheter including a probe and insertable into the vessel, wherein the catheter is configured to generate cross-sectional images of the vessel from signals emitted from the probe and received by the probe; and
a processor configured to:
control the catheter to emit the signals and acquire a series of cross-sectional images of the vessel therefrom,
calculate a series of feature values of the vessel corresponding to the series of cross-sectional images,
determine local maximums of variations in the series of feature values,
select two or more of the cross-sectional images corresponding to the local maximums, and
generate a three-dimensional image of the vessel using the selected images.
2 . The medical imaging apparatus according to claim 1 , wherein the processor is configured to:
input the cross-sectional images to a computer model to generate region information indicating one or more of predetermined regions of the vessel included in each of the cross-sectional images, and
calculate the feature values based on the region information.
3 . The medical imaging apparatus according to claim 2 , wherein the computer model has been trained to classify each of regions included in an input cross-sectional image of the vessel into one of the predetermined regions.
4 . The medical imaging apparatus according to claim 3 , wherein the predetermined regions include a first region outside the vessel, a second region including plaque, and a third region including a lumen of the vessel.
5 . The medical imaging apparatus according to claim 2 , wherein the processor is configured to generate information indicating plaque distribution in an axial direction of the vessel based on the region information for each of the selected images.
6 . The medical imaging apparatus according to claim 2 , wherein the processor is configured to calculate a mean lumen diameter of the vessel based on the region information for each of the selected images.
7 . The medical imaging apparatus according to claim 1 , wherein each of the feature values represents a centroid position of the vessel.
8 . The medical imaging apparatus according to claim 1 , wherein each of the feature values represents a mean lumen diameter of the vessel.
9 . The medical imaging apparatus according to claim 1 , wherein the processor is configured to:
determine a group of points corresponding to a predetermined region of the vessel in each of the selected images,
associate the group of points of each of the selected images with the group of points of another of the selected images, and
generate the three-dimensional image of the vessel based on the associated groups of points.
10 . The medical imaging apparatus according to claim 1 , wherein the processor is configured to determine whether a side branch of the vessel is present using maximum and minimum diameters of the vessel in each of the selected images.
11 . A method for generating a three-dimensional image of a vessel, the method comprising:
controlling a catheter including a probe and inserted into the vessel to emit signals and acquiring a series of cross-sectional images of the vessel therefrom;
calculating a series of feature values of the vessel corresponding to the series of cross-sectional images;
determining local maximums of variations in the series of feature values;
selecting two or more of the cross-sectional images corresponding to the local maximums; and
generating a three-dimensional image of the vessel using the selected images.
12 . The method according to claim 11 , further comprising:
inputting the cross-sectional images to a computer model to generate region information indicating one or more of predetermined regions of the vessel included in each of the cross-sectional images, wherein
the feature values are calculated based on the region information.
13 . The method according to claim 12 , wherein the computer model has been trained to classify each of regions included in an input cross-sectional image of the vessel into one of the predetermined regions.
14 . The method according to claim 13 , wherein the predetermined regions include a first region outside the vessel, a second region including plaque, and a third region including a lumen of the vessel.
15 . The method according to claim 12 , further comprising:
generating information indicating plaque distribution in an axial direction of the vessel based on the region information for each of the selected images.
16 . The method according to claim 12 , further comprising:
calculating a mean lumen diameter of the vessel based on the region information for each of the selected images.
17 . The method according to claim 11 , wherein each of the feature values represents a centroid position of the vessel.
18 . The method according to claim 11 , wherein each of the feature values represents a mean lumen diameter of the vessel.
19 . The method according to claim 11 , further comprising:
determining a group of points corresponding to a predetermined region of the vessel in each of the selected images; and
associating the group of points of each of the selected images with the group of points of another of the selected images, wherein
the three-dimensional image of the vessel is generated based on the associated groups of points.
20 . A non-transitory computer readable storage medium storing a program causing a computer to execute a method for generating a three-dimensional image of a vessel, the method comprising:
controlling a catheter including a probe and inserted into the vessel to emit signals and acquiring a series of cross-sectional images of the vessel therefrom;
calculating a series of feature values of the vessel corresponding to the series of cross-sectional images;
determining local maximums of variations in the series of feature values;
selecting two or more of the cross-sectional images corresponding to the local maximums; and
generating a three-dimensional image of the vessel using the selected images.