Image processing apparatus, image processing system, image processing method, and storage medium

Patent metadata

Field	Value
Publication number	US-9965853-B2
Application number	US-201514725081-A
Country	US
Kind code	B2
Filing date	May 29, 2015
Priority date	Jun 2, 2014
Publication date	May 8, 2018
Grant date	May 8, 2018

Abstract

An image processing apparatus for obtaining a shape of a region of a processing target included in an image, includes: an attribute obtaining unit configured to obtain a intensity distribution attribute of the region of the processing target; and a shape obtaining unit configured to obtain the shape of the region by a calculation method selected in accordance with the intensity distribution attribute.

First claim

What is claimed is:

1. An image processing apparatus for obtaining a scale of a region of a processing target included in an image, comprising:
at least one processor; and
at least one memory storing a program including instructions executed by the at least one processor to:
obtain an intensity distribution attribute of the region of the processing target;
select, based on the intensity distribution attribute, a calculation method for calculating the scale of the region; and
obtain the scale of the region by the selected calculation method,
wherein the intensity distribution attribute defines whether the region of the processing target is a convex region which has a higher intensity value than its surrounding region, a concave region which has a lower intensity value than its surrounding region, or a mixed region including the convex region and the concave region, and
wherein, if the intensity distribution attribute defines the region as the mixed region, a component of the convex region and a component of the concave region in the mixed region are obtained, and the calculation method for calculating the scale of the region for the mixed region is selected based on a comparison between the obtained component of the convex region and the obtained component of the concave region.

2. The apparatus according to claim 1 , wherein the at least one processor executes instructions to determine a parameter to approximate the scale of the region by the calculation method and obtain the scale approximated by the parameter.

3. The apparatus according to claim 1 ,
wherein a Laplacian of Gaussian (LoG) function is used as an evaluation function to obtain the intensity distribution attribute, and
wherein the components of the convex region and the concave region are obtained using a local maximum and a local minimum obtained from a distribution of a power curve of the evaluation function.

4. The apparatus according to claim 3 , wherein if the power curve includes a plurality of local maximums and a plurality of local minimums, the components of the convex region and the concave region are obtained using a maximum value out of the plurality of local maximums and a minimum value out of the plurality of local minimums.

5. The apparatus according to claim 1 , wherein if the component of the convex region with respect to the component of the concave region is larger than a threshold, a calculation method corresponding to the convex region is selected, and
if the component of the convex region with respect to the component of the concave region is not more than the threshold, a calculation method corresponding to the concave region is selected.

6. The apparatus according to claim 1 ,
wherein a Laplacian of Gaussian (LoG) function is used as an evaluation function to obtain the intensity distribution attribute,
wherein a calculation method corresponding to the convex region or a calculation method corresponding to the concave region is selected based on the intensity distribution attribute,
wherein if the calculation method corresponding to the convex region is selected, the scale of the region is approximated based on a parameter representing a scale of the evaluation function corresponding to a maximum value of local maximums of the evaluation function, and
if the calculation method corresponding to the concave region is selected, the scale of the region is approximated based on a parameter representing a scale of the evaluation function corresponding to a minimum value of local minimums of the evaluation function.

7. The apparatus according to claim 1 , wherein the at least one processor further executes instructions to perform processing of specifying an unnecessary region not to be used to obtain the scale of the region from a region of interest including the region of the processing target and removing the unnecessary region from the region of interest, and
wherein the intensity distribution attribute of the region of the processing target included in the region of interest from which the unnecessary region has been removed is obtained.

8. The apparatus according to claim 3 , wherein the at least one processor further executes instructions to obtain a point belonging to the region of the processing target as a seed point, and
wherein the distribution of the power curve of the evaluation function for a region around the seed point is obtained using the seed point as a reference.

9. The apparatus according to claim 1 , wherein the at least one processor further executes instructions to display, on a display unit, an image generated by superimposing and compositing the obtained scale and the image captured by an imaging apparatus.

10. The apparatus according to claim 1 , wherein the image is captured by an imaging apparatus, and the imaging apparatus includes a computer tomography apparatus, a nuclear magnetic resonance imaging apparatus, or a radiography apparatus that radiographs a two-dimensional radiation image.

11. An image processing method of obtaining a scale of a region of a processing target included in an image, the method performed by an image processing apparatus including one or more processors, the method comprising:
using the one or more processors to obtain an intensity distribution attribute of the region of the processing target;
using the one or more processors to select, based on the intensity distribution attribute, a calculation method for calculating the scale of the region; and
using the one or more processors to obtain the scale of the region by the selected calculation method,
wherein the intensity distribution attribute defines whether the region of the processing target is a convex region which has a higher intensity value than its surrounding region, a concave region which has a lower intensity value than its surrounding region, or a mixed region including the convex region and the concave region, and
wherein, if the intensity distribution attribute defines the region as the mixed region, a component of the convex region and a component of the concave region in the mixed region are obtained, and the calculation method for calculating the scale of the region for the mixed region is selected based on a comparison between the obtained component of the convex region and the obtained component of the concave region.

12. The apparatus according to claim 1 , wherein the scale of the region includes a diameter of the region.

13. The apparatus according to claim 1 , wherein the mixed region is the convex region which further includes the concave region.

14. An image processing apparatus for obtaining a scale of a region of a processing target included in an image, comprising:
at least one processor; and
at least one memory storing a program including instructions executed by the at least one processor to:
obtain an intensity distribution attribute of the region of the processing target;
select one of calculation methods corresponding to the obtained intensity distribution attribute; and
obtain the scale of the region by the selected calculation method,
wherein the intensity distribution attribute defines whether a type of the region is a convex region, a concave region, or a mixed region including the convex region and the concave region, based on an intensity distribution of the region, and
wherein, if the intensity distribution attribute defines the type of the region as the mixed region, a component of the convex region and a component of the concave region in the mixed region are obtained, and the calculation method for calculating the scale of the region for the mixed region is selected based on the o

Assignees

• Canon Kk

Inventors

• Chen Bin

Classifications

• G06T2207/30096

  Tumor; Lesion · CPC title

• G06T7/11 Primary

  Region-based segmentation · CPC title

• G06T2207/10081

  Computed x-ray tomography [CT] · CPC title

• G06T7/64

  of convexity or concavity · CPC title

• G06T7/0012 Primary

  Biomedical image inspection · CPC title