Image analysis apparatus, image analysis method, image analysis program and recording medium

1. An image analysis apparatus comprising:

component and space number calculation means for calculating, in a captured image (i) in which a tissue is captured and (ii) which has been binarized by use of a prescribed reference value as a threshold, (I) the number of connected components and (II) the number of spaces, each of the connected components being an aggregate of at least one component which is defined by connecting an outer edge(s) of the at least one component which is a graphic having a closed outer edge, each of the spaces being surrounded by an outer edge(s) of the at least one component;

comparison value calculation means for calculating a comparison value which indicates a difference between the number of connected components and the number of spaces, both of which have been calculated by the component and space number calculation means; and

determination means for determining, by comparing the comparison value calculated by the comparison value calculation means with a predetermined reference value, whether or not an image of a cancer tissue is included in the captured image.

2. The image analysis apparatus as set forth in claim 1 , wherein:

the comparison value calculation means calculates, as the comparison value, a ratio of the number of spaces to the number of connected components.

3. An image analysis apparatus as set forth in claim 1 , further comprising:

dividing means for dividing the captured image into a plurality of divided regions each having a predetermined size,

the number of connected components and the number of spaces being calculated, for each of the plurality of divided regions, by the component and space number calculation means,

the comparison value being calculated, for each of the plurality of divided regions, by the comparison value calculation means, and

the determination means determining, by use of the comparison value calculated for each of the plurality of divided regions, whether or not an image of a cancer tissue is included in the each of the plurality of divided regions.

4. An image analysis apparatus comprising:

space number calculation means for calculating, in a captured image (i) in which a tissue is captured and (ii) which has been binarized by use of a prescribed reference value as a threshold, a one-dimensional Betti number, which represents the number of spaces, each of which is surrounded by an outer edge(s) of a component(s) which is a graphic having a closed outer edge; and

determination means for determining, by comparing the one-dimensional Betti number, calculated by the space number calculation means, with a predetermined reference value, whether or not an image of a cancer tissue is included in the captured image.

5. The image analysis apparatus as set forth in claim 4 , wherein:

the predetermined reference value indicates a range of the number of spaces of a normal tissue; and

the determination means determines that an image of a cancer tissue is included in the captured image in a case where the number of spaces, calculated by the space number calculation means, is out of the range indicated by the predetermined reference value.

6. An image analysis apparatus as set forth in claim 4 , further comprising:

dividing means for dividing the captured image into a plurality of divided regions each having a predetermined size,

the number of spaces being calculated, for each of the plurality of divided regions, by the space number calculation means, and

the determination means determining, for each of the plurality of divided regions, whether or not an image of a cancer tissue is included in the each of the plurality of divided regions.

7. A computer-readable storage medium in which an image analysis program for causing an image analysis apparatus recited in claim 1 to operate, the image analysis program causing a computer to function as each of said means.

8. An image analysis method for use in an image analysis apparatus which analyzes a captured image in which a tissue is captured,

the image analysis method comprising the steps of:

(a) calculating, in a captured image (i) in which a tissue is captured and (ii) which has been binarized by use of a prescribed reference value as a threshold, (I) the number of connected components and (II) the number of spaces, each of the connected components being an aggregate of at least one component which is defined by coming in contact with an outer edge(s) of the at least one component which is a graphic having a closed outer edge, each of the spaces being surrounded an outer edge(s) of the at least one component;

(b) calculating a comparison value which indicates a difference between the number of connected components and the number of spaces, both of which have been calculated in the step (a); and

(c) determining that an image of a cancer tissue is included in the captured image in a case where the comparison value calculated in the step (b) is greater than a predetermined reference value.

9. An image analysis method for use in an image analysis apparatus which analyzes a captured image in which a tissue is captured,

the image analysis method comprising the steps of:

(a) calculating, in a captured image (i) in which a tissue is captured and (ii) which has been binarized by use of a prescribed reference value as a threshold, a one-dimensional Betti number, which represents the number of spaces, each of which is surrounded by an outer edge(s) of a component(s) which is a graphic having a closed outer edge; and

(b) determining, by comparing the one-dimensional Betti number, calculated in the step (a), with a predetermined reference value, whether or not an image of a cancer tissue is included in the captured image.

10. An image analysis apparatus comprising:

component and space number calculation means for calculating, in a captured image (i) in which a structure is captured and (ii) which has been caused to have a low resolution, (I) the number of connected components and (II) the number of spaces, each of the connected components being an aggregate of at least one component which is defined by connecting an outer edge(s) of the at least one component which is a graphic having a closed outer edge, each of the spaces being surrounded by an outer edge(s) of the at least one component;

comparison value calculation means for calculating a comparison value which indicates a difference between the number of connected components and the number of spaces, both of which have been calculated by the component and space number calculation means; and

determination means for determining, by comparing the comparison value calculated by the comparison value calculation means with a predetermined reference value, a composition of the structure included in the captured image.

11. The image analysis apparatus as set forth in claim 10 , wherein:

the component and space number calculation means calculates the number of components and the number of spaces, by processing the captured image having the low resolution by use of a combinational invariant measurement method which is one of mathematical methods employing a homological concept.