JP2002071552A - Method for evaluating biotic tissue with use of image processing - Google Patents

Abstract

PROBLEM TO BE SOLVED: To quantitatively determine and evaluate the features of biotioc tissue by carrying out image processing to biotic tissue images. SOLUTION: Parameters of all H types such as an average, a variance, a contrast, etc., of pixel values are defined (S1). Biotic tissue images are inputted (S2), on which many virtual organisms are generated (S3). Genes indicating (h) combinations (h<=H) among H parameters are fed at random to each of the virtual organisms (S4). Each parameter in the periphery of a generation position is defined as a potential parameter (S5). Each virtual organism is moved at random (S6). A parameter of a peripheral image after the movement is calculated as a present environment parameter, and the virtual organism is fed when the potential parameter is similar to the present environment parameter for (h) parameters indicated by genes (S7). Each virtual organism is let to extinguish or grow in accordance with a state in which the organism takes the feed (S8). This process is repeated (S9). A histogram is formed for genes of the finally surviving virtual organism (S10).

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a biological tissue evaluation method using image processing, and more particularly, to an evaluation method useful for quantitatively evaluating the quality of a tumor image in a biological tissue using a computer.

[0002]

2. Description of the Related Art Various devices using computers have been used as medical diagnosis support devices. For example,
A CT apparatus, an MRI apparatus, and the like are widely used as diagnostic support apparatuses indispensable for current medical diagnosis, and three-dimensional image data of a body tissue can be obtained by three-dimensionally scanning a specimen. . On the other hand, histological examination is indispensable for accurate determination of disease, and more than 5 million tissue diagnoses are performed annually. In such a tissue diagnosis, a two-dimensional image of a biological tissue serving as a specimen is usually used. As a method for obtaining a two-dimensional image of the biological tissue, a method using hematoxylin and eosin staining is generally known, and a microscope image of the stained biological tissue is captured as digital data via a CCD camera or the like. .

[0003]

Even if a two-dimensional image of a biological tissue is obtained by the above-described method using hematoxylin and eosin staining, medical diagnosis of the biological tissue expressed as the two-dimensional image is performed. To do this accurately requires a high degree of medical knowledge and experience. In particular, when a tumor image is present in a biological tissue, an extremely high degree of judgment is required to distinguish whether the tumor is a malignant tumor such as a cancer or a benign tumor. For example, when determining whether a biological tissue on a two-dimensional image obtained using hematoxylin and eosin staining is a malignant tumor, the stained image is divided into a small number of regions based on a threshold value of color difference. Although there is a proposal of a method for performing feature extraction, it has not reached the level of practical use. One of the causes is that, when a biological tissue is stained, cell nuclei and lymphocytes are stained in the same color, and it is difficult to distinguish a cancer cell region or the like only by color-based feature evaluation.
Until now, the discovery of lesions such as cancer cells has been performed by skilled pathologists based on experience and comprehensive knowledge, so for example, an objective index is provided to evaluate the morphological characteristics of the cancer cell area At present, sufficient research has not been conducted on such technologies.

In order to objectively analyze biological tissue images, it is indispensable to construct an image database (electronic medical chart) in which various images obtained clinically are systematically classified. However, the current image database merely records data such as the patient's name, gender, age, case, date and time, and cannot search for the characteristics of the biological tissue image itself. This is because a method for quantitatively evaluating biological tissue images has not been established,
This is because it was difficult to quantify the characteristics of the image itself.

Accordingly, an object of the present invention is to provide a biological tissue evaluation method capable of quantitatively evaluating characteristics of a two-dimensional image of a biological tissue by performing image processing using a computer. And

[0006]

Means for Solving the Problems (1) According to a first aspect of the present invention, an image of a biological tissue to be evaluated is subjected to predetermined image processing using a computer, thereby obtaining a characteristic of the biological tissue. In a biological tissue evaluation method using image processing for quantitatively evaluating an image, a step of defining a plurality of H parameters indicating numerically the characteristics of texture expressed on the image, and inputting an image of the biological tissue to be evaluated And generating a large number of virtual creatures having a predetermined energy value on the input biological tissue image. For each virtual creature, h selected from among H parameters (h ≦ H) )), Defining a gene indicating a combination of parameters, and at least a gene among H types of parameters indicating texture characteristics of a peripheral image of a generation position of each virtual creature. (H) determining the values of the h parameters shown, and defining these parameter values as latent parameter values of each virtual creature;
A process of moving the virtual creature on the biological tissue image and determining a consumed energy value to be consumed by the movement; (b) a peripheral image after the movement of the virtual creature, which is indicated by the gene of the virtual creature as h Is determined as the current environment parameter value, and based on the similarity between h potential parameter values and h current environment parameter values,
The process of determining the energy value to be consumed by the virtual creature, (c) The energy value of the virtual creature is reduced by the consumed energy value, and the energy value is updated by adding the consumed energy value, and the energy value is updated. When the energy value reaches the predetermined lower limit, the virtual creature is removed as dead, and when the updated energy value reaches the predetermined upper limit, the virtual creature is identified as having grown. (A), (b), and (c), a process of generating a new virtual creature having the same gene in the vicinity, a predetermined number of times, and finally surviving on the biological tissue image Creating a histogram of the gene for the virtual creature that is being performed, so that the image of the biological tissue to be evaluated can be quantitatively evaluated as the obtained histogram. It is a thing.

(2) The second aspect of the present invention is the above-mentioned first aspect.
In the biological tissue evaluation method using the image processing according to the aspect, the latent parameter value obtained for the peripheral image of the occurrence position of each virtual creature as an initial value, the current environment parameter value and the latent parameter obtained for the peripheral image after the movement When a similarity to the value is obtained, the update process is performed on the value of the latent parameter so as to approach the value of the current environment parameter.

(3) A third aspect of the present invention is the above-described first aspect.
Alternatively, in the biological tissue evaluation method using image processing according to the second aspect, a random number is used when generating a virtual creature, defining a gene for the virtual creature, and moving the virtual creature, and using a random gene at a random position. A virtual creature with is generated and moves randomly.

(4) The fourth aspect of the present invention is the above-mentioned first aspect.
In the biological tissue evaluation method using the image processing according to the third to third aspects, a brightness value is obtained for a peripheral image after the movement of each virtual creature. A process for reducing the energy value of the virtual creature or the energy value of the virtual creature is further added.

(5) The fifth aspect of the present invention relates to the above-mentioned fourth aspect.
In the biological tissue evaluation method using image processing according to the aspect, for a certain percentage of virtual creatures in descending order of lightness values, a process of reducing the energy value to an extent sufficient for the virtual creatures to die is performed. It is like that.

(6) The sixth aspect of the present invention is the above-mentioned first aspect.
In the biological tissue evaluation method using the image processing according to the fifth to fifth aspects, a near reference area centered on the position after movement of each virtual creature, and a distant area including the near reference area and further extending the boundary to a further distant place A reference region is defined, and when the similarity between the nearby parameter value indicating the texture feature in the near reference region and the far parameter value indicating the texture feature in the far reference region is low, the similarity of the virtual creature is determined. A process for reducing the energy value of the virtual creature or the energy value of the virtual creature is further added.

(7) A seventh aspect of the present invention is the above-mentioned first aspect.
In the biological tissue evaluation method using the image processing according to the sixth to sixth aspects, the average of the density values of the respective pixels in the predetermined reference region is set as a plurality of H types of parameters indicating the texture characteristics of the biological tissue image as numerical values. , Variance, energy, entropy, and contrast.

(8) The eighth aspect of the present invention is the above-mentioned first aspect.
In the biological tissue evaluation method using the image processing according to the seventh to seventh aspects, a color image is used as the biological tissue image, and a parameter of the texture of the biological tissue image as a numerical value within a predetermined reference area Parameter values for the density values of the three primary colors of each pixel of each pixel are used, and the similarity between the parameter values is determined based on the angle difference of the three-dimensional vector defined based on the parameter values of each color component. It is something to do.

(9) The ninth aspect of the present invention is the above-mentioned first aspect.
-In the biological tissue evaluation method using image processing according to the eighth aspect, the age is defined for each virtual creature,
Each time the three processes (a), (b), and (c) are performed, the age of each virtual creature is increased, and virtual creatures whose age has reached a predetermined life are removed as dead. Things.

(10) A tenth aspect of the present invention is a method for evaluating a biological tissue using image processing according to the first to ninth aspects, wherein the gene that the parent virtual organism has is inherited. A mutation is generated with a predetermined probability, and when a mutation occurs, the gene is randomly changed and then inherited.

(11) According to an eleventh aspect of the present invention, there is provided a program for causing a computer to execute each step constituting the biological tissue evaluation method using the image processing according to the first to tenth aspects described above. It is recorded on a computer-readable recording medium.

[0017]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The present invention will be described below based on an embodiment shown in the drawings.

§1. Basic Concept of the Present Invention First, the basic concept of the present invention will be briefly described. Assume that tissue images as shown in FIGS. 1A and 1B are prepared. The tissue image shown here is a mammary gland tissue image of an animal, and FIG. 1 (a) shows a normal mammary gland tissue image, and FIG.
(b) shows an example of a cancerous mammary gland tissue image. FIG.
In the normal tissue shown in (a), the cell nucleus region has an annular tissue structure, whereas in the cancerous tissue shown in FIG. 1 (b),
The state where the cell nucleus region is enlarged can be confirmed. However, for convenience of explanation, the difference between individual cell nucleus regions is illustrated as a very clear pattern, but the difference between normal tissue and cancerous tissue is not so clearly recognizable. In practice, it is difficult to recognize even a part of a cell nucleus region unless a pathologist has some skill. Therefore, it would be convenient if the characteristics of each tissue image could be quantitatively evaluated by taking the tissue image as shown in FIGS. 1A and 1B into a computer as digital data and performing predetermined image processing. It is.

If the evaluation method according to the present invention is used, FIG.
For the tissue images shown in (a) and (b), respectively, FIG.
, (B) can be obtained. In each of the histograms, the horizontal axis is a characteristic factor indicating some characteristic of the texture (pattern) expressed on each tissue image. The parameters used as the characteristic factors will be described in detail later. However, it can be said that the characteristic factors objectively capture some of the latent features in the texture. A histogram as shown in FIG. 2 (a) is obtained for a normal breast tissue image as shown in FIG. 1 (a), and a cancerous breast tissue image as shown in FIG. 1 (b) is obtained as shown in FIG. 2 (b). If the histogram shown in FIG. 2A is obtained, the histogram shown in FIG. 2A can be used as data that objectively shows the features latent in a normal mammary tissue image, and the histogram shown in FIG. The histogram can be used as data that objectively indicates the features latent in the cancerous breast tissue image.

If such a histogram is collected for each of a large number of clinically obtained cases and a database is constructed, this database can be used as auxiliary data for diagnosis. For example, if a histogram is obtained by applying the evaluation method according to the present invention to a tissue image collected from a sample, by comparing the histogram obtained for this sample with a large number of histograms stored in a database, Thus, it is possible to perform a certain diagnosis on the sample. For example, the histogram obtained for the sample is shown in FIG.
If the distribution has a distribution close to the histogram shown in (b), it is possible to obtain information that the biological tissue of the specimen is highly likely to be cancerous.

Of course, the histogram information obtained by the method according to the present invention does not always indicate a correct diagnosis result, and there is a possibility that erroneous diagnosis is performed.
However, in the field of clinical medicine, it is impossible to perform a completely correct diagnosis in the first place, and it is necessary to make a correct diagnosis as much as possible by making a comprehensive judgment based on information obtained from various diagnosis support devices. In such a point, the biological tissue evaluation method according to the present invention has a sufficient industrial value as a technology that enables a computer to be used as a diagnosis support device.

Next, the concept of the basic method used in the present invention will be described with reference to FIG. The feature of the present invention utilizes the environmental adaptability of a virtual creature having a predetermined gene,
The point is that a technique of extracting the characteristics of the texture (picture pattern) expressed on the image of the biological tissue is employed. Now, consider a state in which a virtual environment as shown in FIG. 3A is defined, and a large number of virtual creatures are distributed on this virtual environment. Each virtual creature is given a predetermined gene. Here, three types of genes X, Y, and Z are defined. In the initial state, a total of nine virtual creatures are generated, three virtual creatures have gene X, and three virtual creatures have gene Y. Suppose that three virtual creatures have gene Z. The genes X, Y, and Z indicate some parameters that affect the survival of each virtual creature, and serve as indices indicating what environmental conditions each virtual creature is sensitive to.

For example, it is assumed that the gene X is a parameter of temperature, the gene Y is a parameter of humidity, and the gene Z is a parameter of atmospheric pressure. The value of the parameter indicated by the gene in the environment of the occurrence position is given to each virtual creature as a latent parameter. As a specific example, the virtual creature having the gene X will be given the temperature at each occurrence position as a latent parameter.
Latent parameter values such as C, 30 ° C, 4 ° C will be provided. In other words, the virtual creature having the gene X is sensitive to the environmental condition of temperature, and the temperature environment at the place where it is born is the environment most suitable for its own survival. For a virtual creature having this gene X, the humidity environment and the atmospheric pressure environment are irrelevant to its own survival. On the other hand, the virtual creature having the gene Y is given the humidity at each occurrence position as a latent parameter. For example, humidity 80%, 15%, 60
A latent parameter value such as% will be given.
In other words, the virtual creature having the gene Y is sensitive to the environmental condition of humidity, and the humidity environment at the place where it is born is the environment most suitable for its own survival. For a virtual creature having this gene Y, the temperature environment and the atmospheric pressure environment are irrelevant to its own survival.

Subsequently, these virtual creatures are moved by a predetermined distance, and it is determined whether or not the environment after the movement is suitable for their own living environment. Movement consumes energy, but if the environment after the move is suitable for its own living environment, feed and increase energy. If the environment after the transfer is not suitable for one's own living environment, no food is provided and only energy is consumed. For example, a virtual creature having a gene X indicating that it is sensitive to temperature and given a temperature of 18 ° C as a latent parameter will receive food if the temperature environment after movement is around 18 ° C. And a gene Y indicating sensitivity to humidity.
The virtual creature given 0% has a humidity environment of 80 after moving.
If it is around%, you will get food.

In this way, the virtual creatures that have repeatedly traveled and have consumed their energy without receiving food die, and the virtual creatures whose energy has been increased by receiving food are:
When processing to generate offspring having the same gene is performed, as shown in FIG. 3 (b), the number of virtual creatures having one specific gene increases and another has another specific gene. The population of virtual creatures is decreasing, and finally, Fig. 3 (c)
Stabilizes in the state shown in In the illustrated example, the gene X
The virtual creature with the gene Y has become extinct, the virtual creature with the gene Y has prospered, and the virtual creature with the gene Z has barely survived. Therefore, if a histogram is created in which the genes X, Y, and Z are plotted on the horizontal axis and the frequency is the number of living virtual creatures, the histogram shows quantitative characteristics of the virtual environment. In this example, there is no living environment related to the parameter “temperature” represented by the gene X, but the survival environment related to the parameter “humidity” represented by the gene Y tends to be prepared. This is shown as an objective histogram.

However, since the object of the evaluation method according to the present invention is an image of a biological tissue, the gene to be given to each virtual organism is not represented by the above-mentioned factors such as temperature and humidity, but expressed on the image. An element indicating the characteristic of the texture thus obtained will be used. Hereinafter, a specific procedure of the evaluation method according to the present invention will be described.

§2. Specific evaluation method according to the present invention
Forward Here, the specific procedure of the biological tissue evaluation method using the image processing according to the present invention will be described with reference to the flow diagram of FIG. An object of the present invention is to perform a predetermined image processing on an image of a biological tissue to be evaluated by using a computer to obtain a histogram quantitatively indicating a feature of a texture on the biological tissue image. The steps shown in the flowchart of FIG. 4 are executed using a computer.

First, in step S1, H parameters are defined. The parameters defined here may be any parameters as long as they indicate the characteristics of the texture expressed on the image as numerical values. In general, as such a parameter, a parameter indicating a density value distribution of each pixel forming an image is used. For example, when a biological tissue image as shown in the upper part of FIG. 5 is handled by a computer, the image is taken into the computer as a set of a large number of pixels arranged vertically and horizontally. The following method is used to quantitatively evaluate the characteristics of the texture in the vicinity of a specified point in the biological tissue image thus captured. Here, as an example, in order to quantitatively evaluate the features of the texture at the designated point positions indicated by crosses on the biological tissue image shown in the upper part of FIG. An area consisting of × 5 pixels is considered as a reference area for the specified point. As described above, since the image data taken into the computer is composed of a large number of pixels, it is composed of a set of 25 pixels as shown in the lower part of FIG. Reference areas can be defined. The pixel at the center indicated by the bold frame is the pixel corresponding to the position of the designated point. Here, an area including all 25 pixels including the surrounding area is set as the reference area. It may be a reference area.

Each pixel has a predetermined density value.
In the example shown in FIG. 5, it is assumed that the input biological tissue image is a monochrome image, and the density value of the i-th pixel is Q
(I). Normally, the density value of a pixel has a predetermined gradation. For example, when gradation is expressed by 8 bits, the number of gradations is L = 256. In this case, each pixel takes one of the density values Q from 0 to 255. Specifically, five parameters as shown in FIG. 6 are known as parameters that quantitatively express the characteristics of the texture composed of such a gradation image. That is,
Mean (Ave.), variance (Var.), Energy (E
ngy. ), Entropy (Ent.), And contrast (Cont.). Since these parameters are widely used in the field of image processing by a computer, detailed descriptions thereof are omitted, but the values of the parameters are mathematically defined by the illustrated equations. Here, Qa,
Qv, Qn, Qe, and Qc denote parameter values of average, variance, energy, entropy, and contrast, respectively. L on the right side of the equation is the number of gradations of the density value (L = 256 in the above example); Q is the density value of each pixel (Q = 0 to 255 in the above example), M is the total number of pixels in the reference area (M = 25 in the above example), and N (Q) is the reference area. , The number of pixels having the density value Q, P (Q) is the probability of taking the density value Q in the reference area (here, P (Q) = N
(Calculated as (Q) / M). Note that the energy (Energy.) Shown here is a parameter indicating the texture characteristic, and is different from the energy indicating the survival state of each virtual creature.

The process of step S1 in the flowchart of FIG. 4 is a process for defining such parameters. In the embodiment shown here, in this step S1, FIG.
, The mean (Ave.), the variance (Var.),
Energy (Engy.), Entropy (En)
t. ) And contrast (Cont.) (H =
It is assumed that the parameter of 5) is defined.

Subsequently, in step S2, an input process of a biological tissue image to be evaluated is performed. As a method for obtaining a two-dimensional image from actual biological tissue, a method using hematoxylin and eosin staining is known. A microscope image of biological tissue stained with hematoxylin and eosin is converted into digital data through a CCD camera or the like. By performing the processing for capturing as, a biological tissue image can be prepared in a computer as two-dimensional array data of a large number of pixels.

Next, in step S3, a large number of energy values having a predetermined energy value (for indicating a living state and different from the energy (Energy.) Which is one of the above-mentioned parameters) are provided. Is generated so as to be distributed on the biological tissue image input in step S2. Of course, the generation of this virtual creature is performed as a simulation on a computer, and in practice, as shown in FIG. 7, in the XY two-dimensional coordinate system to which the biological tissue image is input, predetermined coordinate values ( x, y) are defined, and under the assumption that one virtual creature exists at a position corresponding to this coordinate value, the following processes will be performed (in FIG. 7, each virtual creature is The position is indicated by a cross). In the embodiment shown here,
Coordinate values (x, x, y) are used so that a large number of virtual creatures are distributed as uniformly as possible on the biological tissue image.
y) is defined at random.

In the following step S4, step S3
In step S5, a gene is defined for each virtual creature generated in step S5, and latent parameters are defined based on a peripheral image of the generation position of each virtual creature. FIG. 8 is a diagram showing data defined for each virtual creature at the stage after steps S3, S4, and S5. Here, the “position coordinates” are coordinate values (x, y) defined at the stage of generating the virtual creature in step S3. As described above, since each virtual creature is generated at a random position on the biological tissue image, a random value is defined for each of the “position coordinates” as the value of the “position coordinates”. . In step S6 to be described later, each virtual creature moves, but the “coordinate position”
Is data indicating the position of the virtual creature at the present time, so that the value will change successively by moving later. The “energy value” is a value indicating the survival state of each virtual creature, and a predetermined initial energy value is defined for each virtual creature at the stage when the virtual creature is generated in step S3. In this embodiment,
When each virtual creature is generated, a uniform energy value of 1000 is given. Therefore, as shown in FIG. 7, each virtual creature generated on the biological tissue image initially has 100
It has an energy value of zero. As will be described later, this energy value is consumed by the movement, but may gradually be changed depending on the environment after the movement, because new energy may be taken.

The “gene” is selected from among h parameters (h ≦ h) selected from the H parameters defined in step S1.
H) indicates a combination of the parameters, and should be an index indicating what parameters the individual virtual creatures are sensitive to the environment associated with. In the embodiment shown here, five parameters (H = 5) as shown in FIG. 6 are defined. “Gene” is an index indicating which parameter is selected and combined from the five parameters. There are a total of 31 combinations for selecting one or more objects from the five types of objects, but in this embodiment, only combinations for selecting three or more objects are defined as “genes”. I have. FIG. 9 is a table showing the genes thus defined. Combination of three parameters selected from all five parameters (h / H = 3/5)
Is a combination of four parameters (h / H = 4/5) selected from ten kinds of five kinds of parameters, and five types of parameters selected from five kinds of all five kinds of parameters. One combination (h / H = 5/5) is defined, and a total of 16 types of genes are defined, and each gene is represented by 4-bit data. For example,
Gene “0000” has a mean (Ave.) and a variance (Va.
r. ), Energy (Engy.), And the combination of three parameters is shown.
Mean (Ave.), variance (Var.), Energy (E
ngy. ) And entropy (Ent.).

As described above, the gene according to the present invention should be used as an index indicating what parameters each virtual creature is sensitive to the environment associated with. For example, a virtual creature having the gene “0000” is sensitive to the environment related to three parameters of average (Ave.), variance (Var.), And energy (Energy.). If the environment related to is not significantly changed, it is possible to fully adapt to the new environment and to ingest food (energy). Conversely, if the environment related to these three parameters changes significantly, it will not be able to adapt to the new environment,
Food (energy) can no longer be taken and eventually die. In other words, the virtual creature with the gene “0000” is indifferent to the environment related to the parameters of entropy (Ent.) And contrast (Cont.), And even if these two parameters change due to movement, It has no effect on energy consumption or intake.

After all, in step S4, a process of giving one of the 16 genes shown in FIG. 9 to each virtual creature generated in step S3 is performed. In the present embodiment, a gene is determined completely at random using random numbers, and given to each virtual creature. Therefore, each of the virtual creatures is given one of the genes “0000” to “1111” shown in FIG. 9 with a probability of 1/16.

The latent parameter values defined in step S5 for each virtual creature are H (five in this example) parameter values for the peripheral image of the generation position of each virtual creature. The value indicates the environment in which the virtual creature was born. Specifically, for each virtual creature, a peripheral image of the generation position (for example, FIG.
, The average (Ave.) and the variance (Va) of an image composed of 5 × 5 pixels centered on the generation position
r. ), Energy (Engy.), Entropy (E
nt. ) And the calculated value of the contrast (Cont.) Are the latent parameter values of the virtual creature. Here, the latent parameter values are represented as Qa, Qv, Qn, Qe, and Qc. However, in the case of the embodiment described here, it is not necessary to determine the five parameter values Qa, Qv, Qn, Qe, and Qc for all the virtual creatures, and at least h parameter values indicated by the genes It is sufficient to determine as a latent parameter value. For example, for a virtual creature given the gene “0000”, the mean (Ave.), variance (Var.),
Since only three parameter values of energy (Engy.) Affect the survival, it is sufficient to determine only the three parameter values Qa, Qv, and Qn as latent parameter values. However, as described below,
When handling taking into account the element of "gene mutation", the gene may be changed later, so for all virtual creatures, all five types of parameter values are obtained as latent parameter values. To keep.

Thus, steps S3, S4, S in FIG.
By performing each of the steps 5, “position coordinates”, “energy values”, “genes”, and “latent parameter values” are defined for each virtual creature, as shown in FIG. . Subsequent processes in steps S6, S7, and S8 are processes performed for each of these virtual creatures, and are processes that are repeated several times after step S9.

First, the process of step S6 is a process of moving all the living virtual creatures at that time on the biological tissue image and determining the energy consumption value consumed by this movement. In this embodiment, a random moving method based on random numbers is adopted as a moving method of the virtual creature. Specifically, as shown in FIG. 10, a region of 7 × 7 = 49 pixels is taken as a movement range around a virtual creature of interest as a movement target, and any one of these 49 pixels is moved. The method of determining at random is adopted first. However, as the pixels to be moved, pixels at the current position (black circled pixels in the figure) and pixels in which other virtual creatures exist (open triangled pixels in the figure) are avoided. Of course, when all other pixels are occupied by other virtual creatures, the pixel at the current position is set as the destination pixel (substantial movement has not been performed). Further, in the case of this embodiment, no matter what kind of movement is performed (even if no movement is performed), the energy consumption value due to the movement is uniformly set to 300. The new position of the virtual creature after the movement is recorded by updating the data of “position coordinates” shown in FIG.

In the present embodiment, all the virtual creatures are moved at all at random. However, each virtual creature is defined with a unique movement behavior in advance, and the movement processing is performed according to the movement behavior. You can also. For example, each virtual creature defines the front, rear, left, and right directions, and virtual creatures have the habit of going straight as far as possible, and virtual creatures have the habit of rotating clockwise. May be determined.
In the example shown in FIG. 10, the destination is limited to a range of 7 × 7 = 49 pixels, but the destination can be set arbitrarily. However, if a pixel moves to an extremely distant pixel by one movement, the probability of death of the virtual creature increases due to a significant environmental change, and all the virtual creatures may be extinct. It is preferable to set so as not to become too large.

The process in the next step S7 is a process for determining whether or not the environment after the movement of the virtual creature is suitable for the virtual creature to survive. As described above, for each virtual creature, a latent parameter value is defined as the environment of the place where the user was born. Step S7
Then, a process of comparing the current environment parameter value indicating the environment after the movement with the latent parameter value and determining an intake energy value to be taken by the virtual creature based on the similarity between the two is performed. However, each virtual creature has a gene,
Only the parameters indicated by this gene will be compared. That is, for the peripheral image after the movement of the virtual creature, the values of the h kinds of parameters indicated by the genes of the virtual creature are obtained as the current environment parameters (the pixel corresponding to the position after the movement is defined as the central pixel,
For example, as shown in the lower part of FIG. 5, 25 pixels may be extracted, and h necessary parameter values may be obtained for these pixels.) H potential parameter values and h current environment parameter values The intake energy value to be taken by the virtual creature is determined based on the similarity.

For example, in the case of a virtual creature to which the gene “0000” has been given, h
As shown in FIG. 9, the different parameter values are the average (A
ve. ), Dispersion (Var.), Energy (Eng)
y. ), There are three parameter values (h = 3), so it is sufficient to compare only these three parameter values. Now, the latent parameter values of this virtual creature are Qa (average), Qv (variance), and Qn (energy), and the current environment parameter values calculated for the peripheral image after moving are QQa (average) and QQv (variance). ), QQn (energy), Qa and QQa, Qv and QQv, and Qn and QQn may be compared with each other.

In short, 5 which can be a latent parameter value
If one parameter value is denoted as Qa, Qv, Qn, Qe, and Qc, and five parameter values that can be current environment parameter values are denoted as QQa, QQv, QQn, QQe, and QQc, as shown in FIG. , The similarity between the latent parameter value and the current environment parameter value is determined only for the h parameters selected based on the gene from all five parameters. Since each parameter value is represented as some numerical value, the similarity can be determined based on the closeness of the parameter value. The similarity of the parameter values can be determined based on the difference between the two, or can be determined based on the ratio between the two. That is, it can be determined that the smaller the difference or ratio between the two is, the higher the approximation is.

The purpose of step S7 is to determine an energy value to be taken by the virtual creature based on the similarity thus obtained. The evaluation of the similarity of the parameter values to be considered can be performed by, for example, a very similar, fairly similar, slightly similar, slightly similar, dissimilar grade evaluation. If the degree of similarity is greater,
Larger intake energy values can be determined. However, the process of determining the intake energy needs to be performed separately for each virtual creature, and needs to be performed every time each virtual creature moves. Therefore, when a simulation is performed by moving a large number of virtual creatures many times, if the calculation of the similarity requires a complicated calculation, the entire calculation load becomes enormous. In particular, as described in §3, when the tissue image is a color image, the computational load becomes considerably heavy.

Therefore, in this embodiment, only two similarities, “similar” or “not similar”, are defined by the following simple method, Sets the energy intake to 1200 and dissimilar
When it was determined that the intake energy value was 0.
Which of the two similarities is defined by two similarities of “approximate” or “not approximate” for each of the h parameter values determined by the gene (for example, the difference between the parameter values). Is approximated only when is within a predetermined value), and the latent parameter value and the current environment parameter value are determined to be “similar” only when it is determined that all the h parameter values are “approximate”. And the energy intake is set to 1200 and h
If it is determined that even one of the parameter values is "not approximate", the latent parameter value and the current environment parameter value are determined to be "dissimilar" and the intake energy value is set to 0. I have to.

For example, in the case of a virtual creature having the gene "0000", Qa of the parameter values shown in FIG.
If all three comparison results of QQa, Qv and QQv, and Qn and QQn are determined to be “approximate”, the intake energy value is 1200, but if any one is determined to be “not approximate”, Means that the intake energy value is 0.

In step S8, a process of killing or multiplying by increasing or decreasing the energy is performed for each virtual creature. That is, since the consumed energy is determined in step S6 and the intake energy is determined in step S7, the energy value is reduced by adding the intake energy value to the energy value of the virtual creature. Will be updated. In the case of this embodiment, regardless of the presence or absence or form of movement, the energy consumption is uniformly 300, and based on the similarity of the parameters indicated by the genes,
Since the intake energy of 1200 or 0 is to be given, it is eventually determined in step S7 that the latent parameter and the current environment parameter are “similar” (in other words, regarding the parameter indicated by the gene, , The judgment that the current environment is similar to the environment in which it was born)
Is obtained, the energy value of the subtraction 900 is added, and if it is determined that “not similar”, 30 is obtained.
An energy value of 0 will be reduced.

The processes in steps S6, S7, and S8 are repeatedly executed until the end condition in step S9 (for example, whether a predetermined number of repetitions has been exceeded) is satisfied. As a result, each virtual creature moves around on the biological tissue image, and updates the energy value each time. Therefore, in step S8, if the updated energy value reaches the predetermined lower limit, the virtual creature is removed as being dead, and if the updated energy value reaches the predetermined upper limit, A process of generating a plurality of new virtual creatures having the same gene as that of the virtual creature will be performed. Specifically, virtual creatures whose updated energy value has reached the lower limit value 0 are removed as dead, and virtual creatures whose updated energy value has reached the upper limit value 2000 are assumed to be the same as those having proliferated. Are replaced with two new virtual creatures (the initial energy value is 1000) having the above gene.

Next, a specific embodiment relating to the processing for killing / proliferating virtual creatures performed in step S8 will be described. As described above, whether to perform the process of killing / proliferating the virtual creature is determined based on the energy value remaining in the virtual creature at that time. That is, when the energy value updated by reducing the energy consumed by the movement and adding the intake energy given based on the similarity of the parameter reaches a predetermined lower limit (for example, 0), it is regarded as dead. , When it reaches a predetermined upper limit (for example, 2000), it is determined that it has proliferated. As described above, when the killing / proliferation process is performed based only on the updated energy value, as long as the energy value fluctuates between the upper limit value and the lower limit value, neither the death nor the proliferation occurs. It will be a halfway state. Of course, virtual creatures that maintain such an incomplete state are expected to eventually settle into either a state of death or proliferation, but in practice, after a certain number of movements, If a virtual creature that remains in a half-finished state is positively removed, a stable result can be obtained more quickly.

From such a viewpoint, it is actually preferable to adopt the concept of death based on the number of times of movement in addition to the death based on the energy value. Specifically, the age is defined for each virtual creature, and step S9 in FIG.
(In other words, every time the procedure of steps S6 to S8 is repeated), the age of each virtual creature is increased, and the virtual creature whose age has reached a predetermined life is removed as dead. What is necessary is just to add processing which performs. For example, the age of the virtual creature at the time of occurrence is assumed to be 0 years old, and the age of 1 year old is increased every time through step S9.
The virtual creature that has reached the age of 80 may be removed as being dead. When the concept of lifespan is adopted in this way, each virtual creature may die due to its energy value reaching a lower limit (so-called starvation) or may die due to its age reaching its life-span (so-called old death). As a result, as described above, it is not possible to continue living for a long period of time in an incomplete state.

Next, a specific multiplication process will be described.
The breeding process is a process for increasing the number of virtual creatures whose updated energy value has reached a predetermined upper limit value (2000 in this example), and is a new virtual creature having the same gene as the virtual creature. Any method may be used as long as it can be generated in the vicinity. In the present embodiment, the multiplication process is performed by the following method. That is, when growing a virtual creature, the parent virtual creature to be multiplied is removed and a plurality of new child virtual creatures are generated in the vicinity thereof, and the child virtual creature has a predetermined initial energy. In addition to giving the value, the same gene as that of the parent virtual creature is given.

For example, as shown in FIG. 12, consider the case where the i-th virtual creature G (i) indicated by a black circle has become the parent virtual creature to be multiplied (in the above example, this virtual creature G (i)). This means that the updated energy value of G (i) has reached 2000). In this case, the parent virtual creature G
It is assumed that (i) is divided into two and multiplied, and the virtual creature G (i) as the parent is removed, and the (i +)
1) The virtual creatures G (i + 1) a and G (i + 1) b of the next generation are generated. At this time, an initial energy value of 1000 is given to each of the virtual creatures G (i + 1) a and G (i + 1) b as children (or
When the energy value of the virtual creature G (i) as the parent exceeds 2,000, half of the value may be used as the initial energy value of the child.
Further, each virtual creature G (i + 1) a, G (i +
1) The gene possessed by the parent virtual creature G (i) is given to b as it is.

As described above, two offspring that inherit the parent gene as they are are generated, and the generation positions of these two offspring are randomly determined on any pixel near the parent. do it. However, pixels in which other virtual creatures (indicated by triangles) already exist are avoided. In the example shown in FIG. 12, a neighborhood of 7 × 7 pixels is defined centering on the pixel where the parent exists, and is placed on any pixel in this neighborhood (but on a pixel where no other virtual creature exists). , So that children are created. Here, an example in which one parent is split into two children has been described, but it is needless to say that three or more children may be split. In the above-described example, the parent is removed after the multiplication, but, of course, the parent is left as it is (in this case, for example, processing such as returning the energy value to the initial value will be required). ), It is possible to generate new offspring and multiply in such a way that parents and offspring coexist.

When the multiplication process as described above is performed,
Since the child inherits the gene of the parent as it is, the environment in the vicinity of the generation position is generally a favorable environment adapted to the child. Therefore, a certain portion of the biological tissue image has a tendency that virtual creatures having genes suitable for the environment are increasingly proliferated. However, if the descendants of a virtual creature with a certain gene always keep the same gene as the parent, the gene will lose diversity.
In some cases, all offspring may become extinct. Therefore, in practice, when a gene is transmitted from a parent to a child, it is preferable to cause a mutation in the gene held by the parent virtual creature with a predetermined probability. For example, if the probability of mutation is set to 10%, when a gene is inherited in a child, up to 9 out of 10 times are inherited as they are, but once out of 10 times, the gene is randomly inherited. You will have to change and then inherit.

The latent parameter value of the virtual creature generated as a child may be set so as to take over the latent parameter value of the parent as it is. May be determined, and this may be defined as the latent parameter value of the child.

In the embodiments described above,
The latent parameter value of each virtual creature has been treated as being unchanged at the value defined at the time of occurrence of the virtual creature. However, in practice, the value defined at the time of occurrence (obtained for the surrounding image of the occurrence position) If the similarity between the current environment parameter and the latent parameter value obtained after the movement is obtained to some extent (specifically, in the case of the above example, the intake energy value 1200 is used as the initial value). If it is obtained), it is preferable to perform an update process that brings the value of the latent parameter closer to the current environment parameter. Such an updating process may be performed together with the process of step S8 in the flowchart shown in FIG. 4, for example. As described above, if the update process for the latent parameter value of each virtual creature is performed at each movement, the latent parameter value gradually changes according to the environment, and the survival probability of each virtual creature is further increased. be able to.
In other words, each virtual creature gains environmental adaptability as it walks through various places, and while the environment at the point of birth was initially the optimal environment for itself, The optimal environment (latent parameter values) will change.

For example, it is assumed that the latent parameter values of the virtual creature having the gene “0000” are Qa, Qv, and Qn, and the current environment parameter values at the point where the virtual creature has moved are QQa, QQv, and QQn. Try. In this case, in step S7, the similarity between the two parameter values is determined. If the two are determined to be similar, the intake energy value 1200 is given. It becomes 0. Here, when both are dissimilar, the latent parameter values of the virtual creature remain Qa, Qv, and Qn. However, if they are similar, an update process is performed to bring the latent parameter values Qa, Qv, Qn of the virtual creature closer to the current environment parameter values QQa, QQv, QQn, respectively. Specifically, the average value of both is taken and (Qa +
QQa) / 2, (Qv + QQv) / 2, (Qn + QQ
An update process may be performed to make n) / 2 a new latent parameter value.

When the processes of steps S6 to S8 are repeatedly executed until a predetermined termination condition (for example, a predetermined number of times) is satisfied, a virtual creature having a specific gene becomes extinct and another specific creature is extinguished. Virtual creatures with genes will prosper. Therefore, in step S10, a histogram of genes for virtual living organisms finally living on the biological tissue image is created. FIG.
FIG. 1 shows an example of such a histogram. On the horizontal axis,
Sixteen types of genes are shown, and the vertical axis shows the frequency of each gene (final number of virtual organisms having each gene). The fact that the frequency of a specific gene is zero (there is no bar graph) indicates that the virtual creature having the gene has become extinct. This histogram is a material that gives a quantitative evaluation to the features of the biological tissue image input in step S2.

Of course, it cannot be argued that each gene shows what kind of characteristic of a biological tissue image. However, for example,
According to the histogram of FIG. 13, a large number of virtual creatures having the gene “0111” are alive on the biological tissue image, and this indicates that the variance (Va
r. ), Energy (Engy.), Contrast (C
ont. ) Indicates that a region having a certain area having similarity when presently considering three parameters (see FIG. 9) is present on the biological tissue image. In addition, on this biological tissue image, it is shown that the virtual creature having the gene “1111” has been extinct, but this is similarity when all five parameters are comprehensively considered. This indicates that the region having a certain area having no is not present on the biological tissue image.

In any case, one histogram as shown in FIG. 13 is obtained for one biological tissue image, and this histogram functions as a material for quantitatively evaluating the biological tissue image. Will do. Therefore, if a histogram is obtained for a large number of biological tissue images obtained clinically and each case is attached and stored as a database, this database can be used for diagnosis based on biological tissue images. And will provide valuable information. For example, by obtaining a histogram according to the present invention for a biological tissue image obtained from a specific specimen and searching a database for a histogram similar to the histogram, a similar case in the past can be found.

§3. When the tissue image is a color image
Embodiment In the above-described §2, an example in which the tissue image is a monochrome image has been described, but actually, a more accurate result can be obtained by using a color tissue image. Therefore, here, a method of handling each parameter when a color tissue image is used will be briefly described.

In this case, the biological tissue image input in step S2 of FIG. 4 is a color image. Normal,
A color image on a computer is handled as density value data for each color component of the three primary colors. Therefore, as parameters indicating the characteristics of the texture of each tissue image,
A parameter relating to the density value for each of the three primary color components (here, three primary colors of red R, green G, and blue B) of each pixel in the predetermined reference area may be used. For example, as shown in FIG. 14, a density value is defined for each color component of the three primary colors in each pixel constituting a reference area composed of 5 × 5 pixels. Here, Qr (i), Qg
(I) and Qb (i) indicate the density value of the red component, the density value of the green component, and the density value of the blue component of the ith pixel, respectively. Therefore, the five types of parameters shown in FIG. 6 may be obtained separately and independently for each of these color components.

As described above, when a color image is used as a biological tissue image, both the latent parameter value and the current environment parameter value become the parameter values related to the color image. As shown in Table 15, it is necessary to compare parameter values for each color. For example, the average (Ave.)
Parameter, the latent parameter value is
The parameter value Qra for the red component, the parameter value Qga for the green component, and the parameter value Qba for the blue component are obtained. Similarly, as the current environment parameter value,
The parameter value QQra for the red component, the parameter value QQga for the green component, and the parameter value QQba for the blue component are obtained.

In order to determine the similarity regarding the parameter values for each of the three color components obtained in this way, in the present embodiment, the angle difference between the three-dimensional vectors defined based on the parameter values for each of the color components is used. ing. For example, when comparing average (Ave.) parameter values, first, based on three primary color parameter values Qra, Qga, and Qba, which are latent parameter values, FIG.
A three-dimensional vector V (Ave.) as shown in FIG. The three-dimensional vector V (Ave.) is represented by RG indicating the density values of the three primary colors R, G, and B as coordinate axes.
B is a vector defined on the three-dimensional coordinate system, and the origin O
And a vector connecting the point Q (Ave.). here,
The point Q (Ave.) has coordinate values (Qra, Qga, Qb).
The point at the position represented by a). Similarly, three primary color parameter values QQra, QQga,
Based on QQba, a three-dimensional vector VV (Ave.) as shown in FIG. 16B is defined. The three-dimensional vector VV (Ave.) is also a vector defined on an RGB three-dimensional coordinate system in which the density values of the three primary colors R, G, and B are indicated as coordinate axes, respectively, and the origin O, the point QQ (Ave.) Is a vector connecting. Here, the point QQ (Ave.)
Is a point at a position represented by coordinate values (QQra, QQga, QQba).

When two vectors V (Ave.) And VV (Ave.) Can be defined for the average (Ave.) parameter in this manner, the angle difference θ ( Ave.)
The angle difference θ (Ave.) is a value indicating similarity in consideration of the three color components (the smaller the angle difference, the higher the similarity). Similarly, the variance (Va
r. ), Energy (Engy.), Entropy (E
nt. ) And contrast (Cont.) Are defined as three-dimensional vectors, respectively, and the angle difference θ (Va
r. ), Angle difference θ (Engy.), Angle difference θ (En
t. ) And the angle difference θ (Cont.).
FIG. 17 shows an example in which the angle difference is obtained for each of the five types of parameters.

The similarity between the latent parameter value and the current environment parameter value may be determined based on the h angle differences indicated by the genes among the five angle differences. As described above, it is possible to quantitatively evaluate the similarity and determine the value of the intake energy according to the quantitative value.However, in the case of the embodiment shown here, in order to reduce the calculation load, As the similarity evaluation, only two types, “similar” and “dissimilar”, are prepared. In the case of “similar”, the intake energy value is set to 1200 and “dissimilar”
In this case, the intake energy value is set to 0. In this embodiment, the following handling is performed in order to perform two types of evaluations. First, a value of 5 ° is determined as a threshold value of the angle difference θ. If the angle difference θ is less than 5 °, the parameter is determined to be “approximate”, and the angle difference θ is 5 ° or more. In this case, it is determined that the parameter is “not approximate”. Such determination is performed for each of the h parameters indicated by the genes, and when it is determined that all parameters are “approximate”, the latent parameter value and the current environment parameter value are determined to be “similar”. What should be done is.

§4. Assemble virtual creatures in the nuclear region
In the embodiments described above, as shown in FIG. 7, virtual creatures are generated so as to be distributed over the entire region of the biological tissue image,
The simulation was performed by freely moving these virtual creatures, and finally, a histogram of the genes of the surviving virtual creatures was created on this biological tissue image. The histogram thus obtained basically indicates the texture characteristics of the entire region of the given biological tissue image. However, as shown in the examples of mammary gland tissue images shown in FIGS. 1 (a) and 1 (b), a general biological tissue has a cell nucleus region, and it is determined whether the tissue is a normal tissue or a cancerous tissue. The difference is noticeable in the texture properties of this cell nucleus region. Therefore, when diagnosing whether a tumor in a biological tissue is benign or malignant, it is preferable to obtain information on the texture characteristics of the inside of the cell nucleus region.

In order to obtain only the information in the cell nucleus region as a histogram, the final step of creating the histogram (FIG. 4)
In step S10), it is sufficient that virtual creatures (existing at positions indicated by crosses in the figure) are assembled in the cell nucleus region as shown in FIGS. 18 (a) and 18 (b). The histograms created based on the virtual creature distributions as shown in FIGS. 18 (a) and 18 (b) show the information on the texture characteristics of the hatched cell nucleus regions in FIGS. 19 (a) and 19 (b). Will be.

The inventor of the present application has found that there is a lightness difference between the cell nucleus region and the other regions.
At the time of occurrence in step S3, as shown in FIG. 7, even if virtual creatures are dispersed in the entire region of the biological tissue image, at the last stage of the simulation, that is, at the time of creating a histogram in step S10 in FIG.
As shown in FIG. 18 (a), it has been noticed that the virtual creature can be distributed only in the cell nucleus region of the biological tissue image. That is, focusing on the brightness of each region, the brightness value of the cell nucleus region tends to be smaller than the brightness values of the other regions. In other words, the cell nucleus region
Generally, the area is darker than other areas. Therefore, the brightness value is obtained for the peripheral image after the movement of each virtual creature, and the energy value of the virtual creature or the energy value ingested by the virtual creature is calculated for a certain percentage of the virtual creatures in order of decreasing brightness value. By performing the process of decreasing, the probability that a virtual creature that has moved to a region with a large brightness value will die increases, and consequently, the surviving virtual creatures gather in a region with a small brightness value (that is, a cell nucleus region). Become. In the embodiment shown here, for a certain percentage of virtual creatures in order of decreasing lightness value, a process of reducing the energy value is performed to an extent sufficient for the virtual creatures to die, and virtual creatures outside the cell nucleus region are removed. It is thinning out.
Thus, every time the processing of steps S6 to S8 in FIG. 4 is performed once, a certain percentage of virtual creatures will surely die.

Specifically, the following method may be adopted. First, when performing the death or multiplication process shown in step S8, the brightness value of the biological tissue image around the existence position of each virtual creature is obtained. The brightness value can be calculated based on the density value of each pixel. Then, as shown in the table of FIG. 20, all the virtual creatures are sorted in descending order of the brightness values, and a process of immediately reducing the energy value to 0 is performed for the virtual creatures corresponding to the upper fixed ratio, and the virtual creatures are killed. To do. For example, assuming that the number of all the virtual creatures is K, it is determined that the processing to reduce the energy value is performed on the virtual creatures corresponding to the ratio of 50%.
Based on the table of 0, the total (K) from the virtual creature with the largest brightness value to the (K / 2) th virtual creature
/ 2) A process of reducing energy is performed on one virtual creature to kill it.

If the top 50% of the virtual creatures are killed in each movement, many of the virtual creatures that have moved to regions other than the cell nucleus region will die. All virtual creatures are distributed within the cell nucleus region as the movement is repeated. Normally, it is sufficient to perform the thinning process based on the lightness value several times after the start of the simulation. Even after the virtual creatures are distributed in the cell nucleus region, if such thinning processing based on the brightness value is performed, the virtual creatures that should originally survive to the end are killed, which is not preferable. However, if the thinning process based on the brightness value is stopped, the virtual creatures that have gathered in the cell nucleus region may be dispersed to the outside region beyond the boundary of the cell nucleus region due to movement. Therefore, in practice, it is preferable to combine a process of lowering the survival probability of the virtual creature near the boundary of the region to suppress the phenomenon that the virtual creature flows out of the cell nucleus region beyond the boundary. .

More specifically, a near reference area centered on the location of each virtual creature and a distant reference area that includes the near reference area and extends its boundary to a further distance are defined. If the similarity between the near parameter value indicating the texture feature and the distant parameter value indicating the texture feature in the distant reference area is low, the energy value of the virtual creature or the energy value taken by the virtual creature May be further added.

For example, in the example shown in FIG. 21, a near reference area A1 composed of a 5 × 5 pixel area and a distant reference area composed of a 7 × 7 pixel area are centered on the pixel where the virtual creature shown by a black circle exists. An area A2 is defined. Therefore, a near parameter value indicating the feature of the texture in the near reference region A1 and a far parameter value indicating the feature of the texture in the far reference region A2 are obtained. This can be done by calculating the parameter values as shown in FIG. 6 using the density values of the pixels in each area. When the similarity between the near parameter value and the far parameter value is low, a process of reducing the energy of the virtual creature is performed.

In the example shown in FIG. 21, since a boundary as an image exists between the pixels in the second row and the pixels in the third row, the illustrated virtual creature exists near the boundary.
As described above, in the virtual creature near the boundary, the similarity between the near parameter value and the far parameter value obtained by the above-described method is reduced. For example, FIG.
In the example of (1), the calculation of the far parameter value is affected by the density values of the pixels located in the upper two rows, so that a value significantly different from the calculation result of the near parameter value is obtained. Thus, when the similarity between the near parameter value and the far parameter value is low, it is determined that this virtual creature exists near the boundary, and as described above,
What is necessary is just to perform the process which reduces a survival probability.

Although the biological tissue evaluation method using image processing according to the present invention has been described based on several embodiments, the present invention is not limited to these embodiments. Can be implemented in various forms. Further, some embodiments described so far may be executed in any combination. The biological tissue evaluation method using the image processing according to the present invention is based on the processing using a computer, and the procedure shown in the flowchart of FIG. 4 is executed by the computer. Therefore, in order for a computer to execute each of these procedures, a predetermined program is prepared, but the program may be recorded on a computer-readable recording medium such as a magnetic disk or an optical disk and distributed. It is possible, and it is also possible to transfer via a network.

[0076]

As described above, according to the evaluation method of the present invention, it is possible to quantitatively evaluate features by performing image processing using a computer on a two-dimensional image of a biological tissue. Become.

[Brief description of the drawings]

FIG. 1 is a diagram showing an example of images of normal breast tissue and cancerous breast tissue of an animal.

FIG. 2 is a diagram showing an example of a histogram created by using the present invention.

FIG. 3 is a model diagram illustrating a basic concept of the present invention for evaluating a biological tissue by simulation using a virtual creature.

FIG. 4 is a flowchart showing a basic procedure of a biological tissue evaluation method using image processing according to the present invention.

FIG. 5 is a diagram showing pixels constituting a general biological tissue image.

FIG. 6 is a diagram showing an example of parameter values defined in step S1 of the flowchart of FIG.

7 is a diagram showing a state in which a large number of virtual creatures have been generated in step S3 on the biological tissue image input in step S2 of the flowchart of FIG. 4;

FIG. 8 is a diagram showing data defined for each virtual creature used in the present invention.

FIG. 9 is a chart showing an example of a gene provided to a virtual organism used in the present invention.

FIG. 10 is a diagram showing a movement process in step S6 of the flowchart of FIG. 4;

FIG. 11 is a chart showing an environment evaluation process after movement in step S7 of the flowchart of FIG. 4;

FIG. 12 is a diagram showing a process of multiplying virtual creatures in step S8 of the flowchart of FIG. 4;

FIG. 13 is a diagram showing an example of a histogram finally obtained by using the gene shown in FIG. 9;

FIG. 14 is a diagram showing a color pixel configuration in a reference area defined near one point on a biological tissue image.

FIG. 15 is a table showing a comparison between latent parameter values and current environment parameter values for five parameters for each color component of three primary colors.

FIG. 16 is a diagram illustrating an example of a technique for performing similarity determination between a latent parameter value and a current environment parameter value for a parameter for each color component of three primary colors.

FIG. 17 is a diagram illustrating an example of a technique for performing a similarity determination between a latent parameter value and a current environment parameter value for five parameters for each color component of three primary colors.

FIG. 18 is a diagram showing a state in which virtual creatures are finally collected only in the cell nucleus region.

19 is a diagram showing a cell nucleus region from which information can be obtained from the virtual creature shown in FIG.

FIG. 20 is a diagram illustrating an example of a technique for reducing energy to a virtual creature having a large brightness value in a peripheral image after movement.

FIG. 21 is a diagram illustrating a procedure for recognizing a virtual creature located near a boundary of a region.

[Explanation of symbols]

A1: Near reference area A2: Far reference area Ave. ... Parameter indicating the average of the pixel values constituting the texture Cont. ... A parameter indicating the contrast of the pixel values constituting the texture. ... a parameter indicating the energy of the pixel value constituting the texture Ent. ... parameter G (i) ... i-th generation virtual creature G (i + 1) a, G (i + 1) b ... (i + 1) th generation virtual creature Var. .., Parameters Q (Ave.) And QQ (Ave.)... Vector end points Q (Cont.), QQ (Cont.)... Vector end points Q (Engy.), QQ (Engy.): Vector end point Q (Ent.), QQ (Ent.): Vector end point Q (Var.), QQ (Var.): Vector end point Q (1) to Q (25) ): Density value of each pixel Qb (1) to Qb (25): density value of blue component of each pixel Qg (1) to Qg (25): density value of green component of each pixel Qr (1) to Qr ( 25): Density value of red component of each pixel Qa, Qra, Qga, Qba... Average value (latent parameter value) of pixel values constituting texture of image around occurrence position Qc, Qrc, Qgc, Qbc. Texture Contrast values (latent parameter values) of pixel values to be formed Qn, Qrn, Qgn, Qbn... Energy values (latent parameter values) of pixel values constituting the texture of the image around the generation position Qe, Qre, Qge, Qbe. Entropy values (latent parameter values) of pixel values constituting the texture of the image Qv, Qrv, Qgv, Qbv... Dispersion values (latent parameter values) of the pixel values constituting the texture of the image around the generation position QQa, QQra, QQga, QQba ... Average value of pixel values constituting the texture of the moving position surrounding image (current environment parameter value) QQc, QQrc, QQgc, QQbc... Contrast value of the pixel value forming the texture of the moving position surrounding image (current environment parameter value) QQn , QQrn, QQgn, QQbn... Text of the image around the moving position Energy values (current environment parameter values) of pixel values constituting cha QQe, QQre, QQge, QQbe... Entropy values (current environment parameter values) of pixel values constituting the texture of the image around the movement position QQv, QQrv, QQgv, QQbv ... Variance value (current environment parameter value) of pixel values constituting the texture of the image around the moving position V (Ave.)... Vector V (Cont.) Representing the average of the pixel values constituting the texture of the image around the occurrence position. A vector V (Engy.) Indicating the contrast of the pixel values forming the texture of the position surrounding image. A vector V (Ent.) Indicating the energy of the pixel values forming the texture of the generating position surrounding image. A vector V (Var. )... Vector VV (Ave.) indicating the variance of the pixel values constituting the texture of the image around the occurrence position. Vector VV (Cont.) Indicating the average of the pixel values constituting the texture of the image around the movement position. VV (Energy.)... Indicating the contrast of the pixel values forming the texture of the moving position. VV (Ent.) Indicating the energy of the pixel values forming the texture of the moving position surrounding image. Vector VV (Var.) Indicating the entropy of the value. Vector X, Y, Z indicating the variance of the pixel values forming the texture of the image around the moving position. Gene .theta. (Ave.)... ) Angle difference between both vectors θ (Engy.) Angle difference between both vectors θ (Ent.) Angle difference between both vectors θ (V r.) angle difference between the two vectors

 ──────────────────────────────────────────────────続 き Continued on the front page F term (reference) 2G045 AA26 AA40 CB01 JA04 2G059 AA05 AA06 BB12 CC16 EE13 FF01 KK04 MM01 MM02 MM03 MM05 MM09 MM10 5L096 AA06 BA06 CA14 FA32 FA33 FA35 GA08 HA01 JA03 JA11

Claims (11)

[Claims] 1. A method for quantitatively evaluating characteristics of a biological tissue by subjecting an image of the biological tissue to be evaluated to predetermined image processing using a computer, wherein the method is expressed on an image. Defining a plurality of H types of parameters indicating the characteristics of the textures obtained as numerical values, inputting an image of a biological tissue to be evaluated, and providing a large number of virtual creatures having predetermined energy values on the input biological tissue image Generating, for each virtual creature, defining a gene indicating a combination of h (h ≦ H) parameters selected from the H parameters, and Of the H parameters indicating the characteristics of the texture of the peripheral image, at least h parameter values indicated by the genes are obtained, and these parameters are determined. (A) moving the virtual creature on the biological tissue image, and determining the energy consumption value consumed by this movement, (b) With respect to the peripheral image after the movement of the virtual creature, the values of the h kinds of parameters indicated by the genes of the virtual creature are obtained as the current environment parameter values, and the h potential parameters and the h kinds of the current environment parameter values are calculated. Based on the similarity, a process of determining an energy value to be taken by the virtual creature, (c) reducing the consumed energy value with respect to the energy value of the virtual creature, and adding the energy value to obtain the energy value. When the updated energy value reaches a predetermined lower limit, the virtual creature is removed as dead and removed, and the updated energy value is updated. If the value reaches a predetermined upper limit, a process of generating a new virtual creature having the same gene in the vicinity as that the virtual creature has multiplied, three processes (a), (b), and (c) Repeating a predetermined number of times, and a step of creating a histogram of genes for virtual living organisms finally living on the biological tissue image, wherein an organism using image processing Organization evaluation method. 2. The evaluation method according to claim 1, wherein a latent parameter value obtained for a peripheral image of a generation position of each virtual creature is set as an initial value, and a current environment parameter value and a latent parameter obtained for a peripheral image after movement are obtained. A biological tissue using image processing characterized by performing an update process on the value of the latent parameter so as to approach the current environment parameter value when similarity to the value is equal to or greater than a predetermined value. Evaluation method. 3. The biological tissue evaluation method according to claim 1, wherein a random number is used when generating a virtual creature, defining a gene for the virtual creature, and moving the virtual creature, and using a random number at a random position. A virtual creature with genes is generated,
A biological tissue evaluation method using image processing, wherein the biological tissue is moved at random. 4. The biological tissue evaluation method according to claim 1, wherein a brightness value is obtained for a peripheral image of each of the virtual creatures after movement.
For a certain percentage of virtual creatures in the descending order of the lightness value, a process for reducing the energy value of the virtual creature or the energy value taken by the virtual creature is further added. Organization evaluation method. 5. The biological tissue evaluation method according to claim 4, wherein, for a certain percentage of virtual creatures in descending order of lightness value, the energy value is reduced to an extent sufficient for the virtual creatures to die. A biological tissue evaluation method using image processing. 6. The biological tissue evaluation method according to claim 1, wherein a near reference area centered on a position after movement of each virtual creature, and a boundary including the near reference area and further extending a boundary thereof. Define a far reference region that has been extended to a near parameter value indicating a feature of the texture in the near reference region and a far parameter value indicating a feature of the texture in the far reference region when the similarity is low. Is a biological tissue evaluation method using image processing, further comprising a process of reducing the energy value of the virtual creature or the energy value of the virtual creature. 7. The biological tissue evaluation method according to claim 1, wherein the density of each pixel in a predetermined reference region is set as a plurality of H parameters indicating the characteristics of the texture of the biological tissue image as numerical values. A biological tissue evaluation method using image processing, wherein a plurality of parameters selected from the group consisting of average, variance, energy, entropy, and contrast of values are used. 8. The biological tissue evaluation method according to claim 1, wherein a color image is used as the biological tissue image, and a characteristic value of a texture of the biological tissue image is specified as a parameter value. Parameter values related to the density value of each of the three primary colors of each pixel in the reference region of each pixel are used, and the similarity between the parameter values is determined based on the angle of the three-dimensional vector defined based on the parameter values of each of the color components. A biological tissue evaluation method using image processing, wherein the biological tissue evaluation method is determined based on a difference. 9. The biological tissue evaluation method according to claim 1, wherein an age is defined for each virtual creature, and three processes are performed.
Each time (a), (b), or (c) is performed, the age of each virtual creature is increased, and virtual creatures whose age has reached a predetermined life are removed as dead. Biological tissue evaluation method using image processing. 10. The biological tissue evaluation method according to any one of claims 1 to 9, wherein a mutation is generated at a predetermined probability when a gene held by the parent virtual creature is inherited. A biological tissue evaluation method using image processing, characterized in that, when occurs, a gene is randomly changed and then inherited. 11. A computer-readable recording medium in which a program for causing a computer to execute each step constituting the biological tissue evaluation method using the image processing according to claim 1 is recorded.