JP2001094828A - Image processor, system and method for processing image and storage medium - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide an image processor capable of providing a fine gradation- converted image by executing suitable gradation conversion for an input image. SOLUTION: An area extraction means 111a extracts a prescribed area (subject area) from an input image (X-ray image). An average value preparation means 111b finds out the average pixel value of respective coordinate points in the 2nd direction (x-axis direction) of the prescribed area obtained by the means 111a in each of respective coordinate points in the 1st direction (y-axis direction). A position extraction means 111c acquires the coordinates (coordinates of a notice area) of an average pixel value having a prescribed value (maximum value or the like) out of average pixel values obtained by the means 111b and the average pixel value (feature vector). Then gradation conversion processing based on the feature vector is applied to the input image.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an image processing apparatus, an image processing system, an image processing method, and a method for performing a gradation conversion process on a photographed image using, for example, a feature amount extracted from the photographed image. The present invention relates to a storage medium in which processing steps for performing the above are stored in a computer-readable manner.

[0002]

2. Description of the Related Art Conventionally, for example, an X-ray image obtained by X-ray photographing a subject by a photographing device such as a camera having an image sensor is displayed and output on a monitor screen, or on an X-ray diagnostic film. In general, when an X-ray image is output, a gradation conversion process is performed on the X-ray image to convert the X-ray image into a density value that is easy to observe.

Specifically, when an X-ray image obtained by X-ray imaging of the cervical vertebrae is output on an X-ray diagnostic film,
A histogram of the entire X-ray image is created, and a density value (pixel value) of a certain portion (for example, a lower 5% point) of the histogram is extracted as a feature amount, and the feature amount (density value) is extracted.
Is a constant density value (for example, 1.0
) Is performed on the X-ray image.

[0004]

However, in the conventional gradation conversion processing as described above, in the X-ray image,
Only the conversion is performed so that the density value of a certain area (the density value at the lower 5% point of the histogram, etc.) becomes a constant density value on the X-ray diagnostic film. Depending on the region to be extracted, the density value of the entire X-ray image on the X-ray diagnostic film may vary.

[0005] For example, an X-ray image is composed of regions of different tissue parts such as lungs, bones and skin, and the X-ray transmittances are different from each other. For this reason, if the region for extracting the feature amount (density value) used for the gradation conversion is a region other than the region to be actually observed (the region of interest such as bones and lungs), the region of interest is easily observed. Thus, a feature amount that is not appropriate as a feature amount used for gradation conversion is obtained. When gradation conversion is performed using such a feature amount, a variation in density value occurs in the entire X-ray image, and the density value of the attention area may not be converted into a density value suitable for observation in some cases. This leads to problems such as a decrease in diagnosis efficiency and erroneous diagnosis.

Accordingly, the present invention has been made to eliminate the above-mentioned drawbacks, and is configured so that an appropriate gradation conversion can be performed on an input image. An object of the present invention is to provide an image processing apparatus, an image processing system, an image processing method, and a storage medium in which a computer can store an image capable of providing an image in a readable manner by a computer.

[0007]

For such a purpose,
According to a first aspect of the present invention, there is provided an area extracting means for extracting a predetermined area from an input image, and an average for obtaining an average pixel value in a second direction for each coordinate point in the first direction of the predetermined area obtained by the area extracting means. Value acquisition means, position acquisition means for acquiring coordinates in the first direction of an average pixel value having an arbitrary value from the average pixel value of each coordinate point in the first direction obtained by the average value acquisition means, Image processing means for performing predetermined image processing on the input image based on the coordinate information obtained by the position obtaining means.

[0008] In a second aspect based on the first aspect,
The image processing means performs a gradation conversion process on the input image based on an average pixel value corresponding to the coordinates obtained by the position obtaining means.

According to a third aspect of the present invention, there is provided an area extracting means for extracting a predetermined area from an input image, and an average pixel value in the second direction for each coordinate point in the first direction of the predetermined area obtained by the area extracting means. Mean value acquiring means for acquiring, and position acquiring means for acquiring coordinates in the first direction of an average pixel value having an arbitrary value from average pixel values of each coordinate point in the first direction obtained by the average value acquiring means. Analysis means for analyzing a region indicated by the coordinates obtained by the position acquisition means, feature extraction means for extracting a feature amount from an area determined by the analysis result of the analysis means, and feature amount extraction means And image processing means for performing predetermined image processing on the input image based on the characteristic amount obtained by the above.

In a fourth aspect based on the third aspect,
The analysis means, based on the coordinates obtained by the position acquisition means, a profile creation means for creating a profile of the pixel value constituting the input image, based on the profile obtained by the profile creation means,
And an area determining means for determining an area from which the feature amount is extracted.

According to a fifth aspect, in the third aspect,
The feature extracting means may extract a statistic of a pixel value in the determined area as the feature amount.

[0012] In a sixth aspect based on the third aspect,
The image processing unit performs a gradation conversion process on the input image based on the feature amount obtained by the feature extraction unit.

In a seventh aspect based on the first or third aspect, the input image includes an image obtained by radiography, and the area extracting means includes a pass-through area and a predetermined distance from the pass-through area. And extracting an area other than the area in contact with the predetermined area as the predetermined area.

According to an eighth aspect, in the seventh aspect,
The radiation imaging includes X-ray imaging.

A ninth aspect of the present invention is an image processing apparatus for extracting a characteristic amount of a photographed image from a photographed image obtained by photographing a subject. Calculating means for calculating an average pixel value in the first axis direction from the photographed image from which the pass-through area has been deleted; and a characteristic region for extracting the feature amount from the photographed image based on the shape of the calculation result And setting means for setting

According to a tenth aspect, in the ninth aspect, there is provided a profile creating means for creating a profile in the second axis direction, wherein the setting means sets the profile and the profile in accordance with an arbitrary part of the subject. The feature area is set based on the average pixel value.

An eleventh invention is characterized in that, in the ninth invention, a gradation conversion processing means for performing a gradation conversion process on the photographed image in accordance with a feature amount extracted from the feature region is provided. I do.

In a twelfth aspect based on the ninth aspect, the pass-through deleting means deletes a pass-through area from the photographed image based on a condition set according to a density distribution of the photographed image. It is characterized by the following.

In a thirteenth aspect based on the ninth aspect, the subject includes a cervical vertebra.

A fourteenth invention is an image processing system in which a plurality of devices are communicably connected, wherein at least one of the plurality of devices is any one of claims 1 to 13. It has a function of an image processing device.

A fifteenth invention is an image processing method for acquiring information used in a predetermined image processing step,
An area extraction step of extracting a predetermined area from the input image; an average value obtaining step of obtaining an average pixel value in a second direction for each coordinate point in a first direction of the predetermined area obtained by the area extraction step; From the average pixel value of each coordinate point in the first direction obtained in the average value obtaining step,
A position acquiring step of acquiring coordinates in the first direction of the average pixel value having an arbitrary value as coordinates of the attention area in the predetermined area.

In a sixteenth aspect based on the fifteenth aspect, the predetermined image processing step includes the steps of: adding the input image to the input image based on an average pixel value corresponding to the coordinates of the region of interest obtained by the position obtaining step. And a step of performing a gradation conversion process.

A seventeenth invention is an image processing method for acquiring information used in a predetermined image processing step,
An area extraction step of extracting a predetermined area from the input image;
An average value acquisition step of acquiring an average pixel value in the second direction for each coordinate point in the first direction of the predetermined area obtained by the area extraction step; and an average value in the first direction obtained by the average value acquisition step. From the average pixel value of the coordinate point, a position obtaining step of obtaining the coordinates of the average pixel value having an arbitrary value in the first direction as the coordinates of the attention area in the predetermined area, and the coordinates obtained by the position obtaining step It is characterized by including an analysis step of analyzing the indicated region of interest and a feature extraction step of extracting a feature amount from a region within the region of interest determined by the analysis result in the analysis step.

In an eighteenth aspect based on the seventeenth aspect, the analyzing step is a profile creating step of creating a profile of pixel values constituting the input image based on the coordinates obtained in the position obtaining step. And an area determining step of determining an area from which the feature amount is extracted based on the profile obtained in the profile creating step.

In a nineteenth aspect based on the seventeenth aspect, the feature extracting step includes a step of extracting a statistic of pixel values in the determined area as the feature quantity.

In a twentieth aspect based on the seventeenth aspect, the predetermined image processing step performs a gradation conversion process on the input image based on the characteristic amount obtained in the characteristic extraction step. It is characterized by including a step.

[0027] In a twenty-first aspect based on the fifteenth or seventeenth aspect, the input image includes an image obtained by radiography, and the area extracting step includes a pass-through area and a predetermined distance from the pass-through area. And extracting a region other than the region touched by the predetermined region as the predetermined region.

A twenty-second invention is characterized in that, in the twenty-first invention, the radiation imaging includes X-ray imaging.

A twenty-third aspect of the present invention is an image processing method for extracting a feature amount of a photographed image from a photographed image obtained by photographing a subject. A deletion step, a calculation step of calculating an average pixel value in the first axis direction from the photographed image from which the slip-through area has been deleted, and a shape of the calculation result,
Setting a feature area for extracting the feature amount from the photographed image.

According to a twenty-fourth aspect, in the twenty-third aspect, the method further includes a profile creation step of creating a profile in the second axis direction. Setting the characteristic region based on the average pixel value.

According to a twenty-fifth aspect, in the twenty-third aspect, the method further comprises a gradation conversion step of performing a gradation conversion process on the photographed image in accordance with the characteristic amount extracted from the characteristic region. I do.

In a twenty-sixth aspect based on the twenty-third aspect, the pass-through deleting step deletes a pass-through area from the photographed image based on a condition set according to a density distribution of the photographed image. It is characterized by including a step.

In a twenty-seventh aspect based on the twenty-third aspect, the subject includes a cervical vertebra.

According to a twenty-eighth aspect of the present invention, a computer can read a processing program for implementing the image processing apparatus according to any one of the first to thirteenth aspects or the means provided in the image processing system according to the ninth aspect. It is characterized by being a storage medium in which it is stored.

According to a twenty-ninth aspect of the present invention, a computer-readable storage medium stores the image processing method according to any one of claims 15 to 27.

A thirtieth aspect of the present invention is an image processing apparatus for extracting a feature amount of a photographed image from a photographed image obtained by photographing a subject. Calculating means for calculating average pixel values in the vertical and horizontal directions from the photographed image from which the through area has been deleted; and extracting the feature amount from the photographed image based on the shape of the calculation result. Setting means for setting an area.

[0037]

Embodiments of the present invention will be described below with reference to the drawings.

(First Embodiment) The present invention provides, for example,
The present invention is applied to an X-ray imaging apparatus 100 as shown in FIG. The X-ray imaging apparatus 100 according to the present embodiment is an apparatus having an image processing function including a gradation conversion process, and as shown in FIG.
6, CPU 108, main memory 109, operation panel 1
10 and an image processing circuit 111. These components are configured to exchange data with each other via the CPU bus 107. Further, the X-ray imaging apparatus 100
Are a data collection circuit 105 connected to the CPU bus 107 and the preprocessing circuit 106, and a two-dimensional X-ray sensor 104 and an X-ray generation circuit 10 connected to the data collection circuit 105.
1 is provided.

The CPU 108 controls the operation of the entire apparatus, and a processing program and various data for this are stored in the main memory 109 in advance. Therefore, the CPU 108 reads out and executes the processing program from the main memory 109, and controls the operation of the entire apparatus by using various data in the main memory 109. Further, the CPU 108 controls the operation of the entire apparatus so as to operate according to the operation on the operation panel 110.

The main memory 109 stores C as described above.
It stores a processing program and various data necessary for operation control of the entire apparatus by the PU 108, and also includes a work memory for work of the CPU 108. The main memory 109 also has a pre-processing circuit 106
The X-ray image signal after the pre-processing described later is stored.

The X-ray generation circuit 101 emits an X-ray beam 102 to the subject 103 in accordance with an instruction from the CPU 108. The two-dimensional X-ray sensor 104
3 receives the X-ray beam 102 transmitted through
3 is output.

The data collection circuit 105 collects X-ray image information output from the two-dimensional X-ray sensor 104 and converts the X-ray image information into an electric signal. Preprocessing circuit 1
Reference numeral 06 performs pre-processing such as offset correction processing and gain correction processing on the electric signal (X-ray image signal) obtained by the data collection circuit 105.

The image processing circuit 111 includes a pre-processing circuit 106
The X-ray image signal (hereinafter, referred to as an “original image” or an “input image”) after the pre-processing is subjected to a gradation conversion process. , And a body region (hereinafter, these regions are collectively referred to as a "through region") that extracts a body region (hereinafter, these regions are collectively referred to as a "through region") in contact with the through region at a constant width, and
The average value obtained for each point on the vertical axis (y-axis) in the horizontal axis direction (x-axis direction) of the area (subject area) of the original image excluding the pass-through area extracted by the pass-through extraction circuit 111a Value creation circuit 111b and average value creation circuit 111
b) a position extraction circuit 111c for extracting coordinates of a predetermined value (maximum value, minimum value, etc.) of the average pixel value obtained in b, and an original image based on the pixel values corresponding to the coordinates extracted by the position extraction circuit 111c. Conversion circuit 11 that performs gradation conversion on
1f.

In this embodiment, the analysis circuit 111d and the feature extraction circuit 11e shown in FIG. 1 are not essential components. These analysis circuit 111d and feature extraction circuit 1
The configuration provided with 1e will be described in a second embodiment described later.

FIG. 2 is a flowchart showing the operation of the X-ray imaging apparatus 100 according to the present embodiment. The processing program according to this flowchart is stored in the main memory 109 in advance, and is read out from the CPU 108 and executed, whereby the X-ray imaging apparatus 100 operates as follows.

Step S200: First, the X-ray generation circuit 1
Numeral 01 radiates an X-ray beam 102 to a subject (test object) 103. The X-ray beam 102 emitted from the X-ray generation circuit 101 passes through the subject 103 while being attenuated, reaches the two-dimensional X-ray sensor 104, and is output as an X-ray image by the two-dimensional X-ray sensor 104. Is done. 2
The X-ray image output from the dimensional X-ray sensor 104 is, for example, a medical image, and here is a cervical vertebra image as shown in FIG. The data collection circuit 105 converts the X-ray image output from the two-dimensional X-ray sensor 104 into an electric signal and supplies the electric signal to the preprocessing circuit 106. Pre-processing circuit 10
6 performs pre-processing such as offset correction processing and gain correction processing on the electric signal (X-ray image signal) from the data collection circuit 105. The X-ray image signal after the pre-processing by the pre-processing circuit 106 is transferred to the main memory 109 as an original image via the CPU bus 107 under the control of the CPU 108. The image processing circuit 111 includes a main memory 1
09 for the original image in step S201
To S205.

Step S201: First, the pass-through extraction circuit 111a outputs the original image (hereinafter referred to as
An input image is also obtained, and the maximum value (maximum pixel value) among the pixel values of the entire input image is calculated. Then, the pass-through extraction circuit 111a determines a threshold Th1 based on the maximum pixel value. Here, the threshold value Th1 is
For example, the value is set to 90% of the maximum pixel value.

Step S202: Next, the bypass extraction circuit 111a

[0049]

(Equation 1)

According to the following equation (1), the input image f (x,
y), the image f1 after deleting the pass-through region and the body region (pass-through region) in contact with the pass-through region within a certain interval.
(X, y) is obtained. Here, “deletion” means that the pixel value in the bypass area is replaced with a predetermined pixel value (for example, “0” pixel value). In equation (1), "
sgn (x, y) "is

[0051]

(Equation 2)

Is represented by the following equation (2). Also, "d1"
And “d2” indicate constants for determining the width of the fixed interval when deleting a body region that is in contact with the slip-through area within a fixed interval from the input image f (x, y), and indicates the input image f (x, ,
It is set based on the size of y) and the like. In this manner, the body region that is in contact with the through region within a certain interval (replaced with a certain pixel value) is deleted from the input image f (x, y) together with the through region from the through region. This is because there is a possibility that the image may be disturbed by scattering of X-rays, thereby hindering excellent feature amount extraction.

Step S203: Next, the average value extraction circuit 111b performs the processing in step S2 in the bypass extraction circuit 111a.
02 in the image f1 (x, y) obtained by executing the processing of No. 02, the average pixel in the x-axis direction for each point of the y-axis coordinate in the area where the pixel value is not replaced with the “0” pixel value The value f (y) is

[0054]

(Equation 3)

It is determined by the following equations (3) and (4). For example, when the input image f (x, y) is a cervical vertebra image as shown in FIG. 3A, the input image f (x, y)
The average pixel value f (y) for the image f1 (x, y) after removing the empty area is as shown in FIG. In FIG. 3B, the vertical axis indicates the y coordinate, and the horizontal axis indicates the average pixel value at each point on the y axis coordinate.

Step S204: Next, the position extraction circuit 1
11c extracts a coordinate Y1 corresponding to a predetermined value of the average pixel value f (y) obtained by the average value extraction circuit 111b.
Here, as shown in FIG. 3B, the average pixel value f
The coordinates of the maximum value of (y) are extracted as coordinates Y1. The coordinates Y1 indicate, for example, a region (neck portion) where the X-ray transmittance is good in the input image f (x, y), assuming that the pixel value is higher as the X-ray transmittance is better. , The pixel value (maximum value f (Y1)) corresponding to the coordinate Y1 indicates the feature amount of the region. That is, when the region to be observed (the region of interest) is the neck portion where the X-ray transmittance is good, the coordinate Y1 of the maximum average pixel value f (y) at each point on the y-axis coordinate is calculated. The pixel value (maximum value f (Y1)) at the coordinates Y1 may be extracted and used as the feature value.

Step S205: Next, the gradation conversion circuit 1
11f is the coordinate Y obtained by the position extraction circuit 111c.
1 (here, the maximum value f (Y1) of the average pixel value f (y)) based on the pixel value corresponding to the input image f (x , Y). Here, the gradation conversion conditions are such that the maximum value f (Y1) becomes a density value 1.6 according to a gradation conversion curve as shown in FIG. In FIG. 4, the horizontal axis represents the pixel value (input density value) of the input image f (x, y), and the vertical axis represents the pixel value after gradation conversion (output density value).
Is shown.

Step S206: The input image after the above-mentioned gradation conversion processing is displayed and output on a monitor (not shown) or an X-ray diagnostic film (not shown) under the control of the CPU 108. Or output to the top.

According to the present embodiment as described above, in the input image f (x, y), the input image f (x, y) is used as information of the region having good X-ray transmission and the region having poor X-ray transmission.
An average pixel value f (y) in the x-axis direction for each point on the y-axis of the subject region excluding the through region from (x, y) is obtained. From the average pixel value f (y), for example, a portion (for example, a neck portion) in which an input image f (x, y) (a cervical vertebra image as shown in FIG. 3A) has good X-ray transmission, And parts with poor X-ray transmission (eg head and shoulders)
Can be easily separated from each other. That is, a region to be observed (for example, a region of interest such as a neck) can be easily extracted from the input image f (x, y) based on the average pixel value f (y). In the present embodiment, as an example,
The region to be observed (the region of interest) was defined as the neck portion where the X-ray transmittance was good, and the coordinates Y1 of the maximum average pixel value f (y) were extracted.

Also, the value of the average pixel value f (y) is
A value representing a region of each tissue portion such as a head and a shoulder, for example, when a neck is set as a region of interest, the average pixel value of the region of interest is used. By setting the conditions, the density of the attention area can be converted stably and favorably. In this embodiment, as an example, a region to be observed (a region of interest) is defined as a neck portion having a high X-ray transmittance, and a coordinate Y1 of a maximum average pixel value f (y) is extracted. The pixel value of Y1 (maximum value f (Y1)) is used as a feature value, and gradation conversion is performed so that the feature value has a density value of 1.6.

The average pixel value f in the x-axis direction for each point of the y-axis coordinate in the subject area of the image f1 (x, y) after removing the through area from the input image f (x, y)
Since (y) is obtained, the coordinates indicating a predetermined value (maximum value, minimum value, etc.) of the average pixel value f (y) do not change even when the subject is translated or rotated. Thus, the coordinates of the attention area can be stably extracted.

(Second Embodiment) In this embodiment,
X-ray imaging apparatus 100 according to the first embodiment described above
, An analyzing circuit 111d for analyzing a range of an area for extracting a feature based on the coordinates extracted by the position extracting circuit 111c, and a feature extracting circuit for acquiring a feature from an area obtained by the analysis by the analyzing circuit 111d 111e. Therefore, the gradation conversion circuit 111f
Performs gradation conversion on the original image based on the feature amount obtained by the feature extraction circuit 111e.

FIG. 5 is a flowchart showing the operation of the X-ray imaging apparatus 100 according to the present embodiment. The processing program according to this flowchart is stored in the main memory 109 in advance, and is read out from the CPU 108 and executed, whereby the X-ray imaging apparatus 100 operates as follows.

In the flowchart of FIG. 5,
Steps that execute processing in the same manner as in the flowchart of FIG. 2 are given the same step numbers, and detailed descriptions thereof are omitted.

Step S200: First, X-ray imaging is started as described above, and the two-dimensional X-ray sensor 104 obtains, for example, an X-ray image as shown in FIG. This X-ray image was obtained by imaging from the side of the thoracic spine. Such an X-ray image is transferred as an original image to the main memory 109 via the data acquisition circuit 105 and the preprocessing circuit 106. Image processing circuit 11
1 is for the following steps S201 to S204 and step S50 for the original image in the main memory 109.
5 to S508 are executed.

Steps S201 to S204: As described above, first, the pass-through extraction circuit 111a calculates the maximum value (maximum pixel value) among the pixel values of the entire original image (input image) in the main memory 109, A threshold value Th1 (e.g., 90% of the maximum pixel value) based on the maximum pixel value is determined (step S201). Next, the pass-through extraction circuit 111a
Obtains an image f1 (x, y) after deleting a pass-through region and a body region (pass-through region) in contact with the pass-through region within a predetermined interval from the input image f (x, y) (step S).
202). Next, the average value extraction circuit 111b calculates the average in the x-axis direction for each point of the y-axis coordinate in the subject region of the image f1 (x, y) obtained by the execution of the processing of step S202 in the pass-through extraction circuit 111a. The pixel value f (y) is obtained. As a result, an average pixel value f (y) as shown in FIG. 6B is obtained. Next, the position extraction circuit 111c
Is the average pixel value f obtained by the average value extraction circuit 111b.
Coordinate Y corresponding to a predetermined value (here, the maximum value) of (y)
1, that is, the coordinates Y1 of the attention area are extracted.

Step S505: Next, the analysis circuit 111
As for d, a profile as shown in FIG. 6C is created according to the coordinates Y1 of the attention area extracted by the position extraction circuit 111c. Specifically, the input image f (x, y)
, The coordinates Y extracted by the position extraction circuit 111c
1 that crosses in the x-axis direction f2 (x) = f
(X, Y1) is created.

Step S506: Next, the analysis circuit 111
d is the profile f2 created in step S505
By analyzing (x), a coordinate X1 for obtaining a feature amount of the input image f (x, y) is obtained. As shown in FIG. 6C, the coordinate X1 is a profile f2
It is assumed that the coordinates indicate the lowest value of the concave portion of (x). In this case, in the input image f (x, y) (the image of the thoracic vertebra) shown in FIG. 6A, a bone region a having a low X-ray transmittance and a low pixel value (a spine region serving as a base of a rib) Are obtained in the x-axis direction.

In step S506, the profile f2 (x) is used as the coordinate X1 for obtaining the characteristic amount.
The coordinates indicating the maximum value of the convex portion may be obtained.
In this case, the coordinates in the x-axis direction of a region having a good X-ray transmittance (region b shown in FIG. 6A) such as a lung region can be obtained. Further, the unevenness of the profile f2 (x) for obtaining the coordinates X1 may be determined from the height relationship of three points on the profile. Note that the profile f2
An average pixel value in the Y-axis direction may be used instead of (x).

Step S507: Next, the characteristic amount extraction circuit 111e causes the analysis circuit 111d to execute step S5.
05, and an area determined by the coordinate X1 obtained by executing the processing of step S506, for example, a four-sided area having a predetermined width centered on (X1, Y1). Is extracted. The region obtained as a result is the region a (or the region b) shown in FIG. Next, the feature amount extraction circuit 111e calculates a statistic such as a maximum value, a minimum value, and an average value of pixel values in the area a (or the area b) as a feature amount (s507).

Step S508: Next, the gradation conversion circuit 1
Reference numeral 11f denotes a gradation conversion that converts a feature amount (for example, an average pixel value of the area a) obtained by the feature amount extraction circuit 111e into a predetermined density value (a density value of 1.2 or the like). Performed on f (x, y).

Step S206: The input image after the above-described gradation conversion processing is displayed and output on, for example, a monitor (not shown) or an X-ray diagnostic film (not shown) under the control of the CPU 108. Or output to the top.

As described above, in the present embodiment, the coordinates of the region of interest obtained by the configuration according to the first embodiment (bypass extraction circuit 111a, average value generation circuit 111b, and position extraction circuit 111c) are used. On the other hand, by performing further analysis, it is possible to reliably extract a more detailed region of interest (bone, lung, skin region, etc.). Therefore, even when different types of tissues such as lungs, bones, and skin are finely present in the input image, each region can be reliably extracted as the region of interest. Therefore, by performing gradation conversion on the input image based on the feature amount acquired from such a region of interest, even if the region of interest such as bones, lungs, skin, etc. is limited to a detailed region, the target image can be satisfactorily obtained. The area can be observed.

(Summary of Effects of First and Second Embodiments of the Present Invention)

(1) a region extracting means (111a) for extracting a predetermined region (a region other than a through region and a region in contact with the through region at regular intervals, ie, a subject region) from an input image (X-ray image); Average value creating means (111b) for finding an average pixel value in the second direction (x-axis direction) for each coordinate point in the first direction (y-axis direction) of the predetermined area obtained by the extracting means (111a); Value creation means (111
b) a position extracting means (111c) for acquiring coordinates (coordinates of a region of interest) of an average pixel value having a predetermined value (maximum value or the like) among average pixel values obtained in b) and an average pixel value; In this case, the average pixel value in the x-axis direction at each coordinate point in the y-axis direction of the subject area indicates a region where X-rays are transmitted well and a region where X-rays are transmitted poorly (here, the X-ray transmission region). The pixel value of the region with good transmission is increased.) From such an average pixel value, for example, in the cervical vertebra image, a portion having good X-ray transmission (neck portion, etc.) and a portion having poor X-ray transmission (head, shoulder, etc.) can be separated. Etc. can be reliably extracted. Further, since the average pixel value in the x-axis direction for each coordinate point in the y-axis direction of the subject area is extracted, the coordinates of the attention area do not change even when the subject is translated or rotated. Therefore, the attention area can be stably extracted.

(2) By using the average pixel value of the region of interest obtained by the configuration of (1) in the gradation conversion processing for the input image, stable gradation conversion processing can be executed.

(3) In addition to the configuration of (1), analysis for determining an area for acquiring a characteristic amount from a profile created based on the coordinates of the area of interest obtained by the position extracting means (111c) Means (111d) and a feature extracting means (111e) for acquiring a feature amount (statistical value such as a maximum value, a minimum value, and an intermediate value) from the region determined by the analyzing means (111d). That is, if the analysis is further performed after the region of interest is extracted by the configuration of (1), a more detailed region (a region of a bone, a lung part, or the like) of the region of interest can be extracted. For this reason, even if there are regions of different types of fine tissue such as lungs, bones, and skin in the input image, each region can be extracted as a region for extracting a feature amount.

(4) The feature amount obtained from the region obtained by the configuration of (3) is used for gradation conversion processing on the input image, so that the region to be observed is a fine tissue portion such as a bone or a lung. However, the portion can be observed in a good density state.

The object of the present invention is to provide a storage medium storing program codes of software for realizing the functions of the host and terminal of the first and second embodiments.
It is needless to say that the present invention is also achieved by supplying the data to a system or an apparatus, and reading and executing a program code stored in a storage medium by a computer (or CPU or MPU) of the system or the apparatus. In this case, the program code itself read from the storage medium realizes the functions of the above embodiments, and the storage medium storing the program code constitutes the present invention. ROM, floppy disk, hard disk, optical disk, magneto-optical disk, CD-ROM, C
DR, a magnetic tape, a nonvolatile memory card, or the like can be used. The functions of each of the above-described embodiments are not only realized by executing the program code read by the computer, but also the OS or the like running on the computer is actually executed based on the instruction of the program code. It goes without saying that a case where some or all of the processing is performed and the functions of the above embodiments are realized by the processing is also included. Further, after the program code read from the storage medium is written to a memory provided in an extension function board inserted into the computer or a function extension unit connected to the computer, the function extension is performed based on the instruction of the program code. It goes without saying that the CPU or the like provided in the board or the function expansion unit performs part or all of the actual processing, and the processing realizes the functions of the above embodiments.

[0080]

As described above, according to the present invention, an area (characteristic area) from which information used for image processing (such as gradation conversion processing) is extracted can be stably acquired.
Stable and appropriate image processing can be performed, and an image after good image processing can be provided.

[Brief description of the drawings]

FIG. 1 is a block diagram illustrating a configuration of an X-ray imaging apparatus to which the present invention has been applied.

FIG. 2 is a flowchart illustrating an operation of the X-ray imaging apparatus according to the first embodiment.

FIG. 3 is a diagram for describing extraction of a feature amount used for gradation conversion according to the first embodiment.

FIG. 4 is a diagram for explaining a gradation conversion curve of the gradation conversion.

FIG. 5 is a flowchart illustrating an operation of the X-ray imaging apparatus according to the second embodiment.

FIG. 6 is a diagram for describing extraction of a feature amount used for gradation conversion according to the second embodiment.

[Explanation of symbols]

 REFERENCE SIGNS LIST 100 X-ray imaging apparatus 101 X-ray generation circuit 102 X-ray beam 103 subject 104 two-dimensional X-ray sensor 105 data collection circuit 106 preprocessing circuit 107 CPU bus 108 CPU 109 main memory 110 operation panel 111 image processing circuit 111 a slip-through extraction circuit 111b Average value creation circuit 111c Position extraction circuit 111d Analysis circuit 111e Feature extraction circuit 111f Tone conversion circuit

 ──────────────────────────────────────────────────続 き Continuing on the front page F term (reference) 4C093 AA01 AA26 CA01 CA50 EB17 EE01 FC18 FC19 FD03 FD09 FD11 FD12 FF08 FF15 FF16 FF18 FF19 FF22 FF50 FH06 5B057 AA08 BA03 CA08 CA12 CA16 CB08 DB1 PA16 DB02 CE16 PA76 RA07 RA08 RB03 XA35 5C077 LL04 LL19 MP01 NN02 NP01 PP15 PP54 SS01

Claims (30)

[Claims] 1. An area extracting means for extracting a predetermined area from an input image, and an average value for obtaining an average pixel value in a second direction for each coordinate point in a first direction of the predetermined area obtained by the area extracting means. Obtaining means for obtaining an average pixel value having an arbitrary value from the average pixel value of each coordinate point in the first direction obtained by the average value obtaining means;
Position acquisition means for acquiring the coordinates of the direction, based on the coordinate information obtained by the position acquisition means,
An image processing apparatus comprising: an image processing unit that performs predetermined image processing on the input image. 2. The image processing means according to claim 1, wherein said image processing means calculates an average pixel value corresponding to coordinates obtained by said position obtaining means.
The image processing apparatus according to claim 1, wherein a gradation conversion process is performed on the input image. 3. An area extracting means for extracting a predetermined area from an input image, and an average value for obtaining an average pixel value in a second direction for each coordinate point in the first direction of the predetermined area obtained by the area extracting means. Obtaining means for obtaining an average pixel value having an arbitrary value from the average pixel value of each coordinate point in the first direction obtained by the average value obtaining means;
Position obtaining means for obtaining the coordinates of the direction; analyzing means for analyzing an area indicated by the coordinates obtained by the position obtaining means; and a feature for extracting a feature amount from the area determined by the analysis result of the analyzing means. Extracting means, based on the characteristic amount obtained by the characteristic amount extracting means,
An image processing apparatus comprising: an image processing unit that performs predetermined image processing on the input image. 4. A profile creating means for creating a profile of pixel values constituting the input image based on the coordinates obtained by the position acquiring means, and a profile obtained by the profile creating means. 4. The image processing apparatus according to claim 3, further comprising: an area determining unit that determines an area from which the feature amount is extracted based on the information. 5. The image processing apparatus according to claim 3, wherein the feature extracting unit extracts a statistic of a pixel value in the determined area as the feature amount. 6. The image processing apparatus according to claim 3, wherein said image processing means performs a gradation conversion process on said input image based on a feature amount obtained by said feature extraction means. . 7. The input image includes an image obtained by radiography, and the area extracting unit extracts, as the predetermined area, an area other than a pass-through area and an area in contact with the pass-through area at a fixed interval. The image processing apparatus according to claim 1 or 3, wherein: 8. The image processing apparatus according to claim 7, wherein said radiation imaging includes X-ray imaging. 9. An image processing apparatus for extracting a feature amount of a photographed image from a photographed image obtained by photographing a subject, comprising: Calculating means for calculating an average pixel value in the first axis direction from the photographed image from which the missing area has been deleted; and setting for setting a characteristic region for extracting the characteristic amount from the photographed image based on the shape of the calculation result And an image processing apparatus. 10. A profile creating means for creating a profile in the second axis direction, wherein the setting means sets the characteristic region based on the profile and the average pixel value according to an arbitrary part of the subject. The image processing apparatus according to claim 9, wherein: 11. The image processing apparatus according to claim 9, further comprising a gradation conversion processing unit that performs a gradation conversion process on the photographed image in accordance with a feature amount extracted from the characteristic region. 12. The image according to claim 9, wherein the pass-through deletion unit deletes a pass-through area from the photographed image based on a condition set according to a density distribution of the photographed image. Processing equipment. 13. The image processing apparatus according to claim 9, wherein the subject includes a cervical vertebra. 14. An image processing system in which a plurality of devices are communicably connected, wherein at least one of the plurality of devices is an image processing apparatus according to any one of claims 1 to 13. An image processing system having a function. 15. An image processing method for acquiring information used in a predetermined image processing step, comprising: an area extraction step of extracting a predetermined area from the input image; An average value obtaining step of obtaining an average pixel value in the second direction for each coordinate point in the first direction; and an arbitrary value from the average pixel value of each coordinate point in the first direction obtained in the average value obtaining step. Acquiring a coordinate of the average pixel value in the first direction having the above as a coordinate of the attention area in the predetermined area. 16. The predetermined image processing step includes a step of performing a gradation conversion process on the input image based on an average pixel value corresponding to the coordinates of the region of interest obtained in the position obtaining step. 16. The image processing method according to claim 15, wherein: 17. An image processing method for acquiring information used in a predetermined image processing step, comprising: an area extraction step of extracting a predetermined area from an input image; An average value obtaining step of obtaining an average pixel value in the second direction for each coordinate point in one direction; and an arbitrary value from the average pixel value of each coordinate point in the first direction obtained in the average value obtaining step. A position obtaining step of obtaining coordinates of the average pixel value in the first direction as coordinates of a target area in the predetermined area; an analyzing step of analyzing a target area indicated by the coordinates obtained by the position obtaining step; A feature extraction step of extracting a feature amount from an area in the region of interest determined by an analysis result in the analysis step. 18. The method according to claim 17, wherein the analyzing step is based on the coordinates obtained in the position obtaining step.
A profile creation step of creating a profile of pixel values constituting the input image; and an area determination step of determining an area for extracting the feature amount based on the profile obtained in the profile creation step. Claim 17
The image processing method described in the above. 19. The image processing method according to claim 17, wherein the feature extracting step includes a step of extracting a statistic of a pixel value in the determined area as the feature amount. 20. The method according to claim 17, wherein the predetermined image processing step includes a step of performing a gradation conversion process on the input image based on the feature amount obtained in the feature extraction step. The image processing method described in the above. 21. The input image includes an image obtained by radiography, and the area extracting step extracts, as the predetermined area, an area other than a pass-through area and an area in contact with the pass-through area at a constant interval. 2. The method according to claim 1, further comprising the steps of:
18. The image processing method according to 5 or 17. 22. The image processing method according to claim 21, wherein said radiation imaging includes X-ray imaging. 23. An image processing method for extracting a feature amount of a photographed image from a photographed image obtained by photographing a subject, comprising: A calculating step of calculating an average pixel value in the first axis direction from the photographed image from which the pass-through region has been deleted; and setting a characteristic region for extracting the feature amount from the photographed image based on a shape of the calculation result. An image processing method comprising: 24. A profile creation step of creating a profile in a second axis direction, wherein the setting step sets the characteristic region based on the profile and the average pixel value according to an arbitrary part of the subject. The image processing method according to claim 23, further comprising the step of: 25. The method according to claim 23, further comprising a gradation conversion step of performing a gradation conversion process on the photographed image in accordance with the characteristic amount extracted from the characteristic region.
The image processing method described in the above. 26. The method according to claim 23, wherein the pass-through deletion step includes a step of deleting a pass-through area from the photographed image based on a condition set according to a density distribution of the photographed image. The image processing method described in the above. 27. The image processing method according to claim 23, wherein the subject includes a cervical vertebra. 28. A computer readable storage program for executing the image processing apparatus according to any one of claims 1 to 13 or the means provided in the image processing system according to claim 14. Characteristic storage medium. 29. A storage medium, wherein the processing steps of the image processing method according to claim 15 are stored in a computer-readable manner. 30. An image processing apparatus for extracting a feature amount of a photographed image from a photographed image obtained by photographing a subject, comprising: Calculating means for calculating an average pixel value in the vertical direction and the horizontal direction from the photographed image from which the missing area has been deleted; and setting a characteristic region for extracting the feature amount from the photographed image based on the shape of the calculation result. An image processing apparatus comprising: setting means.