JP2003339684A - Device, system, and method for processing image, and storage medium - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide an image processor for reliably extracting an irradiation region by the optimum algorithm corresponding to a photographed image. <P>SOLUTION: The processor includes a plurality of region extracting means 113a(1)-113a(n) for respectively performing irradiation region extracting processings in response to different algorithms. A selecting means 113c selects the region extracting means with high extracting precision among the region extracting means 113a(1)-113a(n) based on the extraction results of the extracting means 113a(1)-113a(n) which are obtained by photographing for the prescribed times. <P>COPYRIGHT: (C)2004,JPO

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention, for example, extracts an irradiation region from an imaged image obtained by photographing a radiation (X-ray or the like) by performing irradiation narrowing and image processing obtained based on the irradiation region. A computer-readable storage of an image processing apparatus, an image processing system, an image processing method, and processing steps for implementing the same, which are used in an apparatus or system that performs image processing such as gradation conversion processing using parameters. Storage medium.

[0002]

2. Description of the Related Art In recent years, due to advances in digital technology, for example, a picked-up image obtained by X-ray photography is digitized, and the digital image is subjected to image processing and displayed on a monitor or for X-ray diagnosis. The output on the film has been done.

By the way, in radiography such as X-ray photography,
For humanitarian reasons, and in order to prevent scattering from unnecessary areas and prevent deterioration of contrast, "irradiation narrowing" is generally performed in which radiation is applied only to the necessary area (region of interest) of the subject. On the other hand, the above-mentioned image processing is generally performed based on image processing parameters determined from the density distribution of the captured image.

However, when the irradiation area, that is, the necessary area (region of interest) is not limited in the picked-up image obtained by the radiography after the irradiation is narrowed down, the information of the region including the so-called unnecessary region outside the region of interest is also included. From
Since the image processing parameters for image processing are determined, appropriate image processing cannot be performed. In order to solve such problems, the irradiation area is extracted from the captured image and the irradiation area (required area, that is, the area of interest) is extracted.
It is necessary to determine the image processing parameters from only the information.

Therefore, the following methods (1) and (2) are used to extract the irradiation area from the captured image.
Is proposed. (1) Differentiate the density value of the captured image and determine the edge of the irradiation region from the value. (2) As described in Japanese Examined Patent Publication No. 6-90412, etc., a skirt region outside the irradiation region is assumed, the skirt region is approximated by a linear approximation formula, and the value and the actual concentration value are compared. The edge of the irradiation area is determined from the difference.

In both of the above methods (1) and (2), it is premised that the imaged image of the processing target is an image obtained by performing the irradiation narrowing, and therefore, the irradiation area of these methods is As a pre-process of the extraction process, it is necessary to determine the presence or absence of irradiation restriction. Various algorithms have been proposed as algorithms for determining the presence / absence of this irradiation restriction (irradiation restriction determination algorithm).

[0007]

However, since the radiation dose and the imaging situation of the radiation imaging apparatus differ depending on the hospital in which the apparatus is used, the object to be imaged, etc., the captured image obtained by radiation imaging Also, although the tendency varies depending on the hospital, the object to be imaged, etc., conventionally, the same irradiation squeezing determination algorithm has been used regardless of the hospital, the object to be imaged, etc. For this reason, it is not possible to accurately determine the presence or absence of the irradiation restriction depending on the hospital, the subject to be imaged, etc. As a result, the irradiation region cannot be accurately extracted.

Further, a radiation apparatus has been proposed in which an algorithm to be used is selected from a plurality of irradiation restriction determination algorithms. However, in this apparatus, an algorithm is selected from a limited evaluation image in selecting the algorithm. It was very difficult to change the algorithm once it was selected.
Therefore, when an inappropriate algorithm is selected, it is not possible to accurately determine the presence or absence of irradiation restriction, and as a result, it is not possible to accurately extract the irradiation region.

Therefore, the present invention has been made to eliminate the above-mentioned drawbacks, and by selecting an optimum algorithm from a plurality of algorithms for extracting an irradiation region, any captured image can be obtained. Also, an image processing apparatus, an image processing system, an image processing method, and an image processing method capable of surely extracting an irradiation region and performing optimum image processing using image processing parameters obtained based on the irradiation region, and An object of the present invention is to provide a storage medium in which the processing steps for implementing it are stored in a computer-readable manner. Further, the present invention makes it possible to select the optimum algorithm from a plurality of algorithms for determining the presence or absence of irradiation, so that it is possible to reliably extract the irradiation region in any captured image. An image processing apparatus and an image processing system capable of performing optimum image processing using the image processing parameters obtained based on
An object of the present invention is to provide an image processing method and a storage medium in which processing steps for implementing the method are stored so that the computer can read the image.

[0010]

[Means for Solving the Problems] Under such a purpose,
A first invention is an image processing apparatus for extracting a predetermined area from a target image, comprising a plurality of area extracting means for executing the predetermined area extracting processing, and an arbitrary area extracting means from the plurality of area extracting means. And a selecting means for selecting.

A second invention is the same as the first invention,
The plurality of area extraction means execute the extraction processing according to different algorithms, and the selection means, based on the extraction results of the plurality of area extraction means for a predetermined number of executions, the arbitrary area extraction means. Is selected.

A third invention is the same as the first invention,
The selecting means is characterized by selecting the arbitrary area extracting means based on the target image.

A fourth invention is the same as the first invention,
The target image includes an image obtained by radiography,
The predetermined region includes an irradiation region at the time of radiography,
It is characterized in that the selecting means selects the arbitrary area extracting means based on the extraction results of the plurality of area extracting means obtained by a predetermined number of times of the radiography.

A fifth aspect of the invention is the same as the first aspect of the invention.
Display means for displaying the predetermined area extracted by the plurality of area extracting means, instruction means for instructing correction of the predetermined area displayed on the display means, predetermined area displayed on the display means, or Storage means for storing the predetermined area after correction by the instructing means, wherein the selecting means has respective information of the predetermined area extracted by the plurality of area extracting means and the predetermined area stored in the storage means. The arbitrary area extracting means is selected based on the extraction accuracy of the plurality of area extracting means obtained by.

A sixth invention is the same as the first invention,
It is characterized in that it comprises an instruction means for instructing the arbitrary area extracting means, and the selecting means selects the arbitrary area extracting means based on an instruction from the instructing means.

A seventh aspect of the present invention is an image processing apparatus for extracting an irradiation area from a photographed image, which comprises irradiation deficiency presence / absence determining means for determining presence / absence of irradiation deflation in the photographed image, and irradiation from the photographed image. A plurality of area extraction means for extracting the area, the determination result in the irradiation squeezing presence determination means,
And display means for displaying the irradiation area of the photographed image obtained from the extraction results of the plurality of area extracting means, input means for giving a correction instruction to the irradiation area displayed on the display means, and the display Storage means for storing the information of the irradiation area displayed on the means or the information of the irradiation area corrected by the input means, and the plurality obtained by the information of the storage means and the extraction results of the plurality of area extracting means Area extraction means based on the extraction accuracy of the area extraction means of
And a selecting unit for selecting from the plurality of region extracting units.

An eighth invention is the above-mentioned seventh invention, wherein
The selection means, by comparing and evaluating the information of the storage means and the extraction results of the plurality of area extraction means, obtain the correct rate of extraction of the irradiation area of the plurality of area extraction means,
It is characterized in that the area extracting means is selected based on the accuracy rate.

In a ninth aspect based on the seventh aspect,
The selecting means is characterized in that the area extracting means is selected after a predetermined number of times of photographing.

A tenth invention is characterized in that, in the seventh invention, the selecting means selects the area extracting means based on the photographed image.

An eleventh aspect of the present invention is an image processing apparatus for determining the presence / absence of irradiation restriction in a captured image, comprising a plurality of irradiation restriction presence / absence determining means for executing the above-described processing for determining the presence / absence of irradiation restriction, and the plurality of irradiation restrictions. It is characterized by further comprising a selecting means for selecting an arbitrary irradiation squeezing presence / absence determining means from the presence / absence determining means.

In a twelfth aspect based on the eleventh aspect, the plurality of irradiation squeezing presence / absence determining means execute the irradiating squeezing presence / absence determining processing according to different algorithms, and the selecting means performs a predetermined execution. It is characterized in that the arbitrary irradiation squeezing presence / absence determining means is selected based on the determination results of the plurality of irradiation squeezing presence / absence determining means for the number of times.

A thirteenth invention is characterized in that, in the eleventh invention, the selecting means selects the arbitrary irradiation narrowing presence / absence determining means based on the photographed image.

In a fourteenth aspect based on the eleventh aspect, a display means for displaying the irradiation area of the photographed image obtained from the judgment results by the plurality of irradiation restriction presence / absence judgment means and a display means for displaying the irradiation area on the display means. The selection means includes a storage unit that stores the irradiation area displayed on the display unit or the irradiation area corrected by the instruction unit. Based on the determination result of the irradiation restriction presence determination means, and the determination accuracy of the plurality of irradiation restriction presence determination means obtained by the information of the irradiation region stored in the storage means, the arbitrary irradiation restriction presence determination means It is characterized by making a selection.

A fifteenth invention is the eleventh invention, further comprising instructing means for instructing the arbitrary irradiation narrowing presence / absence determining means, and the selecting means is based on an instruction from the instructing means. It is characterized in that an arbitrary irradiation restriction presence / absence determining means is selected.

A sixteenth aspect of the present invention is an image processing apparatus for determining whether or not there is an irradiation squeezing in a photographed image, and a plurality of irradiation squeezing presence / absence determining means for determining whether or not there is an illumination squeezing in the photographic image. Area extraction means for extracting an irradiation area from a photographed image, display means for displaying the irradiation area of the photographed image obtained from the determination results by the plurality of irradiation narrowing presence / absence determining means and the extraction result by the area extracting means, An input unit for giving a correction instruction to the irradiation region displayed on the display unit, and a storage for storing information on the irradiation region displayed on the display unit or information on the irradiation region corrected by the input unit Means, and information based on the information stored in the storage means and the determination accuracy of the plurality of irradiation squeezing presence / absence determining means obtained by the determination results of the plurality of irradiation squeezing presence / absence determining means. The diaphragm existence determination means, characterized in that it comprises a selection means for selecting from the plurality of irradiation aperture existence determination means.

In a seventeenth aspect based on the sixteenth aspect, the selection means compares and evaluates the information in the storage means with the determination results of the plurality of irradiation squeezing presence / absence determining means, whereby It is characterized in that the correct answer rate of the determination of presence or absence of irradiation restriction is obtained, and the irradiation restriction presence determination means is selected based on the correct answer rate.

An eighteenth invention is characterized in that, in the sixteenth invention, the selecting means selects the irradiation narrowing presence / absence determining means after a predetermined number of times of photographing.

The nineteenth invention is characterized in that, in the sixteenth invention, the selecting means selects the irradiation narrowing presence / absence determining means based on the photographed image.

A twentieth aspect of the present invention is an image processing system in which a plurality of devices are communicably connected to each other, and at least one of the plurality of devices is a device according to any one of claims 1 to 3.
19. The image processing device according to any one of 19).

A twenty-first aspect of the present invention is an image processing method for extracting a predetermined area from a target image, comprising a plurality of area extraction steps for executing the above-mentioned predetermined area extraction processing, and any of the plurality of area extraction steps. And a selection step of selecting the region extraction step of.

In a twenty-second aspect of the invention based on the twenty-first aspect, the plurality of region extracting steps include a step of executing the extracting process according to different algorithms, and the selecting step includes a predetermined number of executions. The method is characterized by including a step of selecting the arbitrary area extraction step based on the extraction results obtained by the plurality of area extraction steps.

The twenty-third invention is characterized in that, in the twenty-first invention, the selecting step includes a step of selecting the arbitrary region extracting step based on the target image.

In a twenty-fourth aspect based on the twenty-first aspect, the target image includes an image obtained by radiography, the predetermined area includes an irradiation area at the radiography, and the selecting step. Is characterized by including a step of selecting the arbitrary area extraction step based on the extraction results of the plurality of area extraction steps obtained by a predetermined number of times of the radiography.

A twenty-fifth aspect of the present invention is, in the twenty-first aspect, for displaying a predetermined area obtained by the plurality of area extracting steps and for instructing correction of the predetermined area displayed by the display step. Including an instruction step, a predetermined area displayed by the display step, or a storage step of storing a predetermined area after correction according to the instruction in the instruction step, the selection step,
Predetermined area obtained by the plurality of area extraction step,
And a step of selecting the arbitrary area extraction step on the basis of the extraction accuracy in the plurality of area extraction steps obtained from each information of the predetermined area stored in the storage step.

In a twenty-sixth aspect of the present invention based on the twenty-first aspect, an instruction step for externally instructing the arbitrary region extraction step is included, and the selection step is based on the external instruction by the instructing step. It is characterized by including a step of selecting the region extraction step of.

A twenty-seventh aspect of the present invention is an image processing method for extracting an irradiation area from a photographed image, which comprises an irradiation iris presence / absence determining step for determining presence / absence of irradiation iris in the photographed image, and the photographed image. A plurality of area extraction steps for extracting the irradiation area from, the determination result in the irradiation restriction presence determination step, and a display step for displaying the irradiation area of the captured image obtained from the extraction results in the plurality of area extraction steps And an input step for giving a correction instruction to the irradiation area displayed by the display step, information on the irradiation area displayed by the display step, or information on the irradiation area corrected by the input step is stored. It is obtained by the storing step, the information stored by the storing step and the extraction results of the plurality of area extracting steps. The region extraction step based on the accuracy of extracting the plurality of region extraction step, characterized in that it comprises a selection step of selecting from among the plurality of region extraction step.

In a twenty-eighth aspect based on the twenty-seventh aspect, the selection step may be performed by comparing and evaluating the information stored in the storage step with the extraction results of the plurality of area extraction steps. The present invention is characterized by including a step of obtaining a correct answer rate of extraction of an irradiation area in a plurality of area extracting steps and selecting the area extracting step based on the correct answer rates.

The twenty-ninth invention is characterized in that, in the twenty-seventh invention, the selecting step includes a step of selecting the area extracting step after photographing a predetermined number of times.

The thirtieth invention is characterized in that, in the twenty-seventh invention, the selecting step includes a step of selecting the region extracting step based on the photographed image.

A thirty-first aspect of the present invention is an image processing method for determining the presence / absence of irradiation squeezing in a photographed image, which comprises a plurality of irradiation squeezing presence / absence determining steps for executing the above-described irradiation squeezing presence / absence determining processing. And a selection step of selecting an arbitrary irradiation restriction presence / absence determination step from the irradiation restriction presence / absence determination step.

In a thirty-second invention based on the thirty-first invention, the plurality of irradiation squeezing presence / absence determining steps include a step of performing the irradiation squeezing presence / absence determining processing in accordance with different algorithms. The method further comprises a step of selecting the arbitrary irradiation squeezing presence / absence determining step based on the determination results of the plurality of irradiation squeezing presence / absence determining steps for a predetermined number of times.

A thirty-third invention is characterized in that, in the thirty-first invention, the selecting step includes a step of selecting the arbitrary irradiation narrowing presence / absence determining step based on the photographed image.

A thirty-fourth aspect of the present invention is the display apparatus according to the thirty-first aspect of the invention, wherein a display step is provided for displaying an irradiation area of the photographed image obtained from the determination results of the plurality of irradiation restriction presence / absence determination steps, and the display step is performed. An instruction step for giving an instruction to modify the irradiation area, and an irradiation area displayed by the display step, or a storage step of storing the irradiation area after the correction by the instruction step, wherein the selection step includes the plurality of Based on the determination result of the irradiation restriction presence determination step, and the determination accuracy of the plurality of irradiation restriction presence determination step obtained by the information of the irradiation region stored by the storage step, the arbitrary irradiation restriction presence determination step It is characterized by including a step of making a selection.

A thirty-fifth aspect of the present invention is the same as the thirty-first aspect of the present invention, which includes an instruction step for externally instructing the arbitrary irradiation squeezing presence / absence determining step, and the selecting step includes
It is characterized by including a step of selecting the arbitrary irradiation narrowing presence / absence determination step based on an external instruction by the instruction step.

A thirty-sixth aspect of the present invention is an image processing method for determining the presence / absence of irradiation squeezing in a captured image, which comprises a plurality of irradiation squeezing presence / absence determining steps for determining the presence / absence of irradiation squeezing in the captured image. An area extraction step of extracting an irradiation area from the captured image, a display for displaying the irradiation area of the captured image obtained from the determination results of the plurality of irradiation restriction presence determination steps and the extraction result of the area extraction step A step, an input step for giving a correction instruction to the irradiation area displayed by the display step, information on the irradiation area displayed by the display step, or information on the irradiation area corrected by the input step is stored. Of the information stored in the storing step and the plurality of irradiation squeezing presence / absence determining steps The presence determining step diaphragm irradiated based on the accuracy of determining the plurality of irradiation aperture existence determination step obtained by the constant results, characterized in that it comprises a selection step of selecting from the plurality of irradiation aperture existence determination step.

In a thirty-seventh aspect based on the thirty-sixth aspect, the selection step compares and evaluates the information stored in the storage step with the determination results of the plurality of irradiation narrowing presence / absence determining steps. It is characterized by including a step of obtaining a correct answer rate of the determination of presence or absence of irradiation squeezing in the plurality of irradiation squeezing presence / absence determining steps, and selecting the irradiation squeezing presence / absence determining step based on the correct answer rate.

A thirty-eighth aspect of the invention is characterized in that, in the thirty-sixth aspect, the selecting step includes a step of selecting the irradiation narrowing presence / absence determining step after a predetermined number of times of photographing.

In a thirty-ninth aspect based on the thirty-sixth aspect, the selecting step includes a step of selecting the irradiation narrowing presence / absence determining step based on the photographed image.

A fortieth aspect of the present invention is a storage medium in which the processing steps of the image processing method according to any one of the twenty-first to thirty-ninth aspects are stored so that they can be read by a computer.

[0050]

BEST MODE FOR CARRYING OUT THE INVENTION Embodiments of the present invention will be described below with reference to the drawings.

(First Embodiment) In the present invention, for example,
It is applied to the X-ray imaging apparatus 100 as shown in FIG. The X-ray imaging apparatus 100 is capable of performing imaging while performing irradiation narrowing, and has a function of determining the presence or absence of irradiation narrowing from a captured image and extracting an irradiation region. Therefore, as shown in FIG. 1, the X-ray imaging apparatus 100 includes the X-ray generation circuit 101 that generates X-rays and the subject 10.
Two-dimensional X-ray sensor 10 on which X-ray light that has passed through 3 is imaged
4, a data acquisition circuit 105 for acquiring captured images output from the two-dimensional X-ray sensor 104, and a data acquisition circuit 1
A pre-processing circuit 106 that performs pre-processing on the captured image collected in 05, and various information such as a captured image (original image) that has been pre-processed by the pre-processing circuit 106 and a processing program for executing various processes. A main memory 109 for storing the information, an operation panel 110 for giving instructions and various settings to the apparatus such as execution of X-ray imaging, and a captured image (original image) preprocessed by the preprocessing circuit 106. Squeezing presence / absence determining circuit 112 for determining the presence / absence of irradiation squeeze
An irradiation area recognition circuit 113 that extracts an irradiation area from the original image based on the determination result of 12, and an irradiation area recognition circuit 113
A feature extraction circuit 114 that extracts a feature amount from the original image based on the irradiation area obtained in step 1, and a tone conversion that performs a tone conversion process on the original image using the feature amount obtained in the feature extraction circuit 114. The data acquisition circuit 105 includes a circuit 115, an image display 111 for displaying an image and the like after the gradation conversion processing in the gradation conversion circuit 115, and a CPU 108 which controls the operation of the entire apparatus. The circuit 106, the squeezing presence / absence determination circuit 112, the irradiation area recognition circuit 113, the feature amount extraction circuit 114, the gradation conversion circuit 115, the CPU 108, the main memory 109, the operation panel 110, and the image display device 11.
1 are connected to the CPU bus 107, respectively, so that data can be exchanged between them.

Here, the irradiation area recognition circuit 113 is provided with a plurality of algorithms as an algorithm for extracting the irradiation area from the original image based on the judgment result of the squeezing presence / absence judgment circuit 112. It is designed so that you can select the most suitable algorithm from among. Such a configuration is the most characteristic configuration of the present embodiment. For this reason, the irradiation area recognition circuit 113 has a plurality of irradiation area extraction circuits 113a.
(1), 113a (2), ..., 113a (n),
It includes a memory 113b that stores the extraction result of each irradiation area extraction circuit and the like, and a determination circuit 113c that determines the extraction accuracy in each irradiation area extraction circuit from the information stored in the memory 113b. Therefore, the irradiation area extraction circuit determined by the determination circuit 113c to have the highest extraction accuracy is used to extract the irradiation area of the captured image.

Therefore, the X-ray imaging apparatus 100 as described above is used.
First, in the main memory 109, the CPU 10
Data necessary for execution of various kinds of processing in 8 and processing programs are stored in advance, and a work memory for the work of the CPU 108 is included. Main memory 109
As the processing program stored in, particularly, the processing program for extracting the irradiation area, here, for example, the processing program according to the flowcharts of FIGS. 2 to 5 is used.
Therefore, the CPU 108 controls the operation of the entire apparatus as described below according to the operation from the operation panel 110 by reading the processing program and the like from the main memory 109 and executing them.

1. Main process: See Figure 2

Step S200: First, the X-ray generation circuit 1
01 emits the X-ray beam 102 to the inspection object 103. The X-ray beam 102 emitted from the X-ray generation circuit 101 passes through the inspection object 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. To be done.

At this time, when there is no irradiation restriction (in the case of whole surface irradiation), X output from the two-dimensional X-ray sensor 104
The line image is, for example, an image as shown in FIG. On the other hand, in the case where the irradiation is applied, the X-ray image output from the two-dimensional X-ray sensor 104 becomes an image as shown in FIG. 7, for example. In FIG. 7, “A” indicates the image end area, “dx” indicates the width of the area A, and “dy”.
Indicates the vertical width of the area A.

Next, the data acquisition circuit 105 uses the two-dimensional X
The X-ray image output from the line sensor 104 is converted into an electric signal, and the electric signal is supplied to the preprocessing circuit 106. The pre-processing circuit 106 performs pre-processing such as offset correction processing and gain correction processing on the signal (X-ray image signal) from the data acquisition circuit 105. The X-ray image signal pre-processed by the pre-processing circuit 106 is used as the input image information by the CPU 1
Under the control of 08, the data is transferred to the main memory 109, the squeezing presence / absence determination circuit 112, the irradiation area recognition circuit 113, the feature extraction circuit 114, and the gradation conversion circuit 115 via the CPU bus 115.

Step S201: Squeezing presence / absence determining circuit 1
By executing the processing of steps S301 to S306 in FIG. 3, the image processing apparatus 12 determines the presence or absence of the irradiation restriction from the input image (hereinafter, also referred to as “target image”) transferred under the control of the CPU 108.

1-1. Squeezing determination process (step S20
1): See Fig. 3

Step S301: First, in order to determine whether or not there is irradiation squeezing in the left end portion (the area A in FIG. 5) of the target image, the maximum pixel value (MAX value) of the target image is determined. ) Is extracted. As the MAX value here, for example, the pixel value of the upper part (the upper 5% point or the like) of the cumulative histogram of the pixels of the entire target image may be used, or the upper value of the result of sorting the pixel values may be used. You may make it use the pixel value of a part.

Step S302: Next, step S30
A pixel value having a certain ratio of the MAX value extracted in 1 above, for example, 90% or more is calculated.

Step S303: Next, step S30
The appearance frequency of the pixel value obtained in 2 at the left end portion (region A) of the target image is obtained.

Steps S304 to S306: Then, it is judged whether or not the appearance frequency obtained in step S303 is larger than a predetermined value Th1 (step S304). As a result of this judgment, if it is larger, the left end portion of the target image (region Irradiation is not applied to A) (step S305). If not, irradiation is applied to the left end portion (region A) of the target image (step S306).

The presence / absence of the illumination restriction as described above is similarly determined for the right end portion, the upper portion and the lower portion of the target image. Then, based on this determination result, the irradiation area recognition circuit 113 performs the following processing.

Step S202: Return to the main processing of FIG. 2 for reference. First, the first irradiation area extraction circuit 113a (1) operates as shown in FIG.
By executing the processing of steps S401 to S405, the irradiation area is extracted from the target image transferred under the control of the CPU 108.

1-2. First irradiation area extraction processing (step S202): See FIG.

Step S401: First, the target image is "f
(X, y) ", the vertical length of the image is" Lv ", and the horizontal length is" L "
h ”as the projection fh of the entire target image
(X)

[0068]

[Equation 1]

It is created by the following equation (1).

Step S402: Next, step S40
Projection fh (x) created in 1 with constant d
Hold 2 (for example, 5 mm),

[0071]

[Equation 2]

Smoothing is performed by the following equations (2) to (4).

Step S403: Next, step S40
The first-order difference value S1 (x) of the projection f2 (x) after the smoothing in 2 has a difference distance d3 (for example, 7 mm),

[0074]

[Equation 3]

It is obtained by the following equation (5).

Step S404: Next, step S40
The secondary difference value S2 of the primary difference value S1 (x) obtained in 3
(X) with a difference distance d3 (for example, 7 mm),

[0077]

[Equation 4]

It is determined by the following equation (6).

Step S405: Then, the left and right end points El1 and Er1 of the irradiation area of the target image are set to step S404.
With the second-order difference value S2 (x) obtained in

[0080]

[Equation 5]

It is obtained by the following equations (7) and (8).

As described above, the first irradiation area extraction circuit 113a (1) obtains the left and right end points El1 and Er1 of the irradiation area of the target image. Similarly, the upper and lower end points are also obtained. The irradiation area in the target image is determined by these left, right, upper, and lower points.

Step S203: Return to the main processing of FIG. 2 for reference. Next, the second irradiation area extraction circuit 113a (2) operates as shown in FIG.
By executing the processing of steps S501 to S510, the irradiation area is extracted from the target image transferred under the control of the CPU 108.

1-3. Second irradiation area extraction processing (step S203): See FIG.

Step S501: First, the maximum value is obtained from the pixel values of the entire target image and multiplied by a constant (for example,
The value multiplied by 0.8 is set as the threshold Th2. Specifically, for example, a cumulative histogram of pixels of the entire target image is created, the pixel value of the upper portion (upper 5% point, etc.) is obtained, and the multiple of the constant is set as the threshold Th2. Alternatively, the pixel value of the upper part of the result of sorting the pixel values is obtained, and a constant multiple thereof is set as the threshold Th2.

Step S502: Next, the processing from step S503 is performed on each of the regions obtained by dividing the length Lv of the target image in the Y-axis direction by 40 by the distance d1, for example. Therefore, in this step, the area to be processed from step S503 is selected. Here, it is assumed that the n-th row area is selected.

Step S503: Next, step S50
Projection Fn of the nth area selected in 2
(X)

[0088]

[Equation 6]

It is determined by the following equation (9).

Step S504: Next, step S50
Nth projection Fn (x) created in 3
(One-dimensional column data)

[0091]

[Equation 7]

Smoothing is performed by the following equations (10) to (12).

Step S505: Next, step S50
The first-order difference value Sn (x) of the projection Fn (x) after smoothing in 4 has a difference distance d3 (for example, 7 mm),

[0094]

[Equation 8]

It is obtained by the following equation (13).

Step S506: Next, step S50
Second-order difference value Snn of first-order difference value Sn (x) obtained in 5
(X) with a difference distance d3 (for example, 7 mm),

[0097]

[Equation 9]

It is obtained by the following equation (14).

Step S507: Next, step S50
The first-order difference value Sn (x) obtained in 5 is positive, and the second-order difference value Snn obtained in step S506 in the negative region.
The points Eln and Ern at which (x) becomes the minimum value are

[0100]

[Equation 10]

Equation (15) and (16)

[0102]

[Equation 11]

As shown in equations (17) and (18), the projection values Fn of the points Eln and Ern are
When (Eln) and Fn (Ern) are greater than or equal to the threshold value Th2, those points Eln and Ern are set as the left and right end candidate points of the irradiation area.

Step S508: The left and right end candidate points Eln and Ern of the irradiation area acquired in step S507 are stored in the main memory 109.

Step S509: n as described above
When the processing of steps S502 to S508 for the area of the second row is completed, the process returns to step S502 to execute the processing for the area of the next (n + 1) th row. Then, when the processing for the areas of the 1st, 2nd, ..., N, ..., 40th rows is completed, the process proceeds to the next step S510.

Step S510: When the candidate point extraction processing is completed for all the areas up to the 40th, the candidate points of the respective areas stored in the main memory 109 are used to determine the left and right end candidate points Eln and Ern. Overlap Nl (x), Nr
(X) has a constant d4 (for example, 10 mm),

[0107]

[Equation 12]

It is obtained by the following equations (19) and (20). Then, from the overlapping Nl (x) and Nr (x), the left and right end points El2 and Er2 of the irradiation region of the target image are

[0109]

[Equation 13]

It is determined according to the following equations (21) and (22).

As described above, the second irradiation area extraction circuit 113a (2) obtains the left and right end points El2 and Er2 of the irradiation area of the target image. Similarly, the upper and lower end points are also obtained. The irradiation area in the target image is determined by these left, right, upper, and lower points.

Step S204: Return to the main processing of FIG. 2 and refer to the other irradiation area extraction circuits 113a (3) to 113 (n) in the same manner according to the respective algorithms.
The irradiation area is extracted from the target image transferred under the control of 108.

Step S205: As described above, the first irradiation area extraction circuit 113a (1), the second irradiation area extraction circuit 113a (2), ..., The nth irradiation area extraction circuit 113a (n). The extraction result of the irradiation region obtained in each of the above), that is, the extraction result of the n kinds of irradiation regions is stored in the memory 113b.

Step S206: Then, the determination circuit 11
The reference numeral 3c denotes a squeezing presence / absence determination circuit 11 for each of the n types of irradiation region extraction results stored in the memory 113b.
The judgment results of 2 are integrated.

Specifically, for example, when the first irradiation area extraction circuit 113a (1) is the object of integration and the judgment result of the restriction presence / absence judgment circuit 112 is "no irradiation restriction",
The edge of the target image (original image) is adopted as the edge of the irradiation area. On the other hand, the determination result of the presence / absence determination circuit 112 is "
In the case of “with irradiation restriction”, the end of the irradiation area extracted by the first irradiation area extraction circuit 113a (1) is adopted. Then, the result of the integration processing (adopted irradiation area) as described above is used. , The image display 1 together with the target image (original image)
Displayed by 11.

Step S207: Here, the image display 1
Reference numeral 11 has a touch panel function, and the user confirms the content displayed on the image display 111. As a result, for example, when the recognition result of the irradiation area in the original image is incorrect, the correct irradiation area is designated by the touch panel function (touch the touch panel). Alternatively, a correct irradiation area is designated by operating an input means (not shown) such as a mouse. This designation information is used as the determination circuit 113c.
Given to. The determination circuit 113c performs step S206.
Then, it is determined whether or not the irradiation area displayed on the image display device 111 is designated by the user, that is, whether or not the irradiation area is correct.

Steps S208 and S209: Step S
As a result of the determination in 207, if the irradiation area displayed on the image display 111 in step S206 is incorrect, the determination circuit 113c corrects the irradiation area to be finally adopted to the area instructed by the user (step S208) and the coordinates thereof are stored in the memory 113b together with the information of the determination result of step S207 (such as the fact that the extraction of the irradiation area has failed and the identification information of the irradiation area extraction circuit that has performed the extraction) (step S209). ).

Step S210: On the other hand, step S20
As a result of the determination of 7, the image display 11
When the irradiation area displayed in 1 is correct, the determination circuit 113c
Is the irradiation area to be finally adopted as the irradiation area, and the coordinates thereof are the information of the result of the determination in step S207 (the success of the extraction of the irradiation area and the identification of the irradiation area extraction circuit that has performed the extraction). Information 11) together with the memory 11
Save in 3b.

Step S211: When the irradiation area recognition circuit 113 finishes recognition of the irradiation area as described above, the feature extraction circuit 114 analyzes the recognition result (coordinates of the irradiation area) stored in the memory 113b. Then, based on this, from the target image (original image) transferred under the control of the CPU 108, the feature amount max for gradation conversion processing
To calculate. For example, if the target image is a lung image,
The maximum value of the pixels in the lung is extracted as the feature amount max. The gradation conversion circuit 115 extracts the characteristic amount extracted by the characteristic extraction circuit 114 from the target image (original image) transferred under the control of the CPU 108 by, for example, a gradation conversion curve as shown in FIG. max is a predetermined density value (for example, 1.
8) and the like are performed. In FIG. 8, the horizontal axis represents the pixel value of the original image, and the vertical axis represents the pixel value after gradation conversion.

Step S212: Then, the CPU 108
Determines whether or not a series of processes from the start of shooting to the gradation conversion process in steps S200 to S211 has been performed a predetermined number of times Th, that is, whether the number of times of shooting has been repeatedly performed a predetermined number of times Th. If the result of this determination is that the number of executions has not reached the predetermined number Th, step S20.
The process returns to 0 and the processing from the start of shooting is repeatedly executed.

Step S213: The number of times of photographing is a predetermined number of times T
When h (for example, Th = 1000) is reached, the determination circuit 1
13c verifies the coordinates of the irradiation area stored in the memory 113b and the extraction result of each irradiation area extraction circuit,
The extraction accuracy of each irradiation area extraction circuit is evaluated. Specifically, for example, the determination result of the squeezing presence / absence determining circuit 112 is "irradiation is present", and the left end point (left end point of correct answer) finally adopted as the left end of the irradiation area is "E".
l ″, where the left end point, which is the extraction result of the nth irradiation area extraction circuit 113a (n), is “Eln”,

[0122]

[Equation 14]

As shown in the equation (23), if the difference between the left end point Eln in the nth irradiation area extraction circuit 113a (n) and the correct left end point El is within the predetermined value d1, the nth irradiation The area extraction circuit 113a (n) considers that the irradiation area has been successfully extracted. Such an evaluation is performed for each irradiation area extraction circuit, and the number of correct answers is totaled for each irradiation area extraction circuit.

Step S214: Then, the judgment circuit 11
3c selects the irradiation region extraction circuit that has the most correct answers in the n times of imaging from the evaluation result in step S213.

Step S215: As described above, when the optimum irradiation area extraction circuit for the object is selected from the plurality of irradiation area extraction circuits, the actual photographing is performed. The picked-up image obtained by this photographing is subjected to extraction of the irradiation area by the selected irradiation area extraction circuit, extraction of the characteristic amount and gradation conversion processing based thereon, and then the image display 111. Or it is output on the film.

As described above, in the present embodiment, in the photographing for the predetermined number of times Th, the irradiation area based on the judgment result of the restriction presence / absence judgment circuit 112 is selected from the plural irradiation area extraction circuits each having a different algorithm. Since it is configured to automatically select the one with the highest accuracy rate of extraction of
For the subsequent photographing, the irradiation area can be always accurately extracted from the target image by using the optimum irradiation area extraction circuit that depends on the subject to be imaged. Therefore, according to the present embodiment, it is possible to improve the extraction accuracy of the irradiation region and perform favorable gradation conversion processing.

In the above-described embodiment, the evaluation and selection of the irradiation area extraction circuit is not limited to the processing in steps S213 and S214 described above, and for example, for each subject to be imaged (hand, foot, lung). The correct answer rate may be summed up for each irradiation area extraction circuit (for each imaging region) and the irradiation area extraction circuit having the highest correct answer rate may be selected for each subject. As a result, the optimum irradiation area extraction circuit can be automatically selected according to the imaged region.

(Second Embodiment) The present invention is, for example, as follows.
It is applied to an X-ray imaging apparatus 600 as shown in FIG. This X-ray imaging apparatus 600 is the same as the X-ray imaging apparatus 10 shown in FIG.
As in the case of 0, it is possible to perform shooting while performing irradiation narrowing, and to have a function of determining the presence or absence of irradiation narrowing from a captured image and extracting an irradiation region. In the X-ray imaging apparatus 600 shown in FIG. 9, parts that operate in the same manner as the X-ray imaging apparatus 100 shown in FIG. 1 are given the same reference numerals, and detailed description thereof will be omitted.

Here, the X-ray imaging apparatus 600 according to the present embodiment has the same structure as the X-ray imaging apparatus 100 of FIG. 1 described above, but the algorithm for the X-ray imaging apparatus 100 to extract the irradiation region is described. In contrast to the configuration in which a plurality of X-ray imaging apparatuses are provided, the X-ray imaging apparatus 600 according to the present embodiment has a configuration in which a plurality of algorithms for determining whether or not there is an irradiation restriction are provided. That is, the irradiation squeezing determination circuit 602 of the X-ray imaging apparatus 600 is configured to be able to select an optimal algorithm from a plurality of algorithms for irradiating squeezing presence / absence determination. The most characteristic configuration. Therefore, the irradiation squeezing determination circuit 602 determines whether there are a plurality of irradiation squeezing presence determination circuits 602.
a (1), 602a (2), ..., 602a (n)
And a memory 602b that stores the determination result of each irradiation restriction presence / absence determination circuit, and a determination circuit 602c that determines the determination accuracy in each irradiation restriction presence determination circuit from the information stored in the memory 602b. . Therefore, the determination circuit 602c determines the presence or absence of the illumination restriction of the captured image using the illumination restriction presence / absence determination circuit determined to have the highest determination accuracy.

In the X-ray imaging apparatus 600 as described above, first, as a processing program stored in the main memory 109, in particular, as a processing program for determining the presence or absence of irradiation restriction, here, for example, the flowcharts of FIGS. The processing program according to is used. Therefore,
The CPU 108 reads the processing program and the like from the main memory 109 and executes the processing program, so that the operation panel 11
The operation control of the entire apparatus as described below is performed according to the operation from 0.

1. Main processing: See FIG. 10 and FIG.

Step S700: First, the X-ray generation circuit 1
01 emits the X-ray beam 102 to the inspection object 103. The X-ray beam 102 emitted from the X-ray generation circuit 101 passes through the inspection object 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. To be done. At this time,
The X-ray image output from the two-dimensional X-ray sensor 104 is an image without irradiation restriction as shown in FIG. 6 or an image with irradiation restriction as shown in FIG.

Next, the data acquisition circuit 105 outputs the two-dimensional X
The X-ray image output from the line sensor 104 is converted into an electric signal, and the electric signal is supplied to the preprocessing circuit 106. The pre-processing circuit 106 performs pre-processing such as offset correction processing and gain correction processing on the signal (X-ray image signal) from the data acquisition circuit 105. The X-ray image signal pre-processed by the pre-processing circuit 106 is used as the input image information by the CPU 1
Under the control of 08, the data is transferred to the main memory 109, the irradiation area recognition circuit 601, the squeezing presence / absence determination circuit 602, the feature extraction circuit 114, and the gradation conversion circuit 115 via the CPU bus 115.

Step S701: Irradiation area recognition circuit 60
1 executes the processing of steps S801 to S804 in FIG. 12 to extract the irradiation area from the input image (target image) transferred under the control of the CPU 108.

1-1. Irradiation area recognition processing (step S7
01): See FIG.

Step S801: First, in order to extract the left and right end points of the irradiation area in the target image, the target image f
(X, y), its vertical width Dy, horizontal width Dx
holding,

[0137]

[Equation 15]

The projection f (x) is obtained by the following equation (24).

Step S802: Next, step S80
First-order difference value S1 of projection f (x) at 1
(X) with a difference distance d (for example, 1 mm),

[0140]

[Equation 16]

It is obtained by the following equation (25).

Step S803: Next, step S80
The secondary difference value S2 of the primary difference value S1 (x) obtained in 2
(X) with a difference distance d (for example, 1 mm),

[0143]

[Equation 17]

It is obtained by the following equation (26).

Step S804: Then, the left and right end points El1 and Er1 of the irradiation area of the target image are set to step S803.
With the second-order difference value S2 (x) obtained in

[0146]

[Equation 18]

It is obtained by the following equations (27) and (28).

As described above, the irradiation area extraction circuit 60
1, the left and right end points El1 and Er1 of the irradiation area of the target image
Is required. Similarly, the upper and lower end points are also obtained. The irradiation area in the target image is determined by these left, right, upper, and lower points. The result of this irradiation area extraction is stored in the memory 602b. The irradiation area extraction circuit 601
The algorithm used in is not limited to the algorithm shown in FIG. For example, it may be any of the algorithms used in the first to nth irradiation area extraction circuits in the above-described first embodiment.

Step S702: Return to the main processing of FIGS. 10 and 11 for reference. Next, the first restriction presence / absence determining circuit 602a (1) executes the processing of steps S901 to S905 of FIG. The presence / absence of irradiation squeezing of the input image (target image) transferred by the control is performed.

1-2. First squeezing determination process (step S702): see FIG.

Step S901: First, in order to determine whether or not there is an irradiation narrowing at the left end portion (portion A in FIG. 5) of the target image, the maximum pixel value (MAX value) of the target image is determined. ) Is extracted. As the MAX value here, for example, the pixel value of the upper part (the upper 5% point or the like) of the cumulative histogram of the pixels of the entire target image may be used, or the upper value of the result of sorting the pixel values may be used. You may make it use the pixel value of a part. Then, a pixel value having a certain ratio of the MAX value, for example, 90% or more is obtained as the characteristic value.

Step S902: Next, step S90
The appearance frequency of the characteristic value obtained in 1 at the left end portion (region A) of the target image is obtained.

Steps S903 to S905: Then, it is judged whether or not the appearance frequency obtained in step S902 is larger than a predetermined value Th1 (step S903). As a result of this judgment, if the result is large, the left end portion of the target image (region Irradiation is not applied to A) (step S905), and if not, irradiation is applied to the left end portion (region A) of the target image (step S904).

As described above, the first restriction presence / absence determining circuit 602a (1) determines the presence / absence of irradiation restriction at the left end of the target image. In the same manner, the presence / absence of irradiation squeezing is determined for the right end portion, the upper portion and the lower portion.

Step S703: Return to the main process of FIGS. 10 and 11 for reference Next, the second squeezing presence / absence determination circuit 602a (2) executes the processes of steps S1001 to S1009 of FIG. The presence / absence of irradiation squeezing of the input image (target image) transferred by the control is performed.

1-3. Second squeezing determination process (step S703): refer to FIG. 14. It is assumed here that the target image is an image 1020 as shown in FIG. 16 for simplicity of description. This FIG.
The image 1020 is an image obtained by photographing with the illumination restriction, and “Xa” and “Xb” in the figure indicate the positions of the edges of the illumination area with respect to the horizontal axis. In addition, areas A, B, C,
D indicates the end of the irradiation area, and of these areas, areas A and B indicate areas with irradiation restriction, and areas C and D.
Indicates an area without irradiation.

Step S1001: First, in the image 1020 shown in FIG. 16 above, in order to determine whether or not the areas C and D have the irradiation narrowing, the positions Xa and Xb are evenly distributed on the X axis by 10 degrees or the like. The processing from the next step S1002 is executed for each of the divided coordinates i (i = 1 to 10). Therefore, in this step, the coordinate i to be processed is determined.

Step S1002: Next, step 10
The second-order difference value SSi (y) of the one-dimensional data string fi (y) that crosses the coordinate i determined in 01 in the Y-axis direction has a difference distance d (for example, 1 mm),

[0159]

[Formula 19]

It is obtained by the following equation (29).

Step S1003: Next, step S1
From the secondary difference value SSi (y) obtained in 002, the coordinates yi of the end of the irradiation region are

[0162]

[Equation 20]

It is obtained by the following equation (30).

Step S1004: And step S
The coordinate yi obtained in 1002 is stored in the main memory 109, and the process returns to step S1001 to execute the process for the next coordinate y (i + 1).

Step S1005: When the processing of steps S1001 to S1004 for each of the coordinates i = 1 to 10 is completed, the coordinates yi (i = 1 to 10) of the end of the irradiation area stored in the main memory 109. Calculate the average value of.

Step S1006: Next, step S1
The variance value Bv of the coordinates yi at the end of the irradiation area is obtained from the average value obtained in 005.

Steps S1007 to S1009: Then, it is determined whether or not the variance value Bv obtained in step S1006 is smaller than a predetermined value Th5 (step S100).
7) As a result of this determination, if the variance value Bv is smaller than the predetermined value Th5, it is determined that the areas C and D are irradiating (step S1008), and if the variance value Bv is not smaller than the predetermined value Th5. , Areas C and D are determined to have no irradiation (step S1009). This is because the irradiation region end is obtained in a plurality of columns, and if the target region has an irradiation spot, the coordinates of the plurality of end points are arranged on substantially the same horizontal axis, so the variance value Bv becomes small, and if there is no irradiation spot. , Because the coordinates of the plurality of end points are scattered, the variance value Bv becomes large. As the predetermined value Th5 here, a constant determined by experiments or the like is used.

As described above, in the second squeezing presence / absence determining circuit 602a (2), the area C of the target image 1020,
It is determined whether or not there is an irradiation restriction in D (the upper part and the lower part of the irradiation area). In the same manner, the presence / absence of irradiation restriction is also determined for the areas A and B (left and right end portions of the irradiation area).

The second squeezing presence / absence determining circuit 602a
In (2), the second-order difference value SSi (y) is obtained in step S1002. However, for example, when the concentration at the edge of the irradiation region changes abruptly, the first-order difference value, the higher-order difference value, or the like is calculated. You may ask. In this case, the pixel value at the edge of the target image is searched, and the point where the pixel value equal to or larger than the predetermined threshold value first appears is set as the candidate point at the edge of the irradiation area. Further, in step S1007, the variance value Bv is used as an index for determining the presence or absence of irradiation squeezing, but the present invention is not limited to this, and for example, an index indicating the discreteness of other frequencies such as standard deviation may be used. Good.

Step S704: Return to the main processing of FIGS. 10 and 11 for reference. Next, the third restriction presence / absence determining circuit 602a (3) executes the processing of steps S1011 to S1016 of FIG. The presence / absence of irradiation squeezing of the input image (target image) transferred by the control is performed.

1-4. Third squeezing determination processing (step S704): refer to FIG. 15. Here, for the sake of simplicity of explanation, the target image is the one shown in FIG.
It is assumed that the image 1020 is as shown in FIG.

Step S1011: First, in the image 1020 shown in FIG. 16 above, in order to determine whether or not the area C has an illumination restriction, a one-dimensional data string f (x) that horizontally traverses the area C is obtained. Second-order difference value SS (x)
With a difference distance d (for example, 1 mm),

[0173]

[Equation 21]

It is obtained by the following equation (31).

Step S1012: Next, the left end portion x1 of the irradiation area is

[0176]

[Equation 22]

It is obtained by the following equation (32). This formula (3
In 2), “XH” indicates coordinates on the horizontal axis (coordinates between positions Xa and Xb shown in FIG. 16) in the left and right ends of the irradiation area.

Step S1013: Step S1012
In the same manner as above, next, the right end portion x2 of the irradiation area is

[0179]

[Equation 23]

It is obtained by the following equation (33).

Steps S1014 to S1016: Then, in step S701 described above, the result of the irradiation area (here, the lower area) extracted by the irradiation area recognition circuit 112 and the left and right end portions obtained in steps S1012 and S1013. Area C indicated by x1 and x2
And compare

[0182]

[Equation 24]

It is determined whether or not the conditional expression (34) is satisfied (step S1014). As a result of the determination, if the conditional expression (34) is satisfied, it is determined that the area C is not illuminated (step S1015). If the conditional expression (34) is not satisfied, it is determined that the area C has the irradiation restriction (step S1016). In addition, "Th8" in the equation (34)
Is a constant indicating the approximate width and is a value obtained by experiments or the like.

As described above, in the third squeezing presence / absence determining circuit 602a (3), the area C of the target image 1020 is displayed.
The presence / absence of the irradiation restriction in (the lower part of the irradiation region) is determined. In the same manner, the presence / absence of irradiation restriction is also determined for the areas A, B, and D (left and right end portions of the irradiation area, upper portion).

The third restriction presence / absence determining circuit 602a
In step S1014 of (3), the conditional expression (3
Further conditions may be added to 4). For example, a condition may be added in which the secondary difference value is constant and equal to or less than the threshold value. Also, step S101
If the concentration change at the edge of the irradiation region is sharp, instead of the second-order difference value SS (x) of 1, the values of the first-order differential, the second-order differential, and the higher-order differential are used. Good. In this case, the location where the absolute value of each value is equal to or greater than a certain threshold is set as a candidate for the irradiation area edge.

Step S705: Return to the main process of FIGS. 10 and 11, and refer to other squeezing presence / absence determining circuits 602a (4) to 602a.
Similarly for (n), the presence or absence of illumination restriction of the target image transferred under the control of the CPU 108 is determined according to the respective algorithms.

Step S706: As described above, the first squeezing presence / absence determining circuit 602a (1), the second squeezing presence / absence determining circuit 602a (2), the third squeezing presence / absence determining circuit 602a (3), ... The result of the irradiation restriction presence determination obtained by each of the nth restriction determination circuits 602a (n), that is, the result of the n types of irradiation restriction determination is stored in the memory 113b.

Step S708: Then, the judgment circuit 60
2c integrates the recognition result of the irradiation area in the irradiation area recognition circuit 601 with each of the n kinds of irradiation restriction presence / absence determination results stored in the memory 113b.

Specifically, for example, if the first squeezing presence / absence determining circuit 602a (1) is the object of integration and the result of this illumination squeezing presence / absence determination is "no irradiation squeezing", the target image (original image) Is used as the end of the irradiation area. On the other hand, when the result of the presence / absence of irradiation restriction of the first restriction presence / absence determination circuit 602a (1) is “with irradiation restriction”, the end portion of the irradiation region extracted by the irradiation region extraction circuit 601 is adopted. Then, the result of the above-described integration process (adopted irradiation area) is displayed on the image display device 111 together with the target image (original image).

Step S709: Here, the image display 1
Reference numeral 11 has a touch panel function, and the user confirms the content displayed on the image display 111. As a result, for example, when the recognition result of the irradiation area in the original image is incorrect, the correct irradiation area is designated by the touch panel function (touch the touch panel). Alternatively, a correct irradiation area is designated by operating an input means (not shown) such as a mouse. This designation information is used as the determination circuit 602c.
Given to. The determination circuit 602c is step S708.
Then, it is determined whether or not the irradiation area displayed on the image display device 111 is designated by the user, that is, whether or not the irradiation area is correct.

Steps S711 and S712: Step S
If the irradiation area displayed on the image display 111 in step S708 is incorrect as a result of the determination in step 709, the determination circuit 602c corrects the irradiation area to be finally adopted to the area instructed by the user (step S711) and the coordinates thereof are stored in the memory 602b together with the information of the result of the determination in step S709 (the failure of extraction of the irradiation region and the identification information of the target squeezing presence / absence determining circuit, etc.) (step S712). .

Step S710: On the other hand, step S70
As a result of the determination of 9, the image display 11 is displayed in step S708.
When the irradiation area displayed in 1 is correct, the determination circuit 602c
Is the irradiation area to be finally adopted as the irradiation area, and the coordinates thereof are the information of the result of the determination in step S709 (the success of the extraction of the irradiation area and the identification information of the targeted presence / absence determination circuit). Etc.) together with the memory 602
Save in b.

Step S713: When the extraction of the irradiation area is completed as described above, the feature extraction circuit 114 analyzes the extraction result (coordinates of the irradiation area) of the irradiation area stored in the memory 602b, and based on the analysis result. CPU 108
From the target image (original image) transferred under the control of
A feature amount max for gradation conversion processing is calculated. For example, when the target image is a lung image, the maximum value of pixels in the lung is extracted as the feature amount max. Gradation conversion circuit 115
For the target image (original image) transferred under the control of the CPU 108, the feature amount max extracted by the feature extracting circuit 114 is a predetermined density, for example, by the gradation conversion curve as shown in FIG. The gradation conversion processing is performed so that the value (for example, 1.8) is obtained.

Step S714: Then, the CPU 108
Determines whether or not the series of processes from the start of image capturing to the gradation conversion process in steps S700 to S713 has been executed a predetermined number of times Th ', that is, whether the number of times of image capturing has been repeatedly executed a predetermined number of times Th'. If the result of this determination is that the number of executions has not reached the predetermined number Th ', the process returns to step S700, and the processing from the start of shooting is repeatedly executed.

Step S715: The number of times of photographing is the predetermined number T.
When h ′ (for example, Th ′ = 1000) is reached, the determination circuit 602c verifies the coordinates of the irradiation area stored in the memory 602b and the determination result of each squeezing presence determination circuit, and determines each squeezing presence determination circuit. The evaluation accuracy is evaluated, and the number of correct answers is totaled for each squeezing existence judgment circuit.

Step S716: Then, the determination circuit 60
2c selects the squeezing presence / absence determining circuit that has the most correct answers in the n times of imaging from the evaluation result in step S715.

Step S717: As described above, when the optimum shrinkage presence / absence determining circuit for the subject is selected from the plurality of shrinkage presence / absence determining circuits, actual photographing is performed. In the picked-up image obtained by this photographing, the presence / absence of irradiation restriction is determined by the selected restriction presence / absence determining circuit, the irradiation area is extracted by the irradiation area extracting circuit 601, and the feature amount is extracted based on the extraction area. And gradation conversion processing is performed, and thereafter, the image is displayed on the image display device 111 or output on a film.

As described above, in the present embodiment, in the photographing for the predetermined number of times Th, the one having a high correct answer rate of the determination of the presence or absence of the irradiation squeezing is automatically selected from the plurality of squeezing presence / absence determination circuits each having a different algorithm. Since it is configured to be selected selectively, the irradiation region can always be accurately extracted from the target image by using the optimum shake-presence / non-existence determining circuit depending on the subject to be imaged in the subsequent shooting. Therefore, according to the present embodiment, it is possible to improve the extraction accuracy of the irradiation region and perform favorable gradation conversion processing.

Incidentally, in the above-mentioned second embodiment,
The evaluation and selection of the squeezing presence / absence determination circuit is not limited to the processing in steps S715 and S716 described above, and, for example, the accuracy rate is squeezed for each subject to be imaged (for each imaging site such as hand, foot, or lung). Total for each presence / absence determination circuit,
The squeezing presence / absence determining circuit having the highest correct answer rate may be selected for each subject. This makes it possible to automatically select the optimum squeezing presence / absence determining circuit according to the imaged region.

In the first and second embodiments described above, the irradiation area extraction circuit or the squeezing presence / absence determination circuit is automatically selected. However, the present invention is not limited to this. The instruction may be made according to a user's instruction (manual instruction) from the panel 110 or the like. As a result, it is possible to select any irradiation area extraction circuit or squeezing presence / absence determination circuit.

Further, an object of the present invention is to supply a storage medium storing a program code of software for realizing the functions of the host and the terminal of each of the above-described embodiments to a system or an apparatus, and a computer of the system or the apparatus. It is needless to say that it is achieved by (or CPU or MPU) reading and executing the program code stored in the storage medium. In this case, the program code itself read from the storage medium realizes the functions of the respective embodiments, and the storage medium storing the program code constitutes the present invention. As a storage medium for supplying the program code, RO
M, flexible disk, hard disk, optical disk, magneto-optical disk, CD-ROM, CD-R, magnetic tape, non-volatile memory card, etc. can be used. Further, by executing the program code read by the computer, not only the functions of the respective embodiments are realized, but also based on the instruction of the program code,
It goes without saying that this also includes the case where the OS or the like running on the computer performs a part or all of the actual processing and the processing realizes the functions of the respective embodiments.
Further, after the program code read from the storage medium is written in the memory provided in the extended function board inserted in the computer or the extended function unit connected to the computer, the extended function is executed based on the instruction of the program code. C on board and function expansion unit
It goes without saying that a case where a PU or the like performs a part or all of the actual processing and the functions of the respective embodiments are realized by the processing is also included.

[0202]

As described above, according to the present invention, a plurality of area extracting means for extracting a predetermined area from a target image are provided, and an arbitrary area extracting means is selected from them. With this, it is possible to extract a predetermined area using the optimum area extracting means for the target image. Thereby, the extraction accuracy of the predetermined area can be improved. Further, according to the present invention, a plurality of irradiation squeezing presence / absence determining means for determining the presence / absence of irradiation squeezing in a captured image are provided, and an arbitrary irradiation squeezing presence / absence determining means is configured to be selected from among them. The presence / absence of irradiation restriction can be determined using an optimum irradiation restriction presence / absence determining unit for an image. As a result, it is possible to improve the accuracy of determining the presence or absence of irradiation restriction.

[Brief description of drawings]

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

FIG. 2 is a flowchart for explaining main processing executed by the X-ray imaging apparatus.

FIG. 3 is a flowchart for explaining a squeezing determination process of the main process.

FIG. 4 is a flowchart for explaining a first irradiation area extraction process of the main process.

FIG. 5 is a flowchart for explaining a second irradiation area extraction process of the main process.

FIG. 6 is a diagram for explaining an example of an image obtained by imaging without irradiation narrowing in the X-ray imaging apparatus.

FIG. 7 is a diagram for explaining an example of an image obtained by imaging with irradiation narrowing in the X-ray imaging apparatus.

FIG. 8 is a flowchart for explaining a gradation conversion process of the main process.

FIG. 9 is a block diagram showing a configuration of an X-ray imaging apparatus to which the present invention has been applied in the second embodiment.

FIG. 10 is a flowchart for explaining a main process (START to S714) executed by the X-ray imaging apparatus.

FIG. 11 is a flowchart for explaining the main processing (S714 to END).

FIG. 12 is a flowchart illustrating an irradiation field recognition process of the main process.

FIG. 13 is a flowchart illustrating a first squeezing determination process of the main process.

FIG. 14 is a flowchart for explaining a second squeezing determination process of the main process.

FIG. 15 is a flowchart illustrating a third squeezing determination process of the main process.

[Fig. 16] Fig. 16 is a diagram for describing an example of an image that is a target in the narrowing determination process.

[Explanation of symbols]

100 X-ray imaging apparatus 101 X-ray generation circuit 102 X-ray beam 103 Subject 104 Two-dimensional X-ray sensor 105 Data acquisition circuit 106 Pre-processing circuit 107 CPU bus 108 CPU 109 Main memory 110 Operation panel 111 Image display 112 Squeezing presence / absence determination circuit 113 Irradiation Area Recognition Circuits 113a (1) to 113a (n) First to nth Irradiation Area Extraction Circuits 113b Memory 113c Judgment Circuit 114 Feature Extraction Circuit 115 Gradation Conversion Circuit 600 X-Ray Imaging Device 601 Irradiation Area Recognition Circuit 602 Irradiation Squeezing determination circuits 602a (1) to 113a (n) First to nth squeezing presence / absence determination circuit 602b Memory 602c Determination circuit

Claims (40)

[Claims] 1. An image processing apparatus for extracting a predetermined area from a target image, comprising: a plurality of area extracting means for executing the extraction processing of the predetermined area; and an arbitrary area extracting means selected from the plurality of area extracting means. An image processing apparatus, comprising: 2. The plurality of area extraction means execute the extraction processing according to different algorithms, and the selection means performs the extraction processing based on the extraction results of the plurality of area extraction means for a predetermined number of executions. The image processing apparatus according to claim 1, wherein an arbitrary area extracting unit is selected. 3. The image processing apparatus according to claim 1, wherein the selecting means selects the arbitrary area extracting means based on the target image. 4. The target image includes an image obtained by radiography, the predetermined region includes an irradiation region at the time of radiography, and the selection unit is obtained by the radiography of a predetermined number of times. The image processing apparatus according to claim 1, wherein the arbitrary area extracting means is selected based on the extracted results of the plurality of area extracting means. 5. Display means for displaying the predetermined area extracted by the plurality of area extracting means, instruction means for instructing correction of the predetermined area displayed on the display means, and display means on the display means. A predetermined area or a storage means for storing the predetermined area corrected by the instructing means, and the selecting means is stored in the predetermined area extracted by the plurality of area extracting means and the storage means. The image processing apparatus according to claim 1, wherein the arbitrary area extracting means is selected based on the extraction accuracy of the plurality of area extracting means obtained from each information of the predetermined area. 6. An instruction means for instructing the arbitrary area extracting means is provided, and the selecting means is based on an instruction from the instructing means.
The image processing apparatus according to claim 1, wherein the arbitrary area extracting means is selected. 7. An image processing apparatus for extracting an irradiation area from a photographed image, comprising: irradiation restriction presence / absence determining means for determining presence / absence of irradiation restriction in the captured image; and extracting an irradiation area from the captured image. A plurality of area extracting means, a display means for displaying the irradiation area of the photographed image obtained from the determination result by the irradiation restriction presence / absence determining means, and the extraction result of the plurality of area extracting means, and displayed on the display means Input means for giving a correction instruction to the corrected irradiation area, storage means for storing information on the irradiation area displayed on the display means, or information for the irradiation area corrected by the input means, and the storage means From among the plurality of area extracting means, area extracting means based on the extraction accuracy of the plurality of area extracting means obtained from the information of An image processing apparatus comprising: a selection unit for selecting. 8. The selection means compares and evaluates the information stored in the storage means and the extraction results obtained by the plurality of area extraction means to determine the accuracy rate of extraction of the irradiation areas of the plurality of area extraction means. 8. The image processing apparatus according to claim 7, wherein the area extracting means is selected based on the obtained accuracy rate. 9. The image processing apparatus according to claim 7, wherein the selecting means selects the area extracting means after photographing a predetermined number of times. 10. The image processing apparatus according to claim 7, wherein the selecting means selects the area extracting means based on the photographed image. 11. An image processing apparatus for determining the presence or absence of irradiation squeezing in a captured image, comprising: a plurality of irradiation squeezing presence / absence determining means for executing the irradiating squeezing presence / absence determining process; and a plurality of the irradiation squeezing presence / absence determining means. An image processing apparatus comprising: a selection unit that selects an arbitrary irradiation restriction presence / absence determination unit. 12. The irradiation restriction presence / absence determining means executes the irradiation restriction presence / absence determining processing according to different algorithms, and the selecting means determines the irradiation restriction presence / absence determining means for a predetermined number of executions. The image processing apparatus according to claim 11, wherein the arbitrary irradiation squeezing presence / absence determining unit is selected based on the determination result of (1). 13. The image processing apparatus according to claim 11, wherein the selecting unit selects the arbitrary irradiation narrowing presence / absence determining unit based on the captured image. 14. Display means for displaying the irradiation area of the photographed image obtained by the judgment results by the plural irradiation restriction presence / absence judgment means, and an instruction for correcting the irradiation area displayed on the display means. Means, the irradiation area displayed on the display means, or storage means for storing the irradiation area after correction by the instructing means, the selection means, the determination result in the plurality of irradiation squeezing presence or absence determination means, 12. The arbitrary irradiation squeezing presence / absence determining means is selected based on the determination accuracy of the plurality of irradiation squeezing presence / absence determining means obtained from the information on the irradiation region stored in the storage means. The image processing device described. 15. An instruction means for instructing the arbitrary irradiation squeezing presence / absence determining means is provided, and the selecting means is based on an instruction from the instructing means.
The image processing apparatus according to claim 11, wherein the arbitrary irradiation restriction presence / absence determining unit is selected. 16. An image processing apparatus for determining the presence or absence of irradiation restriction in a captured image, comprising a plurality of irradiation restriction presence / absence determining means for determining presence / absence of irradiation restriction in the captured image, and irradiation from the captured image. Area extracting means for extracting an area, display means for displaying the irradiation area of the photographed image obtained from the determination results by the plurality of irradiation restriction presence / absence determining means and the extraction result by the area extracting means, and the display means Input means for giving a correction instruction to the irradiation area displayed on the display means, storage means for storing information on the irradiation area displayed on the display means, or information on the irradiation area corrected by the input means, Irradiation squeezing based on the determination accuracy of the plurality of irradiation squeezing presence / absence determining means obtained from the information of the storage means and the determination results of the plurality of irradiation squeezing presence / absence determining means An image processing apparatus comprising: a non-determination means, and a selection means for selecting from the plurality of irradiation restriction presence / absence determination means. 17. The selection means compares and evaluates the information of the storage means and the determination results of the plurality of irradiation squeezing presence / absence determining means to determine the presence / absence of irradiation squeezing of the plurality of irradiation squeezing presence / absence determining means. 17. The image processing apparatus according to claim 16, wherein the correct answer rate of the determination is obtained, and the irradiation restriction presence / absence determining means is selected based on the correct answer rate. 18. The image processing apparatus according to claim 16, wherein the selection unit selects the irradiation restriction presence / absence determination unit after a predetermined number of times of photographing. 19. The image processing apparatus according to claim 16, wherein the selection unit selects the irradiation restriction presence / absence determination unit based on the captured image. 20. An image processing system comprising a plurality of devices communicably connected to each other, wherein at least one of the plurality of devices is an image processing device according to any one of claims 1 to 19. An image processing system having the function of. 21. An image processing method for extracting a predetermined region from a target image, comprising: a plurality of region extraction steps for executing the predetermined region extraction process; and an arbitrary region extraction step from the plurality of region extraction steps. And a selecting step of selecting. 22. The plurality of area extraction steps include a step of executing the extraction processing according to different algorithms, respectively, and the selection step includes a predetermined number of executions of the plurality of area extraction steps. 22. The image processing method according to claim 21, further comprising a step of selecting the arbitrary area extracting step based on a result. 23. The image processing method according to claim 21, wherein the selecting step includes a step of selecting the arbitrary region extracting step based on the target image. 24. The target image includes an image obtained by radiography, the predetermined region includes an irradiation region at the time of radiography, and the selection step is obtained by a predetermined number of times of radiography. 22. The image processing method according to claim 21, further comprising a step of selecting the arbitrary area extraction step based on the extraction results obtained by the plurality of area extraction steps. 25. A display step of displaying the predetermined area obtained by the plurality of area extraction steps, an instruction step for instructing correction of the predetermined area displayed by the display step, and a display step of the display step. A predetermined area, or a storage step of storing a predetermined area after correction according to the instruction in the instruction step, the selection step, the predetermined area obtained by the plurality of area extraction step, and the storage step 22. The image processing according to claim 21, further comprising a step of selecting the arbitrary area extracting step based on the extraction accuracy in the plurality of area extracting steps obtained from each stored information of the predetermined area. Method. 26. An instruction step for externally instructing the arbitrary area extracting step is included, and the selecting step includes a step of selecting the arbitrary area extracting step based on an external instruction by the instructing step. 22. The image processing method according to claim 21, wherein: 27. An image processing method for extracting an irradiation region from a captured image, comprising: an irradiation restriction presence / absence determining step of determining presence / absence of irradiation restriction in the captured image; and an irradiation region from the captured image. A plurality of area extraction steps to extract, a determination result in the irradiation restriction presence determination step, and a display step of displaying the irradiation area of the captured image obtained from the extraction results in the plurality of area extraction steps; An input step for giving a correction instruction to the irradiation area displayed by the step, a storage step of storing information of the irradiation area displayed by the display step, or information of the irradiation area corrected by the input step; The information obtained by the storage step and the plurality of areas obtained by the extraction results of the plurality of area extraction steps. An image processing method, comprising: a region extracting step based on the extraction accuracy of the region extracting step of 1), and a selecting step of selecting from the plurality of region extracting steps. 28. Extraction of an irradiation area in the plurality of area extraction steps is performed by comparing and evaluating the information stored in the storage step and the extraction results of the plurality of area extraction steps in the selection step. 28. The image processing method according to claim 27, further comprising a step of obtaining a correct answer rate of, and selecting the area extracting step based on the correct answer rate. 29. The image processing method according to claim 27, wherein the selecting step includes a step of selecting the area extracting step after photographing a predetermined number of times. 30. The image processing method according to claim 27, wherein the selecting step includes a step of selecting the region extracting step based on the captured image. 31. An image processing method for determining the presence / absence of irradiation restriction in a captured image, comprising: a plurality of irradiation restriction presence / absence determining steps for executing the determination processing of irradiation restriction presence / absence, and the plurality of irradiation restriction presence / absence determinations. An image processing method, comprising: a selection step of selecting an arbitrary irradiation restriction presence / absence determination step from the steps. 32. The plurality of irradiation squeezing presence / absence determining steps include a step of performing the irradiation squeezing presence / absence determination processing according to different algorithms, and the selecting step includes the plurality of irradiation squeezing times for a predetermined number of executions. 32. The image processing method according to claim 31, further comprising a step of selecting the arbitrary irradiation narrowing presence / absence determining step based on a determination result in the presence / absence determining step. 33. The image processing method according to claim 31, wherein the selecting step includes a step of selecting the arbitrary irradiation restriction presence / absence determining step based on the photographed image. 34. A display step of displaying the irradiation area of the photographed image obtained by the judgment results of the plurality of irradiation restriction presence / absence judgment steps, and an instruction for instructing correction of the irradiation area displayed by the display step. Step, including the irradiation area displayed by the display step, or a storage step of storing the irradiation area after correction by the instruction step, the selection step, the determination result in the plurality of irradiation narrowing presence determination step, And a step of selecting the arbitrary irradiation restriction presence / absence determination step based on the determination accuracy of the plurality of irradiation restriction presence / absence determination steps obtained from the information of the irradiation region stored in the storage step. The image processing method according to claim 31. 35. An instruction step for externally instructing the arbitrary irradiation squeezing presence / absence determining step, wherein the selecting step selects the arbitrary irradiation squeezing presence / absence determining step based on an external instruction by the instructing step. 32. The method of claim 31 including the steps of:
The described image processing method. 36. An image processing method for determining the presence / absence of irradiation restriction in a captured image, comprising: a plurality of irradiation restriction presence / absence determining steps for determining presence / absence of irradiation restriction in the captured image; An area extraction step of extracting an irradiation area from the display area, a display step of displaying the irradiation area of the captured image obtained from the determination results in the plurality of irradiation restriction presence determination steps and the extraction result in the area extraction step, and An input step for giving a correction instruction to the irradiation area displayed by the display step, and a storage step for storing information on the irradiation area displayed by the display step or information on the irradiation area corrected by the input step , The information stored in the storage step and the determination results in the plurality of irradiation squeezing presence / absence determination steps An image processing method characterized by including an irradiation squeezing presence / absence determining step based on the determination accuracy of the plurality of irradiation squeezing presence / absence determining steps, which is selected from the plurality of irradiation squeezing presence / absence determining steps. . 37. In the selection step, the information stored in the storage step and the determination results in the plurality of irradiation squeezing presence / absence determining steps are compared and evaluated to thereby determine in the plurality of irradiation squeezing presence / absence determining steps. 37. The image processing method according to claim 36, further comprising a step of obtaining a correct answer rate for determining whether or not there is an irradiation squeeze and selecting the irradiation squeezing presence / absence determining step based on the correct answer rate. 38. The image processing method according to claim 36, wherein the selecting step includes a step of selecting the irradiation narrowing presence / absence determining step after photographing a predetermined number of times. 39. The image processing method according to claim 36, wherein the selecting step includes a step of selecting the irradiation restriction presence / absence determining step based on the photographed image. 40. A storage medium in which the processing steps of the image processing method according to claim 21 are stored so that they can be read by a computer.