JP2001222704A - Method and device for image processing - Google Patents

Abstract

PROBLEM TO BE SOLVED: To improve the recognition accuracy of an interest area, to perform stable image processing and also to easily and accurately distinguish the inside of a subject from the outside of the subject according to the position recognition of the subject. SOLUTION: A subject position where the subject appears is recognized, and an interest area is decided at a desired position in a radiation image on the basis of the recognition results of the subject position, an image processing condition is decided on the basis of image information in the interest area, and image processing is performed by using the image processing condition. The subject position where the subject exists is also inputted, an interest position is decided on the basis of the inputted subject position, an image processing condition is decided on the basis of image information in the interest area, and image processing is performed by using the image processing condition. The subject position where the subject exists is also inputted, the inputted subject position is recognized, whether the recognized subject position exists at a correct position is discriminated, and an image processing condition is decided on the basis of the inputted subject position when the subject position is decided to be wrong.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

[0001] 1. Field of the Invention [0002] The present invention relates to an image processing method and an image processing apparatus for recognizing a position of a subject on an image and determining a region of interest based on the information to obtain stable image processing conditions.

[0002]

2. Description of the Related Art In recent years, devices capable of directly taking a radiation image as a digital image have been developed. For example, as a device that detects the amount of radiation applied to a subject and obtains a radiation image formed in accordance with the detected amount as an electric signal, a method using a detector using a stimulable phosphor is disclosed in Japanese Patent Application Laid-Open No. H10-163,873. No. 55-12429, JP-A-63-18985
Many publications such as Japanese Patent Publication No. 3 are disclosed. In such an apparatus, a stimulable phosphor is applied to a sheet-like substrate, or a detector fixed by vapor deposition or the like is once irradiated with radiation that has passed through a subject, so that the stimulable phosphor absorbs the radiation. Then, by exciting the stimulable phosphor with light or heat energy, the radiation energy accumulated by absorption by the stimulable phosphor is emitted as fluorescence, and the fluorescence is photoelectrically converted to form an image signal. I'm trying to get.

On the other hand, an electric charge corresponding to the intensity of the irradiated radiation is generated in a photoconductive layer, the generated electric charge is stored in a plurality of two-dimensionally arranged capacitors, and the stored electric charge is taken out. Has been proposed. Such a radiation image detecting apparatus uses what is called a flat panel detector (FPD). This type of FPD is disclosed in JP-A-9-90.
As described in Japanese Patent Application Publication No. 048, fluorescence can be detected by a photodiode or a CCD or C-MOS sensor. A similar FPD is described in Japanese Patent Application Laid-Open No. 6-342098.

In these apparatuses, a process for obtaining a subject area from a radiation image generated based on radiation passing through the subject is described in, for example, JP-A-61-170178 and JP-A-63-29621. As described above, the inside of the irradiation field is subjected to threshold value processing to divide it into a background portion and a subject portion, and as described in Japanese Patent Application Laid-Open No. 04-8351, an image signal at a substantially semicircular edge of the subject portion is obtained. There is a method of recognizing a subject by capturing a change or calculating a very small amount and recognizing a position of the subject from the information.

[0005]

By the way, usually, in order to avoid unnecessary exposure to the human body during radiography, a radiation shielding area called an irradiation field aperture is used to limit an area irradiated with radiation. Photographing is generally performed, and the possibility of erroneously recognizing the subject position is high depending on the size of the subject area, the ratio of the radiation shielding portion included in the image, and the position where a marker or the like is inserted.

[0006] For example, there is a high possibility that the position of the subject is erroneously recognized, particularly when a marker is placed near the radiation shielding portion or when the density of the radiation shielding portion is relatively high.

The present invention has been made in view of such circumstances, and it is possible to improve the accuracy of recognition of a region of interest and perform stable image processing. In addition, it is possible to distinguish the inside and outside of a subject by recognizing the position of the subject. It is intended to be able to perform easily and accurately.

[0008]

Means for Solving the Problems In order to solve the above problems and achieve the object, the present invention has the following constitution.

The first aspect of the present invention is an image processing method for obtaining a radiation image generated based on radiation passing through an object, the method comprising recognizing a position of an object in which the object appears, and A region of interest is determined at a desired position in the radiation image based on the recognition result, an image processing condition is determined based on image information in the region of interest, and image processing is performed using the image processing condition. Image processing method. ].

According to the first aspect of the present invention, the recognition accuracy of the region of interest is improved by recognizing the position of the subject, and the image processing conditions are determined based on the image information in the region of interest, thereby achieving a stable operation. Image processing can be performed.

According to a second aspect of the present invention, there is provided an image processing method for obtaining a radiation image generated based on radiation passing through a subject, wherein the position of the subject where the subject is present is input, and An image processing apparatus comprising: determining a region of interest based on a position of a subject; determining image processing conditions based on image information in the region of interest; and performing image processing using the image processing conditions. ].

According to the second aspect of the present invention, the region of interest can be accurately set at a desired position by manually inputting the position of the subject, and based on image information in the region of interest. By determining the image processing conditions,
More stable image processing can be performed.

According to a third aspect of the present invention, there is provided an image processing method for obtaining a radiation image generated based on radiation passing through a subject, wherein the subject position is recognized, and the recognized subject position is a correct position. Is determined, and when it is determined that the subject position is incorrect, the subject position where the subject exists is input, and the image processing condition is determined based on the input subject position. Image processing method. ].

According to the third aspect of the present invention, the correctness of the recognized subject area is determined, whereby the subject area can be accurately recognized, and when the recognized subject area is incorrect. The object region can be determined, the region of interest can be set more accurately at a desired position, and the image processing condition is determined based on the image information in the region of interest, so that a more stable image can be obtained. Processing can be performed.

According to a fourth aspect of the present invention, there is provided the image processing method according to any one of the first to third aspects, wherein the image is rotated according to the position of the subject. ].

According to the fourth aspect of the present invention, by rotating the direction of the image according to the recognized subject position, for example, the breasts in the same photographing direction are displayed on the monitor in a facing direction, or one breast is displayed. Alternatively, comparative reading and the like can be easily performed by outputting to a plurality of films.

According to a fifth aspect of the present invention, there is provided a method as described above, wherein "the subject position recognition is performed by creating a matrix obtained by rearranging the arrangement of pixels at a predetermined position of the radiation image;
The image processing method according to any one of claims 1 to 4, wherein the position of the subject is recognized from the information obtained by creating the matrix. ].

According to the fifth aspect of the present invention, by rearranging the pixels at the predetermined positions and converting the pixels into a matrix representing the characteristics of the local image, the position of the subject can be determined with higher accuracy than the original image. Can be recognized.

According to a sixth aspect of the present invention, there is provided the image processing method according to the fifth aspect, wherein the one created by the matrix creation is a density co-occurrence matrix. ].

According to the sixth aspect of the present invention, by creating the density co-occurrence matrix, the characteristics of the local image can be well represented, and the position of the subject can be recognized with higher accuracy than the original image. be able to.

According to a seventh aspect of the present invention, there is provided an image processing apparatus according to any one of the first to sixth aspects, wherein the image processing is a gradation processing. ].

According to the present invention, even if the distribution of the image data level fluctuates due to the gradation processing, it is possible to obtain a radiation image having a density and contrast suitable for diagnosis and the like.

[0023] The invention according to an eighth aspect is the image processing method according to any one of the first to seventh aspects, wherein the image processing is a dynamic range compression processing. ].

According to the eighth aspect of the present invention, the entire radiographic image having a wide dynamic range can be kept within the easily viewable density range without deteriorating the contrast of the fine structure portion of the subject by the dynamic range compression processing. it can.

According to a ninth aspect of the present invention, there is provided the image processing method according to any one of the first to seventh aspects, wherein the image processing is frequency processing. ].

According to the ninth aspect, the sharpness of the radiation image can be controlled by the frequency processing.

According to a tenth aspect of the present invention, there is provided an image processing apparatus for obtaining a radiation image generated based on radiation passing through a subject, wherein a subject position recognizing means for recognizing a position where the subject is shown; A region-of-interest determining unit that determines a region of interest at a desired position in a radiation image based on the recognition result obtained by the object position recognition unit; and an image that determines image processing conditions based on image information in the region of interest. An image processing apparatus comprising processing condition determination means, and performing image processing using the image processing conditions. ].

According to the tenth aspect of the invention, the accuracy of the region of interest recognition is improved by recognizing the position of the object by the object position recognizing means, and the image processing condition determining means determines the accuracy based on the image information in the region of interest. By determining the image processing conditions, stable image processing can be performed.

An invention according to claim 11 is an image processing apparatus for obtaining a radiation image generated based on radiation passing through a subject, wherein a subject position input means for inputting a position where the subject exists. A region-of-interest determination unit that determines a region of interest based on the input subject position; and an image processing condition determination unit that determines image processing conditions based on image information in the region of interest. An image processing apparatus, wherein image processing is performed by using an image processing apparatus. ].

According to the eleventh aspect, by manually inputting the position of the subject using the subject position input means, the region of interest can be accurately set at a desired position. By determining the image processing conditions by the image processing condition determining means based on the image information, more stable image processing can be performed.

According to a twelfth aspect of the present invention, there is provided an image processing apparatus for obtaining a radiation image generated based on radiation passing through a subject, the subject position input means for inputting a position where the subject exists. Subject position recognizing means for recognizing the position where the subject is captured, and subject position determining means for determining whether the subject position recognized by the subject position recognizing means is a correct position. An image processing apparatus for determining an image processing condition based on the subject position input by the subject position input means when it is determined that the subject position is incorrect. ].

According to the twelfth aspect of the present invention, the subject area can be accurately recognized by the subject position determining means determining whether the subject area recognized by the subject position recognizing means is correct or not. If the recognized subject area is incorrect, the subject area is determined by the subject position input means, so that the region of interest can be set more accurately at a desired position.

According to a thirteenth aspect of the present invention, there is provided an image processing apparatus as set forth in any one of the tenth to twelfth aspects, further comprising: an image rotating means for rotating an image according to a position of a subject. . ].

According to the thirteenth aspect of the present invention, by rotating the direction of the image according to the recognized position of the subject, for example, the breasts in the same photographing direction can be displayed on the monitor in a facing direction, or one breast can be displayed. Alternatively, comparative reading and the like can be easily performed by outputting to a plurality of films.

According to a fourteenth aspect of the present invention, there is provided the image processing apparatus, wherein the object position recognizing means has a matrix creating means for creating a matrix obtained by rearranging the arrangement of pixels at a predetermined position in the radiation image. 13. The image processing apparatus according to claim 10, wherein a position of a subject is recognized from information obtained by the creating unit. ].

According to the fourteenth aspect of the present invention, by rearranging pixels at predetermined positions and converting them into a matrix that well represents the characteristics of a local image, the position of the subject can be determined with higher accuracy than the original image. Can be recognized.

According to a fifteenth aspect of the present invention, the image processing apparatus according to the fourteenth aspect is characterized in that "the one created by the matrix creating means is a density co-occurrence matrix. 』
It is.

According to the fifteenth aspect of the present invention, by forming the density co-occurrence matrix, the characteristics of the local image can be well represented, and the position of the subject can be recognized with higher accuracy than the original image. be able to.

According to a sixteenth aspect of the present invention, there is provided an image processing apparatus according to any one of the tenth to fifteenth aspects, wherein the image processing is gradation processing. ].

According to the sixteenth aspect, even if the distribution of image data levels fluctuates due to gradation processing, a radiation image having a density and contrast suitable for diagnosis or the like can be obtained.

According to a seventeenth aspect of the present invention, the image processing apparatus according to any one of the tenth to fifteenth aspects, wherein the image processing is a dynamic range compression processing. ].

According to the seventeenth aspect of the present invention, the entire radiographic image having a wide dynamic range can be kept within the easy-to-see density range without deteriorating the contrast of the fine structure of the subject by the dynamic range compression processing. it can.

An image processing apparatus according to any one of claims 10 to 15, wherein the image processing is frequency processing. ].

According to the seventeenth aspect, the sharpness of a radiation image can be controlled by frequency processing.

[0045]

DESCRIPTION OF THE PREFERRED EMBODIMENTS Next, embodiments of the present invention will be described in detail with reference to the drawings, but the present invention is not limited to the description of the embodiments and the drawings.

FIG. 1 is a diagram showing the configuration of the image processing apparatus. The radiation generator 30 is controlled by the controller 10, and the radiation emitted from the radiation generator 30 is applied to the imaging panel mounted on the front of the radiation image reader 40 through the subject 5.

FIG. 2 shows the structure of the image pickup panel. The imaging panel 41 has a substrate having a thickness enough to obtain a predetermined rigidity, and a detection element 412 that outputs an electric signal in accordance with the dose of the irradiated radiation is provided on the substrate.
_{-(1,1) to} 412- _{(m, n)} are two-dimensionally arranged. Also,
Scan lines 415 _{-1 to} 415 _-m and signal lines 416 _{-1 to} 416 _-n
Are arranged, for example, orthogonally.

The scanning line 415 of the imaging panel 41_-1~ 415
_-mAre connected to the scanning drive unit 44. Scan driver 4
4 to scanning line 415_-1~ 415_-mOne of the scan lines 4
Fifteen _-p(P is any value from 1 to m)
When S is supplied, this scanning line 415_-pThe test connected to
Electrical signal S corresponding to the dose of radiation emitted from the output element
V_-1~ SV_-nIs detected, and the signal line 416 is detected._-1~ 416_-nTo
The image data is supplied to the image data generation unit 46 via the image data generation unit 46.

The detecting element 412 may be any element that outputs an electric signal corresponding to the dose of the irradiated radiation. For example, when a detection element is formed using a photoconductive layer in which an electron-hole pair is generated upon irradiation with radiation and the resistance value changes, an amount corresponding to the amount of radiation generated in the photoconductive layer is used. Is stored in the charge storage capacitor, and the charge data stored in the charge storage capacitor is supplied to the image data generator 46 as an electric signal. The photoconductive layer desirably has a high dark resistance value, and is preferably amorphous selenium, lead oxide, cadmium sulfide, mercuric iodide,
Or, a photoconductive organic material (including a photoconductive polymer to which an X-ray absorbing compound is added) is used,
Particularly, amorphous selenium is desirable.

When the detecting element 412 is formed using, for example, a scintillator or the like that generates fluorescence when irradiated with radiation, a photodiode generates an electric signal based on the intensity of the fluorescence generated by the scintillator. The information may be supplied to the image data generator 46. The image data generation unit 46 sequentially selects the supplied electric signals SV based on the output control signal SC from the reading control unit 48 and converts them into digital image data DT. The image data DT is supplied to the reading control unit 48.

The reading control unit 48 is connected to the controller 10.
In the reading control unit 48, the controller 10
Scanning control signal R based on the control signal CTD supplied from
C and an output control signal SC are generated. This scanning control signal C
The scan control signal is supplied to the scan drive unit 44 based on the TD to control the scan.
Scan line 415 based on signal RC_-1~ 415_-mAgainst
The supply of the read signal RS is performed. Further, the output control signal S
C is supplied to the image data generator 46. This reading control
The scanning control signal RC and the output control signal SC from the section 48
Therefore, for example, the imaging panel 41 is (m × n) as described above.
When the detection element 412 is used, the detection element
Child 412_-(1,1)~ 412_{-(m, n)}Based on the electric signal SV from
Data DP_(1,1)~ DP_{8m, n)}Then
Data DP _(1,1), DP_(1,2), ... DP_{(1, n)}, D
P_(2,1), ..., DP_{(m, n)}Image data as order
DT is generated, the image data is generated, and
The image data DT is transferred from the image data generation unit 46 to the reading control unit.
48. Also, the reading control unit 48
Processing for transmitting image data DT to the controller 10 is also performed.
U.

The image data DT obtained by the radiation image reader 40 is supplied to the controller 10 via the reading controller 48. When the image data obtained by the radiation image reader 40 is supplied to the controller 10 and the log-converted image data is supplied, the controller 10
Can simplify the processing of the image data.

The radiation image reader 40 is not limited to the one using the FPD, but may use a stimulable phosphor.

FIG. 3 shows a configuration in which a radiation image reader 60 using a stimulable phosphor is used. In a conversion panel 61 irradiated with radiation, a stimulable phosphor layer is provided on a support. Is provided by a vapor phase deposition of a stimulable phosphor or a stimulable phosphor paint. This stimulable phosphor layer is shielded or covered by a protective member in order to block adverse effects and damage due to the environment.

The light beam generator (gas laser, solid laser, semiconductor laser, etc.) 62 generates a light beam whose emission intensity is controlled. This light beam reaches the scanning unit 63 via various optical systems, is deflected by the scanning unit 63, is further deflected by the reflecting mirror 64, and is guided to the conversion panel 61 as stimulating excitation scanning light. .

At the light-collecting end of the light-collecting body 65 formed of an optical fiber or a sheet-like light guide member, stimulating light is guided as scanning light. The light-collecting end of the light-collecting body 65 formed of an optical fiber or a sheet-shaped light guide member is disposed close to the conversion panel 61 on which the stimulating light is scanned, and scans the light beam from the light beam generator 62. As a result, stimulated emission having an emission intensity proportional to the latent image energy generated in the conversion panel 61 is received.

The filter 66 passes only light in the stimulating emission wavelength region from the light introduced from the light collector 65, and the light passing through the filter 66 is incident on the photomultiplier 67. The photomultiplier 67 generates a current signal corresponding to incident light by photoelectric conversion. This current signal is supplied to the current / voltage converter 70 and converted into a voltage signal. Further, after the voltage signal is amplified by the amplifier 71, the voltage signal is converted into digital image data DT by the A / D converter 72. Here, a logarithmic conversion amplifier (log amplifier) is used as the amplifier 71. The image data DT is sequentially image-processed in the image processing device 80, and the image data DTC after the image processing is transmitted to the printer 83 via the interface 82.

CPU (Central Process)
ing Unit) 81 is for controlling image processing in the image processing device 80,
In the case of 0, various image processings (for example, spatial frequency processing, dynamic range compression, gradation processing, enlargement / reduction, movement, rotation, statistical processing, etc.) are performed on the image data DT, and an image in a form suitable for diagnosis is performed. Generate data DTC. This image data DTC is supplied to the printer 83 and
From 3, a hard copy of the radiation image of each part of the human body can be obtained. Note that a monitor such as a CRT may be connected to the interface 82, and a storage device (filing system) capable of storing image data of a plurality of radiation images (filing system) may be connected.

The reading controller 75 adjusts the light beam intensity of the light beam generator 62, adjusts the gain of the photomultiplier 67 by adjusting the power supply voltage of the high-voltage power supply 76 for the photomultiplier, and amplifies the current / voltage converter 70. Part 71
Is adjusted, and the input dynamic range of the A / D converter 72 is adjusted, so that the reading gain is comprehensively adjusted. Image data DT obtained from the A / D converter 72
Is supplied to the controller 10 and controls the operation of the reading control unit 75 according to the control signal CTD from the controller 10.

The radiation image reader irradiates a silver halide film on which a radiation image is recorded with light from a light source such as a laser or a fluorescent lamp, and photoelectrically converts the transmitted light of the silver halide film to generate image data. May be. Further, a configuration may be employed in which radiation energy is directly converted into an electric signal using a radiation quantum counting type detector to generate image data.

Next, the configuration of the controller 10 is shown in FIG. CPU for controlling operation of controller 10
(Central Processing Unit)
11 is connected to a system bus 12 and an image bus 13, and an input interface 17. CPU 11 for controlling the operation of this controller 10
The operation of is controlled based on a control program stored in the memory 14. System pulse 12 and image bus 13
Are connected to a display control unit 15, a frame memory control unit 16, an output interface 18, a shooting control unit 19, a disk control unit 20, and the like. The transfer of image data between the units via the image bus 13 is performed.

A frame memory 21 is connected to the frame memory control unit 16, and image data obtained by the radiation image reader 40 is stored via the imaging control unit 19 and the frame memory control unit 16. The image data stored in the frame memory 21 is read and supplied to the display control unit 15 and the disk control unit 20. The frame memory 21 may store the image data supplied from the radiation image reader 40 after the CPU 11 processes the image data.

An image display device 22 is connected to the display control unit 15, and a radiographic image based on the image data supplied to the display control unit 15 is displayed on the screen of the image display device 22. Here, when the number of display pixels of the image display device 22 is smaller than the number of pixels of the radiation image reader 40, the entire captured image can be displayed on the screen by thinning out and reading out the image data. In addition, if the image data of the area corresponding to the number of display pixels of the image display device 22 is read out, the captured image at the desired position can be displayed in detail.

From the frame memory 21 to the disk controller 2
When the image data is supplied to the disk controller 20, for example, the image data is read continuously and
The data is written to the O memory, and then sequentially recorded on the disk device 23. Further, image data read from the frame memory 21 and image data read from the disk device 23 can be supplied to the external device 90 via the output interface 18.

In the image processing section 26, the radiation image reader 4
0 to the image data D supplied via the photographing control unit 19
T irradiation field recognition processing, region of interest setting, normalization processing, gradation processing, and the like are performed. Further, frequency emphasis processing, dynamic range compression processing, and the like may be performed. In addition, as a configuration in which the CPU 11 also serves as the image processing unit 26,
Image processing and the like can also be performed.

The input interface 17 is connected to an input device 27 such as a keyboard. By operating the input device 27, management information such as information for identifying image data obtained by shooting and information on shooting is input. As the external device 90 connected to the output interface 18, a scanning laser exposure device also called a laser imager is used. In this scanning laser exposure apparatus, the intensity of a laser beam is modulated by image data, exposed to a conventional silver halide photographic material or a thermal phenomenon silver halide photographic material, and then subjected to an appropriate development process to thereby produce a radiation image. A hard copy is obtained.

Although the frame memory 21 stores the image data supplied from the radiation image reader 40, the image data supplied may be processed by the CPU 11 and then stored. Further, the disk device 23 stores image data stored in the frame memory 21, that is, image data supplied from the radiation image reader 40 and image data obtained by processing the image data by the CPU 11 together with management information and the like. be able to.

Next, the operation will be described. When obtaining a radiation image of the subject 5, it is assumed that the subject 5 is located between the radiation generator 30 and the imaging panel 41 of the radiation image reader 40, and the radiation emitted from the radiation generator 30 is And is incident on the radiation image capturing panel 41 transmitted through the subject 5. In addition, since the radiation image reader 40 is used instead of the radiation image reader 40, the description of the case where the radiation image reader 60 is used is omitted.

Using the input device 27, management information indicating the identification of the subject 5 to be photographed and information relating to the photographing is input to the controller 10. The input of the management information using the input device 27 is performed by operating a keyboard, using a magnetic card, a bar code, an HIS (In-Hospital Information System: information management by network), and the like.

The management information includes, for example, an ID number, a name,
Date of birth, gender, date and time of imaging, location and position of imaging (for example, which part of the human body was irradiated with radiation from which direction), imaging method (simple imaging, contrast imaging, tomography, magnified imaging, etc.), imaging It consists of information such as conditions (tube voltage, tube current, irradiation time, use of scattered radiation removal grid, etc.).

The date and time of photographing can be obtained automatically from the CPU 11 by using the clock function built in the CPU 11. The management information to be input may be only information relating to the subject to be photographed at that time. A series of management information may be input in advance, and the subject may be photographed in the input order, or the management information may be input as needed. The information may be read and used.

When the power switch of the radiation image reader 40 is turned on, the control signal C
Based on the TD, the reading control unit 48 of the radiation image reader 40
The scanning panel 44 initializes the imaging panel 41. This initialization is for obtaining a correct electric signal corresponding to the radiation dose emitted from the imaging panel 41.

When the initialization of the imaging panel 41 is completed in the radiation image reader 40, irradiation of radiation from the radiation generator 30 is enabled. Here, when a switch for irradiating radiation is provided in the radiation generator 30, when the switch is scanned, the radiation
Radiation is irradiated for a predetermined time, and a signal DFS indicating the start of irradiation and a DFE indicating the end of irradiation
Is supplied to the controller 10.

At this time, the radiation dose of the radiation applied to the imaging panel 41 of the radiation image reader 40 is modulated by the subject 5 because the degree of absorption of the radiation by the subject 5 differs. Detection element 412 of imaging panel 41- _(1,1)
In ４ 412- _{(m, n)} , an electric signal based on the radiation modulated by the subject 5 is generated.

Next, in the controller 10, after a predetermined time has elapsed since the signal DFS was supplied, for example, when the irradiation time of the radiation is about 0.1 second, a time longer than the irradiation time (for example, about 1 second) elapses. Or immediately after the signal DFE is supplied, the radiation image reader 40 outputs the image data D
The control signal CTD is supplied to the reading control unit 48 of the radiation image reader 40 to start generation of T.

On the other hand, when a switch for irradiating radiation is provided in the controller 10, when this switch is operated, an irradiation start signal CST for starting irradiation of radiation is transmitted via the imaging control unit 19. The radiation is supplied to the radiation generator 30, and the radiation is emitted from the radiation generator 30 toward the subject 5 for a predetermined time. The irradiation time is set based on, for example, management information.

Next, the controller 10 outputs a control signal CT for starting the generation of image data by the radiation image reader 40 a predetermined time after outputting the irradiation start signal CST.
D is supplied to the reading control unit 48 of the radiation image reader 40. Note that the controller 10 detects the end of radiation irradiation by the radiation generator 30 and then sets the radiation image reader 4
Control signal CTD for starting generation of image data at 0
May be supplied to the radiation image reader 40.
In this case, generation of image data during irradiation of radiation can be prevented.

The reading control section 48 of the radiation image reader 40 generates a scanning control signal RC and an output control signal SC based on a control signal CTD for starting generation of image data supplied from the controller 10. The scanning control signal RC is supplied to the scanning driving unit 44, and the output control signal SC is supplied to the reading control unit 48 with the image data DT. This image data DT is sent to the controller 10 by the reading control unit 48.

The image data DT supplied to the controller 10 is stored in the frame memory 21 via the photographing control unit 19, the frame memory control unit 16 and the like. Using the image data stored in the frame memory 21, a radiographic image can be displayed on the image display device 22. Further, by supplying the image data stored in the frame memory 21 to the display control unit 15, the brightness, contrast, sharpness, and the like are adjusted, and a radiation image suitable for diagnosis or the like can be displayed. Further, the image data subjected to the image processing is transferred to an external device 9 such as a laser film printer.
By supplying 0, a hard copy of a radiation image suitable for diagnosis or the like can be obtained. Further, a soft copy may be obtained by outputting to an image display device such as a CRT, a liquid crystal display, and a plasma display.

The image processing section 26 is configured as shown in FIGS.

By the way, when taking a radiographic image,
For example, to prevent radiation from being irradiated to a part not required for diagnosis, or to irradiate radiation to a part not required for diagnosis, radiation scattered in this part is incident on a part required for diagnosis. To prevent the resolution from deteriorating, a part of the subject 5 and the radiation generator 3
A radiation non-transmissive substance such as a lead plate is placed at 0, and an irradiation field stop for limiting an irradiation field of the radiation to the subject 5 is performed.

When the irradiation field aperture is performed, if level conversion processing and subsequent gradation processing are performed using the image data of the irradiation field inside area and the irradiation field outside area, the image data of the irradiation field outside area will be used. Image processing of a portion required for diagnosis in the irradiation field is not properly performed.

That is, as shown in FIG. 5, an image including the radiation image area A1 and the radiation shielding section or the patient information area A2 and including and outside the radiation image area is read and output.
Usually, in order to avoid unnecessary exposure to the human body during radiography, use a radiation shield called an irradiation field stop to limit the area where radiation is irradiated, or to capture patient information together In general, the subject area B
There is a high possibility that the position of the subject is erroneously recognized depending on the size of the inside, the ratio of the radiation shielding portion included in the image, and the position where the marker area C or the like is inserted.

For example, particularly when the marker area C is located near the radiation shielding section or the patient information area A2, or when the density of the radiation shielding section or the patient information area A2 is relatively high, the position of the subject may be incorrect. Highly likely to recognize.

For this reason, in the image processing apparatus of the present invention, the image processing section 26 is configured as shown in FIGS.

The image processing unit 26 of the embodiment shown in FIG.
Is a subject position recognizing means 100 for recognizing a position where a subject is captured, and a region of interest determining means 101 for determining a region of interest at a desired position in a radiographic image based on the recognition result obtained by the subject position recognizing means 100. And an image processing condition determining unit 102 for determining an image processing condition based on image information in the region of interest. The image processing unit 103 performs image processing using the image processing condition.

As described above, by recognizing the object position by the object position recognizing means 100, the region of interest determining means 1
By improving the region-of-interest recognition accuracy by the image processing unit 01 and determining the image processing conditions based on the image information in the region of interest by the image processing condition determining unit 101, stable image processing can be performed by the image processing unit 103.

The selection of the look-up table to be output and the rotation and translation of the gradation curve depend on the photographing position, photographing conditions,
The selection may be changed based on a shooting method or the like.
When such information is input as management information using the input device 27, by using this management information, the basic gradation curve can be easily selected and the rotation direction of the basic gradation curve can be selected. And the amount of translation can be determined.

The image processing section 26 of the embodiment shown in FIG. 7 includes a subject position input means 110 for inputting a position where a subject is present, and an interest for determining a region of interest based on the input subject position. The apparatus includes a territory determining means 101 and an image processing condition determining means 102 for determining image processing conditions based on image information in a region of interest, and performs image processing by the image processing means 103 using the image processing conditions.

As described above, by manually inputting the position of the subject by the subject position input unit 110, the region of interest can be accurately set at a desired position by the region-of-interest determination unit 101. By determining the image processing conditions by the image processing condition determining means 102 based on the image information, more stable image processing can be performed by the image processing means 103.

The image processing section 26 of the embodiment shown in FIG. 8 includes a subject position input means 110 for inputting a position where a subject is present, and a subject position recognition means 100 for recognizing a position where the subject is captured. And subject position recognition means 1
00 has a subject position discriminating means 120 for discriminating whether or not the subject position recognized is correct, and when the subject position discriminating means 120 determines that the subject position is incorrect, the subject position input means 110 Image processing condition determining means 102 based on the input subject position
, Image processing conditions are determined by the above, and image processing is performed by the image processing means 103 using the image processing conditions.

As described above, the subject position judging means 120 makes a correct / wrong judgment of the subject area recognized by the subject position recognizing means 100, whereby the subject area can be accurately recognized. If the recognized subject area is incorrect, the subject area is determined by the subject position input unit 110, so that the region of interest can be set more accurately at a desired position.

The image processing apparatus according to the embodiment shown in FIGS. 6 to 8 has an image rotating means 130 for rotating an image in accordance with the position of a subject. For example, as shown in the pectoral region of FIG. 9, the breasts in the same imaging direction face each other,
By displaying on a monitor or outputting to one or a plurality of films, comparative reading and the like can be easily performed. FIG. 9A shows MLs of the left and right pectoral muscle regions.
FIG. 9B shows a photograph taken in the CC direction of the left and right pectoral muscle regions (the direction in which the breast is sandwiched vertically) by photographing in the O direction (direction in which the breast is sandwiched diagonally). It is a thing to be reflected.

Object position input means 11 of this embodiment
As 0, a method in which the operator inputs coordinates from a keyboard or the like, a touch panel method in which the operator specifies a subject position on a display, or the like can be used.

The subject position recognizing means 100 can automatically recognize the subject position and determine a specific area in the image. For example, in FIG.
2 may be automatically determined, but is not limited to this.

The object position recognizing means 100 has a matrix creating means 100a. This matrix creation means 100a
Creates a matrix obtained by rearranging the arrangement of pixels at predetermined positions in the regions D1 and D2 of the radiographic image in FIG. 10, and recognizes the subject position from the information obtained by the matrix creating unit 100a. By rearranging the pixels at the predetermined positions and converting the pixels into a matrix that well represents the characteristics of the local image, the object position can be recognized with higher accuracy than the original image.

What is created by the matrix creating means 100a is a density co-occurrence matrix. By creating a density co-occurrence matrix, the characteristics of a local image can be better expressed, and The position of the subject can be recognized with high accuracy.

The density co-occurrence matrix is the probability Pδ (i, j), (i, j = p) that the density of a point separated by a constant displacement δ = (γ, θ) from the point of the density i of the image is j. 0, 1, ..., n
A matrix having -1) as an element is obtained, a feature amount is calculated from the matrix, and the texture is characterized by those values.
The texture is a state in which fine pattern patterns are uniformly distributed, and regions in an image can be distinguished by a difference in texture. γ is 2.8 mm to 8.4 m
m and θ = 0 ° are desirable, but not limited thereto.

That is, as shown in FIG.
When the density co-occurrence matrix of No. 2 is created and the region D1 is inside the subject, a large frequency appears relatively near the center of the matrix depending on the structure of the subject.

On the other hand, when the area D2 is applied to the outside of the subject, in the first case where the outside of the subject is the radiation image area A1 directly irradiated with X-rays, or in a radiation shielding section in which X-rays are blocked by lead or the like, or The second, which is the patient information area A2
In the third case where these regions are bounded,
In each of these cases, the matrix shows a large frequency near the periphery.

In calculating the feature values inside and outside the subject, a complicated algorithm is necessary to recognize the first to third cases. It is possible to easily and accurately recognize the inside and outside of the subject.

Here, the position where the density co-occurrence matrix is created is
A specific position in the image, for example, an area near the left and right edges of the image,
By comparing areas near the upper and lower ends, a position more likely to be within the subject area may be roughly determined to be within the subject area, or a plurality of local areas may be set to include all areas on the image. Then, of those areas, those meeting certain conditions may be used as the subject area.

The created matrix may be a difference statistic or a run-length matrix in addition to the density co-occurrence matrix.

The difference statistic is a constant displacement δ =
The probability P that the difference between the densities of two points separated by (γ, θ) is k
.delta. (k), (k = 0, 1,..., n-1) are obtained, feature amounts are calculated from the matrix, and the texture is characterized by those values. For example, when the region is within the breast region,
k shows a large value near the center of 0 to n-1, but outside the breast region, k shows a large value near 0 or near n-1.

The run-length matrix is a frequency Pθ (i, j), (i = j) in which j points of density i in the direction of θ continue in the image.
0, 1,..., N−1, j = 1, 2,..., L) are obtained, a feature amount is calculated from the matrix, and the texture is characterized by those values. Attach. For example, the run length has a small value in the breast region, but the run length has a large value in a region where the density is small or large when the region is outside the breast region.

For these matrices, see Mikio Takagi and Hirohisa Shimoda, Image Analysis Handbook. University of Tokyo Press,
Shunji Mori, Tsugako Sakakura: Basics of Image Recognition [II]. Ohmsha, Image Processing Standard Textbook Editing Committee: Image Processing <Image Processing Standard Textbook>. Listed in the Image Information Education Promotion Association.

Then, by setting the region of interest for determining the reference signal value by the region-of-interest determination means 101 based on the information obtained here, it is possible to more stably output a desirable image.

The region-of-interest determination means 101 can automatically set a region of interest in a photographed image or can manually set the region of interest. The manual setting position can be obtained by the operator setting a rectangular region of interest, for example, surrounding the entire lung field while watching the CRT screen.

As an automatic setting, for example, setting of a region of interest in the thoracic septum will be described with reference to FIG. 11. First, the left and right lines are determined by the following steps 1 to 3.

Step 1: Obtain a vertical projection (one-way cumulative value of data) of a portion of the image data excluding the upper and lower portions of the image and the irradiation field portion, which have less influence on the whole (FIG. 11B). ).

Step 2: From the obtained vertical projection, a range of 1/3 of the central portion (1/3 in FIG. 11)
3 * x to 2/3 * x) and the signal value is the minimum value (Pc)
Is defined as a midline column (Xc).

Step 3: Left and right of the entire image, 1 /
From the three columns (2/3 * x, 1/3 * x in FIG. 11) to the outside (left / right direction) of the image, the point where the calculated vertical projection value is equal to or less than the threshold value (Tl, Tr). And the first point is defined as the left / right end (X1, Xr) of the lung field.
As the threshold value, the maximum value (Plx, Prx) of the projection value from the column of Pc and 1/3 of the entire image
Is updated toward the outside (left-right direction) of the image, and Tl = ((k1-1) * Plx + Pc) / k1 Tr = ((k2-1) * Prx + Pc) / k2 (where k1, k2 are constants) I do.

Next, upper and lower lines are determined in steps 4 and 5 described below.

Step 4: A horizontal projection is performed in the section determined in the above step (FIG. 11).
(C)).

Step 5: Upper and lower parts of 1/1 of the whole image
From the 4, 1/2 line (1/4 * y, 1/2 * y) to the outside of the image (vertical direction), find a point where the obtained horizontal projection value is equal to or less than the threshold value, The first point is the upper and lower ends (Yt, Yb) of the right lung field. The threshold values are １ ／ * y to ＊* y of the entire image and 1
The maximum value (Ptx, Pbx) of the projection value in the range of / 2 * y to 4 / * y and the minimum value (Ptn, Pbn) of the projection value in the range outside (up and down) of the image from the line of the maximum value Tt = ((k3-1) * Ptx + Ptn) / k3) Tb = ((k4-1) * Pbx + Pbn) / k4) (where k3 and k4 are constants).

The parameters k1 to k4 used for obtaining the threshold value by the above equations can be empirically obtained.

In the setting of the region of interest, when the portion to be diagnosed is wide ranging from a portion having a high density region to a portion having a high density region, for example, from a lung field portion having a high density region such as a rib portion. When the diagnosis is performed by photographing the abdomen including many low-density regions, the setting is made so as to include all regions in the irradiation field where observation is desired.

Further, two regions of interest (separate regions) are determined for the highest density region and the lowest density region among the diagnostic reading points, and each region is output at a predetermined density. You may.

In the image processing, even when the level distribution of the image data output from the imaging panel 41 fluctuates due to the difference in the radiation dose, the image data DT is always obtained so that a stable radiation image can be obtained. Normalization processing is performed. Also, even if the distribution of the image data level fluctuates,
To obtain a radiation image having a suitable density and contrast for diagnosis or the like, gradation processing is performed on normalized image data DTreg which is image data after normalization processing. Further, in the image processing, the frequency enhancement processing for controlling the sharpness of the normalized radiation image with respect to the normalized image data DTreg, and the entire radiation image having a wide dynamic range can be performed without lowering the contrast of the fine structure portion of the subject. A dynamic range compression process for keeping the density within the easy-to-see density range may be performed.

In the normalization processing of the image data DT, when representative values D1 and D2, which are levels of the image data at which the cumulative histogram has the predetermined ratios m1 and m2, are set, a normalization processing lookup table provided in advance is set. Referring to FIG. 12, the representative values D1 and D2 are changed to a desired reference value S as shown in FIG.
Normalization processing for level conversion to 1 and S2 is performed. Here, the characteristic curve CC indicates the level of a signal output according to the radiation dose of the radiation applied to the imaging panel 41. Further, the normalization processing look-up table is generated by an operation using an inverse function of the function indicating the characteristic curve CC of the imaging panel 41. It is needless to say that the normalization processing may be performed by arithmetic processing without using the normalization processing lookup table.

As a result of this normalization processing, as shown in FIG. 13, the radiation dose R is lower than the doses R1 and R2 at which the radiation can obtain image data of the desired reference values S1 and S2.
Since the image data of the desired reference values S1 and S2 can be obtained even with a to Rb, the exposure of the subject can be reduced, and at the same time, the variation in the signal distribution due to the difference in the body type of the subject is corrected. be able to.

Next, gradation processing is performed using the normalized image data DTreg obtained by the normalization processing. In the gradation processing, for example, a gradation conversion curve as shown in FIG. 14 is used, and the reference value S of the normalized image data DTreg is used.
1 and S2 are parameter values of levels S1 ′ and S2 ′, and the normalized image data DTreg is output image data DTou.
is converted to t. The levels S1 'and S2' correspond to predetermined luminance or photographic density in the output image.

The gradation conversion curve is represented by the normalized image data DTr.
It is preferable that the function is continuous over the entire signal region of eg, and that its differential function is also continuous. Further, it is preferable that the sign of the differential coefficient is constant over the entire signal region.

Further, since the preferred shape of the gradation conversion curve and the levels S1 'and S2' are different depending on the photographing part, photographing position, photographing condition, photographing method and the like, the gradation conversion curve is created for each image. Also, for example, Japanese Patent Publication 5-2
As shown in No. 6138, a plurality of basic tone conversion curves are stored in advance, and one of the basic tone conversion curves is read out and rotated and translated to obtain a desired tone conversion curve. Can be easily obtained. The image processing unit 26 is provided with a gradation processing lookup table corresponding to a plurality of basic gradation curves, and an image obtained by referring to the gradation processing lookup table based on the normalized image data DTreg. By correcting the data according to the rotation and parallel movement of the basic gradation conversion curve, it is possible to obtain output image data DTout that has been subjected to gradation conversion. In the gradation conversion processing, not only two reference values S1 and S2 but also one reference value or three or more reference values may be used.

Here, the selection of the basic gradation curve and the rotation and translation of the basic gradation curve are performed based on the photographing part, photographing position, photographing conditions, photographing method and the like. When such information is input as management information using the input device 27, by using this management information, the basic gradation curve can be easily selected and the rotation direction of the basic gradation curve can be selected. And the amount of translation can be determined. Further, the levels of the reference values S1 and S2 may be changed based on an imaging part, an imaging position, imaging conditions, and an imaging method.

Further, the selection of the basic gradation curve and the rotation or translation of the basic gradation curve may be performed based on the information on the type of the image display device and the type of the external device for outputting the image. This is because the preferable gradation may differ depending on the image output method.

Next, the frequency emphasis processing and the dynamic range compression processing will be described. In the frequency emphasizing process, for example, in order to control the sharpness by the non-sharp mask process shown in Expression (1), the function F is calculated as follows.
3 and JP-B-62-62376.

Soua = Sorg + F (Sorg−Sus) (1) Here, Soua is the image data after the processing, Sorg is the image data before the frequency enhancement processing, and Sus is the average of the image data before the frequency enhancement processing. This is unsharp data obtained by a conversion process or the like.

In this frequency emphasizing process, for example, F (So
rg-Sus) is β × (Sorg-Sus),
When β (emphasis coefficient) is equal to the reference values T1 and T2 as shown in FIG.
Varies approximately linearly between

As shown by the solid line in FIG. 16, when values "A" and "B" are set to emphasize low luminance, β from the reference value T1 to the value "A" is maximized. Therefore, the value is minimized up to the value “B” −the reference value T2. The value "A"-
Up to the value “B”, β changes almost linearly. When emphasizing high luminance, as shown by the broken line, β from the reference value T1 to the value “A” is minimized, and the value “B” −the reference value T2
Up to the maximum. Further, from the value “A” to the value “B”, β
Is changed almost linearly. It should be noted that although not shown, β of the value “A” to the value “B” is maximized when the medium luminance is emphasized. Thus, in the frequency emphasis processing, the sharpness of an arbitrary luminance portion can be controlled by the function F.

Further, the method of frequency emphasis processing is not limited to the non-sharp mask processing described above.
For example, a technique such as the multi-resolution method disclosed in Japanese Patent No. 645 may be used. In the frequency emphasizing process, the frequency band to be emphasized and the degree of emphasis are set based on the photographing site, photographing position, photographing condition, photographing method, and the like, similarly to the selection of the basic gradation curve in the gradation process. .

In the dynamic range compression processing, a function G is determined by a method disclosed in Japanese Patent Publication No. 266318 in order to perform control so that the density is within a legible range by the compression processing shown in Expression (2).

Stb = Sorg + G (Sus) (2) Note that Stb is image data after processing, Sorg is image data before dynamic range compression processing, and Sus is image data before dynamic range compression processing. This is the unsharp data obtained by the above method.

Here, as shown in FIG. 17 (a), G (Sus) is low, including the case where the non-sharp data Sus has a characteristic that G (Sus) increases when the level becomes lower than the level “La”. It is assumed that the density of the density region is high, and FIG.
The image data Sorg shown in (b) is image data Stb in which the dynamic range on the low density side is compressed as shown in FIG. Also, G (Sus) is shown in FIG.
As shown in (d), the unsharp data Sus has the level “L”.
In the case where G (Sus) is smaller than “b”, the density of the high-density area is determined to be high, and the image data Sorg shown in FIG.
As shown in FIG. 7E, the dynamic range on the high density side is compressed. In the dynamic range compression process as well, the correction frequency band and the degree of correction are set based on the imaging site, imaging body position, imaging conditions, imaging method, and the like.

Here, reference values T1 and T2 and values "A" and "B" or levels "La" and "Lb" which are processing conditions in the frequency emphasizing process and the dynamic range compressing process.
Is determined by a method similar to the method of determining the representative values D1 and D2.

As described above, according to the above-described embodiment, even when the ratio between the high-density area and the low-density area greatly changes, stable gradation processing is performed without depending on the distribution of image data. Therefore, a radiation image having a density and contrast suitable for diagnosis or the like can always be obtained stably.

The image data used to determine the processing conditions may be, for example, image data that has been subjected to thinning processing. In this case, since the data amount is reduced, the processing speed can be improved and the memory capacity and the like can be reduced. In this case, the effective pixel size of the reduced image obtained by thinning is 0.4 mm to 10.0 mm, preferably 1.
It is preferable to use image data thinned to be 0 mm to 6.0 mm.

[0138]

As described above, claims 1 to 1 are as described above.
According to the invention described in Item 8, it is possible to improve the accuracy of region of interest recognition and perform stable image processing, and to easily and accurately distinguish between inside and outside of a subject by recognizing the position of the subject. it can.

[Brief description of the drawings]

FIG. 1 is a diagram illustrating a configuration of an image processing apparatus.

FIG. 2 is a diagram illustrating a configuration of an imaging panel.

FIG. 3 is a diagram showing a configuration when a radiation image reader using a stimulable phosphor is used.

FIG. 4 is a diagram showing a configuration of a controller.

FIG. 5 is a diagram illustrating an example of an image including an area outside a radiation image area.

FIG. 6 is a diagram illustrating a configuration of an image processing apparatus.

FIG. 7 is a diagram illustrating a configuration of another image processing apparatus.

FIG. 8 is a diagram illustrating a configuration of another image processing apparatus.

FIG. 9 is an image diagram of a typical mammogram photographing direction.

FIG. 10 is a diagram showing an area where a density co-occurrence matrix is created.

FIG. 11 is a diagram illustrating an example in which a region of interest is automatically set to a captured image.

FIG. 12 is a diagram showing level conversion.

FIG. 13 is a diagram showing a normalization process.

FIG. 14 is a diagram showing gradation conversion characteristics.

FIG. 15 is a diagram illustrating a relationship between an enhancement coefficient and image data.

FIG. 16 is a diagram illustrating a relationship between an enhancement coefficient and image data.

FIG. 17 is a diagram illustrating a dynamic range compression process.

[Explanation of symbols]

 26 image processing unit 100 subject position recognition means 101 region of interest determination means 102 image processing condition determination means 103 image processing means 110 subject position input means 120 subject position determination means

 ──────────────────────────────────────────────────続 き Continued on the front page F-term (reference) 2G083 AA03 AA04 BB05 EE10 2H013 AC06 5B057 AA08 BA24 CA08 CA12 CA16 CD03 CE11 DA07 DB02 DB09 DC19 DC22 5L096 AA03 AA06 BA06 DA02 EA12 FA14 FA38 FA69 9A001 HH23 HH24H25H25H25HJH

Claims (18)

[Claims] An image processing method for obtaining a radiation image generated based on radiation that has passed through a subject, comprising: recognizing a position of a subject in which the subject is shown; Determining an area of interest at a desired position, determining image processing conditions based on image information in the area of interest, and performing image processing using the image processing conditions. 2. An image processing method for obtaining a radiation image generated based on radiation passing through a subject, comprising: inputting a position of a subject where the subject is present; and setting a region of interest based on the input subject position. An image processing apparatus comprising: determining an image processing condition based on image information in a region of interest; and performing image processing using the image processing condition. 3. An image processing method for obtaining a radiation image generated based on radiation passing through a subject, comprising: recognizing a subject position; determining whether the recognized subject position is a correct position; An image processing method characterized by inputting a subject position where a subject exists when it is determined that the position is incorrect, and determining an image processing condition based on the inputted subject position. 4. The image processing method according to claim 1, wherein the image is rotated according to the position of the subject. 5. A method according to claim 1, wherein said subject position recognition comprises creating a matrix obtained by rearranging the arrangement of pixels at a predetermined position in said radiation image, and recognizing the subject position from information obtained by said matrix creation. The image processing method according to any one of claims 1 to 4, wherein 6. What is created by said matrix creation is:
6. The image processing method according to claim 5, wherein the image processing method is a density co-occurrence matrix. 7. The image processing apparatus according to claim 1, wherein said image processing is gradation processing. 8. The image processing method according to claim 1, wherein said image processing is a dynamic range compression processing. 9. The image processing method according to claim 1, wherein said image processing is frequency processing. 10. An image processing apparatus for obtaining a radiation image generated based on radiation that has passed through a subject, comprising: a subject position recognizing unit that recognizes a position where the subject is captured; Region-of-interest determining means for determining a region of interest at a desired position in the radiation image based on the recognition result, and image processing condition determining means for determining an image processing condition based on image information in the region of interest, An image processing apparatus for performing image processing using the image processing conditions. 11. An image processing apparatus for obtaining a radiation image generated based on radiation that has passed through a subject, comprising: subject position input means for inputting a position where the subject exists; A region-of-interest determination unit that determines a region of interest by using the image processing condition, and an image processing condition determination unit that determines an image processing condition based on image information in the region of interest. An image processing apparatus characterized by the above-mentioned. 12. An image processing apparatus for obtaining a radiation image generated based on radiation that has passed through a subject, comprising: subject position input means for inputting a position where the subject exists; A subject position recognizing means for recognizing; and a subject position determining means for determining whether the subject position recognized by the subject position recognizing means is a correct position. If the subject position determining means determines that the subject position is incorrect, An image processing apparatus comprising: determining an image processing condition based on a subject position input by the subject position input means when the determination is made. 13. An image processing apparatus according to claim 10, further comprising an image rotating means for rotating an image according to a position of a subject. 14. The object position recognizing means has a matrix creating means for creating a matrix obtained by rearranging the arrangement of pixels at predetermined positions of the radiation image,
13. The image processing apparatus according to claim 10, wherein a position of a subject is recognized from information obtained by the matrix creating unit. 15. The matrix created by the matrix creating means is a density co-occurrence matrix.
An image processing apparatus according to claim 1. 16. The image processing apparatus according to claim 10, wherein said image processing is gradation processing. 17. The image processing apparatus according to claim 10, wherein said image processing is a dynamic range compression processing.
The image processing device according to any one of claims 1 to 4. 18. The image processing apparatus according to claim 10, wherein the image processing is frequency processing.