JP7501138B2 - Radiation image capturing system, program, and image processing method - Google Patents

Description

The present invention relates to a radiographic imaging system, a program, and an image processing method.

Conventionally, technology has been proposed that uses optical images to set positioning and imaging conditions during radiation imaging.

For example, Patent Literature 1 describes a technique for starting imaging when a part of a subject to be imaged is captured within the outer frame of a camera image captured by a webcam.
Furthermore, Patent Document 2 describes a technique for identifying a cassette to be used for radiography from a camera image and automatically setting the cassette to be used in the console.
Furthermore, Patent Document 3 describes a method for determining whether or not a predetermined change has occurred in an exposed area based on an optical image capturing at least a portion of the exposed area to which radiation is irradiated, and for halting radiation generation when the predetermined change has occurred.

JP 2012-24399 A JP 2019-33828 A JP 2008-206740 A

The techniques of Patent Documents 1 to 3 can simplify the work involved in radiography and perform appropriate radiography. However, in order to perform appropriate image processing on the captured radiographic images, the user needs to set information about the subject, processing parameters, etc., on a console or the like.

The objective of the present invention is to eliminate or simplify the user's setting operations for performing appropriate image processing on radiological images.

In order to solve the above problem, the radiation image capturing system of the present invention according to claim 1 comprises:
a radiation image capturing unit that detects radiation that has been irradiated from a radiation source and transmitted through a subject, and captures a radiation image;
an optical image capturing unit configured to capture an optical image of at least a portion of the subject;
a positioning determination unit that determines whether the positioning of the subject is good or bad based on the optical image captured by the optical image capturing unit;
an image processing unit that performs image processing on the radiation image captured by the radiation image capturing unit;
Equipped with
the image processing unit sets image processing conditions for the radiographic image based on the optical image captured by the optical image capturing unit, and performs image processing under the set image processing conditions only on the radiographic image captured by the radiographic image capturing unit for which the positioning determination unit has determined that the positioning of the subject is good ;
The radiation image capturing section is characterized in that, when the positioning determination section determines that the positioning of the subject is poor, the radiation image capturing section does not capture a radiation image .

The invention described in claim 2 is the invention described in claim 1,
the optical image capturing unit captures an optical image of at least a part of an area of the subject irradiated with radiation from the radiation source;
The image processing unit analyzes the optical image to determine a part of the subject that is the imaging target in the radiation image, and sets the image processing conditions in accordance with the determined part.

The invention described in claim 3 is the invention described in claim 1,
The image processing unit determines the physical build of the subject by analyzing the optical image, and sets the image processing conditions in accordance with the determined physical build of the subject.

The invention described in claim 4 is the invention described in claim 1,
The image processing unit calculates a feature amount of the subject by analyzing the optical image, and sets the image processing condition in accordance with the calculated feature amount.

The invention described in claim 5 is the invention described in claim 4,
The feature amount is a feature amount that represents a size or a shape of a predetermined structure of the subject.

The invention described in claim 6 is the invention described in any one of claims 1 to 5,
The image processing condition is at least one of dynamic range compression processing, contrast correction processing, density correction processing, LUT conversion processing, frequency emphasis processing, scattered radiation correction processing, noise suppression processing, image cropping, image masking, image rotation, and image inversion.

The program of the invention according to claim 7 comprises:
a computer that detects radiation that has been irradiated from a radiation source and transmitted through a subject, and performs image processing on a radiation image captured by a radiation image capturing unit that captures a radiation image;
a positioning determination unit that determines whether the positioning of the subject is good or bad based on an optical image captured by an optical image capturing unit that captures an optical image of at least a partial area of the subject;
an image processing unit that sets image processing conditions for the radiation image based on the optical image captured by the optical image capturing unit, and does not capture a radiation image when the positioning determination unit determines that the positioning of the subject is good or that the positioning determination unit determines that the positioning of the subject is poor, and performs image processing under the set image processing conditions only on the radiation image captured by the radiation image capturing unit that captures a radiation image when the positioning determination unit determines that the positioning of the subject is good;
Function as.

The image processing method according to the eighth aspect of the present invention comprises:
a step of detecting radiation that has been irradiated from a radiation source and transmitted through a subject, and capturing a radiation image by a radiation image capturing unit that captures a radiation image;
capturing an optical image of at least a portion of an area of a subject;
determining whether the positioning of the subject is good or bad based on the captured optical image;
setting image processing conditions for the radiographic image based on the captured optical image, and performing image processing under the set image processing conditions only on radiographic images captured by the radiographic image capturing unit for which the positioning of the subject is determined to be good;
Including,
The radiation image capturing section is characterized in that, when the positioning of the subject is determined to be poor, the radiation image capturing section does not capture a radiation image .

The present invention can eliminate or simplify the user's setting operations for performing appropriate image processing on radiological images.

1 is a diagram showing an overall configuration of a radiation image capturing system according to an embodiment of the present invention. FIG. 2 is a block diagram showing the functional configuration of the console of FIG. 1 . 3 is a flowchart showing a flow of a radiation image generating process A executed by the control unit of FIG. 2 in the first embodiment. 10 is a flowchart showing a flow of a radiation image generating process B executed by the control unit of FIG. 2 in the second embodiment. 13 is a flowchart showing the flow of a radiation image generating process C executed by the control unit of FIG. 2 in the third embodiment. 13 is a flowchart showing the flow of a first photographing process A executed by the control unit in FIG. 2 in the fourth embodiment. 13 is a flowchart showing the flow of a second photographing process A executed by the control unit in FIG. 2 in the fourth embodiment. 13 is a flowchart showing a flow of a first photographing process B executed by the control unit in FIG. 2 in the fifth embodiment. 13 is a flowchart showing the flow of a second photographing process B executed by the control unit in FIG. 2 in the fifth embodiment.

Embodiments of the present invention will be described below with reference to the drawings. However, the scope of the invention is not limited to the illustrated examples.

First Embodiment
[Configuration of Radiation Image Capturing System 100]
First, the configuration of the first embodiment of the present invention will be described.
1 is a diagram showing an example of the overall configuration of a radiation image capturing system 100 according to this embodiment. The radiation image capturing system 100 is a system that performs radiation imaging of a subject H and performs image processing on the obtained radiation image.

As shown in FIG. 1, the radiation image capture system 100 includes a radiation irradiation device 1, a radiation detection device 2, a console 3, and an optical camera 4. The console 3 is connected to the radiation irradiation device 1, the radiation detection device 2, and the optical camera 4 so as to be able to transmit and receive data.

The radiation irradiation device 1 has a radiation source 11 arranged opposite the radiation detection device 2 across the subject H (examinee), and irradiates the subject H with radiation (X-rays) under the control of the console 3.

The radiation detection device 2 is a radiation image capturing section that detects radiation irradiated from the radiation source 11 and transmitted through the subject H, and captures a radiation image, and is configured with a detector holding section 22, a radiation detector P, etc. The radiation detector P is configured with an FPD (Flat Panel Detector), etc. The radiation detector P has, for example, a glass substrate, etc., and a plurality of detection elements (pixels) are arranged in a matrix at predetermined positions on the substrate, which detect radiation (X-rays) irradiated from the radiation irradiation device 1 and transmitted through at least the subject H according to its intensity, convert the detected radiation into an electrical signal, and store it. Each pixel is configured with a switching section, for example, a TFT (Thin Film Transistor). The radiation detector P controls the switching section of each pixel based on the image reading conditions input from the console 3, switches the reading of the electrical signal stored in each pixel, and acquires image data (radiation image) by reading the electrical signal stored in each pixel. The radiation detector P then outputs the acquired image data to the console 3.

The console 3 outputs radiation irradiation conditions to the radiation irradiation device 1 and image reading conditions to the radiation detection device 2, and controls the radiation irradiation by the radiation irradiation device 1 and the radiation image reading operation by the radiation detection device 2. The console 3 also performs image processing on the captured radiation image as an image processing unit.

As shown in FIG. 2, the console 3 is configured with a control unit 31, a memory unit 32, an operation unit 33, a display unit 34, and a communication unit 35, and each unit is connected by a bus 36.

The control unit 31 is composed of a CPU (Central Processing Unit), a RAM (Random Access Memory), etc. In response to the operation of the operation unit 33, the CPU of the control unit 31 reads out the system program and various processing programs stored in the storage unit 32 and expands them into the RAM, and centrally controls the operation of each part of the console 3 and the operation of the radiation irradiation device 1 and the radiation detection device 2 according to the expanded programs.

The storage unit 32 is configured with a non-volatile semiconductor memory, a hard disk, etc. The storage unit 32 stores various programs executed by the control unit 31, parameters required for executing processes by the programs, data such as processing results, etc. The various programs are stored in the form of readable program codes, and the control unit 31 sequentially executes operations in accordance with the program codes.
The storage unit 32 also stores the radiographic images acquired by imaging in association with patient information (patient ID, patient name, etc.) and examination information (examination date, imaging site, etc.).

The operation unit 33 is configured with a keyboard equipped with cursor keys, numeric input keys, various function keys, etc., and a pointing device such as a mouse, and outputs instruction signals input by key operations on the keyboard or mouse operations to the control unit 31. The operation unit 33 may also be equipped with a touch panel on the display screen of the display unit 34, in which case it outputs instruction signals input via the touch panel to the control unit 31. Furthermore, the operation unit 33 is equipped with an exposure switch, etc., for instructing the radiation irradiation device 1 to perform radiation imaging.

The display unit 34 is composed of a monitor such as an LCD (Liquid Crystal Display) or CRT (Cathode Ray Tube), and displays input instructions and data from the operation unit 33 according to the instructions of the display signal input from the control unit 31.

The communication unit 35 has an interface for transmitting and receiving data with the radiation irradiation device 1, the radiation detection device 2, and the optical camera 4. Note that communication between the console 3 and the radiation irradiation device 1, the radiation detection device 2, and the optical camera 4 may be wired communication or wireless communication.

The optical camera 4 is an optical image capturing unit that captures optical images and is configured, for example, with a CCD (Charge Coupled Device) camera, a CMOS (Complementary Metal Oxide Semiconductor Device) camera, or an infrared camera. In this embodiment, the optical camera 4 is provided near the radiation source 11 of the radiation irradiation device 1, and captures an optical image of at least a portion of the area irradiated with radiation from the radiation source 11 (basically an area slightly larger than the area irradiated with radiation) in accordance with instructions from the console 3, and transmits the captured optical image to the console 3.

[Operation of Radiation Image Capturing System 100]
Next, the operation of the radiation image capturing system 100 will be described.
When performing radiography, the radiographer first prepares for radiography. That is, the radiographer accepts input of patient information and the like through the operation unit 33 of the console 3, and positions the subject H. When radiography preparation is complete, the radiographer issues an instruction to start radiography through the operation unit 33. When the instruction to start radiography is received from the operation unit 33, the console 3 executes radiographic image generation process A shown in FIG. The radiographic image generation process A is executed by the control unit 31 in cooperation with a program stored in the storage unit 32.

In the radiation image generating process A, the control unit 31 first causes the optical camera 4 to capture an image and obtain an optical image (step S1).
That is, an optical image of at least a part of the area irradiated with radiation from the radiation source 11 is obtained.

Next, the control unit 31 analyzes the acquired optical image to determine the imaging site (step S2).
The imaging region is a region that is the subject of imaging for a radiation image.
There is no particular limitation on the method of determining the imaging site from the optical image. For example, a template image of an optical image for each site that can be an imaging site in a radiological examination is prepared in advance, template matching is performed between the optical image acquired from the optical camera 4 and each template image, and the site with the highest similarity is determined to be the imaging site.

Next, the control unit 31 sets image processing conditions for the radiation image based on the determined imaging region (step S3).
For example, a conversion table that associates each imaging site with the optimal image processing conditions (image processing parameters) corresponding to the imaging site is stored in the storage unit 32, and the control unit 31 uses this conversion table to specify the image processing conditions corresponding to the imaging site determined in step S3, and sets the specified image processing conditions as the image processing conditions for the radiographic image to be captured. Here, the image processing conditions that are set according to the imaging site include at least one of the following image processing conditions: dynamic range compression processing, contrast correction processing, density correction processing, LUT (Look Up Table) processing, frequency emphasis processing, scattered radiation correction processing, noise suppression processing, image trimming (for example, trimming to a hexagonal size when determined to be a hand bone), image masking, image rotation, and image inversion (for example, inverting the image when determined to be a chest PA).

Next, in response to pressing of the exposure switch, the control unit 31 causes the radiation irradiation device 1 and the radiation detection device 2 to perform radiation photography and obtain a radiation image (step S4).
Then, the acquired radiographic image is subjected to image processing under the image processing conditions set in step S3 (step S5), and the image-processed radiographic image is stored in the memory unit 32 in association with the patient information and examination information (step S6), and the radiographic image generation process A is terminated.

In the above-mentioned radiation image generation process A, the imaging area is identified based on the optical image, and image processing conditions according to the imaging area are automatically set and image processing is performed on the radiation image, so that appropriate image processing according to the imaging area is possible without the user having to set the imaging area or image processing conditions. In other words, the user's setting operation for performing appropriate image processing on the radiation image can be omitted or simplified.

In the above description, the image processing conditions for the radiographic image are automatically set based on the imaging area determined by analyzing the optical image. However, it is also possible to automatically set imaging conditions and image reading conditions based on the determined imaging area, and perform radiography to obtain the radiographic image.
In addition, in FIG. 3, the radiation image is acquired after the image processing conditions are set, but the radiation image may be acquired in parallel with the analysis of the optical image.

Second Embodiment
A second embodiment of the present invention will now be described.
In the case of a radiation image, the optimum image processing conditions change depending on the physique of the subject H.
In the second embodiment, an example will be described in which the physique of the subject H is determined based on an optical image obtained by capturing the subject H, and appropriate image processing according to the physique is applied to the radiation image.

In the second embodiment, the optical camera 4 is positioned with its lens facing the side of the subject H, and acquires an optical image of the side of the subject H (which may be the entire side of the subject H or part of it) in response to instructions from the console 3 and transmits it to the console 3.
Other configurations of the radiation image capturing system 100 are similar to those described in the first embodiment, so the description will be used here, and the operation of the second embodiment will be described below.

When preparation for imaging is complete and an instruction to start imaging is given by the operation unit 33, the console 3 executes the radiation image generation process B shown in FIG. 4. The radiation image generation process B is executed by the control unit 31 in cooperation with a program stored in the storage unit 32.

In the radiographic image generating process B, the control unit 31 first causes the optical camera 4 to capture an image and obtain an optical image (step S11).
That is, an optical image of the side of the subject H is obtained.

Next, the control unit 31 analyzes the acquired optical image to determine the physical build of the subject H (step S12).
For example, as described in JP 2011-139761 A, the control unit 31 extracts the contour of the subject H from an optical image capturing the side of the subject H, and calculates the body thickness from the extracted contour. Then, by comparing the calculated body thickness with a plurality of predetermined reference values, it is determined whether the physique of the subject H is, for example, obese, normal, or thin.

Next, the control unit 31 sets image processing conditions for the radiation image based on the determined physique (step S13).
For example, a conversion table that associates each physique with the optimal image processing conditions according to the physique is stored in the storage unit 32, and the control unit 31 uses this conversion table to identify the image processing conditions according to the physique determined in step S12, and sets the identified image processing conditions as the image processing conditions to be applied to the radiographic image to be captured. Here, the image processing conditions that are set according to the physique include, for example, at least one of dynamic range compression processing, contrast correction processing, density correction processing, LUT (Look Up Table) processing, frequency emphasis processing, scattered radiation correction processing, noise suppression processing, image trimming, image masking, image rotation, and image inversion.

Next, in response to pressing of the exposure switch, the control unit 31 causes the radiation irradiation device 1 and the radiation detection device 2 to perform radiation photography and obtain a radiation image (step S14).
Then, the acquired radiographic image is subjected to image processing under the image processing conditions set in step S13 (step S15), and the image-processed radiographic image is stored in the memory unit 32 in association with the patient information and examination information (step S16), and the radiographic image generation process B is terminated.

In the above-mentioned radiation image generation process B, the physique of the subject H is determined based on the optical image, and image processing conditions according to the physique are automatically set, so that appropriate image processing according to the physique is possible without the user having to set the physique of the subject H or image processing parameters. In other words, the user's setting operation for performing appropriate image processing on the radiation image can be omitted or simplified.

In the above description, the image processing conditions for the radiographic image are automatically set based on the physique determined by analyzing the optical image. However, it is also possible to automatically set the shooting conditions and image reading conditions based on the determined physique, and then perform radiography to obtain the radiographic image.
In addition, in FIG. 4, the radiation image is acquired after the image processing conditions are determined, but the radiation image may be acquired in parallel with the analysis of the optical image.

Third Embodiment
A third embodiment of the present invention will now be described.
For example, for hospitalized patients, radiation images may be periodically acquired to monitor the progress of their condition. If the image processing conditions are different each time a follow-up is performed, it is not possible to determine whether the patient's condition has changed, and an appropriate diagnosis cannot be made.
Therefore, in the third embodiment, an example will be described in which an optical image of the subject H is acquired during radiation photography, the patient is identified based on the acquired optical image, and image processing conditions applied to a radiation image (past image) previously taken of the patient are identified and applied to the radiation image acquired this time.

In the third embodiment, the storage unit 32 stores, in association with the captured radiographic image, patient information, examination information, an optical image of the subject captured during radiographic image capture, features calculated from the optical image, and image processing conditions for image processing applied to the radiographic image.

The optical camera 4 is also positioned in a position where it can capture an optical image including a specific structure of the subject H (e.g., the face or eyes), and obtains an optical image including the specific structure of the subject H in response to an instruction from the console 3 and transmits it to the console 3.

The rest of the configuration of the radiographic imaging system 100 is the same as that described in the first embodiment, so we will refer to that description and explain the operation of the third embodiment below.

When preparation for imaging is complete and an instruction to start imaging is given from the operation unit 33, the console 3 executes the radiographic image generation process C shown in FIG. 5. The radiographic image generation process C is executed by the control unit 31 in cooperation with a program stored in the storage unit 32.

In the radiographic image generating process C, the control unit 31 first causes the optical camera 4 to capture an image and obtain an optical image (step S21).
That is, an optical image including predetermined structures of the subject H (for example, the face, eyes, etc.) is obtained.

Next, the control unit 31 calculates the feature amount (image feature amount) of the subject H by analyzing the acquired optical image (step S22).
In step S22, the control unit 31 calculates, for example, feature quantities representing the size and shape of a predetermined structure of the subject H. For example, as described in JP 2015-219879 A, a face region is recognized from an optical image using a known image recognition technique, and a predetermined structure (eyes, nose, mouth) in the face region is recognized and feature quantities representing the size and shape are calculated. For example, a plurality of feature points are set on the structure, and the distance between the predetermined feature points and the like are obtained as the feature quantities of the size. In addition, the positions of the feature points and the distance between the feature points and the like can be obtained as the feature quantities of the shape. Alternatively, as described in JP 2012-29894 A, the feature quantities of the pupils may be calculated using a known pupil authentication processing technique. In addition, the feature quantities of a plurality of structures may be calculated.

Next, the control unit 31 sets image processing conditions for the radiographic image based on the calculated feature amount (step S23).
In step S23, the calculated feature amount is compared with feature amounts (feature amounts calculated from optical images) stored in association with past radiographic images (of the same imaging site) in the storage unit 32, and if a matching feature amount is found, the image processing conditions used for the past radiographic image associated with that feature amount are read out and set as the image processing conditions for the radiographic image to be captured this time. This makes it possible to set the same image processing conditions as those used for the past radiographic images of subject H (same patient).
If no matching feature exists in the storage unit 32, the user may set image processing conditions via the operation unit 33, for example.

Next, in response to pressing of the exposure switch, the control unit 31 causes the radiation irradiation device 1 and the radiation detection device 2 to perform radiation photography and obtain a radiation image (step S24).
The acquired radiographic image is then subjected to image processing under the image processing conditions set in step S23 (step S25), and the image-processed radiographic image is stored in the memory unit 32 in association with the patient information, examination information, acquired optical image, feature amounts and image processing conditions (step S26), and the radiographic image generation process C is terminated.

In the above-mentioned radiation image generation process C, the characteristic amounts of the subject H are calculated from the optical image, and the image processing conditions applied to the past radiation images of the subject H are identified and automatically set based on the calculated characteristic amounts, so that appropriate image processing that allows follow-up observation can be performed without the user having to identify and set the image processing conditions applied to the past radiation images of the subject H. In other words, the user's setting operations for performing appropriate image processing on the radiation images can be omitted or simplified.

In the above description, the image processing conditions for the radiographic image are automatically set based on the feature amounts calculated by analyzing the optical image. However, it is also possible to automatically set the shooting conditions and image reading conditions based on the calculated feature amounts, and perform radiography to obtain the radiographic image.
In addition, in FIG. 5, the radiation image is acquired after the image processing conditions are determined, but the radiation image may be acquired in parallel with the analysis of the optical image.

Fourth Embodiment
Next, a fourth embodiment of the present invention will be described.
When taking radiographs, the person performing the radiography positioning the patient and taking the images is responsible. However, because looking at the surface of the body does not reveal the condition inside the body, the actual radiographic images obtained may not be suitable for diagnosis and the images may have to be taken again.
Therefore, in the fourth embodiment, whether the positioning is good (whether the positioning is suitable for diagnosis) is determined before radiation imaging based on an optical image acquired during radiation imaging, and the user is notified if the positioning is poor.

In the fourth embodiment, the memory unit 32 stores various programs, including a machine learning program for determining whether the positioning during radiation imaging is good or bad through machine learning based on an input optical image, and a learning parameter generation program for performing learning based on learning data consisting of optical images and positioning determination results, and generating learning parameters to be used in the machine learning program.
The storage unit 32 is also provided with a learning data storage unit for accumulating and storing learning data, and a learning parameter storage unit for storing learning parameters.
In addition, the optical camera 4 is provided near the radiation source 11 of the radiation irradiation device 1, and in accordance with instructions from the console 3, captures an optical image of the area irradiated with radiation from the radiation source 11 and transmits the captured optical image to the console 3.
Other configurations of the radiation image capturing system 100 in the fourth embodiment are similar to those described in the first embodiment, so the description will be used here and the operation of the fourth embodiment will be described below.

When preparation for imaging is complete and an instruction to start imaging is given from the operation unit 33, the console 3 refers to the learning parameter storage unit, and if the learning parameters are not stored, executes the first imaging process A shown in FIG. 6. If the learning parameters are stored, executes the second imaging process A shown in FIG. 7. The first imaging process A and the second imaging process A are executed by cooperation between the control unit 31 and the program stored in the storage unit 32.

(First Shooting Process A)
First, the first photographing process A will be described with reference to FIG.
In the first photographing process A, the control unit 31 first causes the optical camera 4 to capture an image and obtain an optical image (step S31).

Next, in response to pressing the exposure switch, the control unit 31 causes the radiation irradiation device 1 and the radiation detection device 2 to perform radiography to obtain a radiographic image, which is then stored in the memory unit 32 (step S32).

Next, the control unit 31 determines the positioning from the acquired radiographic image (step S33).
For example, the control unit 31 displays the acquired radiographic image on the display unit 34, accepts input of whether the positioning is good or bad by the user through the operation unit 33, and judges the positioning according to the input of whether the positioning is good or bad. Alternatively, the control unit 31 may analyze the radiographic image and automatically judge the positioning. For example, the control unit 31 may perform a detection process of a site of interest according to the imaging site, and judge the positioning to be good if the site of interest is included without any loss, and judge the positioning to be bad if the site of interest is lost.

Next, the control unit 31 associates the optical image acquired in step S31 with the positioning judgment result and stores (adds) them as learning data in the learning data storage unit of the storage unit 32 (step S34).

Next, the control unit 31 performs learning based on the learning data stored in the learning data storage unit in accordance with the learning parameter generation program, and generates machine learning learning parameters for determining whether the positioning is good or bad from the input optical image (step S35).
As the machine learning, for example, a convolutional neural network or the like can be used, but is not limited to this.

Then, the control unit 31 stores the generated learning parameters in the storage unit 32 (step S36), and ends the first photographing process A.
If the positioning determination result determined in step S33 is poor positioning, the user issues an instruction to photograph using the operation unit 33 and photographs again.

It is preferable that steps S34 to S36 are performed for each imaging region.
The processes in steps S35 to S36 may be performed when a predetermined number of learning data items or more are stored.

(Second Shooting Process A)
Next, the second photographing process A will be described with reference to FIG.

In the second photographing process A, the control unit 31 first causes the optical camera 4 to capture an image and obtain an optical image (step S41).

Next, the control unit 31 uses the acquired optical image as an input and determines whether the positioning is good or bad through machine learning using the learning parameters stored in the learning parameter storage unit of the storage unit 32 (step S42).

When it is determined that the positioning is poor (step S43; YES), the control unit 31 notifies that the positioning is poor (step S44), and ends the second imaging process A.
In step S44, the control unit 31 displays a notification such as "Positioning is poor" on the display unit 34. Alternatively, the console 3 may be configured to include a voice output unit, and a notification message such as "Positioning is poor" may be output by voice.

On the other hand, if it is determined that the positioning is not poor (is good) (step S43; NO), the control unit 31 causes the radiation irradiation device 1 and the radiation detection device 2 to perform radiography in response to pressing of the exposure switch, to obtain a radiographic image, and stores it in the memory unit 32 (step S45).

Next, the control unit 31 determines the positioning from the acquired radiographic image, updates the learning parameters based on the determination result (step S46), and ends the second imaging process A.
In step S46, the control unit 31 executes the same processes as those in steps S33 to S36 in FIG. 6, and updates the learning parameters stored in the learning parameter storage unit.
If the positioning determination result determined in step S46 is poor positioning, the user issues an instruction to photograph using the operation unit 33 and photographs again.

In this way, in the fourth embodiment, it is possible to determine whether the positioning is good (whether the positioning is suitable for diagnosis) based on the optical image before radiography, which makes it possible to reduce the effort required for re-imaging and the patient's exposure to radiation.

Fifth embodiment
Next, a fifth embodiment of the present invention will be described.
When taking radiographs, the person performing the radiography positioning the patient and taking the images is responsible. However, because looking at the surface of the body does not reveal the condition inside the body, the actual radiographic images obtained may not be suitable for diagnosis and the images may have to be taken again.
Therefore, in the fifth embodiment, whether the positioning is good (whether the positioning is suitable for diagnosis) is determined before radiation imaging based on an optical image, and if the positioning is poor, the amount of positioning adjustment is notified to the user.

In the fifth embodiment, the memory unit 32 stores various programs, including a machine learning program that uses machine learning to determine whether positioning during radiation imaging is good or bad based on input optical images and estimates the amount of positioning adjustment in the event of poor positioning, and a learning parameter generation program that learns based on learning data consisting of optical images, positioning determination results, and positioning adjustment amounts in the event of poor positioning, and generates learning parameters to be used in the machine learning program.
The storage unit 32 is also provided with a learning data storage unit for accumulating and storing learning data, and a learning parameter storage unit for storing learning parameters.
In addition, the optical camera 4 is provided near the radiation source 11 of the radiation irradiation device 1, and in accordance with instructions from the console 3, captures an optical image of the area irradiated with radiation from the radiation source 11 and transmits the captured optical image to the console 3.
Other configurations of the radiation image capturing system 100 in the fifth embodiment are similar to those described in the first embodiment, so the description will be used here and the operation of the fifth embodiment will be described below.

When preparation for imaging is complete and an instruction to start imaging is given from the operation unit 33, the console 3 refers to the learning parameter storage unit, and if the learning parameters are not stored, executes the first imaging process B shown in FIG. 8. If the learning parameters are stored, executes the second imaging process B shown in FIG. 9. The first imaging process B and the second imaging process B are executed by cooperation between the control unit 31 and the program stored in the storage unit 32.

(First Shooting Process B)
First, the first photographing process B will be described with reference to FIG.

In the first imaging process B, the control unit 31 first causes the optical camera 4 to capture an image and obtain an optical image (step S51).

Next, in response to pressing the exposure switch, the control unit 31 causes the radiation irradiation device 1 and the radiation detection device 2 to perform radiography to obtain a radiographic image, which is then stored in the memory unit 32 (step S52).

Next, the control unit 31 performs a positioning determination of the acquired radiographic image (step S53).
The process of step S53 is similar to that described in step S33 of FIG. 6, and therefore the description thereof will be cited.

Next, the control unit 31 determines whether or not the positioning determination result indicates a positioning defect (step S54).
When it is determined that there is no positioning failure (step S54; NO), the control unit 31 proceeds to step S60.

On the other hand, if it is determined that the positioning is poor (step S54; YES), the control unit 31 performs image capture again.
That is, the control unit 31 causes the optical camera 4 to capture an image and obtain an optical image (step S55).
Next, in response to pressing of the exposure switch, the control unit 31 causes the radiation irradiation device 1 and the radiation detection device 2 to perform radiation imaging to obtain a radiation image, and stores the image in the storage unit 32 (step S56).

Next, the control unit 31 determines the positioning of the acquired radiographic image (step S57).
The process of step S57 is similar to that described in step S33 of FIG. 6, and therefore the description thereof will be cited.

Next, the control unit 31 determines whether the positioning determination result is a positioning defect or not (step S58).
When it is determined that the positioning is defective (step S58; YES), the control unit 31 returns to step S55 and repeats steps S55 to S58.

If it is determined that the positioning is not poor (is good) (step S58; NO), the control unit 31 estimates the amount of positioning adjustment based on the optical image of poor positioning acquired in step S51 and the optical image of good positioning acquired in step S55 (step S59), and proceeds to step S60.
For example, a local matching process or the like is performed on an optical image with poor positioning and an optical image with good positioning to calculate the amount of movement required to align the optical image with poor positioning with the optical image with good positioning, and the amount of movement is estimated as the positioning adjustment amount (see, for example, Kano Akiko and Morokachiko, "Research on Time-lapse Differential Processing of X-ray Images in Mass Chest Screening Examinations," Konica Minolta Technology Report, Vol. 8 (1995)).

In step S60, the control unit 31 associates the acquired optical image, the positioning judgment result, and, if the positioning judgment result indicates poor positioning, the positioning adjustment amount, and stores (adds) them as learning data in the learning data storage unit of the storage unit 32 (step S60).

Next, the control unit 31 performs learning based on the learning data stored in the learning data storage unit in accordance with the learning parameter generation program, and generates machine learning learning parameters for determining whether the positioning is good or bad from the input optical image and estimating the amount of positioning adjustment in the event of poor positioning (step S61).
As the machine learning, for example, a convolutional neural network or the like can be used, but is not limited to this.

Then, the control unit 31 stores the generated learning parameters in the storage unit 32 (step S62), and ends the first photographing process B.
It is preferable that steps S60 to S62 are performed for each imaging region.
Furthermore, the processes in steps S61 and S62 may be performed when a predetermined number of learning data items or more are stored.

(Second Shooting Process B)
Next, the second photographing process B will be described with reference to FIG.

In the second photographing process B, the control unit 31 first causes the optical camera 4 to capture an image and obtain an optical image (step S71).

Next, the control unit 31 uses the acquired optical image as an input and determines whether the positioning is good or bad through machine learning using the learning parameters stored in the learning parameter storage unit of the storage unit 32 (step S72).

If it is determined that the positioning is poor (step S73; YES), the control unit 31 estimates the amount of positioning adjustment by machine learning (step S74), notifies the estimated amount of positioning adjustment (step S75), and terminates the second shooting process B.
In step S75, the control unit 31 displays a notification such as "Positioning is poor. Please move the subject 0 cm to the right" on the display unit 34. Alternatively, the console 3 may be configured to include an audio output unit, and a notification message such as "Positioning is poor. Please move the subject 0 cm to the right" may be output by voice.

On the other hand, if it is determined that the positioning is not poor (is good) (step S73; NO), the control unit 31 causes the radiation irradiation device 1 and the radiation detection device 2 to perform radiography in response to pressing of the exposure switch, to obtain a radiographic image, and stores it in the memory unit 32 (step S76).

Next, the control unit 31 determines the positioning from the acquired radiographic image, updates the learning parameters based on the determination result (step S77), and ends the second imaging process B.
In step S77, the control unit 31 executes the same processes as those in steps S53 to S62 in FIG. 8, and updates the learning parameters stored in the learning parameter storage unit.
If the positioning determination result determined in step S77 is defective positioning, the user issues an instruction to shoot using the operation unit 33 and shoots again.

In this way, in the fifth embodiment, it is possible to determine whether the positioning is good (whether the positioning is suitable for diagnosis) based on the optical image before radiography, which makes it possible to prevent the trouble of re-imaging and the patient's exposure to radiation. Furthermore, if the positioning is poor, the user can be notified of the amount of positioning adjustment required, so the user can easily understand how to adjust the positioning, making it easier to adjust the positioning.

The first to fifth embodiments have been described above, but the contents described in the above embodiments are preferred examples of the present invention and are not limited to these.

For example, in the above explanation, a hard disk or a non-volatile semiconductor memory is used as a computer-readable medium for the program according to the present invention, but the present invention is not limited to this example. Portable recording media such as CD-ROMs can be used as other computer-readable media. Furthermore, carrier waves can also be used as a medium for providing data for the program according to the present invention via a communication line.

In addition, the detailed configuration and operation of each device that constitutes the radiation imaging system may be modified as appropriate without departing from the spirit and scope of the present invention.

Reference Signs List 100 Radiation image capturing system 1 Radiation irradiation device 11 Radiation source 2 Radiation detection device P Radiation detector 3 Console 31 Control unit 32 Storage unit 33 Operation unit 34 Display unit 35 Communication unit 36 Bus 4 Optical camera

Claims (8)

a radiation image capturing unit that detects radiation that has been irradiated from a radiation source and transmitted through a subject, and captures a radiation image;
an optical image capturing unit configured to capture an optical image of at least a portion of the subject;
a positioning determination unit that determines whether the positioning of the subject is good or bad based on the optical image captured by the optical image capturing unit;
an image processing unit that performs image processing on the radiation image captured by the radiation image capturing unit;
Equipped with
the image processing unit sets image processing conditions for the radiographic image based on the optical image captured by the optical image capturing unit, and performs image processing under the set image processing conditions only on the radiographic image captured by the radiographic image capturing unit for which the positioning determination unit has determined that the positioning of the subject is good ;
2. A radiation image capturing system according to claim 1, wherein the radiation image capturing section does not capture a radiation image when the positioning determination section determines that the positioning of the subject is poor . the optical image capturing unit captures an optical image of at least a part of an area of the subject irradiated with radiation from the radiation source;
The radiation image capturing system according to claim 1 , wherein the image processing unit determines the part of the subject that is to be imaged in the radiation image by analyzing the optical image, and sets the image processing conditions according to the determined part. The radiographic imaging system according to claim 1, wherein the image processing unit determines the physique of the subject by analyzing the optical image, and sets the image processing conditions according to the determined physique of the subject. The radiographic imaging system according to claim 1, wherein the image processing unit calculates the feature amount of the subject by analyzing the optical image, and sets the image processing conditions according to the calculated feature amount. The radiographic imaging system according to claim 4, wherein the feature quantity represents the size or shape of a specific structure of the subject. The radiographic imaging system according to any one of claims 1 to 5, wherein the image processing condition is at least one of dynamic range compression processing, contrast correction processing, density correction processing, LUT conversion processing, frequency emphasis processing, scattered radiation correction processing, noise suppression processing, image trimming, image masking, image rotation, and image inversion. a computer that detects radiation that has been irradiated from a radiation source and transmitted through a subject, and performs image processing on a radiation image captured by a radiation image capturing unit that captures a radiation image;
a positioning determination unit that determines whether the positioning of the subject is good or bad based on an optical image captured by an optical image capturing unit that captures an optical image of at least a partial area of the subject;
an image processing unit that sets image processing conditions for the radiation image based on the optical image captured by the optical image capturing unit, and does not capture a radiation image when the positioning determination unit determines that the positioning of the subject is good or that the positioning determination unit determines that the positioning of the subject is poor, and performs image processing under the set image processing conditions only on the radiation image captured by the radiation image capturing unit that captures a radiation image when the positioning determination unit determines that the positioning of the subject is good;
A program to function as a a step of detecting radiation that has been irradiated from a radiation source and transmitted through a subject, and capturing a radiation image by a radiation image capturing unit that captures a radiation image;
capturing an optical image of at least a portion of an area of a subject;
determining whether the positioning of the subject is good or bad based on the captured optical image;
setting image processing conditions for the radiographic image based on the captured optical image, and performing image processing under the set image processing conditions only on radiographic images captured by the radiographic image capturing unit for which the positioning of the subject is determined to be good;
Including,
The image processing method according to claim 1, wherein the radiation image capturing section does not capture a radiation image when the positioning of the subject is determined to be poor.

Images