Information processing device, radiographic system, method for processing information, and program

Abstract

To provide an information processing device that can improve determination accuracy for imaging posture and reduce probability of useless exposure due to wrong imaging posture when radiographing a subject and determining an imaging posture from an optical image of the subject.SOLUTION: An information processing device 100 includes: radiation image acquisition means 102 for acquiring a radiation image of a subject; optical image acquisition means 103 for acquiring an optical image of a subject; first processing means 210 for analyzing an optical image to determine whether subject examination information is satisfiable; and second processing means 220 for determine whether an optical image has image quality capable of being provided to the analysis by the first processing means 210 precedent to the processing by the first processing means 210.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present disclosure relates to an information processing device, a radiation imaging system, an information processing method, and a program. [Background technology]

[0002] In recent years, in radiography for medical examinations, radiography support using optical images has become common, in which the radiography site is optically photographed to acquire an optical image, and additional information obtained by analyzing the optical image is provided to the operator along with a live image. For example, Patent Document 1 provides a system that determines the radiography position of the subject from an optical image and outputs information regarding the appropriateness of the radiography position, thereby enabling efficient radiography that does not depend on the skill or experience of the radiologist. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2020-199163 Summary of the Invention [Problem to be solved by the invention]

[0004] The technology described in Patent Document 1 determines the photographing position of a subject from an optical image. However, while the image analysis technology applied to such photographing position determination improves the accuracy of image recognition by using a deep learning model or the like, the accuracy of photographing position determination may decrease if there is a problem with the image quality of the optical image, such as the subject protruding from the optical image.

[0005] The present disclosure has been made in view of the above-mentioned problems, and aims to provide an information processing device that can improve the accuracy of determining the radiographic mode when determining the appropriateness of the radiographic mode from an optical image of a subject, and can reduce the possibility of unnecessary exposure to radiation due to an error in the radiographic mode. [Means for solving the problem]

[0006] The information processing device of the present disclosure includes a radiological image acquisition means for acquiring a radiological image of a subject, an optical image acquisition means for acquiring an optical image of the subject, a first processing means for analyzing the optical image and determining whether the radiographic aspect of the subject in the optical image is appropriate, and a second processing means for determining whether the optical image input to the first processing means has image quality that can be used for analysis by the first processing means.

[0007] The information processing method disclosed herein comprises a first step of acquiring a radiological image of a subject, a second step of acquiring an optical image of the subject, a third step of analyzing the optical image to determine whether the radiographic aspect of the subject in the optical image is appropriate, and a fourth step of determining whether the optical image input in the third step has image quality that can be used for analysis by the third step. [Effects of the Invention]

[0008] According to the present disclosure, when performing radiography on a subject, an information processing device is realized that can improve the accuracy of determining the radiography mode when determining the appropriateness of the radiography mode from an optical image of the subject, and can reduce the possibility of unnecessary exposure to radiation due to an incorrect radiography mode. [Brief explanation of the drawings]

[0009] [Figure 1] 1 is a schematic diagram showing a radiation imaging system including an information processing device according to a first embodiment. [Figure 2] 10 is a flowchart showing image quality determination processing by a second processing unit in the information processing device according to the first embodiment. [Figure 3] FIG. 4 is a schematic diagram illustrating an example of a filter process according to the first embodiment. [Figure 4] 3A and 3B are schematic diagrams for explaining an example of contour extraction of a subject region of an optical image in the first embodiment. [Figure 5] 10 is a table for determining whether image quality is appropriate. [Figure 6] FIG. 10 is a schematic diagram showing a result of contour extraction. [Figure 7] 2 is a schematic diagram showing an optical image and the corresponding contour of a subject area; FIG. [Figure 8] FIG. 10 is a schematic diagram showing a case where another person is reflected in an optical image. [Figure 9] FIG. 10 is a schematic diagram showing a radiation imaging system including an information processing device according to a third modified example of the first embodiment. [Figure 10] 10 is a flowchart showing an image quality determination process by a second processing unit of an information processing device according to a third modified example of the first embodiment. [Figure 11] FIG. 10 is a schematic diagram showing a radiation imaging system including an information processing device according to a second embodiment. [Figure 12] FIG. 2 is a schematic diagram illustrating an example of an optical image. [Figure 13] 10 is a flowchart showing an image quality determination process by a second processing unit of an information processing device according to a second embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0010] -Basic configuration of information processing device in various embodiments- Before specifically disclosing the embodiments, the basic configuration of an information processing device in the present disclosure will be described.

[0011] The information processing device according to the present disclosure includes a radiographic image acquisition means for acquiring a radiographic image of a subject and an optical image acquisition means for acquiring an optical image of the subject, and further includes a first processing means and a second processing means. The first processing means analyzes the optical image and determines whether the radiographic imaging mode of the subject in the optical image is appropriate. The radiographic imaging mode of the subject refers to various aspects such as the imaging position and posture of the subject during the radiological examination. One example is that the imaging position of the subject is chest / front and the posture of the subject is upright. The first processing means determines whether the radiographic imaging mode of the subject in the optical image matches the examination information of the subject.

[0012] The second processing means determines whether the optical image input to the first processing means has image quality that can be used for analysis by the first processing means. In the present disclosure, the second processing means performs the determination, and if it is determined that the image quality is sufficient, the first processing means performs processing. This improves the accuracy of determining the radiography mode when determining the appropriateness of the radiography mode from the optical image of the subject when performing radiography of the subject, and reduces the possibility of unnecessary exposure to radiation due to an incorrect radiography mode.

[0013] Specific examples of insufficient optical image quality include (1) when part of the subject's (object's) area is cut off at the edge of the screen (extending beyond the edge of the screen), (2) when unnecessary body parts or body parts of other people are captured in the optical image, (3) when the image is out of focus, (4) when the optical image is not bright enough, and (5) when the hue and saturation of the optical image are inappropriate (when the person is not wearing appropriate clothing for radiography).

[0014] As a configuration to address (1), the second processing means includes a contour extraction unit that extracts the contour of the subject area in the optical image, and an intersection determination unit that uses the examination information of the subject to determine whether the intersection point between the contour extracted by the contour extraction unit and the periphery of the optical image is appropriate. As a configuration for dealing with (2), the second processing means determines that the optical image does not have sufficient image quality when the contour extraction unit extracts multiple contours. As a configuration for dealing with (3), the second processing means determines that the optical image is out of focus when the contour extraction section cannot extract the contour of the subject region. As a configuration to address (4), the second processing means further includes a brightness determination unit that determines whether the brightness of the optical image is below a threshold value. As a configuration to address (5), the second processing means further includes a hue / saturation determination unit that determines whether the hue of the subject area in the optical image is within the first region and whether the saturation of the subject area in the optical image is within the second region.

[0015] In the present disclosure, in a configuration that addresses (1), the above-described contour extraction unit and intersection determination unit may be replaced with the following coordinate detection unit and intersection determination unit. The coordinate detection unit determines whether or not coordinates at the edge of the subject area in the optical image match coordinates on the periphery of the optical image. The intersection determination unit uses examination information on the subject to determine whether or not the position on the periphery of the coordinates determined to match by the coordinate detection unit is appropriate. The second processing means determines that the image does not have sufficient image quality when the intersection determination unit determines that the position on the periphery of the coordinates determined to match by the coordinate detection unit does not match the examination information.

[0016] Preferred embodiments to which the present disclosure can be applied will be described in detail below with reference to the drawings. In the following description, common components across multiple drawings are assigned common reference numerals. Therefore, the common components will be described with mutual reference to multiple drawings, and descriptions of the components assigned common reference numerals will be omitted as appropriate. The radiation in the various embodiments may include α-rays, β-rays, γ-rays, and the like, which are beams formed by particles (including photons) emitted by radioactive decay, as well as beams having the same or higher energy levels, such as X-rays, particle beams, and cosmic rays.

[0017] -First embodiment- In the first embodiment, an example of a radiation imaging system including an information processing device to which the present disclosure is applied will be described.

[0018] <Configuration of Radiography System> FIG. 1 is a schematic diagram showing a radiation imaging system including an information processing apparatus according to the first embodiment. The radiation imaging system includes an information processing device 100 according to this embodiment, a radiation generating device 120, a radiation detecting device 130, an optical imaging device 140, a display unit 150, and an operation unit 160. The information processing device 100 controls radiation imaging using the radiation detecting device 130 and the radiation generating device 120.

[0019] The radiation detection device 130 detects radiation that has been irradiated from the radiation generation device 120 and passed through a subject (not shown), and outputs image data corresponding to the radiation. The image data can also be referred to as a medical image or a radiological image. Specifically, the radiation detection device 130 detects the radiation that has passed through the subject as electric charges corresponding to the amount of transmitted radiation. For example, the radiation detection device 130 may use a direct conversion sensor that directly converts radiation into electric charges, such as a-Se, or an indirect sensor that converts radiation into visible light and uses a scintillator, such as CsI, and a photoelectric conversion element, such as a-Si. Furthermore, the radiation detection device 130 generates image data by A / D converting the detected electric charges and outputs the image data to the information processing device 100.

[0020] The information processing device 100 is communicably connected to the radiation detection device 130 via, for example, a wired or wireless network or a dedicated line. The radiation detection device 130 captures radiation generated by the radiation generation device 120 and outputs image data to the information processing device 100. The information processing device 100 has an application function that runs on a computer. That is, the information processing device 100 has one or more processors and memories, and the processors execute programs stored in the memories to realize each of the functional units described below. However, some or all of the functional units may be realized by dedicated hardware.

[0021] The information processing device 100 includes a radiographic image acquisition unit 101, an image processing unit 102, an optical image acquisition unit 103, an image display control unit 104, a first processing unit 210, a second processing unit 220, and an examination information management unit 107. The first processing unit 210 includes an image analysis unit 211 and an image determination unit 212. The second processing unit 220 includes a contour extraction unit 221 and an intersection determination unit 222.

[0022] Based on the examination information received by the operation unit 160, the radiation generation device 120 controls the timing of generating radiation and the radiation imaging conditions. The radiation image acquisition unit 101 controls the timing of capturing and outputting image data by the radiation detection device 130, and receives the generated image data. The image processing unit 102 performs image processing on the received image data, and the image display control unit 104 displays the processed image on the display unit 150. A graphical user interface is provided using the display unit 150, and instructions from the operator are received by the operation unit 160. Examination information is selected based on the received input, and the examination information is managed by the examination information management unit 107.

[0023] The information processing device 100 controls the conditions, timing, frame rate, etc. under which the optical imaging device 140 acquires optical images. The optical image acquisition unit 103 acquires optical images from the optical imaging device 140. The image display control unit 104 adds information to be displayed outside the optical image, and controls the content to be displayed using the display unit 150. The image storage unit 108 stores the images acquired by the radiation image acquisition unit 101 and the optical image acquisition unit 103.

[0024] The image analysis unit 121 analyzes the radiographic aspects of the subject (examinee) in the optical image, such as the imaging position and posture, and the part and posture of the subject, using the optical image acquired from the optical image acquisition unit 103 and the examination information acquired from the examination information management unit 107. The image determination unit 212 determines whether the radiographic aspects of the subject in the optical image match the settings of the examination information.

[0025] If the image determination unit 212 determines that the radiographic mode of the subject in the optical image matches the settings of the examination information, the image display control unit displays that fact along with the optical image on the display unit 150. If it determines that the radiographic mode of the subject does not match the settings of the examination information, the image display control unit displays a warning to that effect and the reason for the mismatch on the display unit 150 along with the optical image.

[0026] The judgment in the first processing unit 210 may be performed by an inference processing unit 213 that uses machine learning or the like. The inference processing unit 213 assigns the same numbers or characters to the optical image and the imaging failure information immediately before radiography, links them, and performs machine learning using these as learning data to obtain a learning result. For example, a convolution neural network may be used for machine learning. The image judgment unit 212 judges the positioning related to the radiography mode when radiographing the subject from the optical image of the subject. The second processing unit 220 controls the output of information related to the appropriateness of the radiography mode to the image display control unit 104 according to the judgment result.

[0027] Before the first processing unit 210 makes the above-mentioned determination, the second processing unit 220 uses the contour of the subject area extracted by the contour extraction unit 221 to determine whether the optical image to be input to the first processing unit 210 has image quality suitable for image analysis by the first processing unit 210. In the second processing unit 220, the contour extraction unit 221 extracts the contour of the subject area in the optical image. The intersection determination unit 222 detects intersections between the contour of the subject area output by the contour extraction unit 221 and each of the top, bottom, left, and right edges of the optical image. Specific operational functions of the second processing unit 220 will be described later.

[0028] The contour extraction unit 221 extracts a subject region from the optical image using, for example, semantic segmentation, extracts the contour by filtering, and passes the contour to the intersection determination unit 222. Semantic segmentation can be performed using, for example, a trained model. A trained model is a model that has been trained (learned) in advance using appropriate teacher data (learning data) for a machine learning model based on an arbitrary machine learning algorithm, such as deep learning. The trained model in this embodiment can be generated, for example, by training a combination of an optical image of a subject and an image in which the subject region in the optical image is labeled as teacher data. However, although the trained model is obtained in advance using appropriate training data, this does not mean that further learning is not performed; additional learning can also be performed. Additional learning can also be performed after the information processing device 100 is installed at the destination of use. The trained model may be stored in a storage unit (not shown) and can be retrieved from the storage unit for use.

[0029] The operation unit 160 is realized, for example, by displaying a plurality of pieces of acquired examination information in a list format on the display unit 150, and setting the selected examination information as the examination target in response to an operation input by the user to select one piece of examination information from the list. Note that the user may also directly input examination information from the operation unit 160. After selecting an examination, the operation unit 160 also accepts an input to select the imaging content to be the imaging target.

[0030] <Information processing method> The information processing method according to this embodiment will be described below. Fig. 2 is a flowchart showing the image quality determination process performed by the second processing unit 220.

[0031] In step S201, the test information management unit 107 allows the user to select one of the multiple pieces of test information acquired from the operation unit 160 and sets it as the test target. This process is realized, for example, by displaying the acquired multiple pieces of test information in a list format and setting the selected test information as the test target in response to a user's operation input to select one piece of test information from the list. Note that the user may also directly input test information from the operation unit 160.

[0032] In step S202, the information processing device 100 starts the examination by transmitting a signal to the radiation detection device 130 to transition to a preparation state in accordance with the set examination information. In response to this signal, for example, the radiation detection device 130 controls the bias power supply using a main control circuit to apply a bias voltage to the two-dimensional image sensor. Thereafter, in order to read out dark current signals accumulated in the pixels, initialization is performed in which an image signal is read out from the pixel array using a drive circuit. After completion of initialization, the radiation detection device 130 transmits status information indicating that the radiation detection device 130 is ready to obtain a radiographic image to the information processing device 100. Furthermore, the information processing device 100 (examination information management unit 107) sets operating parameters (tube voltage, etc.) of the radiation generation device 120 based on the examination information selected in step S201. When the information processing device 100 receives a notification from the radiation detection device 120 that imaging preparations are complete based on the status information, it notifies the radiation generation device 120 of permission to emit radiation.

[0033] In step S203, the optical image acquisition unit 103 acquires an optical image captured by the optical imaging device 140.

[0034] In step S204, the image display control unit 104 controls the display content of the optical image acquired by the optical image acquisition unit 103 and displays it on the display unit 150.

[0035] In step S205, the contour extraction unit 221 of the second processing unit 220 processes the optical image acquired by the optical image acquisition unit 103 and the examination information acquired by the examination information management unit 107. Specifically, the contour extraction unit 221 performs, for example, semantic segmentation processing on the optical image and applies filtering processing to extract the contour of the subject region.

[0036] FIG. 3 is a schematic diagram showing an example of the filter processing in this embodiment. In filter processing, for example, the contour of the subject area is extracted by processing each pixel such that (1) if that pixel is 0, it returns 0, and (2) if that pixel is 1, it returns 1 if any one of the eight neighboring pixels is 0, and returns 0 if all eight neighboring pixels are 1. The eight neighboring pixels are the eight pixels located above, below, left, right, and diagonally from the center pixel.

[0037] FIG. 4 is a schematic diagram for explaining an example of contour extraction of a subject region of an optical image in this embodiment. An example of the acquired optical image is shown in the left diagram of Fig. 4. The contour extraction unit 221 distinguishes between the subject and the background in this optical image, extracts the subject area using, for example, semantic segmentation, and performs the above-mentioned filtering process, etc. As a result, the contour of the subject area is extracted, as shown in the right diagram of Fig. 4.

[0038] The method for extracting the contour of a subject in an image is not limited to a method using semantic segmentation processing, and any method such as rule-based processing can be used. For example, the subject area may be extracted by subtracting it from a background image acquired in advance, and the contour line may be extracted by filtering or the like.

[0039] In step S206, the second processing unit 220 determines the image quality of the optical image using the result of the semantic segmentation and the examination information acquired by the examination information management unit 107. In the image quality determination, the intersection determination unit 222 of the second processing unit 220 detects intersections between the contour of the subject area output by the contour extraction unit 221 and each of the top, bottom, left, and right edges of the optical image as protrusions from each edge.

[0040] FIG. 5 is a table for determining whether the image quality of an optical image is appropriate. The intersection determination unit 222 determines whether the presence or absence of overhang at the top, bottom, left, and right ends matches the imaging position included in the examination information, for example, by referring to the table shown in Fig. 5. If the overhang detection result matches the table in Fig. 5, the intersection determination unit 222 determines that the overhang is appropriate, and the second processing unit 220 determines that the image quality of the optical image is sufficient. On the other hand, if the overhang detection result does not match the table in Fig. 5, the intersection determination unit 222 determines that the overhang is inappropriate, and the second processing unit 220 determines that the image quality of the optical image is insufficient.

[0041] For example, if the imaging position included in the examination information acquired by the examination information management unit 107 is "chest, front" and the subject's head protrudes from the optical image, the intersection determination unit 222 uses the contour extraction result to detect protrusion at the upper end of the optical image as shown in Fig. 6. The second processing unit 220 refers to the protrusion table shown in Fig. 5 for the imaging position "chest, front," and if the upper end protrudes, determines that the image quality is "insufficient."

[0042] As another example, when the imaging position is "hand - right hand," the part of the hand ahead of the elbow is generally placed on the radiation detection device 130, and radiation is irradiated perpendicularly from the back of the hand, as shown in the right diagram of Fig. 7. In this example, if only one of the top, bottom, left, or right edges of the optical image, for example only the top edge as shown in the left diagram of Fig. 7, extends beyond the optical image, the second processing unit 220 determines that the imaging position matches, since only the top edge of the outline intersects (extends beyond) in the right diagram of Fig. 7.

[0043] In S207, the image display control unit 104 controls the image quality judgment result by the second processing unit 220, for example by superimposing a message that the image quality of the optical image is sufficient or that the image quality of the optical image is insufficient on the display content, and displays it on the display unit 150.

[0044] In step S208, if the result of the image quality determination in S206 is determined to be "sufficient image quality," the image quality determination process for the optical image is terminated. On the other hand, in step S208, if the result of the image quality determination in S206 is determined to be "insufficient image quality," the process returns to the optical image acquisition step S203 again.

[0045] According to this embodiment, when performing radiography of a subject, an information processing device is realized that can improve the accuracy of determining the radiography mode when determining the appropriateness of the radiography mode from an optical image of the subject, and can reduce the possibility of unnecessary exposure to radiation due to an incorrect radiography mode.

[0046] -Variations- Various modifications of the first embodiment will be described below.

[0047] [Variation 1] In the first modification, in the image quality judgment, in addition to the protrusion judgment of the subject area described in the first embodiment, it is also judged whether or not the subject area is in focus in the optical image.

[0048] In Modification 1, as in the first embodiment, image quality determination processing is performed by executing S201 to S208 in FIG. 2 described above. Here, in S205 in FIG. 2, there are cases where the contour of the subject region in the optical image cannot be extracted. Specifically, there are cases where a contour line such as that shown in FIG. 3 cannot be obtained during filtering. In Modification 1, if the contour of the subject region cannot be extracted, the second processing unit 220 executes the following processing, for example, prior to the image quality determination based on the presence or absence of overflow in the first embodiment. That is, in this case, in S206, the second processing unit 220 determines that the subject region is out of focus (out of focus: so-called defocus) and determines that "image quality is insufficient." In S207, the image display control unit 104 performs control to, for example, superimpose on the display content a message that the image quality of the optical image is insufficient and a message that the reason is out of focus, and displays this on the display unit 150.

[0049] According to Modification 1, when performing radiation imaging of a subject, in determining whether the radiation imaging mode is appropriate from an optical image of the subject, the accuracy of determining the radiation imaging mode of the subject can be improved, and the possibility of unnecessary exposure to radiation due to an incorrect radiation imaging mode can be reduced. This prevents imaging errors and increases the variety of reasons why the image quality of an optical image is insufficient, thereby making the workflow more efficient.

[0050] [Variation 2] In the second modification, when extracting the subject area described in the first embodiment in the image quality judgment, consideration is given to the case where an unnecessary subject area such as an image of another person is recognized in addition to the subject area of ​​the subject.

[0051] In the second modification, as in the first embodiment, the image quality determination process is performed by executing S201 to S208 in FIG. 2 described above. Here, in S205 in FIG. 2, there may be a case where not one but multiple contours of the subject region in the optical image are extracted. For example, as shown in FIG. 8, a contour 801 of the entire image of the subject (subject) and a contour 802 of another person's arm may be extracted in the optical image. In the second modification, for example, if multiple contours are extracted, the second processing unit 220 determines in S206 that there are multiple contours of the subject region and determines that "the image quality is insufficient." In S207, the image display control unit 104 performs control to, for example, superimpose on the display content a message that the image quality of the optical image is insufficient and, as the reason, a message that multiple subjects appear in the optical image, and displays this on the display unit 150.

[0052] According to Modification 2, when performing radiation imaging of a subject, in determining whether the radiation imaging mode is appropriate from an optical image of the subject, the accuracy of determining the radiation imaging mode of the subject can be improved, and the possibility of unnecessary exposure to radiation due to an incorrect radiation imaging mode can be reduced. This prevents imaging errors and increases the variety of reasons why the image quality of an optical image is insufficient, thereby making the workflow more efficient.

[0053] [Variation 3] In the third modification, in the image quality judgment, it is judged whether the brightness of the optical image, and the brightness, hue, and saturation of the subject area in the optical image are appropriate.

[0054] FIG. 9 is a schematic diagram showing a radiation imaging system including an information processing device 100 according to a third modification of the first embodiment. In the third modification, the second processing unit 220 of the information processing device 100 further includes an HSV (hue, saturation, and brightness) detection unit 231 including a brightness determination unit and a hue and saturation determination unit. The HSV detection unit 231 applies known HSV decomposition to the optical image to detect brightness in the optical image and calculate the proportion of brightness below a predetermined threshold. For hue and saturation, it determines whether the hue of the subject area in the optical image is within a predetermined area (first area) or whether the saturation of the subject area is within a predetermined area (second area). The hue and saturation are mainly determined in relation to the subject's clothing.

[0055] FIG. 10 is a flowchart showing the image quality determination process by the second processing unit 220 of the information processing device 100 according to the third modification of the first embodiment. In the third modification, similarly to FIG. 2 of the first embodiment, steps S201 to S208 of FIG. 10 are executed to perform the image quality determination process. Here, in S1001, in parallel with S205 of FIG. 10 (or by executing each step in order), the HSV detection unit 231 performs HSV decomposition of the optical image to detect the hue, saturation, and brightness. That is, as described above, the HSV detection unit 231 calculates the percentage of brightness in the optical image that is below a predetermined threshold. In S206, in parallel with the image quality determination based on the presence or absence of overflow in the first embodiment, if the calculated percentage is lower than a predetermined value, the second processing unit 220 determines that the brightness of the optical image is sufficient and that the image quality is "sufficient." If the calculated percentage is equal to or greater than a predetermined value, the second processing unit 220 determines that the brightness of the optical image is insufficient and that the image quality is "insufficient." In S207, the image display control unit 104 controls the display content to, for example, superimpose a message indicating that the image quality of the optical image is sufficient or insufficient, and that the brightness of the optical image is sufficient or insufficient as the reason for this, and displays this on the display unit 150.

[0056] In S206, the HSV detection unit 231 determines whether the hue of the subject area in the optical image is within the first area. If the hue is within the first area, the hue is appropriate, and the second processing unit 220 determines that the image quality is sufficient. On the other hand, if the hue is not within the first area, the hue is inappropriate, and the second processing unit 220 determines that the image quality is insufficient. In S207, the image display control unit 104 performs control to superimpose on the display content a message that the image quality of the optical image is sufficient or insufficient, and a message that the hue of the optical image is appropriate or inappropriate as the reason for this, and displays this on the display unit 150.

[0057] In S206, the HSV detection unit 231 determines whether the saturation of the subject area in the optical image is within the second region. If the saturation is within the second region, the saturation is appropriate, and the second processing unit 220 determines that the image quality is sufficient. On the other hand, if the saturation is not within the second region, the saturation is inappropriate, and the second processing unit 220 determines that the image quality is insufficient. In S207, the image display control unit 104 performs control to superimpose on the display content a message that the image quality of the optical image is sufficient or insufficient, and a message that the saturation of the optical image is appropriate or inappropriate as the reason, and displays this on the display unit 150.

[0058] According to Modification 3, when performing radiation imaging of a subject, in determining whether the radiation imaging mode is appropriate from an optical image of the subject, the accuracy of determining the radiation imaging mode of the subject can be improved, and the possibility of unnecessary exposure to radiation due to an incorrect radiation imaging mode can be reduced. This prevents imaging errors and increases the variety of reasons why the image quality of an optical image is insufficient, thereby making the workflow more efficient.

[0059] -Second embodiment- The second embodiment will be described below. This embodiment differs from the first embodiment in that the method for determining whether or not the subject area in the optical image is protruding is different.

[0060] FIG. 11 is a schematic diagram showing a radiation imaging system including an information processing apparatus 100 according to the second embodiment. In this embodiment, the second processing device 220 of the information processing device 100 in the first embodiment includes a coordinate detection unit 241 instead of the contour extraction unit 221. Unlike the contour extraction unit 221, the coordinate detection unit 241 does not extract the contour of the entire subject area, but instead determines whether the coordinates at the edge of the subject area in the optical image match the coordinates at the periphery of the optical image. If the subject area in the optical image extends beyond the top, bottom, left, or right edges, the coordinates of the subject area at the top, bottom, left, or right edges of the optical image will match the coordinates at the periphery of the optical image. For example, as shown in FIG. 12, consider a case in which the subject area 1202 in the optical image 1201 is cut off (extends) at the upper end of the top, bottom, left, or right edges 1203. In this case, a pair of coordinates a1(x1, y1) and a2(x2, y2) at the upper end of the subject area 1202 matches a pair of coordinates a1(x1, y1) and a2(x2, y2) at the upper end of the optical image 1201. If the subject area 1202 does not extend beyond the upper end of the optical image 1201 , the coordinates of (the vertex of) the head in the subject area 1202 will not coincide with the coordinates of the upper end of the optical image 1201 .

[0061] In this embodiment, the intersection determination unit 222 uses the inspection information to determine whether the position on the periphery of the coordinates determined to match by the coordinate detection unit 222 is appropriate. Even if the subject area in the optical image extends beyond the top, bottom, left, or right edge, if it matches the inspection information, the extension is determined to be appropriate. On the other hand, if it does not match the inspection information, the extension is determined to be inappropriate.

[0062] FIG. 13 is a flowchart showing the image quality determination process by the second processing unit 220 of the information processing device 100 according to the second embodiment. In this embodiment, image quality determination processing is performed by executing steps S201 to S208. Here, steps S201 to S204 and S206 to S208 are the same as those in the first embodiment.

[0063] In S1301, the coordinate detection unit 241 determines whether a pair of coordinates at an edge of a subject area in an optical image matches coordinates on the periphery of the optical image, i.e., whether such coordinates exist. For a subject area in an optical image, the fact that the coordinates at the edge match coordinates on the periphery of the optical image is synonymous with the subject area intersecting at the edge.

[0064] If it is determined that the coordinates at the edge of the subject area match the coordinates at the periphery of the optical image, the following process is executed. That is, in S206, the intersection determination unit 222 refers to the protrusion pattern table shown in FIG. 5, for example, to determine whether the presence or absence of protrusion at the top, bottom, left, and right edges matches the photographing position included in the examination information. If the protrusion detection result matches the table in FIG. 5, the protrusion is appropriate, and the second processing unit 220 determines that the image quality of the optical image is sufficient. On the other hand, if the protrusion detection result does not match (mismatch) the table in FIG. 5, the protrusion is inappropriate, and the second processing unit 220 determines that the image quality of the optical image is insufficient.

[0065] For example, if the imaging position included in the examination information acquired by the examination information management unit 107 is "chest, front" and the subject's head protrudes from the optical image, the intersection determination unit 222 uses the contour extraction result to detect protrusion at the upper end of the optical image as shown in Fig. 6. The second processing unit 220 refers to the protrusion table shown in Fig. 5 for the imaging position "chest, front," and if the upper end protrudes, determines that the image quality is "insufficient." Thereafter, steps S207 and S208 are executed in the same manner as in the first embodiment.

[0066] According to this embodiment, when performing radiography on a subject, an information processing device is realized that can improve the accuracy of determining the radiography mode when determining the appropriateness of the radiography mode from an optical image of the subject, and can reduce the possibility of unnecessary exposure to radiation due to an incorrect radiography position.

[0067] In addition, one or more functions selected from the functions of Modification Example 1, the functions of Modification Example 2, the functions of Modification Example 3 (HSV detection unit 231), and the functions of the second embodiment (coordinate detection unit 241 and intersection determination unit 222) may be added to the information processing device 100 according to the first embodiment as appropriate.

[0068] -Other embodiments- In the above-described embodiment and modified examples, a computer program for controlling the information processing device 110 is stored in a storage medium such as a ROM or an HDD or SSD. This computer program is a program for realizing the functions of each component of the information processing device 100, such as the radiation image acquisition unit 101, the image processing unit 102, the optical image acquisition unit 103, the image display control unit 104, the first processing unit 210, the second processing unit 220, and the examination information management unit 107, and is, for example, a program corresponding to steps S201 to S208 in Fig. 2, S1001 in Fig. 10, S1301 in Fig. 13, etc. The information processing device 100 includes, for example, a CPU, which reads out and executes the computer program from the ROM or the storage medium.

[0069] The disclosure of the various embodiments includes the following configurations and methods. (Configuration 1) a radiation image acquisition means for acquiring a radiation image of a subject; an optical image acquisition means for acquiring an optical image of the subject; a first processing means for analyzing the optical image and determining whether the radiographic aspect of the subject in the optical image is appropriate; a second processing means for determining whether the optical image input to the first processing means has image quality that can be subjected to analysis by the first processing means; Equipped with Information processing device. (Configuration 2) The second processing means a contour extraction unit that extracts a contour of the subject in the optical image; an intersection determination unit that determines whether or not an intersection point between the contour extracted by the contour extraction unit and a periphery of the optical image is appropriate, using examination information of the subject; Equipped with 2. The information processing device according to configuration 1. (Configuration 3) the contour extraction unit uses a subject region of the subject extracted using semantic segmentation; 3. The information processing device according to configuration 1 or 2. (Configuration 4) The second processing means determining that the optical image does not have the image quality when the contour extraction unit extracts multiple contours; 4. The information processing device according to configuration 2 or 3. (Configuration 5) The second processing means If the contour extraction unit cannot extract the contour, it is determined that the optical image is out of focus and does not have the image quality. 5. The information processing device according to any one of configurations 2 to 4. (Configuration 6) The second processing means The image processing device further includes a brightness determination unit that determines that the optical image does not have the image quality when the brightness of the optical image is below a threshold value. 6. The information processing device according to any one of configurations 2 to 5. (Configuration 7) The second processing means a hue / saturation determining unit that determines that the optical image does not have the image quality when the hue of the optical image is not within a first region and when the saturation of the optical image is not within a second region, 7. The information processing device according to any one of configurations 2 to 6. (Configuration 8) The second processing means a coordinate detection unit that determines whether or not coordinates at an end of a subject region of the subject in the optical image match coordinates at a periphery of the optical image; an intersection determination unit that determines whether or not a position on the periphery of the coordinates determined to match by the coordinate detection unit is appropriate, using the examination information of the subject; Equipped with the intersection determination unit determines that the image does not have the image quality when the position of the coordinates on the periphery determined by the coordinate detection unit to match does not match the inspection information; 2. The information processing device according to configuration 1. (Configuration 9) The second processing means uses the examination information of the subject to determine whether the optical image has image quality that can be subjected to analysis by the first processing means. 9. The information processing device according to any one of configurations 1 to 8. (Configuration 10) the first processing means determines whether or not the radiographic aspect of the subject in the optical image matches examination information of the subject; 10. The information processing device according to any one of configurations 1 to 9. (Configuration 11) further comprising a test information management unit that manages test information of the subject; the first processing means and the second processing means acquire the test information from the test information management unit; 11. The information processing device according to any one of configurations 1 to 10. (Configuration 12) an image display control unit that controls the display of the radiation image and the optical image; 12. The information processing device according to any one of configurations 1 to 11. (Configuration 13) a radiation detection device for detecting radiation; The information processing device according to any one of configurations 1 to 12, which is communicably connected to the radiation detection device; Equipped with Radiography system. (Method 1) a first step of acquiring a radiological image of a subject; a second step of acquiring an optical image of the object; a third step of analyzing the optical image to determine whether the radiographic aspect of the subject in the optical image is appropriate; a fourth step of determining whether the optical image input in the third step has image quality that can be subjected to analysis in the third step; Equipped with Information processing methods. (Configuration 14) A program for causing a computer to execute each step of method 1. [Explanation of symbols]

[0070] 100: Information processing device 101: Radiation image acquisition unit 102: Image processing unit 103: Optical image acquisition unit 104: Image display control unit 105: Optical image analysis department 106: Inference processing unit 107: Test Information Management Department 108: Image storage unit 109: Contour extraction unit 120: Radiation generator 130: Radiation detection device 140: Optical photographing device 150: Display section 160:Operation unit 210: First processing unit 211: Image analysis unit 212: Image judgment unit 213: Inference processing unit 220: Second processing section 221: Contour extraction unit 222: Intersection detection unit 231: HSV detection unit 241: Coordinate detection unit

Claims

1. a radiation image acquisition means for acquiring a radiation image of a subject; an optical image acquisition means for acquiring an optical image of the subject; a first processing means for analyzing the optical image and determining whether the radiographic aspect of the subject in the optical image is appropriate; a second processing means for determining whether the optical image input to the first processing means has image quality that can be subjected to analysis by the first processing means; Equipped with Information processing device.

2. The second processing means a contour extraction unit that extracts a contour of the subject in the optical image; an intersection determination unit that determines whether or not an intersection point between the contour extracted by the contour extraction unit and a periphery of the optical image is appropriate, using examination information of the subject; Equipped with The information processing device according to claim 1 .

3. the contour extraction unit uses a subject region of the subject extracted using semantic segmentation; The information processing device according to claim 2 .

4. The second processing means determining that the optical image does not have the image quality when the contour extraction unit extracts multiple contours; The information processing device according to claim 2 .

5. The second processing means If the contour extraction unit cannot extract the contour, it is determined that the optical image is out of focus and does not have the image quality. The information processing device according to claim 2 .

6. The second processing means The image processing device further includes a brightness determination unit that determines that the optical image does not have the image quality when the brightness of the optical image is below a threshold value. The information processing device according to claim 1 .

7. The second processing means a hue / saturation determining unit that determines that the optical image does not have the image quality when the hue of the optical image is not within a first region and when the saturation of the optical image is not within a second region, The information processing device according to claim 1 .

8. The second processing means a coordinate detection unit that determines whether or not coordinates at an end of a subject region of the subject in the optical image match coordinates at a periphery of the optical image; an intersection determination unit that determines whether or not a position on the periphery of the coordinates determined to match by the coordinate detection unit is appropriate, using the examination information of the subject; Equipped with the intersection determination unit determines that the image does not have the image quality when the position of the coordinates on the periphery determined by the coordinate detection unit to match does not match the inspection information; The information processing device according to claim 1 .

9. the second processing means uses the examination information of the subject to determine whether the optical image has image quality that can be subjected to analysis by the first processing means; The information processing device according to claim 1 .

10. the first processing means determines whether or not the radiographic aspect of the subject in the optical image matches examination information of the subject; The information processing device according to claim 1 .

11. further comprising a test information management unit that manages test information of the subject; the first processing means and the second processing means acquire the test information from the test information management unit; The information processing device according to claim 1 .

12. an image display control unit that controls the display of the radiation image and the optical image; The information processing device according to claim 1 .

13. a radiation detection device for detecting radiation; an information processing device according to any one of claims 1 to 12, which is communicably connected to the radiation detection device; Equipped with Radiography system.

14. a first step of acquiring a radiological image of a subject; a second step of acquiring an optical image of the object; a third step of analyzing the optical image to determine whether the radiographic aspect of the subject in the optical image is appropriate; a fourth step of determining whether the optical image input in the third step has image quality that can be subjected to analysis in the third step; Equipped with Information processing methods.

15. A program for causing a computer to execute the steps recited in claim 14.

Images