Information processing apparatus, method, and program product

Abstract

The invention provides an information processing device, method, and program product capable of appropriately detecting feature points when setting an imaging range. The processor acquires at least one of a first camera image generated by capturing a moving image of a subject on a bed by a first camera and a second camera image generated by capturing a moving image of the subject by a second camera having a higher photographing sensitivity than the first camera; selecting at least one detection model from a plurality of detection models including a first detection model configured to detect a plurality of feature points on the subject included in the first camera image and a second detection model configured to detect a plurality of feature points on the subject included in the second camera image; detecting a plurality of feature points on the subject included in the first camera image or the second camera image by means of the selected detection model; and determining the photographing range of the subject according to the plurality of feature points.

Description

Technical Field

[0001] The present invention relates to an information processing device, method and program. Background Art

[0002] In recent years, due to the development of medical equipment such as CT (Computed Tomography) devices and MRI (Magnetic Resonance Imaging) devices, higher-quality high-resolution three-dimensional images are used in image diagnosis.

[0003] In imaging devices such as CT devices and MRI devices, when imaging a subject, positioning imaging is performed before the actual imaging to obtain a three-dimensional image in order to determine the imaging range, thereby obtaining a two-dimensional positioning image (positioning image). The operator of the imaging device (engineer, etc.) sets the imaging range during the actual imaging while observing the positioning image.

[0004] Before positioning photography, the operator sets the photography range of the positioning photography of the subject on the diagnostic bed. For example, a cross-shaped laser is irradiated to the subject, the scanning start position of the positioning photography is set, and the scanning end position of the positioning photography is set to become a photography range corresponding to the photography part. During positioning photography, if the diagnostic bed moves from the initial position of the diagnostic bed to the scanning start position, the scanning of the positioning photography starts, and if the diagnostic bed moves to the scanning end position, the scanning of the positioning photography ends. After the operator sets the photography range of the formal photography according to the positioning image obtained by the positioning photography, the formal photography is performed to obtain a three-dimensional image.

[0005] Here, when setting the photography range for positioning photography, the camera installed above the examination bed photographs the subject, detects the subject's ankles, waist, elbows, shoulders and other feature points, and determines the photography range based on the detected feature points. At this time, the detection of feature points uses a learned detection model constructed by a machine learning neural network.

[0006] On the other hand, a method has been proposed for efficiently processing medical images by preparing a plurality of learned models for performing different processing and selecting which learned model to use according to the situation when applying a learned model to medical images (for example, refer to Patent Document 1).

[0007] Patent Document 1: Japanese Patent Application Publication No. 2021-079013

[0008] The imaging device is installed in the inspection room, but if the brightness of the inspection room is insufficient, the image acquired by the camera will have more noise, so it is impossible to detect the feature points with high accuracy. If the feature points cannot be detected with high accuracy, the imaging range cannot be determined with high accuracy. Summary of the invention

[0009] The present invention has been made in view of the above circumstances, and an object of the present invention is to enable appropriate detection of feature points according to the brightness of an inspection room when setting an imaging range.

[0010] The information processing device according to the present invention comprises at least one processor.

[0011] The processor performs the following processing:

[0012] acquiring at least one of a first camera image generated by performing dynamic image photography of a subject on a diagnostic couch with a first camera and a second camera image generated by performing dynamic image photography of the subject with a second camera having a higher photography sensitivity than the first camera;

[0013] selecting at least one detection model from a plurality of detection models including a first detection model and a second detection model, wherein the first detection model is constructed to detect a plurality of feature points on the subject included in the first camera image, and the second detection model is constructed to detect a plurality of feature points on the subject included in the second camera image;

[0014] Using the selected detection model to detect a plurality of feature points on the subject included in the first camera image or the second camera image; and

[0015] The imaging range of the subject is determined based on the plurality of feature points.

[0016] “High photographic sensitivity” means that the photographic performance in dark places is high. Therefore, as the second camera, for example, a camera having a higher ISO sensitivity than the NIR camera, the night vision camera, or the first camera is used.

[0017] In addition, in the information processing device based on the present invention, the processor may also perform the following processing: when the brightness of the environment in which the diagnostic bed is set is above the benchmark, the first detection model is selected to detect multiple feature points on the subject contained in the first camera image; when the brightness is less than the benchmark, the second detection model is selected to detect multiple feature points on the subject contained in the second camera image.

[0018] Furthermore, in the information processing device according to the present invention, the processor may acquire the first camera image and determine the brightness based on brightness information derived from the first camera image.

[0019] Furthermore, in the information processing device according to the present invention, the processor may acquire the first camera image and determine the brightness based on noise included in the first camera image.

[0020] Furthermore, in the information processing device based on the present invention, the processor may also perform the following processing: acquiring the first camera image, detecting feature points from the first camera image using the first detection model, and determining the brightness based on the detection accuracy of the feature points.

[0021] Furthermore, in the information processing device according to the present invention, the processor may determine the brightness using a sensor that detects the brightness of the environment.

[0022] Furthermore, in the information processing device based on the present invention, the processor can perform the following processing: acquire the first camera image, select the first detection model and detect feature points from the first camera image, determine whether the brightness is above the benchmark based on the first camera image, and when the brightness is above the benchmark, determine the photographic range based on the feature points detected using the first detection model; when the brightness is less than the benchmark, select the second detection model and determine the photographic range based on the feature points detected using the second detection model.

[0023] Furthermore, in the information processing device according to the present invention, the first detection model and the second detection model are models that focus on the frame rate when detecting feature points.

[0024] The plurality of detection models further include: a third detection model constructed to detect a plurality of feature points on the subject included in the first camera image, and focusing on the accuracy when detecting the feature points; and a fourth detection model constructed to detect a plurality of feature points on the subject included in the second camera image, and focusing on the accuracy when detecting the feature points.

[0025] The processor may select a detection model according to the brightness of the environment in which the diagnostic bed is set and the imaging part of the subject.

[0026] Furthermore, in the information processing device based on the present invention, the processor can perform the following processing: when the brightness is above the benchmark, select any one of the first detection model and the third detection model to detect multiple feature points on the subject contained in the first camera image; when the brightness is less than the benchmark, select any one of the second detection model and the fourth detection model to detect multiple feature points on the subject contained in the second camera image.

[0027] Furthermore, in the information processing device according to the present invention, the processor may select any one of the first detection model and the third detection model and any one of the second detection model and the fourth detection model according to the imaging part of the subject.

[0028] Furthermore, in the information processing device based on the present invention, the processor can perform the following processing: determine the detection accuracy of the feature points, determine the photographic range based on the feature points when the detection accuracy is above the benchmark, and issue a warning when the detection accuracy is lower than the benchmark.

[0029] Furthermore, in the information processing device according to the present invention, the first detection model is a model that focuses on the frame rate when detecting feature points.

[0030] The plurality of detection models further include a third detection model, wherein the third detection model is constructed to detect a plurality of feature points on the subject included in the first camera image, and focuses on the accuracy of detecting the feature points.

[0031] The processor can perform the following processing:

[0032] Acquire a first camera image and a second camera image, select a first detection model and detect feature points from the first camera image;

[0033] determining the detection accuracy of the feature points detected using the first detection model;

[0034] When the detection accuracy is equal to or higher than the first standard, determining the imaging range based on the feature points detected using the first detection model;

[0035] When the detection accuracy is lower than the first benchmark, a third detection model is selected, and feature points are detected from the first camera image using the third detection model;

[0036] Determining the detection accuracy of the feature points detected using the third detection model; if the detection accuracy is greater than the second standard, determining the photographing range based on the feature points detected using the third detection model;

[0037] When the detection accuracy is lower than the second benchmark, selecting a second detection model, and using the second detection model to detect feature points from the second camera image; and

[0038] The imaging range is determined based on the feature points detected using the second detection model.

[0039] Furthermore, in the information processing device according to the present invention, the processor may perform the following processing:

[0040] Determine the detection accuracy of the feature points detected using the first detection model when the detection accuracy is greater than the first benchmark, the detection accuracy of the feature points detected using the third detection model when the detection accuracy is greater than the second benchmark, or the detection accuracy of the feature points detected using the second detection model,

[0041] determining the photographing range based on feature points detected using the first detection model when the detection accuracy is higher than the third standard and when the detection accuracy is higher than the first standard, feature points detected using the third detection model when the detection accuracy is higher than the second standard, or feature points detected using the second detection model; and

[0042] If the detection accuracy is lower than the third standard, a warning is issued.

[0043] Furthermore, in the information processing device according to the present invention, the first detection model is a model that focuses on the frame rate when detecting feature points.

[0044] The plurality of detection models further include a third detection model, wherein the third detection model is constructed to detect a plurality of feature points on the subject included in the first camera image, and focuses on the accuracy of detecting the feature points.

[0045] The processor can perform the following processing:

[0046] Acquire a first camera image and a second camera image, select a first detection model and detect feature points from the first camera image;

[0047] detecting movement of the subject based on the first camera image;

[0048] When the movement of the subject is equal to or greater than a first reference, determining an imaging range based on feature points detected using a first detection model;

[0049] When the movement of the subject is less than the first criterion, the second detection model and the third detection model are selected;

[0050] Detect feature points from the first camera image using the third detection model;

[0051] detecting feature points from a second camera image using a second detection model;

[0052] comparing the detection accuracy of the feature points detected using the third detection model and the detection accuracy of the feature points detected using the second detection model;

[0053] When the detection accuracy of the feature points detected using the third detection model is higher, determining the imaging range based on the feature points detected using the third detection model; and

[0054] When the detection accuracy of the feature points detected using the second detection model is higher, the imaging range is determined based on the feature points detected using the second detection model.

[0055] Furthermore, in the information processing device according to the present invention, the processor may perform the following processing:

[0056] When the movement is greater than the first reference, determining the detection accuracy of the feature points detected using the first detection model, the detection accuracy of the feature points detected using the third detection model, or the detection accuracy of the feature points detected using the second detection model;

[0057] determining the imaging range based on feature points detected using the first detection model when the detection accuracy is greater than or equal to the second standard and when the movement is greater than or equal to the first standard, feature points detected using the third detection model, or feature points detected using the second detection model; and

[0058] When the detection accuracy is lower than the second standard, a warning is issued.

[0059] Furthermore, in the information processing device according to the present invention, the processor may derive the moving range of the diagnostic bed based on the imaging range.

[0060] Furthermore, in the information processing device according to the present invention, the processor may display a human body image simulating a human body on the display, and draw a movement start line and a movement end line of the diagnostic bed based on the movement range of the diagnostic bed on the human body image.

[0061] Furthermore, in the information processing apparatus according to the present invention, the imaging range may be the imaging range when imaging the positioning image acquired before the actual imaging of the subject.

[0062] In the information processing method according to the present invention, the computer performs the following processing:

[0063] acquiring at least one of a first camera image generated by performing dynamic image photography of a subject on a diagnostic couch with a first camera and a second camera image generated by performing dynamic image photography of the subject with a second camera having a higher photography sensitivity than the first camera;

[0064] selecting at least one detection model from a plurality of detection models including a first detection model and a second detection model, wherein the first detection model is constructed to detect a plurality of feature points on the subject included in the first camera image, and the second detection model is constructed to detect a plurality of feature points on the subject included in the second camera image;

[0065] Using the selected detection model to detect a plurality of feature points on the subject included in the first camera image or the second camera image; and

[0066] The imaging range of the subject is determined based on the plurality of feature points.

[0067] The information processing program according to the present invention enables a computer to execute the following steps:

[0068] acquiring at least one of a first camera image generated by performing dynamic image photography of a subject on a diagnostic couch with a first camera and a second camera image generated by performing dynamic image photography of the subject with a second camera having a higher photography sensitivity than the first camera;

[0069] selecting at least one detection model from a plurality of detection models including a first detection model and a second detection model, wherein the first detection model is constructed to detect a plurality of feature points on the subject included in the first camera image, and the second detection model is constructed to detect a plurality of feature points on the subject included in the second camera image;

[0070] Using the selected detection model to detect a plurality of feature points on the subject included in the first camera image or the second camera image; and

[0071] The imaging range of the subject is determined based on the plurality of feature points.

[0072] Effects of the Invention

[0073] According to the present invention, when setting the imaging range, it is possible to appropriately detect feature points according to the brightness of the inspection room. BRIEF DESCRIPTION OF THE DRAWINGS

[0074] Figure 1 This is a perspective view schematically showing a CT apparatus to which the information processing apparatus according to the first embodiment of the present invention is applied.

[0075] Figure 2 This is a diagram showing a CT apparatus to which the information processing apparatus according to the first embodiment is applied, as seen from the side.

[0076] Figure 3 This is a schematic perspective view showing the appearance of a camera.

[0077] Figure 4 This is a diagram showing a schematic configuration of an information processing device according to the first embodiment.

[0078] Figure 5 This is a diagram showing the functional structure of the information processing device according to the first embodiment.

[0079] Figure 6 It is a diagram for explaining feature points.

[0080] Figure 7 The diagram is a schematic diagram showing a scanning start line and a scanning end line.

[0081] Figure 8 This is a flowchart showing the processing performed in the first embodiment.

[0082] Fig. 9 This is a flowchart showing the processing performed in the second embodiment.

[0083] Fig.10 This is a diagram showing the functional structure of an information processing device according to the third embodiment.

[0084] Fig.11This is a flowchart showing the processing performed in the third embodiment.

[0085] Fig.12 This is a flowchart showing the processing performed in the fourth embodiment.

[0086] Fig.13 This is a flowchart showing the processing performed in the fourth embodiment.

[0087] Fig.14 This is a diagram showing the functional structure of an information processing device based on the fifth embodiment.

[0088] Fig.15 This is a flowchart showing the processing performed in the fifth embodiment.

[0089] Fig.16 This is a flowchart showing the processing performed in the fifth embodiment.

[0090] Explanation of symbols

[0091] 1-CT device, 2-gantry, 3-diagnostic bed, 3A-diagnostic bed part, 3B-base, 3C-driving part, 4-console, 5-opening part, 7-camera, 10, 10A, 10B-information processing device, 11-CPU, 12-information processing program, 13-storage device, 14-display, 15-input device, 16-memory, 17-network I / F, 18-bus, 20-photography control part, 21-camera control part, 22-selection part , 22A-1st detection model, 22B-2nd detection model, 22C-3rd detection model, 22D-4th detection model, 23-feature point detection unit, 24-photographic range determination unit, 25-motion detection unit, 31-RGB camera, 32-RGB sensor, 33-base, 35-NIR camera, 36, 37-NIR sensor, 38-NIR projector, 40-schematic diagram, 41-starting line, 42-ending line, H-subject. DETAILED DESCRIPTION

[0092] Hereinafter, embodiments of the present invention will be described with reference to the drawings. Figure 1 is a perspective view showing an overview of a CT apparatus to which an information processing apparatus according to a first embodiment of the present invention is applied, Figure 2 This is a side view of a CT apparatus to which the information processing apparatus according to the first embodiment of the present invention is applied. Figure 1 and Figure 2 As shown, the CT apparatus 1 according to the present embodiment includes a gantry 2 , a diagnostic bed 3 , and a console 4 .

[0093] The gantry 2 has a tunnel-like structure with an opening 5 at the center thereof. A radiation source unit that radiates X-rays and a detection unit that detects X-rays and generates a radiographic image (neither of which is shown in the figure) are provided inside the gantry 2. The radiation source unit and the detection unit are respectively capable of rotating along the annular shape of the gantry 2 while maintaining a mutually opposing positional relationship. Furthermore, a control unit that controls the operation of the CT apparatus 1 is provided inside the gantry 2.

[0094] The diagnostic bed 3 includes a diagnostic bed portion 3A on which a patient lies, a base portion 3B supporting the diagnostic bed portion 3A, and a driving portion 3C for reciprocating the diagnostic bed portion 3A in the direction of arrow A. The diagnostic bed portion 3A can slide relative to the base portion 3B in the direction of arrow A by the driving portion 3C. When taking a CT image, the diagnostic bed portion 3A slides, whereby the patient H lying on the diagnostic bed portion 3A is transported into the opening portion 5 of the gantry 2.

[0095] Moreover, a camera 7 is provided above the diagnostic bed 3. The camera 7 is composed of an integrated RGB camera capable of capturing RGB color images by detecting reflected light from the subject H and a NIR (Near InfraRed) camera capable of stereoscopic photography. Figure 3 7 is a schematic three-dimensional diagram showing the appearance of the camera 7. Figure 3 As shown, the camera 7 is composed of an RGB camera 31 and a NIR camera 35 mounted on a base 33. The RGB camera 31 has an RGB sensor 32 including a lens and an imaging element such as a CCD (Charge Coupled Device). The RGB camera 31 captures the subject H on the diagnostic bed 3 at a predetermined frame rate, thereby acquiring an RGB color dynamic image, i.e., an RGB camera image, and outputs it to the console 4.

[0096] The NIR camera 35 includes a left NIR sensor 36 and a right NIR sensor 37 including imaging elements such as lenses and CCDs, and a NIR projector 38. The NIR camera 35 irradiates near-infrared rays from the NIR projector 38 toward the subject H, and detects the reflected light of the near-infrared rays of the subject H at a predetermined frame rate through the left and right NIR sensors 36 and 37. Thus, the NIR camera 35 obtains left and right NIR camera images and outputs them to the console 4. In addition, the left and right NIR camera images are monochrome images. Here, the left NIR sensor 36 is separated from the right NIR sensor 37, so the left and right NIR camera images have parallax. Therefore, the camera 7 derives the depth information of the subject H and other objects contained in the left and right NIR camera images based on the parallax, and outputs the depth information together with the left and right NIR camera images. In addition, in the following description, when referred to as NIR camera images, any one of the left and right NIR camera images is represented.

[0097] The NIR camera 35 performs imaging based on near infrared rays, and therefore, even if the imaging room where the CT device 1 is installed is dark, it is possible to obtain an NIR camera image that allows visual identification of the subject H. On the other hand, the RGB camera 31 performs imaging based on visible light, and therefore, if the ambient brightness is insufficient, it is difficult to visually identify the subject H in the acquired RGB camera image. Therefore, in order to obtain an RGB camera image that allows visual identification of the subject H, the imaging room needs to be bright to a certain extent. The RGB camera 31 is an example of the first camera of the present invention. The NIR camera 35 is an example of the second camera of the present invention having a higher imaging sensitivity than the first camera. The RGB camera image is an example of the first camera image of the present invention, and the NIR camera image is an example of the second camera image of the present invention.

[0098] In addition, in the present embodiment, the camera 7 is configured to simultaneously acquire an RGB camera image by the RGB camera 31 and an NIR camera image by the NIR camera 35 .

[0099] The gantry 2 is driven, the bed 3 is driven, and the camera 7 captures the image of the subject H through input from the operator of the console 4. The console 4 includes the information processing device according to the first embodiment.

[0100] Next, the information processing device according to the first embodiment included in the console 4 will be described. Figure 4 , the hardware structure of the information processing device involved in the first embodiment is described. Figure 4 As shown, the information processing device 10 is a computer such as a workstation, a server computer, and a personal computer, and includes a CPU (Central Processing Unit) 11, a non-volatile storage device 13, and a memory 16 as a temporary storage area. In addition, the information processing device 10 includes a display 14 such as a liquid crystal display, an input device 15 such as a keyboard and a mouse, and an interface such as a network I / F (InterFace: interface) 17 connected to the CT device 1. The CPU 11, the storage device 13, the display 14, the input device 15, the memory 16, and the network I / F 17 are connected to a bus 18. In addition, the CPU 11 is an example of a processor in the present invention. The display 14 and the input device 15 are also shown in the figure. Figure 1 and Figure 2 middle.

[0101] The storage device 13 is implemented by a HDD (Hard Disk Drive), an SSD (Solid State Drive), a flash memory, etc. The storage device 13 as a storage medium stores an information processing program 12 installed in the information processing apparatus 10. The CPU 11 reads the information processing program 12 from the storage device 13, expands it into the memory 16, and executes the expanded information processing program 12.

[0102] The information processing program 12 is stored in a storage device or network storage of a server computer connected to a network in a state that can be accessed from the outside, and is downloaded and installed in the computer constituting the information processing device 10 as needed. Alternatively, the information processing program 12 is distributed by being recorded in a recording medium such as a DVD (Digital Versatile Disc) or a CD-ROM (Compact Disc Read Only Memory), and is installed in the computer constituting the information processing device 10 from the recording medium.

[0103] Next, the functional configuration of the information processing device according to the first embodiment will be described. Figure 5 1 is a diagram showing the functional structure of the information processing device involved in the first embodiment. Figure 5 As shown, the information processing device 10 includes a photographing control unit 20, a camera control unit 21, a selection unit 22, a feature point detection unit 23, and a photographing range determination unit 24. Furthermore, when the CPU 11 executes the information processing program 12, the CPU 11 functions as the photographing control unit 20, the camera control unit 21, the selection unit 22, the feature point detection unit 23, and the photographing range determination unit 24.

[0104] The imaging control unit 20 controls the imaging unit, the detection unit, and the control unit provided on the gantry 2 according to the command from the input device 15 to perform imaging of the subject H. In addition, when performing CT imaging, in order to determine the imaging range, positioning imaging is performed before performing the actual imaging for acquiring a three-dimensional CT image. The positioning imaging is performed by imaging the subject H with the imaging unit and the detection unit fixed.

[0105] During positioning photography, the photography range of the subject H is set as described later, and the diagnostic bed 3 is moved to the opening 5 of the gantry 2 in a manner to shoot the set photography range to perform positioning photography. The positioning image obtained by positioning photography is a two-dimensional X-ray image included in the photography range set for the subject H. The positioning image is displayed on the display 14. The operator observes the positioning image displayed on the display 14 and sets the photography range for formal photography. After setting the photography range, the operator issues a formal photography command from the input device 15, thereby performing formal photography and acquiring a three-dimensional CT image of the subject H. The acquired positioning image and CT image are stored in the storage device 13.

[0106] The camera control unit 21 controls the photography of the subject H on the diagnostic bed 3 based on the camera 7. The photography of the subject H based on the camera 7 is performed in order to set the photography range when performing positioning photography. The photography of the subject H based on the camera 7 starts from the preparation stage before photography. That is, the camera control unit 21 starts the photography based on the camera 7 from the moment before the subject H lies supine on the diagnostic bed 3, so that the camera 7 acquires a camera image. In addition, if the operator issues a command to start positioning photography, the camera control unit 21 stops the photography based on the camera 7. In order to determine the photography range described later, the acquired camera image is stored in the memory 16. In the following description, the RGB camera image and the NIR camera image are sometimes referred to as camera images.

[0107] In the first embodiment, the selection unit 22 selects one detection model from the first detection model 22A and the second detection model 22B, wherein the first detection model 22A is constructed to detect multiple feature points on the subject H included in the RGB camera image acquired by the detection camera 7, and the second detection model 22B is constructed to detect multiple feature points on the subject H included in the NIR camera image. The first detection model 22A and the second detection model 22B are constructed by machine learning neural networks.

[0108] The first detection model 22A is a model for detecting feature points from RGB camera images, so a model constructed to detect feature points from color images is used. The second detection model 22B is a model for detecting feature points from NIR camera images, so a model constructed to detect feature points from monochrome images is used.

[0109] In the learning of the first detection model 22A, a color image containing the whole body of a human body and having 17 known feature points is used as a teacher image. Specifically, an RGB camera image acquired by the RGB camera 31 is used. In the learning of the second detection model 22B, a monochrome image containing the whole body of a human body and having 17 known feature points is used as a teacher image. In practice, an NIR camera image of either the left or right side acquired by the NIR camera 35 is used as a teacher image. In addition, similarly to the case of an actual inspection, a teacher image is acquired by, for example, photographing a person wearing an inspection suit by the camera 7.

[0110] In addition, a neural network having the same structure may be used in the first detection model 22A and the second detection model 22B, or a neural network having a structure suitable for detecting feature points from an RGB camera image and an NIR camera image, respectively, may be used.

[0111] In the first embodiment, the selection unit 22 selects any one of the first detection model 22A and the second detection model 22B according to the brightness of the radiography room where the diagnostic bed 3 is installed. The brightness can also be determined based on the brightness information derived from the RGB camera image, for example. In this case, the selection unit 22 can also be set to derive the brightness in each pixel of the RGB camera image, and derive the average value of the brightness in all pixels of the RGB camera image as the brightness information, and determine it to be bright when the brightness information is above the threshold, and determine it to be dark when the brightness information is less than the threshold. In addition, the brightness of each pixel can be derived according to the following formula (1) based on the respective signal values ​​of R, G, and B of each pixel. In formula (1), Y is the brightness.

[0112] Y=0.299×R+0.587×G+0.114×B (1)

[0113] On the other hand, when the brightness is insufficient, the RGB camera image will contain more noise. Therefore, the selection unit 22 can also be set to derive the noise characteristics of the RGB camera image and determine the brightness based on the noise characteristics. As a noise characteristic, the standard deviation of the pixel value of each pixel of the RGB camera image can be used. Regarding the standard deviation, it is sufficient to calculate it using the RMS (root mean square) of the pixel value of each pixel of the RGB camera image. In this case, the selection unit 22 calculates the square average value N of the pixel value of each pixel of the RGB camera image. 2 m, by taking the average value N 2 m square root (i.e., √N 2m). If the standard deviation is greater than a predetermined threshold, the selection unit 22 determines that it is dark, and if the standard deviation is less than the threshold, the selection unit 22 determines that it is bright. In addition, the variance of the pixel value of the RGB camera image or the difference between the maximum value and the minimum value can be calculated instead of the standard deviation as the noise characteristic.

[0114] Furthermore, a brightness sensor for detecting brightness near the diagnostic bed 3 may be provided in the CT apparatus 1 or the radiography room, and the brightness may be determined based on the output of the brightness sensor. In this case, if the detection value of the brightness sensor is greater than a predetermined threshold, the selection unit 22 determines that it is bright, and if the detection value of the brightness sensor is less than the threshold, the selection unit 22 determines that it is dark.

[0115] The feature point detection unit 23 detects feature points from the camera image using the detection model selected by the selection unit 22 . Figure 6 is a diagram used to illustrate feature points. Figure 6 As shown, in this embodiment, the first detection model 22A and the second detection model 22B are constructed to detect 17 feature points on the subject H contained in the camera image. The 17 feature points are eyes, nose, ears, shoulders, elbows, hands, waist, knees and feet. In addition, it can also be set that the point in the middle of the clavicle is added to these 17 feature points, and a total of 18 feature points are used.

[0116] The first detection model 22A and the second detection model 22B derive the probability of each possibility of 17 feature points in each pixel of the camera image. Moreover, for each of the 17 feature points, the feature point detection unit 23 detects the pixel with the highest derived probability as the feature point. For example, in the case of detecting the right eye as a feature point, the feature point detection unit 23 compares the probability of being the right eye for all pixels of the camera image derived by the first detection model 22A and the second detection model 22B, and detects the pixel with the highest probability as the feature point of the right eye.

[0117] The photographic range determination unit 24 determines the photographic range of the subject H when performing positioning photography based on the 17 feature points detected by the feature point detection unit 23. Therefore, the photographic range determination unit 24 first determines the detection accuracy of the feature points detected by the feature point detection unit 23. As described above, for each of the 17 feature points, the feature point detection unit 23 detects and derives the pixel with the highest probability as the feature point. For the detected feature points, the higher the probability output by the detection model, the better the detection accuracy. Therefore, the photographic range determination unit 24 compares the representative value of the probability derived by the detection model for the 17 feature points with a predetermined threshold value, and determines that the detection accuracy is good when the representative value is above the threshold value, and the detection accuracy is poor when the representative value is less than the threshold value. As a representative value, an average value, an intermediate value, a weighted average value corresponding to the photographic part, etc. can be used, but it is not limited to these.

[0118] If it is determined that the detection accuracy is good, the imaging range determination unit 24 performs processing to determine the imaging range. On the other hand, if it is determined that the detection accuracy is poor, the imaging range determination unit 24 displays a warning on the display 14. Here, if the subject H moves too much, or the subject H is covered with a thick blanket, or the whole body of the subject H is not included in the imaging range of the camera 7, no matter which detection model is used, the feature points cannot be detected with high accuracy, and the detection accuracy deteriorates. In this case, the imaging range determination unit 24 determines that the detection accuracy is poor.

[0119] In addition, when the warning display is displayed, the operator manually sets the imaging range of the positioning imaging. That is, the operator measures the distance from the initial position of the diagnostic bed to the scanning start line, and further measures the distance between the scanning start line and the scanning end line, and inputs the measured distance from the input device 15. The movement of the diagnostic bed 3 during the positioning imaging is controlled according to the input distance.

[0120] The following is a description of the process of determining the photographic range by the photographic range determination unit 24. For example, in the case where the photographic part is the head, the top of the head to the end of the chin in the positioning image is the photographic range. Therefore, the photographic range determination unit 24 sets a line connecting the two eyes or ears among the feature points detected by the feature point detection unit 23, and further sets a scan start line at the top of the head, and sets a scan end line between the chin and the shoulders. Then, based on the distance relationship between the line connecting the two eyes or ears and the scan start line and the scan end line, the distance D1 between the scan start line and the scan end line is derived. The range of the distance D1 between the scan start line and the scan end line becomes the photographic range.

[0121] Here, before the positioning photography, the diagnostic bed 3 is located at the initial position, and the subject H lies supinely on the diagnostic bed 3, so the distance from the end of the diagnostic bed 3 to the top of the head of the subject H can be known from the camera image. Therefore, the photography range determination unit 24 calculates the distance D2 from the end of the diagnostic bed 3 to the top of the head of the subject H as the movement amount of the diagnostic bed from the initial position to the scanning start line, that is, the movement amount of the diagnostic bed 3 until the top of the head of the subject H reaches the scanning position in the CT device 1.

[0122] When the imaging range is determined, the imaging range determination unit 24 displays the scanning start line and the scanning end line on the human body diagram, that is, the schematic diagram displayed on the display 14 . Figure 7 : is a diagram showing a schematic diagram showing a start line and an end line. Figure 7As shown, a scanning start line 41 and a scanning end line 42 are shown in the schematic diagram 40. The operator confirms the scanning start line and the scanning end line displayed on the display 14. After confirmation, if it is confirmed, the operator uses the input device 15 to issue a command to start positioning imaging.

[0123] According to the command to start the locator imaging, the information of the distances D1 and D2 is output to the CT device 1. In the imaging control unit 20, after the driving unit 3C moves the diagnostic bed 3 by the distance D2, the locator imaging scan is started, and when the driving unit 3C moves the diagnostic bed 3 by the distance D1, the CT device 1 is controlled to end the locator imaging scan.

[0124] The positioning image acquired by the positioning radiography is displayed on the display 14. The operator confirms the positioning image displayed on the display 14 and sets the radiography range of the main radiography to the positioning image. Thereafter, the main radiography is performed by issuing a radiography command for the main radiography using the input device 15, and a three-dimensional CT image of the radiography part of the subject H is acquired within the radiography range of the set main radiography.

[0125] Next, the processing performed in the first embodiment will be described. Figure 8 1 is a flowchart showing the processing performed in the first embodiment. The processing is started by issuing a command to start imaging from the input device 15, and the selection unit 22 determines the brightness of the imaging room where the CT apparatus 1 is installed (step ST1). Then, the selection unit 22 selects one of the first detection model 22A and the second detection model 22B based on the determined brightness (detection model selection; step ST2).

[0126] Next, the camera control unit 21 starts acquiring a camera image based on the photography of the camera 7 (step ST3), and the feature point detection unit 23 detects feature points from the camera image using the detection model selected by the selection unit 22 (step ST4). Next, the photography range determination unit 24 determines the detection accuracy of the feature points (step ST5). When it is determined that the detection accuracy is good, the photography range determination unit 24 determines the photography range for positioning photography based on the feature points (step ST6), and draws the scanning start line and the scanning end line for positioning photography on the schematic diagram displayed on the display 14 based on the determined photography range (drawing line; step ST7). On the other hand, when it is determined that the detection accuracy is poor, the photography range determination unit 24 displays a warning (step ST8). When the warning is displayed, the information processing device 10 ends the photography range determination process. In this case, as described above, the operator manually sets the photography range for positioning photography.

[0127] Next, it is determined whether the operator has issued a start command for positioning photography (step ST9). If step ST9 is negative, the process returns to step ST3 and the process after step ST3 is repeated. If step ST9 is positive, the camera control unit 21 stops photography by the camera 7 (step ST10), and the information processing device 10 ends the photography range determination process.

[0128] After that, the imaging control unit 20 performs the positioning imaging to obtain the positioning image, and displays it on the display 14. After confirming the positioning image, the operator sets the imaging range of the main imaging. Furthermore, the operator performs the main imaging by issuing a command for the main imaging from the input device 15, thereby obtaining a three-dimensional CT image of the subject H.

[0129] Thus, in the first embodiment, the detection model for detecting feature points is selected according to the brightness of the inspection room. Therefore, when the inspection room is bright, the first detection model 22A for detecting feature points from the RGB camera image can be selected, and when the inspection room is dark, the second detection model 22B for detecting feature points from the NIR camera image can be selected. Therefore, when setting the imaging range, feature points can be appropriately detected according to the brightness of the inspection room, and as a result, the imaging range during positioning imaging can be appropriately determined using the detected feature points.

[0130] In addition, in the first embodiment described above, both the RGB camera image and the NIR camera image are acquired by the camera 7, but the present invention is not limited thereto. It is also possible that when the selection unit 22 determines that it is bright, the RGB camera 31 of the camera 7 acquires only the RGB camera image, and when the selection unit 22 determines that it is dark, the NIR camera 35 of the camera 7 acquires only the NIR camera image.

[0131] Next, the second embodiment of the present invention is described. In addition, the hardware structure and functional structure of the information processing device based on the second embodiment are the same as those of the first embodiment, so detailed description is omitted here. The information processing device 10 of the second embodiment is different from the first embodiment in that the first detection model 22A is first selected and feature points are detected from the RGB camera image, and it is determined whether the brightness is above the reference based on the RGB camera image. When the brightness is above the reference, the photographic range is determined based on the feature points detected from the RGB camera image using the first detection model 22A. When the brightness is less than the reference, the second detection model 22B is selected, and the photographic range is determined based on the feature points detected from the NIR camera image using the second detection model 22B.

[0132] Next, the processing performed in the second embodiment will be described. Fig. 92 is a flowchart showing the processing performed in the second embodiment. For example, the processing is started by a command to start photographing from the input device 15, and the camera control unit 21 starts to acquire an RGB camera image based on photographing by the camera 7 (step ST21). Next, the selection unit 22 selects the first detection model 22A (step ST22), and the feature point detection unit 23 detects feature points from the RGB camera image using the first detection model 22A selected by the selection unit 22 (step ST23).

[0133] Next, the selection unit 22 derives brightness information from the RGB camera image, and determines the brightness of the inspection room where the CT device 1 is installed based on the brightness information (step ST24). If it is determined that the brightness is dark, the selection unit 22 selects the second detection model 22B instead of the first detection model 22A (step ST25). Next, the feature point detection unit 23 detects feature points from the NIR camera image using the second detection model 22B (step ST26), and the imaging range determination unit 24 determines the detection accuracy of the feature points (step ST27). In step ST24, if it is determined that it is bright, the process proceeds to step ST27, and the imaging range determination unit 24 determines the detection accuracy of the feature points detected from the RGB camera image in step ST23.

[0134] If it is determined that the detection accuracy is good, the imaging range determination unit 24 determines the imaging range for positioning imaging based on the feature points (step ST28), and draws the scanning start line and the scanning end line for positioning imaging on the schematic diagram displayed on the display 14 based on the determined imaging range (drawing lines; step ST29). On the other hand, if it is determined that the detection accuracy is poor, the imaging range determination unit 24 displays a warning (step ST30). When the warning is displayed, the information processing device 10 ends the imaging range determination process. In this case, as described above, the operator manually sets the imaging range for positioning imaging.

[0135] Next, it is determined whether the operator has issued a start command for positioning photography (step ST31). If step ST31 is negative, the process returns to step ST21 and the process after step ST21 is repeated. If step ST31 is positive, the camera control unit 21 stops photography by the camera 7 (step ST32), and the information processing device 10 ends the photography range determination process.

[0136] Thus, in the second embodiment, the first detection model 22A is used to detect feature points from the RGB camera image, the RGB camera image is used to determine the brightness, and the detected feature points are used directly in a bright situation, and the second detection model 22B is used in a dark situation and the feature points are detected using the NIR camera image. Therefore, when setting the photographic range, the feature points can be appropriately detected according to the brightness of the photographic room, and as a result, the photographic range during positioning photography can be appropriately determined using the detected feature points.

[0137] In addition, in the above-mentioned second embodiment, the brightness is determined based on the brightness information derived from the RGB camera image, but it is not limited to this. It can also be set that the first detection model 22A is used to detect feature points from the RGB camera image, and the brightness is determined based on the detection accuracy of the feature points. Here, when the examination room is dark, the subject H becomes difficult to visually recognize in the RGB camera image, so the detection accuracy of the feature points decreases. Therefore, the selection unit 22 can also be set to compare the representative value of the probability derived by the detection model for 17 feature points with a predetermined threshold value. When the representative value is above the threshold, the detection accuracy is good, so it is determined that the examination room is bright. When the representative value is less than the threshold, the detection accuracy is poor, so it is determined that the examination room is dark.

[0138] Next, a third embodiment of the present invention will be described. Note that the hardware configuration of the information processing device according to the third embodiment is the same as that of the information processing device according to the first embodiment, and therefore detailed description thereof will be omitted. Fig.10 1 is a diagram showing the functional structure of an information processing device according to the third embodiment. Fig.10 In, with Figure 5 The same structure is given the same reference number, and detailed description is omitted. The information processing device 10A based on the third embodiment is different from the first embodiment in that, in addition to the first detection model 22A and the second detection model 22B, it also has a third detection model 22C and a fourth detection model 22D, and the detection model for detecting feature points is selected from the first detection model 22A, the second detection model 22B, the third detection model 22C, and the fourth detection model 22D.

[0139] In the third embodiment, the first detection model 22A is a model that focuses on frame rate for detecting feature points from RGB camera images, and the second detection model 22B is a model that focuses on frame rate for detecting feature points from NIR camera images. The third detection model 22C is a model that focuses on accuracy for detecting feature points from RGB camera images, and the fourth detection model 22D is a model that focuses on accuracy for detecting feature points from NIR camera images.

[0140] “Focusing on frame rate” means, for example, increasing the processing speed for detecting feature points by reducing the amount of data to be processed or omitting calculations, etc. Since the first detection model 22A and the second detection model 22B focus on frame rate, a model with a small amount of calculation and a high processing speed for detecting feature points is used.

[0141] “Focusing on accuracy” means that the accuracy of detecting feature points is improved even though the operation time is long without reducing the amount of data or omitting the operation. Since the third detection model 22C and the fourth detection model 22D focus on accuracy, the amount of calculation is large and the processing speed is slower than the first detection model 22A and the second detection model 22B, but the model used for detecting feature points has a higher accuracy than the first detection model 22A and the second detection model 22B.

[0142] The first detection model 22A and the second detection model 22B use a neural network with a structure that has a small amount of calculation and can perform feature point detection processing at a high speed. The third detection model 22C and the fourth detection model 22D use a neural network with a structure that has a large amount of calculation but can detect feature points with higher accuracy than the first detection model 22A and the second detection model 22B. For any neural network, a teacher image is also used for learning, and the teacher image is obtained by photographing a human body using a camera 7, and includes the whole body of the human body, and 17 feature points are known. In addition, similar to the case of performing an actual inspection, the teacher image is obtained by photographing a person wearing an inspection suit with a camera 7. In the third embodiment, in the learning of the first detection model 22A and the third detection model 22C, an RGB camera image is used as a teacher image. And, in the learning of the second detection model 22B and the fourth detection model 22D, an NIR camera image as a gray image is used as a teacher image.

[0143] In addition, the same structure of the neural network can also be used in the first detection model 22A and the second detection model 22B and the third detection model 22C and the fourth detection model 22D. In this case, different teacher images are used in the first detection model 22A and the second detection model 22B and the third detection model 22C and the fourth detection model 22D to learn the neural network. For example, as for the first teacher image used in the learning of the first detection model 22A and the second detection model 22B, an image with a lower resolution is used. On the other hand, as for the second teacher image used in the learning of the third detection model 22C and the fourth detection model 22D, an image with a resolution greater than that of the first teacher image is used.

[0144] In the third embodiment, the selection unit 22 selects a detection model based on the brightness of the examination room and the photographed part of the subject H. Here, the photographed parts of the subject H include the head, chest, abdomen, lower limbs, and whole body, but the head is easy to move during photographing, while the chest or abdomen is not easy to move during photographing. Therefore, when the examination room is bright and the photographed part is the head, or when the photographed part is the whole body including the head, the selection unit 22 selects the first detection model 22A that focuses on the frame rate and detects feature points from the RGB camera image. On the other hand, when the examination room is dark and the photographed part is the head, or when the photographed part is the whole body including the head, the selection unit 22 selects the second detection model 22B that focuses on the frame rate and detects feature points from the NIR camera image.

[0145] Furthermore, when the imaging part is the abdomen or lower limbs, the imaging is often performed with a blanket covering the abdomen or lower limbs. In this case, when the examination room is bright, the selection unit 22 selects the third detection model 22C that focuses on accuracy to detect feature points from the RGB camera image. Furthermore, when the examination room is dark, the selection unit 22 selects the fourth detection model 22D that focuses on accuracy to detect feature points from the NIR camera image.

[0146] In addition, which part of the subject H is to be imaged is included in the examination form provided by the doctor at the time of imaging, and the operator sets it through the input device 15 according to the examination form.

[0147] Next, the processing performed in the third embodiment will be described. Fig.11 4 is a flowchart showing the processing performed in the third embodiment. For example, the processing is started by issuing a command to start imaging from the input device 15, and the selection unit 22 determines the brightness of the imaging room where the CT apparatus 1 is installed and the imaging part included in the examination order (step ST41). Then, the selection unit 22 selects any one of the first detection model 22A and the fourth detection model 22D based on the determined brightness (detection model selection; step ST42).

[0148] If the part is determined to be bright and the imaging part is easy to move, the selection unit 22 selects the first detection model 22A, and if it is determined to be dark and the imaging part is easy to move, the selection unit 22 selects the second detection model 22B. Furthermore, if it is determined to be bright and the imaging part is difficult to move, the selection unit 22 selects the third detection model 22C, and if it is determined to be dark and the imaging part is difficult to move, the selection unit 22 selects the fourth detection model 22D.

[0149] Next, the camera control unit 21 starts acquiring a camera image based on photography by the camera 7 (step ST43 ), and the feature point detection unit 23 detects feature points from the camera image using the detection model selected by the selection unit 22 (step ST44 ).

[0150] That is, when the first detection model 22A is selected, the feature point detection unit 23 detects feature points from the RGB camera image using the first detection model 22A. When the second detection model 22B is selected, the feature point detection unit 23 detects feature points from the NIR camera image using the second detection model 22B. And, when the third detection model 22C is selected, the feature point detection unit 23 detects feature points from the RGB camera image using the third detection model 22C. When the fourth detection model 22D is selected, the feature point detection unit 23 detects feature points from the NIR camera image using the fourth detection model 22D.

[0151] Next, the imaging range determination unit 24 determines the detection accuracy of the feature points (step ST45). If it is determined that the detection accuracy is good, the imaging range determination unit 24 determines the imaging range for positioning imaging based on the feature points (step ST46), and draws the scanning start line and the scanning end line for positioning imaging on the schematic diagram displayed on the display 14 based on the determined imaging range (drawing line; step ST47). On the other hand, if it is determined that the detection accuracy is poor, the imaging range determination unit 24 displays a warning (step ST48).

[0152] Next, it is determined whether the operator has issued a start command for positioning photography (step ST49). If step ST49 is negative, the process returns to step ST43 and the process after step ST43 is repeated. If step ST49 is positive, the camera control unit 21 stops photography by the camera 7 (step ST50), and the information processing device 10 ends the photography range determination process.

[0153] After that, the imaging control unit 20 performs the positioning imaging to obtain the positioning image, and displays it on the display 14. After confirming the positioning image, the operator sets the imaging range of the main imaging. Furthermore, the operator performs the main imaging by issuing a command for the main imaging from the input device 15, thereby obtaining a three-dimensional CT image of the subject H.

[0154] Thus, in the third embodiment, in addition to the brightness of the examination room, the detection model for detecting feature points is selected according to the imaging part. Therefore, the feature points can be detected using an appropriate detection model according to the brightness of the examination room and the imaging part. Therefore, the imaging range during positioning imaging can be appropriately determined using the detected feature points.

[0155] In addition, in the third embodiment, both the RGB camera image and the NIR camera image are acquired by the camera 7, but the present invention is not limited thereto. It is also possible that when the selection unit 22 determines that it is bright, the RGB camera 31 of the camera 7 acquires only the RGB camera image, and when the selection unit 22 determines that it is dark, the NIR camera 35 of the camera 7 acquires only the NIR camera image.

[0156] Next, the fourth embodiment of the present invention is described. In addition, the hardware structure and functional structure of the information processing device based on the fourth embodiment are the same as those of the third embodiment, so detailed description is omitted here. In the fourth embodiment, the difference from the third embodiment is that first, the first detection model 22A focusing on frame rate is selected to detect feature points from the RGB camera image, and according to the detection accuracy of the feature points, the third detection model 22C focusing on accuracy is used to detect feature points from the RGB camera image, or the fourth detection model 22D focusing on accuracy is used to detect feature points from the NIR camera image.

[0157] Next, the processing performed in the fourth embodiment will be described. Fig.12 and Fig.13 : is a flowchart showing the processing performed in the third embodiment. For example, the processing is started by issuing a command to start photographing from the input device 15, and the camera control unit 21 starts acquiring a camera image including an RGB camera image and an NIR camera image based on photographing by the camera 7 (step ST61). Next, the selection unit 22 selects the first detection model 22A focusing on the frame rate (step ST62), and the feature point detection unit 23 detects feature points from the RGB camera image using the detection model selected by the selection unit 22 (step ST63).

[0158] Next, the imaging range determination unit 24 determines the detection accuracy of the feature points (step ST64). If the imaging range determination unit 24 determines that the detection accuracy is poor, the selection unit 22 selects the third detection model 22C that emphasizes accuracy instead of the first detection model 22A (step ST65). Next, the feature point detection unit 23 detects feature points from the RGB camera image (step ST66), and the imaging range determination unit 24 determines the detection accuracy of the feature points (step ST67).

[0159] When the imaging range determination unit 24 determines that the detection accuracy is poor, the selection unit 22 selects the fourth detection model 22D that focuses on accuracy to detect feature points from the NIR camera image instead of the third detection model 22C (step ST68). Alternatively, the second detection model 22B that focuses on frame rate to detect feature points from the NIR camera image may be selected instead of the fourth detection model 22D. Next, the feature point detection unit 23 detects feature points from the NIR camera image (step ST69), and the imaging range determination unit 24 determines the detection accuracy of the feature points (step ST70).

[0160] If it is determined that the detection accuracy is good, the imaging range determination unit 24 determines the imaging range for positioning imaging based on the feature points (step ST71), and draws the scanning start line and the scanning end line for positioning imaging on the schematic diagram displayed on the display 14 based on the determined imaging range (drawing lines; step ST72). On the other hand, if it is determined that the detection accuracy is poor, the imaging range determination unit 24 displays a warning (step ST73). When the warning is displayed, the information processing device 10 ends the imaging range determination process. In this case, as described above, the operator manually sets the imaging range for positioning imaging.

[0161] In addition, when the imaging range determination unit 24 determines that the detection accuracy is good in step ST64 and step ST67, the process proceeds to step ST71 and the processes after step ST71 are performed.

[0162] Next, it is determined whether the operator has issued a start command for positioning photography (step ST74). If step ST74 is negative, the process returns to step ST61 and the process after step ST61 is repeated. If step ST74 is positive, the camera control unit 21 stops photography by the camera 7 (step ST75), and the information processing device 10 ends the photography range determination process.

[0163] Thus, in the fourth embodiment, feature points are first detected from the RGB camera image using the first detection model 22A that focuses on the frame rate. When the detection accuracy of the feature points detected using the first detection model 22A is good, the photographic range is determined using the feature points detected using the first detection model 22A that focuses on the frame rate. When the detection accuracy of the feature points detected using the first detection model 22A is poor, the feature points are detected from the RGB camera image using the third detection model 22C that focuses on accuracy. When the detection accuracy of the feature points detected using the third detection model 22C is good, the photographic range is determined using the feature points detected using the third detection model 22C. When the detection accuracy of the feature points detected using the third detection model 22C is poor, the feature points are detected from the NIR camera image using the fourth detection model 22D that focuses on accuracy. Therefore, when setting the photographic range, the feature points can be appropriately detected according to the detection accuracy of the feature points, and as a result, the photographic range during positioning photography can be appropriately determined using the detected feature points.

[0164] Next, a fifth embodiment of the present invention will be described. The hardware configuration of the information processing device according to the fifth embodiment is the same as that of the third embodiment, and therefore detailed description thereof will be omitted. Fig.14 1 is a diagram showing the functional structure of an information processing device according to the fifth embodiment. Fig.14 In, with Fig.10 The same reference numerals are used to designate the same configurations, and detailed description thereof will be omitted. The information processing apparatus 10B according to the fifth embodiment is different from the third embodiment in that a movement detection unit 25 for detecting movement of the subject H is provided.

[0165] The motion detection unit 25 detects the motion of the subject H. Specifically, the two-dimensional motion of the feature points detected by the feature point detection unit 23 is detected between temporally adjacent frames in the camera image. In addition, in the fifth embodiment, the selection unit 22 first selects the first detection model 22A that focuses on the frame rate, and the feature point detection unit 23 detects feature points from the RGB camera image using the first detection model 22A. Regarding the feature points for detecting the motion of the subject H, feature points corresponding to the photographed part can also be used. For example, when the photographed part is the head, the nose, the eyes, or the ears can be used, and when the photographed part is the chest, the shoulders and the base of the left and right feet can be used. In addition, as the motion, it can also be set to obtain a representative value of all the motions of the 17 feature points.

[0166] When the detected movement is equal to or larger than a predetermined threshold, the movement detection unit 25 determines that the movement is large, and when it is smaller than the threshold, the movement detection unit 25 determines that the movement is small. The threshold for determining the size of the movement is an example of a reference.

[0167] In the fifth embodiment, if the movement detection unit 25 determines that the movement of the subject H is small, the selection unit 22 selects the third detection model 22C that focuses on accuracy and detects feature points from the RGB camera image and the fourth detection model 22D that focuses on accuracy and detects feature points from the NIR camera image instead of the first detection model 22A. The second detection model 22B that focuses on the frame rate may be selected instead of the fourth detection model 22D. The feature point detection unit 23 uses both the third detection model 22C and the fourth detection model 22D selected by the selection unit 22 to detect feature points. The imaging range determination unit 24 determines the imaging range using the feature points detected by the detection model with high detection accuracy among the third detection model 22C and the fourth detection model 22D. On the other hand, if the movement detection unit 25 determines that the movement of the subject H is large, the feature point detection unit 23 continues to detect feature points using the first detection model 22A for detecting feature points for detecting movement. The imaging range determination unit 24 determines the imaging range using the feature points detected by the first detection model 22A.

[0168] Next, the processing performed in the fifth embodiment will be described. Fig.15 and Fig.16 This is a flowchart showing the processing performed in the fifth embodiment. For example, the processing is started by issuing a command to start photographing from the input device 15, and the camera control unit 21 starts acquiring a camera image including an RGB camera image and an NIR camera image based on photographing by the camera 7 (step ST81). Next, the selection unit 22 selects the first detection model 22A that focuses on the frame rate (step ST82), and the feature point detection unit 23 detects feature points from the RGB camera image using the detection model selected by the selection unit 22 (step ST83).

[0169] Next, the movement detection unit 25 detects the movement of the subject H using the feature points detected by the feature point detection unit 23 (step ST84), thereby determining whether the movement is large (step ST85). If the movement of the subject H is small and step ST85 is negative, the selection unit 22 first selects the third detection model 22C that focuses on accuracy to detect feature points from the RGB camera image instead of the first detection model 22A (step ST86). Furthermore, the feature point detection unit 23 detects feature points from the RGB camera image (step ST87). Next, the selection unit 22 selects the fourth detection model 22D that focuses on accuracy to detect feature points from the NIR camera image instead of the third detection model 22C (step ST88). Furthermore, the feature point detection unit 23 detects feature points from the NIR camera image (step ST89).

[0170] In addition, the processing of steps ST86 and ST87 and the processing of steps ST88 and ST89 may be performed in parallel, or the processing of steps ST88 and ST89 may be performed before the processing of steps ST86 and ST87.

[0171] Next, the imaging range determination unit 24 compares the detection accuracy (set to R3) of the feature points based on the third detection model 22C with the detection accuracy (set to R4) of the feature points based on the fourth detection model 22D (step ST90). Specifically, the imaging range determination unit 24 compares the representative value of the probability of the 17 feature points derived for the third detection model 22C with the representative value of the probability of the 17 feature points derived for the fourth detection model 22D. As the representative value, an average value, a median value, a weighted average value corresponding to the imaging part, etc. can be used, but it is not limited to these.

[0172] When the detection accuracy R3 of the feature points based on the third detection model 22C is greater than the detection accuracy R4 of the feature points based on the fourth detection model 22D (R3 ≥ R4), in order to determine the photographic range, the photographic range determination unit 24 determines to use the feature points detected using the third detection model 22C for determining the photographic range (step ST91). When the detection accuracy R3 of the feature points based on the third detection model 22C is less than the detection accuracy R4 of the feature points based on the fourth detection model 22D (R3 < R4), the photographic range determination unit 24 determines to use the feature points detected using the fourth detection model 22D for determining the photographic range (step ST92).

[0173] Next, the imaging range determination unit 24 determines the detection accuracy of the feature points (step ST93 ). If the step ST85 is affirmative, the process proceeds to step ST93 , and the imaging range determination unit 24 determines the detection accuracy of the feature points detected in step ST83 .

[0174] If it is determined that the detection accuracy is good, the imaging range determination unit 24 determines the imaging range for positioning imaging based on the feature points (step ST94), and draws the scanning start line and the scanning end line for positioning imaging on the schematic diagram displayed on the display 14 based on the determined imaging range (drawing lines; step ST95). On the other hand, if it is determined that the detection accuracy is poor, the imaging range determination unit 24 displays a warning (step ST96). If the warning is displayed, the information processing device 10 ends the imaging range determination process. In this case, as described above, the operator manually sets the imaging range for positioning imaging.

[0175] Next, it is determined whether the operator has issued a start command for positioning photography (step ST97). If step ST97 is negative, the process returns to step ST81 and the process after step ST81 is repeated. If step ST97 is positive, the camera control unit 21 stops photography by the camera 7 (step ST98), and the information processing device 10B ends the photography range determination process.

[0176] Thus, in the fifth embodiment, the first detection model 22A focusing on the frame rate first detects feature points from the RGB camera image, and when the detection accuracy of the feature points detected using the first detection model 22A is good, the feature points detected using the first detection model 22A are used to determine the photographic range. When the detection accuracy of the feature points detected using the first detection model 22A is poor, the third detection model 22C focusing on accuracy is used to detect feature points from the RGB camera image, and the fourth detection model 22D focusing on accuracy is used to detect feature points from the NIR camera image. Furthermore, the photographic range is determined using feature points with good detection accuracy. Therefore, when setting the photographic range, the feature points can be appropriately detected using the detection model corresponding to the detection accuracy of the feature points, and as a result, the photographic range during positioning photography can be appropriately determined using the detected feature points.

[0177] In the above-mentioned embodiments, although the NIR camera 35 is provided on the camera 7, the present invention is not limited thereto. A night vision camera may be used instead of the NIR camera 35. Furthermore, a camera having a higher ISO sensitivity than the RGB camera 31 may be used instead of the NIR camera 35.

[0178] Furthermore, in each of the above-mentioned embodiments, the NIR camera 35 is used as a stereo camera, but the present invention is not limited thereto and only one NIR camera may be used.

[0179] Furthermore, in each of the above-mentioned embodiments, the camera 7 is provided with the RGB camera 31 , but the present invention is not limited thereto. Instead of the RGB camera 31 , a camera capable of capturing a monochrome image may be used.

[0180] Furthermore, in the above-mentioned embodiment, although the RGB camera 31 and the NIR camera 35 are provided on the camera 7, the present invention is not limited thereto. The RGB camera 31 and the NIR camera 35 may be provided separately.

[0181] Furthermore, in the above-mentioned embodiments, the information processing device according to the present invention is applied to a CT device, but the present invention is not limited thereto. If the device is an imaging device that obtains a positioning image for setting an imaging range before actual imaging, the information processing device according to the present invention may also be applied to an MRI device or the like.

[0182] Furthermore, in each of the above-mentioned embodiments, the information processing device is provided with the imaging control unit 20, but the present invention is not limited thereto. The imaging control unit 20 may be provided separately from the information processing device.

[0183] Furthermore, in the above-mentioned embodiments, for the detection model focusing on frame rate, multiple detection models with different processing speeds for feature point detection may be used. Also, for the detection model focusing on accuracy, multiple detection models with different accuracy for feature point detection may be used.

[0184] Furthermore, in the fourth and fifth embodiments described above, as detection models for detecting feature points from NIR camera images, the second detection model 22B focusing on frame rate and the fourth detection model 22D focusing on accuracy are used, but the present invention is not limited thereto. The information processing device 10B may also have only one of the second detection model 22B focusing on frame rate and the fourth detection model 22D focusing on accuracy. Furthermore, a detection model that can detect feature points from NIR camera images at a certain frame rate and a certain accuracy may be used instead of the second detection model 22B and the fourth detection model 22D.

[0185] Furthermore, in the above-mentioned embodiment, for example, as a hardware structure of a processing unit (Processing Unit) that executes various processes such as the photography control unit 20, the camera control unit 21, the selection unit 22, the feature point detection unit 23, the photography range determination unit 24, and the motion detection unit 25, various processors (Processor) shown below can be used. As described above, the above-mentioned various processors include, in addition to a general-purpose processor, i.e., a CPU, that executes software (programs) and functions as various processing units, a processor whose circuit structure can be changed after manufacturing, such as a FPGA (Field Programmable Gate Array), a processor having a circuit structure designed specifically for executing specific processing, i.e., a dedicated circuit, such as a programmable logic device (PLD), and an ASIC (Application Specific Integrated Circuit).

[0186] One processing unit may be composed of one of these various processors, or a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs or a combination of a CPU and an FPGA). Furthermore, multiple processing units may be composed of one processor.

[0187] As an example of a plurality of processing units constituted by one processor, there is the following method: as represented by computers such as clients and servers, one processor is constituted by a combination of one or more CPUs and software, and the processor functions as a plurality of processing units. Second, there is the following method: as represented by a system on chip (SoC), a processor that implements the functions of the entire system including a plurality of processing units by one IC (Integrated Circuit) chip is used. In this way, various processing units are constituted using one or more of the above-mentioned various processors as a hardware structure.

[0188] Furthermore, as the hardware configuration of these various processors, more specifically, a circuit (Circuitry) in which circuit elements such as semiconductor elements are combined can be used.

[0189] The additional items of the present invention are described below.

[0190] (Supplementary Item 1)

[0191] An information processing device comprising at least one processor.

[0192] The processor performs the following processing:

[0193] acquiring at least one of a first camera image generated by performing dynamic image photography of a subject on a diagnostic couch with a first camera and a second camera image generated by performing dynamic image photography of the subject with a second camera having a higher photography sensitivity than the first camera;

[0194] selecting at least one detection model from a plurality of detection models including a first detection model and a second detection model, wherein the first detection model is constructed to detect a plurality of feature points on the subject included in the first camera image, and the second detection model is constructed to detect the plurality of feature points on the subject included in the second camera image;

[0195] using the selected detection model to detect the plurality of feature points on the subject included in the first camera image or the second camera image; and

[0196] An imaging range of the subject is determined based on the plurality of feature points.

[0197] (Supplementary Item 2)

[0198] The information processing device according to supplementary item 1, wherein:

[0199] The processor performs the following processing: when the brightness of the environment in which the diagnostic bed is set is above a benchmark, the first detection model is selected to detect the multiple feature points on the subject contained in the first camera image; when the brightness is less than the benchmark, the second detection model is selected to detect the multiple feature points on the subject contained in the second camera image.

[0200] (Supplementary item 3)

[0201] The information processing device according to supplementary item 2, wherein:

[0202] The processor acquires the first camera image and determines the brightness based on brightness information derived from the first camera image.

[0203] (Supplementary Item 4)

[0204] The information processing device according to supplementary item 2, wherein:

[0205] The processor acquires the first camera image and determines the brightness according to noise included in the first camera image.

[0206] (Supplementary Note 5)

[0207] The information processing device according to supplementary item 2, wherein:

[0208] The processor performs the following processing: acquiring the first camera image, detecting the feature points from the first camera image using the first detection model, and determining the brightness according to the detection accuracy of the feature points.

[0209] (Supplementary Note 6)

[0210] The information processing device according to supplementary item 2, wherein:

[0211] The processor determines the brightness by a sensor that detects the brightness of the environment.

[0212] (Supplementary Note 7)

[0213] An information processing device according to any one of supplementary items 2 to 6, wherein:

[0214] The processor performs the following processing: acquiring the first camera image, selecting the first detection model and detecting the feature points from the first camera image, determining whether the brightness is above a benchmark based on the first camera image, and when the brightness is above the benchmark, determining the photographic range based on the feature points detected using the first detection model; and when the brightness is less than the benchmark, selecting the second detection model and determining the photographic range based on the feature points detected using the second detection model.

[0215] (Supplementary Item 8)

[0216] The information processing device according to supplementary item 1, wherein:

[0217] The first detection model and the second detection model are models that focus on the frame rate when detecting the feature points.

[0218] The plurality of detection models further include: a third detection model constructed to detect the plurality of feature points on the subject included in the first camera image, and focusing on the accuracy when detecting the feature points; and a fourth detection model constructed to detect the plurality of feature points on the subject included in the second camera image, and focusing on the accuracy when detecting the feature points.

[0219] The processor selects the detection model according to the brightness of the environment in which the diagnostic bed is installed and the imaging part of the subject.

[0220] (Supplementary Note 9)

[0221] The information processing device according to supplementary note 8, wherein:

[0222] The processor performs the following processing: when the brightness is above the benchmark, any one of the first detection model and the third detection model is selected to detect the multiple feature points on the subject contained in the first camera image; when the brightness is less than the benchmark, any one of the second detection model and the fourth detection model is selected to detect the multiple feature points on the subject contained in the second camera image.

[0223] (Supplementary Item 10)

[0224] The information processing device according to supplementary note 9, wherein:

[0225] The processor selects one of the first detection model and the third detection model and one of the second detection model and the fourth detection model according to the imaging part of the subject.

[0226] (Supplementary Note 11)

[0227] An information processing device according to any one of attachments 1 to 10, wherein:

[0228] The processor performs the following processing: determining the detection accuracy of the feature points, determining the photographing range based on the feature points when the detection accuracy is above a reference, and issuing a warning when the detection accuracy is lower than the reference.

[0229] (Supplementary Item 12)

[0230] The information processing device according to supplementary item 1, wherein:

[0231] The first detection model is a model that focuses on the frame rate when detecting the feature points.

[0232] The plurality of detection models further include a third detection model, the third detection model being constructed to detect the plurality of feature points on the subject included in the first camera image, and focusing on the accuracy of detecting the feature points.

[0233] The processor performs the following processing:

[0234] Acquire the first camera image and the second camera image, select the first detection model and detect the feature points from the first camera image;

[0235] determining a detection accuracy of the feature point detected using the first detection model;

[0236] When the detection accuracy is equal to or higher than a first standard, determining the imaging range based on the feature points detected using the first detection model;

[0237] When the detection accuracy is lower than the first benchmark, selecting the third detection model, and using the third detection model to detect the feature points from the first camera image;

[0238] determining a detection accuracy of the feature points detected using the third detection model;

[0239] When the detection accuracy is equal to or higher than a second standard, determining the photographing range based on the feature points detected using the third detection model;

[0240] When the detection accuracy is lower than the second benchmark, selecting the second detection model, and using the second detection model to detect the feature points from the second camera image; and

[0241] The imaging range is determined based on the feature points detected using the second detection model.

[0242] (Supplementary Item 13)

[0243] The information processing device according to supplementary item 12, wherein:

[0244] The processor performs the following processing:

[0245] determining the detection accuracy of the feature points detected using the first detection model when the detection accuracy is greater than the first benchmark, the detection accuracy of the feature points detected using the third detection model when the detection accuracy is greater than the second benchmark, or the detection accuracy of the feature points detected using the second detection model,

[0246] determining the photographing range based on the feature points detected using the first detection model when the detection accuracy is higher than the third standard and when the detection accuracy is higher than the first standard, the feature points detected using the third detection model when the detection accuracy is higher than the second standard, or the feature points detected using the second detection model; and

[0247] When the detection accuracy is lower than the third standard, a warning is issued.

[0248] (Supplementary Item 14)

[0249] The information processing device according to supplementary item 1, wherein:

[0250] The first detection model is a model that focuses on the frame rate when detecting the feature points.

[0251] The plurality of detection models further include a third detection model, the third detection model being constructed to detect the plurality of feature points on the subject included in the first camera image, and focusing on the accuracy of detecting the feature points.

[0252] The processor performs the following processing:

[0253] Acquire the first camera image and the second camera image, select the first detection model and detect the feature points from the first camera image;

[0254] detecting movement of the subject based on the first camera image;

[0255] determining the imaging range based on feature points detected using the first detection model when the movement of the subject is greater than or equal to a first reference;

[0256] When the movement of the subject is smaller than the first reference, selecting the second detection model and the third detection model;

[0257] detecting the feature points from the first camera image using the third detection model;

[0258] detecting the feature points from the second camera image using the second detection model;

[0259] comparing the detection accuracy of the feature points detected using the third detection model and the detection accuracy of the feature points detected using the second detection model;

[0260] When the detection accuracy of the feature points detected using the third detection model is higher, determining the imaging range based on the feature points detected using the third detection model; and

[0261] When the detection accuracy of the feature points detected using the second detection model is higher, the imaging range is determined based on the feature points detected using the second detection model.

[0262] (Supplementary Item 15)

[0263] The information processing device according to supplementary item 14, wherein:

[0264] The processor performs the following processing:

[0265] When the movement is greater than the first reference, determining the detection accuracy of the feature points detected using the first detection model, the detection accuracy of the feature points detected using the third detection model, or the detection accuracy of the feature points detected using the second detection model;

[0266] determining the photographing range based on the feature points detected using the first detection model when the detection accuracy is greater than or equal to the second standard and when the movement is greater than or equal to the first standard, the feature points detected using the third detection model, or the feature points detected using the second detection model; and

[0267] When the detection accuracy is lower than the second standard, a warning is issued.

[0268] (Supplementary Item 16)

[0269] An information processing device according to any one of supplementary items 1 to 15, wherein:

[0270] The processor derives a moving range of the bed based on the imaging range.

[0271] (Supplementary Item 17)

[0272] The information processing device according to supplementary item 16, wherein:

[0273] The processor displays a human body image simulating a human body on a display, and draws a movement start line and a movement end line of the diagnostic couch based on a movement range of the diagnostic couch on the human body image.

[0274] (Supplementary Item 18)

[0275] An information processing device according to any one of attachments 1 to 17, wherein:

[0276] The imaging range is an imaging range when capturing a positioning image acquired before performing a main imaging of the subject.

[0277] (Supplementary Item 19)

[0278] An information processing method, wherein:

[0279] The computer performs the following processing:

[0280] acquiring at least one of a first camera image generated by performing dynamic image photography of a subject on a diagnostic couch with a first camera and a second camera image generated by performing dynamic image photography of the subject with a second camera having a higher photography sensitivity than the first camera;

[0281] selecting at least one detection model from a plurality of detection models including a first detection model and a second detection model, wherein the first detection model is constructed to detect a plurality of feature points on the subject included in the first camera image, and the second detection model is constructed to detect the plurality of feature points on the subject included in the second camera image;

[0282] detecting the plurality of feature points on the subject included in the first camera image or the second camera image using the selected detection model; and

[0283] An imaging range of the subject is determined based on the plurality of feature points.

[0284] (Note 20]

[0285] An information processing program that causes a computer to execute the following steps:

[0286] acquiring at least one of a first camera image generated by performing dynamic image photography of a subject on a diagnostic couch with a first camera and a second camera image generated by performing dynamic image photography of the subject with a second camera having a higher photography sensitivity than the first camera;

[0287] selecting at least one detection model from a plurality of detection models including a first detection model and a second detection model, wherein the first detection model is constructed to detect a plurality of feature points on the subject included in the first camera image, and the second detection model is constructed to detect the plurality of feature points on the subject included in the second camera image;

[0288] using the selected detection model to detect the plurality of feature points on the subject included in the first camera image or the second camera image; and

[0289] An imaging range of the subject is determined based on the plurality of feature points.

Claims

1. An information processing device comprising at least one processor, The processor performs the following processing: acquiring at least one of a first camera image generated by performing dynamic image photography of a subject on a diagnostic couch with a first camera and a second camera image generated by performing dynamic image photography of the subject with a second camera having a higher photography sensitivity than the first camera; selecting at least one detection model from a plurality of detection models including a first detection model and a second detection model, wherein the first detection model is constructed to detect a plurality of feature points on the subject included in the first camera image, and the second detection model is constructed to detect the plurality of feature points on the subject included in the second camera image; using the selected detection model to detect the plurality of feature points on the subject included in the first camera image or the second camera image; and An imaging range of the subject is determined based on the plurality of feature points.

2. The information processing device according to claim 1, wherein: The processor performs the following processing: when the brightness of the environment in which the diagnostic bed is set is above a benchmark, the first detection model is selected to detect the multiple feature points on the subject contained in the first camera image; when the brightness is less than the benchmark, the second detection model is selected to detect the multiple feature points on the subject contained in the second camera image.

3. The information processing device according to claim 2, wherein: The processor acquires the first camera image and determines the brightness based on brightness information derived from the first camera image.

4. The information processing device according to claim 2, wherein: The processor acquires the first camera image and determines the brightness according to noise included in the first camera image.

5. The information processing device according to claim 2, wherein: The processor performs the following processing: acquiring the first camera image, detecting the feature points from the first camera image using the first detection model, and determining the brightness according to the detection accuracy of the feature points.

6. The information processing device according to claim 2, wherein: The processor determines the brightness by a sensor that detects the brightness of the environment.

7. The information processing device according to any one of claims 2 to 6, wherein: The processor performs the following processing: acquiring the first camera image, selecting the first detection model and detecting the feature points from the first camera image, determining whether the brightness is above a benchmark based on the first camera image, and when the brightness is above the benchmark, determining the photographic range based on the feature points detected using the first detection model; and when the brightness is less than the benchmark, selecting the second detection model and determining the photographic range based on the feature points detected using the second detection model.

8. The information processing device according to claim 1, wherein: The first detection model and the second detection model are models that focus on the frame rate when detecting the feature points. The plurality of detection models further include: a third detection model constructed to detect the plurality of feature points on the subject included in the first camera image, and focusing on the accuracy when detecting the feature points; and a fourth detection model constructed to detect the plurality of feature points on the subject included in the second camera image, and focusing on the accuracy when detecting the feature points. The processor selects the detection model according to the brightness of the environment in which the diagnostic bed is installed and the imaging part of the subject.

9. The information processing device according to claim 8, wherein: The processor performs the following processing: when the brightness is above the benchmark, any one of the first detection model and the third detection model is selected to detect the multiple feature points on the subject contained in the first camera image; when the brightness is less than the benchmark, any one of the second detection model and the fourth detection model is selected to detect the multiple feature points on the subject contained in the second camera image.

10. The information processing device according to claim 9, wherein: The processor selects one of the first detection model and the third detection model and one of the second detection model and the fourth detection model according to the imaging part of the subject.

11. The information processing device according to claim 1, wherein: The processor performs the following processing: determining the detection accuracy of the feature points, determining the photographing range based on the feature points when the detection accuracy is above a reference, and issuing a warning when the detection accuracy is lower than the reference.

12. The information processing device according to claim 1, wherein: The first detection model is a model that focuses on the frame rate when detecting the feature points. The plurality of detection models further include a third detection model, the third detection model being constructed to detect the plurality of feature points on the subject included in the first camera image, and focusing on the accuracy of detecting the feature points. The processor performs the following processing: Acquire the first camera image and the second camera image, select the first detection model and detect the feature points from the first camera image; determining a detection accuracy of the feature point detected using the first detection model; When the detection accuracy is equal to or higher than a first standard, determining the imaging range based on the feature points detected using the first detection model; When the detection accuracy is lower than the first benchmark, selecting the third detection model, and using the third detection model to detect the feature points from the first camera image; determining a detection accuracy of the feature points detected using the third detection model; When the detection accuracy is equal to or higher than a second standard, determining the photographing range based on the feature points detected using the third detection model; When the detection accuracy is lower than the second benchmark, selecting the second detection model, and using the second detection model to detect the feature points from the second camera image; and The imaging range is determined based on the feature points detected using the second detection model.

13. The information processing device according to claim 12, wherein: The processor performs the following processing: determining the detection accuracy of the feature points detected using the first detection model when the detection accuracy is greater than the first benchmark, the detection accuracy of the feature points detected using the third detection model when the detection accuracy is greater than the second benchmark, or the detection accuracy of the feature points detected using the second detection model, Determine the photographic range based on the feature points detected using the first detection model when the detection accuracy is above the third benchmark and when the detection accuracy is above the first benchmark, the feature points detected using the third detection model when the detection accuracy is above the second benchmark, or the feature points detected using the second detection model; and When the detection accuracy is lower than the third standard, a warning is issued.

14. The information processing device according to claim 1, wherein: The first detection model is a model that focuses on the frame rate when detecting the feature points. The plurality of detection models further include a third detection model, the third detection model being constructed to detect the plurality of feature points on the subject included in the first camera image, and focusing on the accuracy of detecting the feature points. The processor performs the following processing: Acquire the first camera image and the second camera image, select the first detection model and detect the feature points from the first camera image; detecting movement of the subject based on the first camera image; determining the imaging range based on feature points detected using the first detection model when the movement of the subject is greater than or equal to a first reference; When the movement of the subject is smaller than the first reference, selecting the second detection model and the third detection model; detecting the feature points from the first camera image using the third detection model; detecting the feature points from the second camera image using the second detection model; comparing the detection accuracy of the feature points detected using the third detection model and the detection accuracy of the feature points detected using the second detection model; When the detection accuracy of the feature points detected using the third detection model is higher, determining the photographing range based on the feature points detected using the third detection model; and When the detection accuracy of the feature points detected using the second detection model is higher, the imaging range is determined based on the feature points detected using the second detection model.

15. The information processing device according to claim 14, wherein: The processor performs the following processing: When the movement is greater than the first reference, determining the detection accuracy of the feature points detected using the first detection model, the detection accuracy of the feature points detected using the third detection model, or the detection accuracy of the feature points detected using the second detection model; Determining the photographing range based on the feature points detected using the first detection model when the detection accuracy is greater than the second standard and when the movement is greater than the first standard, the feature points detected using the third detection model, or the feature points detected using the second detection model; and When the detection accuracy is lower than the second standard, a warning is issued.

16. The information processing device according to claim 1, wherein: The processor derives a moving range of the bed based on the imaging range.

17. The information processing device according to claim 16, wherein: The processor displays a human body image simulating a human body on a display, and draws a movement start line and a movement end line of the diagnostic couch based on a movement range of the diagnostic couch on the human body image.

18. The information processing device according to claim 1, wherein: The imaging range is an imaging range when capturing a positioning image acquired before performing a main imaging of the subject.

19. An information processing method, wherein: The computer performs the following processing: acquiring at least one of a first camera image generated by performing dynamic image photography of a subject on a diagnostic couch with a first camera and a second camera image generated by performing dynamic image photography of the subject with a second camera having a higher photography sensitivity than the first camera; selecting at least one detection model from a plurality of detection models including a first detection model and a second detection model, wherein the first detection model is constructed to detect a plurality of feature points on the subject included in the first camera image, and the second detection model is constructed to detect the plurality of feature points on the subject included in the second camera image; using the selected detection model to detect the plurality of feature points on the subject included in the first camera image or the second camera image; and An imaging range of the subject is determined based on the plurality of feature points.

20. A program product, comprising an information processing program, the information processing program causing a computer to execute the following steps: acquiring at least one of a first camera image generated by performing dynamic image photography of a subject on a diagnostic couch with a first camera and a second camera image generated by performing dynamic image photography of the subject with a second camera having a higher photography sensitivity than the first camera; selecting at least one detection model from a plurality of detection models including a first detection model and a second detection model, wherein the first detection model is constructed to detect a plurality of feature points on the subject included in the first camera image, and the second detection model is constructed to detect the plurality of feature points on the subject included in the second camera image; using the selected detection model to detect the plurality of feature points on the subject included in the first camera image or the second camera image; and An imaging range of the subject is determined based on the plurality of feature points.

Images