X-ray imaging apparatus and image processing method

Abstract

An X-ray imaging apparatus and an image processing method are provided. An image of a subject is captured by a camera. A skeleton of a human figure included in the image is detected, and a skeleton of the subject mounted on a top plate of the X-ray imaging apparatus is extracted based on the detected skeleton. A movement amount of corresponding pixels, i.e., an optical flow, is calculated between the captured image and an image captured by the camera at a timing only a predetermined time earlier than a timing at which the image is acquired. A plurality of attention regions are set on an image of the subject based on positions of the skeleton of the subject. A determination unit determines whether or not a body motion has occurred in the subject based on the movement amount of the pixels of the subject within the attention regions. An attention region setting unit includes an attention region selection unit that selects one or more of the attention regions set by the attention region setting unit for use by the determination unit in the determination of the body motion, or specifies a position of the attention region used by the determination unit in the determination of the body motion as the attention region selection unit.

Description

Technical Field

[0001] This invention relates to an X-ray imaging device for acquiring images by irradiating a subject with X-rays. Background Technology

[0002] IVR (Interventional Radiology) is a procedure in which, while X-ray imaging is used to obtain fluoroscopic images of the patient, an endoscope and catheters are inserted into the patient's body to perform various surgical procedures. The doctor performs the surgery while simultaneously viewing monitors displaying both the fluoroscopic images and the endoscopic images.

[0003] When confirming the patient during surgery while reviewing fluoroscopic images, the doctor may visually inspect the patient's face, feet, or hands, or inspect a monitor displaying camera images mounted on the ceiling or wall of the room, and confirm the patient through the camera images.

[0004] On the other hand, Patent Document 1 discloses a technique for detecting the body movement of a subject by performing image processing on a perspective image.

[0005] Patent document 2 discloses the following technology: using a camera to photograph multiple workers performing a task, and processing the images to perform skeleton detection, thereby identifying the worker performing a specific task from among the multiple workers.

[0006] Patent Document 1: Japanese Patent Application Publication No. 2021-186199

[0007] Patent Document 2: Japanese Patent Application Publication No. 2021-196783

[0008] IVR (Intraoperative Vacuum Respiratory Monitoring) involves inserting an endoscope or catheter into the patient while acquiring fluoroscopic images to perform various procedures. This is typically done while the patient is sedated, but patients sometimes unconsciously attempt to pull out the endoscope or move their body. In cases of movement, the surgeon must call for help from nurses or other staff in or outside the examination room and instruct them to hold the patient down. Therefore, even while monitoring the endoscopic monitor during surgery, the surgeon must be attentive to the patient's movements.

[0009] However, during surgery, doctors need to move their line of sight from the endoscopic monitor to the patient in order to visually confirm the patient's condition, which becomes a burden for the doctors.

[0010] On the other hand, when doctors check the monitor images from indoor cameras to identify patients, it is difficult to immediately grasp the patient's condition because the camera images also show doctors, technicians, and nurses in addition to the patient. Summary of the Invention

[0011] The purpose of this invention is to detect the body movement of the subject during the capture of a fluoroscopic image.

[0012] To achieve the above objectives, according to the present invention, an X-ray imaging apparatus is provided, comprising: a top plate for mounting a subject; an X-ray irradiation device for irradiating the subject with X-rays; an X-ray detector for detecting X-rays irradiated and transmitted through the X-ray irradiation device onto the subject; and a motion detection unit for receiving images from a camera that captures the subject and processing the images to detect the occurrence of motion in the subject. The motion detection unit includes a skeleton detection unit, an optical flow calculation unit, a region of interest setting unit, and a determination unit. The skeleton detection unit detects the skeleton of a human figure included in the image and extracts the skeleton of the subject mounted on the top plate based on the detected skeleton. The optical flow calculation unit calculates the amount of movement of corresponding pixels between the image and an image acquired by the camera at a time that is only a preset time earlier than the time at which the image was acquired. The region of interest setting unit sets multiple regions of interest on the image of the subject based on the position of the subject's skeleton extracted by the skeleton detection unit. The determination unit determines whether motion has occurred in the subject based on the amount of movement of pixels of the subject within the regions of interest. The attention area setting unit includes an attention area selection unit. The attention area selection unit selects one or more attention areas from the multiple attention areas set by the attention area setting unit for use by the determination unit in motion determination, or designates the position of the attention area for use by the determination unit in motion determination as the attention area setting unit.

[0013] Invention Effects

[0014] According to the present invention, it is possible to detect the body movements of the subject during the taking of fluoroscopic images, so that by notifying the doctor of the detection results, the doctor can easily grasp the occurrence of the patient's body movements even during surgery. Attached Figure Description

[0015] Figure 1 (a) is a front view of the X-ray imaging device 1 according to Embodiment 1. Figure 1 (b) Figure 1 (c) is a diagram showing an example of an image displayed on a camera image display monitor.

[0016] Figure 2 This is a functional block diagram of the X-ray imaging device according to Embodiment 1.

[0017] Figure 3This is a diagram illustrating an example of the configuration of the top plate 80 of the X-ray imaging device 1, the patient 10, and the doctor / nurse in a general examination room.

[0018] Figure 4 This is a diagram showing an image captured by the camera of the X-ray imaging device 1 according to Embodiment 1 and a skeleton detected from the image.

[0019] Figure 5 In implementation method 1 Figure 4 The feature points of the skeleton are used to define the region of interest in the graph 52.

[0020] Figure 6 (a) represents an image in which the optical flow (movement amount) calculated from the image captured by the camera of the X-ray imaging apparatus of Embodiment 1 is used as the pixel value. Figure 6 (b) is an image of pixels representing moving shadows calculated from images captured by the camera. Figure 6 (c) represents the region of interest with more pixels excluding shadows.

[0021] Figure 7 This is a flowchart illustrating the operation of the X-ray imaging device according to Embodiment 1.

[0022] Figure 8 This is a diagram showing the state of the notification dialog box 161 and the chart 162 displayed on the display screen of the camera image display monitor 15 of the X-ray imaging apparatus in Embodiment 1, indicating that a body movement has occurred.

[0023] Figure 9 It's enlarged. Figure 8 The figure in chart 162.

[0024] Figure 10 (a) and (b) are diagrams showing how body movement is indicated by the color of the edge of image 21a when image 21a is displayed on the display screen of the camera image display monitor 15 of the X-ray imaging apparatus of Embodiment 1.

[0025] Figure 11 (a) is an image showing a portion of the subject 10 covered by a protective curtain in embodiment 2-1 and a diagram of the defined area of ​​interest 52. Figure 11 (b) is a diagram of an image that excludes one region of interest, 52a.

[0026] Figure 12 This is a functional block diagram of the X-ray imaging device according to embodiment 2-1.

[0027] Figure 13 This is a flowchart illustrating the operation of the X-ray imaging device in Embodiment 2-1.

[0028] Figure 14 (a) is an image showing the X-ray imaging device of embodiment 2-1 with the protective curtain button closed and the set area of ​​interest. Figure 14 (b) is an image showing the X-ray imaging device of embodiment 2-1 with the protective curtain button in the open state and the set area of ​​interest.

[0029] Figure 15 This is a functional block diagram of the X-ray imaging device in Implementation Method 2-2.

[0030] Figure 16 This is a flowchart illustrating the operation of the X-ray imaging device in Embodiment 2-2.

[0031] Figure 17 This is a functional block diagram of the X-ray imaging device in embodiments 2-3.

[0032] Figure 18 (a) represents the whole-body selection button 204a of the X-ray imaging device in embodiments 2-3 and the image of the set area of ​​interest. Figure 18 (b) represents the selection button 204b on the upper part of the X-ray imaging device in embodiments 2-3 and the image of the set area of ​​interest. Figure 18 (c) is an image of the head and shoulder selection button 204c and the set area of ​​interest of the X-ray imaging device of embodiments 2-3.

[0033] Figure 19 This is a flowchart illustrating the operation of the X-ray imaging device in embodiments 2-3.

[0034] Figure 20 It is an image representing the second region of interest 152, the subject 10, and the skeleton other than the subject 10 of the X-ray imaging device of Embodiment 3-1.

[0035] Figure 21 This is a flowchart illustrating the operation of the X-ray imaging device in Embodiment 3-1.

[0036] Figure 22 (a) is an image showing the second region of interest 152, the subject 10, and the skeleton excluding the subject 10 of the X-ray imaging apparatus of Embodiment 3-1. Figure 22 (b) is an image showing the subject 10 of the X-ray imaging device of embodiment 3-2 and the skeleton lines other than the subject 10.

[0037] Figure 23 This is a flowchart illustrating the operation of the X-ray imaging device in Embodiment 3-2.

[0038] Figure 24It is an image showing the state of the skeleton other than the subject through the area of ​​interest of the subject 10 of the X-ray imaging device of embodiment 3-3.

[0039] Figure 25 This is a flowchart illustrating the operation of the X-ray imaging device in Embodiment 3-3.

[0040] Figure 26 (a) is a schematic diagram showing an image of the subject 10 of the X-ray imaging device of Embodiment 4 covered by a protective curtain. Figure 26 (b) is a schematic diagram showing the state in which the area of ​​interest 52 is set on the image of the X-ray imaging device of Embodiment 4 covered by a protective curtain.

[0041] Figure 27 This is a functional block diagram of the X-ray imaging device in Embodiment 4.

[0042] Figure 28 This is a flowchart illustrating the operation of the X-ray imaging device in Embodiment 4.

[0043] Symbol Explanation

[0044] 1-X-ray imaging device, 10-subject, 11-X-ray irradiation device, 12-X-ray detector, 13-X-ray image generation unit, 14-fluoroscopic image display monitor, 15-camera image display monitor, 16-endoscopic image display monitor, 20-body motion detection unit, 21-camera, 21a-image, 22-image reading unit, 23-image rotation unit, 24-skeleton detection unit, 25-subject skeleton extraction unit, 26-area of ​​interest setting unit, 27-optical flow calculation unit, 28-judgment unit, 29-notification unit, 41-midpoint, 45-center, 50-X-ray support unit, 50a-length direction, 50b-short Side direction, 50c-tilt, 51-rectangular area, 52-area of ​​interest, 52a-area of ​​interest, 60-X-ray up-down movement mechanism, 61-X-ray tilting mechanism, 62-pressing tool, 70-support, 77-position, 80-top plate, 81-top plate support, 152-second area of ​​interest, 161-notification dialog box, 162-chart, 180-area of ​​interest storage, 201-shadow detection unit, 202-button, 203-protective curtain detection unit, 204-area of ​​interest range selection button, 204a-button, 204b-button, 204c-button, 210-protective curtain, 220-medical personnel. Detailed Implementation

[0045] Hereinafter, the X-ray imaging apparatus according to embodiments of the present invention will be described with reference to the accompanying drawings.

[0046] The X-ray imaging device of this embodiment includes a camera and has the function of determining whether the subject has moved based on the image captured by the camera.

[0047] Specifically, first, the skeleton of the human figure is detected, and then the skeleton of the subject is extracted from the top plate of the X-ray camera device based on the detected skeleton.

[0048] Next, the amount of movement of the corresponding pixels is calculated between the image and the image acquired by the camera at a time that is only a preset time earlier than the time at which the image was acquired, thereby determining the optical flow.

[0049] Furthermore, multiple regions of interest are defined on the image of the subject based on the position of the subject's skeleton. One or more regions of interest are selected from the defined regions of interest for motion determination, or the position of one or more regions of interest for motion determination is specified, and the regions of interest are defined at that position. The amount of movement (optical flow) of the pixels of the regions of interest at the specified and selected regions of interest or positions is used to determine whether the subject has undergone motion.

[0050] Hereinafter, the motion detection function of the X-ray imaging device of this embodiment will be further explained through embodiments 1 to 4.

[0051] <<Implementation Method 1>>

[0052] The X-ray imaging apparatus 1 of Embodiment 1 will be described with reference to the accompanying drawings. Figure 1 (a) is a front view of X-ray imaging device 1. Figure 1 (b) Figure 1 (c) represents the image displayed on the camera image display monitor. Figure 2 This is a functional block diagram of X-ray imaging device 1. Figure 3 This is a diagram showing the setup of the X-ray imaging equipment, the patient, and the doctor / nurse in the examination room. Figures 4-6 This is an example of images captured by a camera and image processing. Figure 7 This is a flowchart illustrating the operation of the X-ray imaging device 1. Figures 8-10 This is a diagram showing an example of the results of a body movement test.

[0053] like Figure 1As shown in (a), the X-ray imaging apparatus 1 includes a top plate 80 for mounting a subject 10 and an X-ray irradiation device 11 for irradiating the subject 10 with X-rays. The X-ray irradiation device 11 supports the bracket 70 via an X-ray support 50. The bracket 70 includes: an X-ray vertical movement mechanism 60 for moving the X-ray support 50 vertically; a long-side movement mechanism (not shown) for moving the X-ray support 50 along the long side direction 50a of the top plate 80; a short-side movement mechanism (not shown) for moving the X-ray support 50 along the short side direction 50b of the top plate 80; and an X-ray tilting mechanism 61 for tilting (50c) the central axis of the X-ray support 50 about the short side direction of the top plate. Furthermore, the X-ray support 50 includes an X-ray rotation mechanism (not shown) for rotating the X-ray irradiation device 11 about the long side direction of the top plate. The X-ray support 50 is equipped with a pressing tool 62 for pressing the abdomen of the subject 10 during imaging.

[0054] On the other hand, the top plate 80 supports the bracket 70 through the top plate support part 81.

[0055] An X-ray detector 12 is disposed inside the top plate support portion 81. The X-ray detector 12 is a planar detector with X-ray detection elements arranged in two dimensions. The X-ray detector 12 detects X-rays that have been irradiated and transmitted from the X-ray irradiation device 11 to the subject 10.

[0056] The X-ray support 50 or the X-ray irradiation apparatus 11 includes a camera 21 for photographing the subject 10. The camera 21 is positioned so as not to block the X-rays emitted from the X-ray irradiation apparatus 11. Figure 1 (b) Figure 1 As shown in (c), the viewing angle of camera 21 is set to capture the entire body of the subject 10 on the top plate 80. Alternatively, camera 21 can also be fixed to the housing (frame) of the X-ray irradiation device 11.

[0057] When the X-ray support 50 moves along the long side direction 50a of the top plate 80, the viewing angle of the camera 21 is as follows: Figure 1 As shown in (b), with the movement of the X-ray support 50 along the short side direction 50b of the top plate 80, the viewing angle of the camera 21 is as follows: Figure 1 (c) shows the movement that accompanies it.

[0058] like Figure 2As shown, an X-ray image generation unit 13 is connected to the X-ray detector 12. The X-ray image generation unit 13 receives signals from the X-rays detected and output by each X-ray detection element of the X-ray detector 12, and generates an X-ray image (here, a fluoroscopic image) at a predetermined frame rate. A fluoroscopic image display monitor 14 is connected to the X-ray image generation unit 13. The fluoroscopic image is displayed on the fluoroscopic image display monitor 14.

[0059] On the other hand, a motion detection unit 20 is connected to the camera 21. The motion detection unit 20 receives images from the camera 21 and processes them. Specifically, the motion detection unit 20 receives images from the camera 21 and detects the skeletons of all human figures included in the received images. Based on the detected skeletons, the motion detection unit 20 calculates pre-set feature values ​​and extracts the image of the subject 10 mounted on the top plate 80 from among the multiple human figures. The motion detection unit 20 displays the extracted image of the subject 10 on the connected camera image display monitor 15.

[0060] To explain in further detail, the motion detection unit 20 includes an image reading unit 22, an image rotation unit 23, a skeleton detection unit 24, a subject skeleton extraction unit 25, a region of interest setting unit 26, an optical flow calculation unit 27, a shadow detection unit 201, and a determination unit 28. Furthermore, the region of interest setting unit 26 includes a region of interest selection unit 126.

[0061] The image reading unit 22 reads the image 21a output by the camera 21 at preset time intervals. The preset time interval can be set to be the same as the frame rate of the fluoroscopic image generated by the X-ray image generation unit 13. Figure 1 (b) Figure 1 As shown in (c), the image 21a output by camera 21 is an image taken with the body axis of the subject on top plate 80 as the horizontal axis of the image.

[0062] Image rotation unit 23 rotates image 21a 90 degrees in a preset direction, such as Figure 4 As shown, the head of the subject 10 on the top plate 80 is positioned above the image 21a. Since the position of the head of the subject 10 on the end of the top plate 80 along its length is predetermined, the direction of rotation of the image 21a is predetermined based on the predetermined head position on the top plate 80 and the direction of the camera 21.

[0063] And, as Figure 3 As shown, an endoscope is positioned near the ceiling 80 of the examination room. To insert the endoscope into the patient 10 and perform surgery, medical personnel such as doctors or nurses stand or sit in chairs around the ceiling 80. Therefore, as... Figure 1 (b) Figure 1 As shown in (c), in image 21a taken by camera 21, in addition to the subject 10, medical personnel are also reflected.

[0064] like Figure 4 As shown, the skeleton detection unit 24 extracts feature points (both ears, nose, eyes, shoulders, elbows, wrists, waist, knees, ankles, etc.) of the skeletons of all human figures mapped into image 21a. The skeleton detection unit 24 detects the skeletons of all human figures by detecting these two-dimensional coordinates. The skeleton detection unit 24 can be implemented using a known pose detection algorithm. For example, the pose estimation algorithm OpenPose (registered trademark) included in OpenVINO (registered trademark) provided by Intel Corp. can be used.

[0065] The subject skeleton extraction unit 25 uses the feature points of all the human figures' skeletons detected by the skeleton detection unit 24 to calculate the preset feature quantity, and extracts the skeleton of the subject 10 mounted on the top plate based on the calculated feature quantity.

[0066] For example, the subject skeleton extraction unit 25 will select the shoulder and ear skeletons from all the detected human skeletons and set them as subject candidates. Figure 4 As shown, the subject skeleton extraction unit 25 determines the midpoint 41 of the line connecting the shoulders of each subject candidate for each subject candidate, and calculates the distance between the determined midpoint 41 of the shoulders and the center 45 of the image 21a. The subject candidate with the shortest distance between the midpoint 41 of the shoulders and the center 45 of the image 21a is determined as subject 10.

[0067] Furthermore, if there are two or more candidate subjects whose distances from the midpoint 41 of the shoulders to the center 45 of the image 21a are equal, the subject skeleton extraction unit 25 also calculates the angle θ between the line connecting the candidate subjects' shoulders and the horizontal direction of the image 21a (parallel to the short side direction of the top plate 80) as a feature quantity, and determines the candidate subjects 10 whose angle θ of the line connecting the shoulders is close to zero, that is, close to the horizontal direction of the image 21a.

[0068] Furthermore, if the distance between the midpoint 41 of the shoulders of the skeleton of the subject 10 and the center 45 of the image 21a differs from the average distance between the midpoint 41 of the shoulders of the subject 10 and the center 45 of the image 21a in the multiple images 21a captured by the camera 21 after the start of the perspective image capture by the camera 21 by a predetermined value, the subject skeleton extraction unit 25 may determine that the subject 10 does not exist.

[0069] like Figure 5As shown, the region of interest setting unit 26 sets multiple regions of interest 52 on the image of the subject 10 based on the position of the skeleton of the subject 10 extracted by the skeleton detection unit 24.

[0070] On the other hand, the optical flow calculation unit 27 calculates the amount of movement (optical flow) of the corresponding pixel by performing calculations on a pixel-by-pixel basis between the most recent image 21a and an image 21a acquired by the camera 21 at a time that is only a preset time earlier than the time at which the image 21a was acquired. Figure 6 (a)). The optical flow is calculated using well-known methods such as the Farneback method.

[0071] For example, the optical flow calculation unit 27 calculates the amount of movement (optical flow) of the corresponding pixels between the most recently acquired image 21a and the image 21a acquired at a time that is only a predetermined time earlier than its acquisition time by performing calculations on a per-pixel basis.

[0072] The shadow detection unit 201 detects moving shadows included in the most recent image 21a. Figure 6 (b)). For example, moving shadows within image 21a are detected using foreground / background region segmentation based on a mixed normal distribution. For example, "BackgroundSubtractorMOG2" is used as a foreground / background region segmentation algorithm.

[0073] like Figure 3 As shown, during the surgery, there are many medical personnel around the patient 10, who operate endoscopes or move the endoscopes themselves. Therefore, the image 21a sometimes includes shadows that move with the movement of the medical personnel, causing the optical flow calculation unit 27 to misdetect the optical flow of the moving shadows as the movement of the patient 10.

[0074] Therefore, in this embodiment, the shadow detection unit 201 detects moving shadows. The region of interest selection unit 126 removes the region of interest 52 containing shadows above a threshold from the plurality of regions of interest 52 set by the region of interest setting unit 26 from the motion determination of the subject 10.

[0075] The determination unit 28 calculates the number of interest regions with optical flow greater than a predetermined value for the interest regions 52 remaining in the image 21a after the interest region selection unit 126 is removed, and determines whether the subject 10 has body movement based on whether the number is greater than a threshold (e.g., 3).

[0076] A notification unit 29 is connected to the motion detection unit 20. When the determination unit 28 determines that a motion has occurred, the notification unit 29 notifies the user of this intention. For example, the notification unit 29 displays a pre-set notification dialog box 161 (see reference) on the display screen of the connected camera image display monitor 15 to notify the user of the motion occurrence. Figure 8 Furthermore, the notification unit 29 can display the amount of movement calculated by the optical flow calculation unit 27 in numerical or graphical form on the display screen of the camera image display monitor 15 (see reference). Figure 9 Alternatively, both can be displayed (see reference). Figure 8 ).

[0077] And, as Figure 10 of (a) Figure 10 As shown in (b), the notification unit 29 can be configured to notify the structure of physical movement by changing the color of the edge of the image 21a displayed on the camera image display monitor 15. For example, the notification unit 29 displays a green line at the edge of the image 21a when there is no physical movement, and a red line at the edge of the image 21a when there is physical movement.

[0078] The monitor that displays the notification is not limited to the camera image display monitor 15, but may also be the fluoroscopic image display monitor 14 or the endoscope image display monitor 16.

[0079] Furthermore, the notification unit 29 can notify the occurrence of physical movement through alarm sounds or lights.

[0080] The following uses Figure 7 The process describes the operation of each part of the motion detection unit 20.

[0081] Furthermore, the functions of each part (22-26) of the motion detection unit 20 can be implemented through software. In this case, the motion detection unit 20 is constructed from a computer equipped with a processor such as a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), and memory. The CPU reads and executes the program stored in memory, thereby implementing these functions. Alternatively, part or all of the motion detection unit 20 can be constructed from hardware. For example, custom ICs such as ASICs (Application Specific Integrated Circuits) or programmable ICs such as FPGAs (Field-Programmable Gate Arrays) can be used to design circuits to implement the functions of each part.

[0082] (Step S101)

[0083] The image reading unit 22 reads images 21a from the camera 21 at predetermined time intervals. The timing for the image reading unit 22 to start reading images can be a timing that receives a start instruction from the operator, or a timing that starts displaying the endoscope image on the endoscope image display monitor 16.

[0084] (Step S102)

[0085] The image rotation unit 23 rotates the image 21a by 90 degrees in a predetermined direction. As a result, the end of the head of the predetermined subject 10 mounted on the top plate 80 is positioned on the upper part of the image 21a.

[0086] (Step S103)

[0087] The skeleton detection unit 24 extracts feature points (both ears, nose, eyes, shoulders, elbows, wrists, waist, knees, ankles, etc.) of the skeletons of all human figures mapped into image 21a, and detects their two-dimensional coordinates (see reference). Figure 4 Therefore, the skeletons of all the characters were extracted.

[0088] (Step S104)

[0089] In step S103, if the skeleton cannot be detected, return to step S101 and read the next image 21a. If the skeleton can be detected, proceed to step S105.

[0090] (Step S105)

[0091] The subject skeleton extraction unit 25 uses the position coordinates of the feature points of all human figures detected by the skeleton detection unit 24 to calculate the preset feature quantity, and extracts the skeleton of the subject 10 mounted on the top plate based on the calculated feature quantity.

[0092] Furthermore, in the subject skeleton extraction section 25, the human figures other than the extracted subject 10 are the medical personnel around the top plate 80. Therefore, subject 10 is distinguished, and only the human figures of subject 10 are extracted, such as... Figure 1 (b) Figure 1 (c) is shown on the camera image display monitor 15.

[0093] (Step S106)

[0094] The attention area setting unit 26, based on the location of characteristic points of the skeleton of the subject 10, such as... Figure 5 As shown, a region of interest 52 is set locally based on the position of a pre-defined feature point in the skeletal feature point of the subject 10.

[0095] Specifically, the attention area setting unit 26 sets attention areas 52 of a predetermined size centered on the skeletal feature points of the subject 10 detected by the skeleton detection unit 24 at the shoulders, elbows, wrists, waist, knees and ankles.

[0096] Furthermore, the attention area setting unit 26 determines the position of the subject 10's head and sets an attention area 52 of a predetermined size for the head position. For example, the attention area is set such that a portion of the outline of the back of the subject 10's head is located inside the attention area 52. The method for determining the head position can be any method. For example, the attention area setting unit 26 determines the coordinates of the ear on the side of the subject 10's ears detected by the skeleton detection unit 24, which is close to the center of the subject 10's body in the y-axis direction (the direction of the long side of the top plate 80) and parallel to the x-axis direction (the direction of the short side of the top plate 80). The attention area setting unit 26 also determines a line passing through the midpoint of the line connecting the two shoulders and parallel to the y-axis direction. The attention area setting unit 26 can set the intersection of the two determined lines as the head position 77.

[0097] The size of the attention area 52 is set to the same predefined size. For example, it is set to a size slightly larger than the arm of a 170cm adult male, or it is predefined to not overlap with the surgeon's hand.

[0098] (Step S107)

[0099] The optical flow calculation unit 27 calculates the amount of movement (optical flow) of the corresponding pixels between the image 21a rotated in step S102 and the image 21a acquired and rotated at a time predetermined time earlier than the acquisition timing by performing calculations on a pixel-by-pixel basis (reference). Figure 6 (a)). Image 21a used to calculate the movement is the entire image including all human figures, rather than just an image of the human figures extracted from subject 10.

[0100] (Step S108)

[0101] The determination unit 28 determines whether optical flow is detected in the area surrounding the skeleton of the subject extracted in step S107. If optical flow is detected in the area surrounding the skeleton of the subject, the process proceeds to step S109. If no optical flow is detected in the area surrounding the skeleton of the subject, the process returns to step S101.

[0102] (Step S109)

[0103] The shadow detection unit 201 detects the moving shadow area included in image 21a. Figure 6 (b)). Use the same image used to calculate the optical flow in step S107.

[0104] (Step S110)

[0105] The attention region selection unit 126 determines whether there is an attention region 52 where the number of pixels in the shadow region detected in step S109 is at or above a preset threshold. If there is an attention region 52 where the number of pixels in the shadow region is at or above the preset threshold, the process proceeds to step S111. If there is no such attention region 52, the process proceeds to step S112.

[0106] (Step S111)

[0107] The region of interest selection unit 126 removes pixels from the region of interest 52 that are identified as shadows in step S110 at a proportion exceeding a preset threshold. (Reference) Figure 6 (c)).

[0108] (Step S112)

[0109] The determination unit 28 determines the region of interest where the number of pixels whose pixel movement exceeds a threshold is greater than a predetermined value (e.g., 20% of the number of pixels in one region of interest 52) ​​for the region of interest 52 retained after the processing in step S111.

[0110] Furthermore, the determination unit 28 calculates the number of interest areas whose movement exceeds a predetermined value. If this number exceeds a preset value (e.g., 3), the optical flow of the interest area 52 exceeds a threshold, thus determining that the subject 10 has experienced body movement, and proceeding to step S113. If the number of interest areas whose movement exceeds the predetermined value is below the threshold, no body movement occurs, and therefore proceeding to step S114.

[0111] (Step S113)

[0112] If the determination unit 28 determines that a body movement has occurred in step S112, the notification unit 29 notifies the user that a body movement has occurred.

[0113] Specifically, such as Figure 8 As shown, the notification unit 29 displays a pre-set notification dialog box 161 to the camera image display monitor 15 and notifies that physical movement has occurred. Alternatively, as... Figure 9 As shown, the notification unit 29 displays the amount of movement calculated by the optical flow calculation unit 27 in numerical value or graph 162, and notifies that body movement exists. Alternatively, the notification unit 29 displays both a notification dialog box 161 and graph 162. Furthermore, as... Figure 10 As shown, the notification unit 29 can notify of the presence of motion by changing the color of the edge of the image 21a displayed on the camera image display monitor 15.

[0114] Furthermore, the notification unit 29 can issue an alarm via sound or light when there is physical movement.

[0115] (Steps S115, S116)

[0116] The notification unit 29 determines whether a predetermined time (e.g., 10 seconds) has elapsed since the start of the physical notification in step S113 (step S115). If the predetermined time has elapsed, it proceeds to step S116 to stop the notification and returns to step S101.

[0117] On the other hand, in step S115, if no prescribed time has elapsed since the start of the physical movement notification, the notification is not stopped and the process returns to step S101.

[0118] (Step S114)

[0119] On the other hand, if the determination in step S110 is "no", and if the determination in step S112 is also "no", proceed to step S114 to determine whether a physical activity notification is in progress. If a physical activity notification is in progress, proceed to step S115. On the other hand, if it is not a physical activity notification period, return to step S101.

[0120] Thus, by performing steps S114 to S116, it is possible to continuously provide physical movement notifications for a specified time (e.g., 10 seconds).

[0121] As described above, according to Embodiment 1, it is possible to extract and display an image of the subject 10, and after removing the light flow of shadows from the movement of medical personnel or others included in the image, determine whether the subject 10 has physical movement and notify the user.

[0122] Therefore, according to Embodiment 1, it is possible to avoid misjudgment of body movement caused by moving shadows.

[0123] Therefore, the X-ray imaging device of this embodiment can detect the body movement of the subject during the capture of fluoroscopic images with high precision, so that doctors can easily grasp the patient's body movement even during surgery.

[0124] <<Implementation Method 2>>

[0125] In embodiments 2-1, 2-2, and 2-3, in order to prevent ineffective exposure of the subject 10, the X-ray irradiation device 11 is surrounded by, for example... Figure 11 of (a) Figure 11 In the case shown in (b) where the protective curtain 210 is installed, since the image of the protective curtain 210 is included in the image of the camera 21, the skeleton detection unit 24 may sometimes falsely detect the joints of the skeleton of the subject 10. For example, in Figure 11In example (a), the joint position of the arm of medical personnel 220 was mistakenly detected, and the area of ​​interest 52a was set.

[0126] Therefore, in embodiments 2-1, 2-2, and 2-3, a designated unit is provided to receive from the operator whether a protective curtain has been used, or a detection unit is provided to detect the protective curtain. The area of ​​interest selection unit 126 excludes the designated area of ​​interest 52a from the area of ​​interest 52 used to determine body movement. Figure 11 (b)). The following is a detailed explanation.

[0127] <Implementation Method 2-1>

[0128] like Figure 12 As shown, in the X-ray imaging device 1 of embodiment 2-1, a button 202 with a protective curtain is provided as a designated part for receiving instructions from the operator on whether to use the protective curtain.

[0129] (Steps S101 to S108)

[0130] like Figure 13 As shown, steps S101 to S108 are performed in the same manner as in Embodiment 1.

[0131] (Step S120)

[0132] Next, the attention area selection unit 126 proceeds to step S120. In step S120, it is determined whether the operator has turned on the button 202 with the protective curtain. If the button 202 with the protective curtain is turned on, the attention area selection unit 126 proceeds to step S121.

[0133] If button 202 with the protective curtain is closed, proceed to step S112.

[0134] (Step S121)

[0135] In step S121, the attention area selection unit 126 retains only the preset attention areas (here, the attention areas of the head and shoulders) in the attention area 52 set by the attention area setting unit 26 in step S106, and excludes other attention areas 52a from the attention areas.

[0136] (Step S112)

[0137] The determination unit 28 proceeds to step S112, using only the area of ​​interest (here, the area of ​​interest for the head and shoulders) 52 retained in step S121, and similarly to embodiment 1, determines whether body movement has occurred by determining whether the optical flow exceeds the threshold.

[0138] (Steps S113 to S116)

[0139] Similar to Implementation 1, notification is given that body movement has occurred.

[0140] Therefore, as Figure 14 As shown in (b), when the protective curtain button 202 is turned on, it is possible to eliminate the area of ​​interest that is mistakenly set on the joint position of the medical personnel 220, and to determine the occurrence of body movement using only the area of ​​interest 52 of the head and shoulders of the subject 10, thereby avoiding the misjudgment of the occurrence of body movement.

[0141] On the other hand, such as Figure 14 As shown in (a), when the button 202 with the protective curtain is closed, in step S121, the determination unit 28 uses all areas of interest 52 to determine that body movement has occurred. Therefore, body movement determination of the subject 10 can be performed with high accuracy.

[0142] <Implementation Method 2-2>

[0143] like Figure 15 As shown, the X-ray imaging device 1 of Embodiment 2-2 includes a protective curtain detection unit 203 for detecting whether a protective curtain 210 is installed in the X-ray irradiation device 11.

[0144] For example, a recessed area is provided around the X-ray irradiation device 11 for hooking the protective curtain 210. The protective curtain detection unit 203 is a pressure sensor provided at the location of the recessed area. When the protective curtain detection unit 203 detects the weight of the protective curtain 210 as pressure, the protective curtain 210 is installed on the X-ray irradiation device 11.

[0145] like Figure 16 The process is shown in the figure. In embodiment 2-2, the X-ray imaging device 1 performs step S130 instead of step S120 in embodiment 2-1.

[0146] (Step S130)

[0147] In step S130, the area of ​​interest selection unit 126 determines whether the protective curtain detection unit 203 detects that the protective curtain 210 is suspended on the X-ray irradiation device 11. If the protective curtain 210 is suspended, the area of ​​interest selection unit 126 proceeds to step S121, retaining only the pre-set area of ​​interest (here, the area of ​​interest for the head and shoulders), and excluding other areas of interest 52a from the area of ​​interest.

[0148] On the other hand, if the protective curtain 210 is not detected, the attention area selection unit 126 proceeds to step S112.

[0149] Other structures and operations are the same as in implementation method 2-1, so the description is omitted.

[0150] <Implementation Method 2-3>

[0151] In the case of X-ray fluoroscopy, in addition to installing a protective curtain 210 on the X-ray irradiation device 11, sometimes a blanket is also placed on the subject 10.

[0152] Therefore, as Figure 17 As shown, in embodiments 2-3, a selection button 204 for the area of ​​interest that is not covered by a protective curtain or blanket, which is the area of ​​interest used for motion determination, is provided on the X-ray imaging device 1.

[0153] Specifically, such as Figure 18 of (a) Figure 18 (b) Figure 18 As shown in (c), for example, the focus area selection button 204 includes: a button 204a for selecting the focus area 52 of the whole body of the subject 10; a button 204b for selecting only the focus area 52 of the upper body when the lower body of the subject 10 is covered by a blanket; and a button 204c for selecting only the focus area 52 of the head and shoulders, as in the case of using a protective curtain 210.

[0154] like Figure 19 The process is shown in the figure. In embodiment 2-3, the X-ray imaging device 1 performs steps S140 and S141 instead of steps S130 and S121 in embodiment 2-2.

[0155] (Step S140)

[0156] In step S140, the attention area selection unit 126 determines which button of the attention area range selection button 204 is turned on.

[0157] (Step S141)

[0158] In step S140, the attention area selection unit 126 selects the button 204 according to the activated attention area range and excludes unselected attention areas.

[0159] Other structures and operations are the same as in implementation method 2-2, therefore, the description is omitted.

[0160] In embodiments 2-3, by pre-setting multiple desired areas of interest selection buttons 204, it is possible to set the selection range of multiple areas of interest, such as when using a blanket.

[0161] <<Implementation Method 3>>

[0162] During X-ray fluoroscopy, if the subject 10 moves, medical personnel may sometimes hold the subject's body down to prevent further movement. In such cases, the image captured by camera 21 may sometimes show the subject's image (skeleton) close to or overlapping with the medical personnel's image (skeleton). In this situation, the determination unit 28 may misinterpret the medical personnel's movement as the subject's body movement.

[0163] In embodiments 3-1, 3-2, and 3-3, when the image of the subject 10 overlaps with the image of the medical personnel in the image, the region of interest selection unit 126 excludes all regions of interest 52 and does not use them for determining body movement.

[0164] <Implementation Method 3-1>

[0165] like Figure 20 As shown, in embodiment 3-1, a large second region of interest 152 is set to surround the subject 10. If the skeleton other than the subject 10 enters the second region of interest 152, the image is excluded from the determination of body movement.

[0166] like Figure 21 The process is shown in the figure. In Embodiment 3-1, the X-ray imaging device 1 performs steps S150 and S151 instead of steps S109 to S111 in Embodiment 1.

[0167] (Steps S101 to S108)

[0168] Steps S101 to S108 are performed in the same manner as in Embodiment 1. In step S106, the region of interest setting unit 26 sets a region of interest 52 at feature points such as joints of the subject 10.

[0169] (Step S150)

[0170] In step S150, the area of ​​interest setting unit 26 sets a large second area of ​​interest 152 surrounding the subject 10.

[0171] Specifically, in step S105, the region of interest setting unit 26 determines the coordinates of the left, right, top, and bottom ends of a rectangular region including the subject 10 based on the calculated coordinates of the feature points of the subject 10, and sets the second region of interest 152. For example, in step S102, when the horizontal direction of the rotated image 21a is taken as the x-axis and the vertical direction as the y-axis, among the feature points (both ears, nose, eyes, shoulders, elbows, wrists, waist, knees, and ankles), the coordinates of the feature point located at the leftmost point in the x-axis direction are defined as the left end of the region by a distance (e.g., 30 pixels) from the coordinates of the feature point located at the rightmost point in the x-axis direction by a distance (e.g., 30 pixels) from the coordinates of the feature point located at the rightmost point in the x-axis direction by a distance (e.g., 30 pixels) from the coordinates of the feature point located at the bottommost point in the y ... Furthermore, when the y-coordinate of the lower ear (located on the y-axis) is set to Ye, and the y-coordinate of the upper shoulder (located on the y-axis) is set to Ys, the position of Ye-(Ys-Ye) is taken as the upper end of the region. Thus, a large second region of interest 152 surrounding the subject 10 can be defined.

[0172] (Step S151)

[0173] In step S151, the region of interest selection unit 126 determines whether the skeleton detected in step S103, excluding the skeleton of the subject 10 extracted in step S105, is located inside the second region of interest 152. If the skeleton other than the subject 10's skeleton is located inside the second region of interest 152, the region of interest selection unit 126 excludes all regions of interest 52 and returns to step S101. Therefore, the determination unit 28 does not use this image for motion determination.

[0174] On the other hand, if the skeleton other than the skeleton of the subject 10 does not enter the inner side of the second area of ​​interest 152, the area of ​​interest selection unit 126 proceeds to step S112. The determination unit 28 uses all areas of interest 52 to determine whether body movement has occurred.

[0175] Since other structures and operations are the same as in Implementation Method 1, the description is omitted.

[0176] <Implementation Method 3-2>

[0177] In embodiment 3-1, the region of interest selection unit 126 is structured such that when the skeleton other than the subject 10 is located in the second region of interest 152, all regions of interest 52 are excluded, and their images are not used for motion determination. However, as... Figure 22As shown in (a), in embodiment 3-1, the skeleton other than the subject 10 is located in the second region of interest 152, but even if the skeleton other than the subject 10 does not overlap with the subject 10, its image is not used for body movement determination.

[0178] Therefore, as Figure 22 As shown in (b), in embodiment 3-2, when the skeleton line connecting the joints of the subject 10 intersects with skeleton lines other than the subject 10, the region of interest selection unit 126 excludes all regions of interest 52 and does not use their images for body movement determination.

[0179] like Figure 23 The process is shown in the figure. In embodiment 3-2, the X-ray imaging device 1 performs steps S160 and S161 instead of steps S150 and S151 in embodiment 3-1.

[0180] (Steps S101 to S108)

[0181] Steps S101 to S108 are performed in the same manner as in Embodiment 1. In step S103, all skeletons are inspected, and in step S105, the skeleton of the subject 10 is extracted.

[0182] (Step S160)

[0183] In step S160, the region of interest selection unit 126 calculates all skeletal lines of the subject 10 and all skeletal lines of the subject 10, based on the joint positions of the subject and the skeleton other than the subject calculated in step S103.

[0184] (Step S161)

[0185] In step S161, the region of interest selection unit 126 determines whether there is an intersection between the skeleton line of the subject 10 and the skeleton lines other than the subject 10.

[0186] like Figure 22 As shown in (b), when the skeleton line of the subject 10 intersects with the skeleton line outside the subject 10, the area of ​​interest selection unit 126 excludes all areas of interest 52, returns to step S101, and does not use the image for body motion determination.

[0187] On the other hand, if the skeletal lines of the subject 10 do not intersect with skeletal lines other than those of the subject 10, the region of interest selection unit 126 proceeds to step S112. The determination unit 28 uses the region of interest 52 to determine whether body movement has occurred.

[0188] Other structures and operations are the same as in implementation method 3-1, therefore, the description is omitted.

[0189] <Implementation Method 3-3>

[0190] In embodiments 3-1 and 3-2, when the skeleton other than the subject 10 is located in the second region of interest 152 or when the skeleton of the subject 10 intersects with the skeleton other than the subject 10, the region of interest selection unit 126 excludes all regions of interest 52 and does not use the entire image for motion determination. Therefore, it is impossible to utilize the detection results of the optical flow of the region of interest of the subject 10 that does not overlap with the skeleton other than the subject 10.

[0191] Therefore, as Figure 24 As shown in Embodiment 3-3, when the skeleton line other than the subject 10 passes through the region of interest 52, the region of interest selection unit 126 excludes only the region of interest 52 from the determination of body movement.

[0192] like Figure 25 The process is shown in the figure. In embodiment 3-3, the X-ray imaging device 1 performs steps S170 to S172 instead of steps S160 and S161 in embodiment 3-2.

[0193] (Steps S101 to S108)

[0194] Steps S101 to S108 are performed in the same manner as in Embodiment 1. In step S103, all skeletons are detected, and in step S105, the skeleton of the subject 10 is extracted. Furthermore, in step S106, regions of interest 52 are set at feature points such as joints of the subject 10.

[0195] (Step S170)

[0196] In step S170, the region of interest selection unit 126 calculates all skeletal lines except for the subject 10 based on the joint positions of the subject and the skeleton other than the subject calculated in step S103.

[0197] (Step S171)

[0198] In step S171, the region of interest selection unit 126 determines whether the skeleton line other than the subject 10 passes through the region of interest 52 of the subject 10. If the skeleton line other than the subject 10 passes through the region of interest 52, the region of interest selection unit 126 proceeds to step S172. If it does not pass through, it proceeds to step S112.

[0199] (Step S172)

[0200] In step S172, the area of ​​interest selection unit 126 excludes the area of ​​interest 52 through which the skeleton line passes, except for the subject 10, and proceeds to step S112.

[0201] In step S112, the determination unit 28 uses the optical flow of the region of interest that was not excluded but retained to determine whether the subject 10 has physical movement.

[0202] Therefore, the detection results of the optical flow in the region of interest 52 of the subject 10, which does not overlap with the skeleton other than the subject 10, can be utilized.

[0203] Other structures and operations are the same as in implementation method 3-1, therefore, the description is omitted.

[0204] <<Implementation Method 4>>

[0205] In embodiments 2 and 3, the configuration is as follows: when the protective curtain 210 is suspended on the X-ray irradiation device 11, the focus area 52 of the head and shoulders of the subject 10 is used. However, as Figure 26 As shown in (a), if the protective curtain 210 covers the shoulder of the subject 10, the skeleton detection unit 24 cannot extract the skeleton of the subject 10, and the area of ​​interest 52 cannot be set for the head that is not covered by the protective curtain 210. Therefore, the determination unit 28 cannot detect body movement.

[0206] Therefore, as Figure 27 As shown, the X-ray imaging apparatus 1 of Embodiment 4 includes a region of interest storage unit 180. The region of interest selection unit 126 stores the positions of the regions of interest 52 set by the region of interest setting unit 26 in the region of interest storage unit 180 for each image. When the shoulder of the subject 10 is covered by a protective curtain 210 or the like, preventing the setting of the region of interest 52, the region of interest selection unit 126 instructs the region of interest setting unit 26 to read the position of the region of interest set for the previous image and set the region of interest 52 at the same position in the current image. Figure 26 (b)

[0207] like Figure 28 The flowchart shows that the X-ray imaging device 1 of Embodiment 4 does not execute steps S109 to S111 of Embodiment 1. If the skeleton cannot be detected in step S104, in steps S191 and S192, the area of ​​interest 52 is set at the previously saved position.

[0208] (Steps S101 to S103, S105)

[0209] Steps S101 to S103 and S105 are performed in the same manner as in Embodiment 1. In step S103, the skeleton detection unit 24 detects all skeletons and proceeds to step S105, where the subject skeleton extraction unit 25 extracts the skeleton of the subject 10.

[0210] (Steps S190, S106)

[0211] In step S190, the subject skeleton extraction unit 25 determines whether the subject skeleton can be extracted. If it can be extracted, the process proceeds to step S106, where the attention area setting unit 26 sets the attention area for feature points such as joints.

[0212] (Step S193)

[0213] The attention area selection unit 126 proceeds to step S193, where the position of the attention area 52 set in step S106 is stored in the attention area storage unit 180.

[0214] (Step S191)

[0215] On the other hand, in step S190, if it is determined that the skeleton detection unit 24 cannot detect a skeleton, the process proceeds to step S191, whereby the skeleton detection unit 24 notifies the operator that a skeleton cannot be detected. For example, since no skeleton is detected in the camera image display monitor 15, it is displayed that the area of ​​interest 52 cannot be set. Furthermore, it is also displayed that the area of ​​interest 52 can be set in the same way as the previous image.

[0216] (Step S192)

[0217] In step S192, the attention area selection unit 126 reads the setting position of the attention area 52 of the previous image stored in the attention area storage unit 180, and instructs the attention area setting unit 26 to set the attention area 52 at the same position in the current image. The attention area setting unit 26 sets the attention area 52 at the same position as the previous image.

[0218] (Steps S107, S108, S112 to S116)

[0219] Proceed to step S107, where the optical flow calculation unit 27 calculates the optical flow for this image.

[0220] The determination unit 28 proceeds to step S108, which determines whether the optical flow exceeds the threshold and whether there is body movement regarding the area of ​​interest set in the current image in step S106 or S192.

[0221] Steps S113 to S116 are the same as in Embodiment 1, so the description is omitted.

[0222] According to embodiment 4, the protective curtain 210 covers the shoulders of the subject 10. Even if the skeleton detection unit 24 cannot extract the skeleton of the subject 10, a focus area 52 can be set for the head and other parts not covered by the protective curtain 210, so body movement can be detected.

Claims

1. An X-ray imaging device, characterized in that, have: Top plate, carrying the test subject; An X-ray irradiation device is used to irradiate the subject with X-rays. An X-ray detector detects X-rays that have been irradiated by the X-ray irradiation device and transmitted through the subject. and The body movement detection unit receives images from a camera that captures images of the subject, processes the images, and detects the occurrence of body movements in the subject. The motion detection unit includes a skeleton detection unit, an optical flow calculation unit, a region of interest setting unit, and a determination unit. The skeleton detection unit detects the skeleton of the human figure included in the image, and extracts the skeleton of the subject mounted on the top plate based on the detected skeleton. The optical flow calculation unit calculates the corresponding pixel movement between the image and an image acquired by the camera at a time that is only a preset time earlier than the time at which the image was acquired. The region of interest setting unit sets multiple regions of interest on the image of the subject based on the position of the subject's skeleton extracted by the skeleton detection unit. The determination unit determines whether the subject has undergone body movement based on the amount of movement of the pixels of the subject within the region of interest. The region of interest setting unit includes a region of interest selection unit. The attention area selection unit selects one or more attention areas from the plurality of attention areas set by the attention area setting unit for the determination unit to determine body movement, or designates the position of the attention area for the determination unit to determine body movement as the attention area setting unit.

2. The X-ray imaging device according to claim 1, characterized in that, The motion detection unit includes a shadow detection unit. The shadow detection unit detects pixels of moving shadows included in the image. The attention region selection unit removes attention regions from the plurality of attention regions set by the attention region setting unit, where the number of pixels including the shadow is above a predetermined value. The determination unit determines whether body movement has occurred in the subject based on the amount of movement of the pixels of the subject in the region of interest that are retained after being removed by the region of interest selection unit.

3. The X-ray imaging device according to claim 1, characterized in that, The motion detection unit includes a protective curtain designation / detection unit. The protective curtain designation / detection unit receives from the operator a designation of the presence or absence of a protective curtain or the area of ​​interest used for motion detection, or performs a detection of the presence or absence of the protective curtain. The area of ​​interest selection unit removes a specified area of ​​interest from the plurality of areas of interest set by the area of ​​interest setting unit based on the result or detection result received by the protective curtain designation / detection unit. The determination unit determines whether the subject has undergone body movement based on the amount of movement of the pixels of the subject in the region of interest retained after being removed by the region of interest selection unit.

4. The X-ray imaging device according to claim 3, characterized in that, The protective curtain designation / detection unit is a button that receives the presence or absence of the protective curtain or a button that allows selection of various ranges of interest areas for motion detection.

5. The X-ray imaging device according to claim 3, characterized in that, The designated / detection unit of the protective curtain is a sensor installed at the installation location of the protective curtain of the X-ray irradiation device.

6. The X-ray imaging apparatus according to claim 1, wherein, The region of interest selection unit determines whether, in the image, a skeleton other than the subject is close to or intersects with the skeleton of the subject. If a skeleton other than the subject is close to or intersects with the subject, it removes part or all of the plurality of regions of interest set by the region of interest setting unit. The determination unit determines whether the subject has undergone body movement based on the amount of movement of the pixels of the subject in the area of ​​interest retained after removal by the area of ​​interest selection unit.

7. The X-ray imaging apparatus according to claim 6, wherein, The region of interest setting unit also sets a second region of interest that surrounds the entire subject. If the region of interest selection unit includes a skeleton other than the subject in the second region of interest, it removes all regions of interest. The determination unit determines whether body movement has occurred in the image.

8. The X-ray imaging device according to claim 6, characterized in that, The region of interest selection unit determines whether there are any intersections between the skeletal lines of the subject and the skeletal lines of the subject, other than the subject itself. If there are intersections, all regions of interest are removed. The determination unit determines whether body movement has occurred in the image.

9. The X-ray imaging apparatus according to claim 6, wherein, The region of interest selection unit determines whether the skeleton line other than the subject has passed through the region of interest of the subject. If it has, the region of interest through which the skeleton line other than the subject has passed is removed from the plurality of regions of interest set by the region of interest setting unit. The determination unit uses the retained region of interest to determine the occurrence of body movement.

10. The X-ray imaging device according to claim 1, characterized in that, The motion detection unit includes a storage unit. The region of interest selection unit stores the location of the set region of interest in the storage unit. If the skeleton detection unit cannot detect a skeleton in the image, the region of interest selection unit instructs the region of interest setting unit to set the region of interest at the location of the region of interest stored in the storage unit for a previous image. The region of interest setting unit then sets the region of interest at the location read from the storage unit. The determination unit uses the region of interest set at the location read from the storage unit to determine the occurrence of body movement.

11. An image processing method for an X-ray imaging apparatus equipped with a camera, comprising processing an image captured by the camera of the X-ray imaging apparatus equipped with a camera, characterized in that the image processing method includes the following processing: The skeleton of the human figure included in the image is detected, and the skeleton of the subject mounted on the top plate of the X-ray imaging device is extracted based on the detected skeleton. Between the image and an image acquired by the camera at a time that is only a preset time earlier than the time at which the image was acquired, the amount of movement of the corresponding pixels is calculated; Based on the position of the skeleton of the subject, multiple regions of interest are set on the image of the subject. One or more regions of interest for motion determination are selected from the set regions of interest, or the position of one or more regions of interest for motion determination is specified and the regions of interest are set at that position. and The amount of movement of pixels in the selected area of ​​interest or a specified location is used to determine whether the subject has experienced body movement.

Images