X-ray imaging device

Abstract

This X-ray imaging device (100) comprises: an image generation unit (72) that generates a plurality of X-ray images (10); and an imaging control unit (71), wherein the image generation unit (72) extracts at least one of a medical device (200) and a blood vessel in each of the plurality of X-ray images (10) to generate a plurality of extraction images (11), and calculates the amount of change in noise between the plurality of generated extraction images (11), and the imaging control unit (71) controls X-ray conditions so that the amount of change in noise is not more than a first prescribed value.

Description

X-ray equipment

[0001] The present invention relates to an X-ray imaging apparatus.

[0002] BACKGROUND ART X-ray imaging devices have been known in the art. Such an X-ray imaging device is disclosed, for example, in Japanese Patent Application Laid-Open No. 2018-192237.

[0003] Japanese Patent Application Laid-Open Publication No. 2018-192237 discloses an X-ray diagnostic apparatus (X-ray imaging apparatus) equipped with a control circuit. The control circuit reads a program related to automatic brightness adjustment from a storage circuit and executes the read program related to automatic brightness adjustment to realize an automatic brightness adjustment function. Automatic brightness adjustment is a technique for obtaining appropriate brightness in an X-ray image. Automatic brightness adjustment is a control for maintaining a constant brightness level within a target range by, for example, changing the X-ray irradiation conditions for the next frame so that the average or weighted average of pixel values ​​within a region of interest in an X-ray image of a certain frame approaches a target range for the next frame.

[0004] Japanese Patent Application Laid-Open No. 2018-192237

[0005] Here, examples of surgical procedures for treating a stenotic portion of a subject's blood vessel include balloon dilation and stent placement. Balloon dilation involves introducing a balloon catheter containing a guidewire into the subject's blood vessel, passing the balloon catheter through the blood vessel to the stenotic portion, and expanding the balloon to widen the blood vessel and restore blood flow. Balloon dilation requires accurate positioning of the balloon relative to the stenotic portion of the blood vessel. Stent placement involves placing a stent in the stenotic portion of the blood vessel, inflated by the balloon, within the blood vessel to widen the blood vessel and maintain normal blood flow. Stent placement requires accurate assessment of the degree of stent expansion after placement. Therefore, during balloon dilation and stent placement, the surgeon must confirm the shape and position of medical devices such as balloons and stents, as well as the subject's blood vessel, using continuously acquired X-ray images. However, in the control by the automatic brightness adjustment function of the X-ray diagnostic apparatus (X-ray imaging apparatus) of JP 2018-192237 A, there are cases where the medical device or the blood vessels of the subject are not displayed clearly and stably due to fluctuations in the amount of change in noise between each of the multiple X-ray images acquired continuously. Therefore, there is a demand for an X-ray imaging apparatus that can improve the visibility of the shape and position of the medical device or blood vessel in the X-ray image, thereby improving the accuracy of positioning and placement of the medical device relative to the blood vessel.

[0006] The present invention has been made to solve the above-mentioned problems, and one object of the present invention is to provide an X-ray imaging apparatus that can improve the accuracy of positioning and placement of a medical device relative to a blood vessel by improving the visibility of the shape and position of the medical device or blood vessel in an X-ray image.

[0007] In one aspect of the present invention, an X-ray imaging apparatus includes an X-ray irradiation unit that irradiates a subject with X-rays, an X-ray detection unit that detects X-rays that have passed through the subject, an image generation unit that generates a plurality of X-ray images based on the X-rays detected by the X-ray detection unit, and an imaging control unit that controls the X-ray conditions for the X-rays irradiated from the X-ray irradiation unit, wherein each of the plurality of X-ray images includes at least one of a medical device inside the subject's body and the subject's blood vessels, the image generation unit generates a plurality of extracted images by extracting at least one of the medical device and the blood vessels in each of the plurality of X-ray images, and calculates the amount of change in noise between each of the generated plurality of extracted images, and the imaging control unit controls the X-ray conditions so that the amount of change in noise is equal to or less than a first predetermined value.

[0008] In the X-ray imaging apparatus according to the above aspect, the image generation unit generates a plurality of extracted images by extracting at least one of a medical device and a blood vessel from each of a plurality of X-ray images, and calculates the amount of noise change between each of the generated extracted images. The imaging control unit controls the X-ray conditions so that the amount of noise change is equal to or less than a first predetermined value. By controlling the X-ray conditions so that the amount of noise change between each of the extracted images is equal to or less than the first predetermined value, fluctuations in the amount of noise change between each of the extracted images can be suppressed. This improves the visibility of the shape and position of the medical device or blood vessel in the X-ray image. Therefore, improving the visibility of the shape and position of the medical device or blood vessel in the X-ray image improves the accuracy of positioning and placement of the medical device relative to the blood vessel.

[0009] FIG. 1 is a schematic diagram showing the overall configuration of an X-ray imaging apparatus according to an embodiment. FIG. 2 is a block diagram showing the configuration of an X-ray imaging apparatus according to an embodiment. FIG. 3 is a schematic diagram showing an example of generation of an X-ray image and an extracted image. FIG. 4 is a diagram for explaining generation of an enhanced image. FIG. 5 is a diagram for explaining generation of a trained model. FIG. 6 is a schematic diagram showing an example of an X-ray image and an extracted image when the amount of change between the second number of pixels and the first number of pixels is greater than a first predetermined value. FIG. 7 is a schematic diagram showing an example of an X-ray image and an extracted image when the amount of change between the second number of pixels and the first number of pixels is smaller than a second predetermined value. FIG. 8 is a flowchart for explaining control of change of X-ray conditions according to an embodiment.

[0010] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, embodiments of the present invention will be described with reference to the accompanying drawings.

[0011] (Configuration of X-Ray Imaging Apparatus) The configuration of an X-ray imaging apparatus 100 according to this embodiment will be described with reference to FIGS.

[0012] As shown in FIG. 1 , an X-ray imaging apparatus 100 irradiates X-rays onto a subject 101 having a medical device 200 inserted therein. The X-ray imaging apparatus 100 then performs X-ray imaging by detecting X-rays that have passed through the subject 101. The X-ray imaging apparatus 100 generates images for confirming the state of the subject 101's internal body when performing, for example, percutaneous coronary intervention (PCI). Percutaneous coronary intervention is a treatment for diseases such as angina pectoris and myocardial infarction caused by stenosis and blockage of coronary arteries in the heart, in which a device 200 is used to relieve the stenosis and blockage of blood vessels. The device 200 is placed inside the subject 101. The device 200 includes, for example, a catheter, a guidewire, a stent, or the like placed in a blood vessel near the heart of the subject 101.

[0013] In percutaneous coronary intervention, catheters, guidewires, and the like are used to position a stent or the like at a target location within a blood vessel (coronary artery) of a subject 101. The catheter, guidewire, and the like are inserted from a blood vessel (radial artery, femoral artery, etc.) in the wrist or thigh to the narrowed portion of the coronary artery. In percutaneous coronary intervention, a stent is positioned at the narrowed portion of the coronary artery using a catheter, guidewire, and the like inserted into the blood vessel. The narrowed blood vessel is then treated by expanding the stent.

[0014] As shown in FIG. 2, the X-ray imaging device 100 includes a tabletop 1, an X-ray irradiation unit 2, an X-ray detection unit 3, a moving unit 4, a display unit 5, an operation unit 6, a control unit 7, and a memory unit 8.

[0015] A subject 101 to be irradiated with X-rays is placed on the top board 1. The device 200 is inserted into the subject 101 while the subject 101 is placed on the top board 1, and X-ray imaging is performed. The top board 1 is configured to be movable by a top board moving unit (not shown) based on the control of the control unit 7.

[0016] The X-ray irradiator 2 irradiates X-rays onto the subject 101 having a medical device 200 placed inside the subject 101. The X-ray irradiator 2 includes an X-ray tube 21 that irradiates X-rays when a voltage is applied to it. The X-ray tube 21 is configured so that the voltage applied to the X-ray tube 21 is controlled by the control unit 7, thereby controlling the X-rays to be irradiated. The X-ray irradiator 2 irradiates the device 200 inside the subject 101 with X-rays one or more times.

[0017] The X-ray detection unit 3 detects X-rays that have passed through the subject 101. The X-ray detection unit 3 then outputs a detection signal based on the detected X-rays. The X-ray detection unit 3 includes, for example, an FPD (Flat Panel Detector).

[0018] The moving unit 4 movably holds the X-ray irradiator 2 and the X-ray detector 3. Specifically, the moving unit 4 supports the X-ray irradiator 2 and the X-ray detector 3 so that they face each other across the top board 1 on which the subject 101 is placed. The moving unit 4 supports the X-ray irradiator 2 and the X-ray detector 3 so that their positions and angles with respect to the subject 101 can be changed. The moving unit 4 also supports the X-ray irradiator 2 and the X-ray detector 3 so that the distance between them can be changed. In other words, the moving unit 4 moves the X-ray irradiator 2 and the X-ray detector 3 to perform X-ray imaging of the subject 101 from various positions and angles.

[0019] The display unit 5 is, for example, a monitor such as a liquid crystal display, etc. The display unit 5 displays the X-ray image 10 generated by the control unit 7 and an enhanced image 12 (still image and moving image) in which the device 200 is enhanced.

[0020] The operation unit 6 is configured to accept input operations for operating the X-ray imaging apparatus 100. The operation unit 6 accepts, for example, operations for moving the top board 1 and the moving unit 4. The operation unit 6 also accepts operations for irradiating X-rays when X-ray imaging is performed on the subject 101. The operation unit 6 also accepts input operations for executing control by the control unit 7.

[0021] The control unit 7 is a computer including a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a ROM (Read Only Memory), and a RAM (Random Access Memory). The CPU executes a predetermined control program, whereby the control unit 7 controls each unit of the X-ray imaging device 100, controls the generation of the X-ray image 10 and the extracted image 11, and controls the X-ray irradiation unit 2 to irradiate X-rays based on the X-ray conditions. The control unit 7 is also configured to control the X-ray conditions so that the amount of change in noise is equal to or less than a first predetermined value. The control unit 7 is also configured to control the X-ray conditions so that the amount of change in noise is equal to or less than the first predetermined value and equal to or greater than a second predetermined value that is smaller than the first predetermined value.

[0022] The control unit 7 includes, as functional components, an imaging control unit 71, an image generation unit 72, and a display control unit 73. That is, the control unit 7 functions as the imaging control unit 71, the image generation unit 72, and the display control unit 73 by the CPU executing a predetermined control program. Details of the control by the control unit 7 will be described later.

[0023] The storage unit 8 is configured with a storage device such as a hard disk drive or a solid state drive (SSD). The storage unit 8 is configured to store image data, information on X-ray conditions, a reference amount, and various setting values. The information on X-ray conditions includes the tube voltage, the tube current, the pulse width of the X-rays irradiated from the X-ray irradiator 2, and the thickness of the soft ray removal filter. The pulse width of the X-rays means the irradiation time (exposure time) during which the subject 101 is irradiated with X-rays to capture one X-ray image 10. The storage unit 8 also stores a program for causing the controller 7 to function.

[0024] The storage unit 8 also stores a trained model 80 (see FIG. 5 ) that has been generated in advance by machine learning. The trained model 80 is generated in advance by machine learning that trains the process of detecting the position of the device 200 from the input X-ray image 10. The generation of the trained model 80 will be described in detail later.

[0025] (Control of X-ray imaging device by control unit) The imaging control unit 71 of the control unit 7 controls the X-ray irradiator 2 and the X-ray detector 3 to perform X-ray imaging. The imaging control unit 71 controls the irradiation of X-rays by the X-ray irradiator 2. The imaging control unit 71 controls the X-ray conditions for the X-rays irradiated from the X-ray irradiator 2. Specifically, the imaging control unit 71 causes the X-ray irradiator 2 to irradiate X-rays based on predetermined X-ray conditions. More specifically, the imaging control unit 71 causes the X-ray irradiator 2 to irradiate X-rays with a blur suppression pulse width. The blur suppression pulse width is a pulse width equal to or less than the pulse width at which the detection accuracy of the device 200 in the X-ray image 10 based on the trained model 80 is maximized. The imaging control unit 71 controls the pulse width of the X-rays irradiated from the X-ray tube 21 by controlling the voltage applied to the X-ray tube 21.

[0026] The imaging control unit 71 also controls the X-ray conditions so that the amount of noise change between each of the multiple extracted images 11 calculated by the image generation unit 72 is equal to or less than a first predetermined value, and causes the X-ray irradiator 2 to irradiate X-rays based on the controlled X-ray conditions. Specifically, when the amount of noise change between multiple frames of extracted images 11 exceeds the first predetermined value, the imaging control unit 71 changes the X-ray conditions to increase the X-ray irradiation dose so that the amount of noise change is equal to or less than the first predetermined value, and causes the X-ray irradiator 2 to irradiate X-rays based on the changed X-ray conditions. When the amount of noise change between multiple frames of extracted images 11 is less than a second predetermined value, the imaging control unit 71 changes the X-ray conditions to decrease the X-ray irradiation dose so that the amount of noise change is equal to or less than the first predetermined value and equal to or greater than the second predetermined value, and causes the X-ray irradiator 2 to irradiate X-rays based on the changed X-ray conditions. Details of the control of the change of the X-ray conditions will be described later.

[0027] (Generation of X-ray image, extracted image, and enhanced image by control unit) As shown in Fig. 3, the image generation unit 72 of the control unit 7 generates an X-ray image 10 by taking an X-ray image. The image generation unit 72 generates a plurality of X-ray images 10 based on the X-rays detected by the X-ray detection unit 3. That is, the image generation unit 72 generates an X-ray image 10 including a plurality of frames.

[0028] The image generator 72 is also configured to generate a plurality of extracted images 11 from a plurality of X-ray images 10 based on a trained model 80 (see FIG. 8 ) generated by machine learning. The image generator 72 generates a plurality of extracted images 11 by extracting an object from each of the plurality of X-ray images 10 based on the trained model 80. That is, the image generator 72 generates an extracted image 11 including a plurality of frames from which an object detected in each of the plurality of frames of X-ray images 10 is extracted based on the trained model 80. Each of the plurality of X-ray images 10 includes the object. The image generator 72 generates an extracted image 11 from which the object is extracted for each frame of the X-ray images 10. The object includes a medical device 200 in the body of the subject 101 or a blood vessel of the subject 101. In the present embodiment, the object is the medical device 200.

[0029] The image generation unit 72 is configured to detect the device 200 as an object from the X-ray image 10 based on a trained model 80 generated by machine learning using the generated X-ray image 10 as a teacher image. Specifically, the image generation unit 72 acquires position information (coordinates) of the device 200 included in the X-ray image 10 by detecting the position of the device 200 in the X-ray image 10 from the generated X-ray image 10 based on the trained model 80. The image generation unit 72 distinguishes, from the X-ray image 10, an area of ​​the device 200 and an area of ​​the background other than the device 200 based on the acquired position information. Then, the image generation unit 72 generates an extracted image 11 in which the object detected from the X-ray image 10 is extracted based on the result of distinguishing between the area of ​​the device 200 and the area of ​​the background other than the device 200.

[0030] The image generation unit 72 also performs image processing to highlight the device 200 detected in the X-ray image 10, thereby generating an enhanced image 12 in which the device 200 is highlighted. Specifically, the image processing unit of the control unit 7 performs image processing to increase the density of a region of the X-ray image 10 that is determined to represent the device 200. The image processing unit also performs image processing to decrease the density of a region of the X-ray image 10 that is determined to represent the background rather than the device 200. In this manner, the image generation unit 72 acquires position information of the device 200 based on the trained model 80, and generates an enhanced image 12 (see FIG. 4 ) in which the device 200 is highlighted from the X-ray image 10 based on the acquired position information. That is, the image generation unit 72 generates an enhanced image 12 in which the device 200 is highlighted at a high resolution from the X-ray image 10 in which the device 200 is highlighted at a low resolution.

[0031] The display control unit 73 of the control unit 7 controls the display of the display unit 5. Specifically, the display control unit 73 causes the generated emphasized image 12 to be displayed on the display unit 5. The display control unit 73 causes the display unit 5 to display the emphasized image 12 (see FIG. 4 ) generated in real time as a moving image at a predetermined frame rate.

[0032] (Trained Model) As shown in FIG. 5 , the trained model 80 is generated by machine learning using a teacher image corresponding to the X-ray image 10 captured by X-rays with a blur suppression pulse width. The blur suppression pulse width refers to a pulse width at which the detection accuracy of the device 200 based on the trained model 80 is maximized. The trained model 80 is generated by machine learning using a teacher input X-ray image 81 generated to simulate the device 200 inside the body of the subject 101 in the X-ray image 10 captured by X-rays with the blur suppression pulse width, and teacher output information 82 indicating the position (coordinates) of the device 200 included in the teacher input X-ray image 81. The teacher input X-ray image 81 is generated to simulate the device 200 inside the body of the subject 101 based on a simulated X-ray image generated by X-rays with the blur suppression pulse width. The trained model 80 is generated in advance by a learning device 110 separate from the X-ray imaging device 100.

[0033] The learning device 110 is a computer for machine learning that includes, for example, a CPU, a GPU, a ROM, and a RAM.

[0034] The learning device 110 uses the teacher input X-ray image 81 as input and the teacher output information 82 as output to perform learning through machine learning and generate a trained model 80. That is, the learning device 110 uses the teacher input X-ray image 81 and the teacher output information 82 as teacher data (training set) to train the trained model 80 through machine learning. The learning device 110 generates the trained model 80 using the teacher input X-ray image 81 generated from multiple types of simulated X-ray images. As the machine learning method, deep learning, which is machine learning using a multilayer neural network, is used. For example, the machine learning method is deep learning using a fully convolutional neural network (FCN). The generated trained model 80 is provided to the X-ray imaging device 100 via a network or by being recorded on a recording medium such as a flash memory.

[0035] The X-ray imaging apparatus 100 acquires position information (area) of the device 200 from the generated X-ray image 10 based on the trained model 80 generated to correspond to the blur suppression pulse width.

[0036] 6 to 8, the amount of change in noise between extracted images 11 of multiple frames will be described. Specifically, the amount of change in noise refers to the amount of change between a first number of pixels determined to be an object in extracted image 11 of the current frame and a second number of pixels determined to be an object in extracted image 11 of a frame earlier than the current frame. In other words, the shooting control unit 71 can determine the amount of noise in extracted image 11 of the current frame by comparing the first number of pixels with the second number of pixels.

[0037] The imaging control unit 71 is configured to control the X-ray conditions so that the amount of change in noise is equal to or less than a first predetermined value. Specifically, when the amount of change in noise between the extracted images 11 of multiple frames generated by the image generation unit 72 exceeds the first predetermined value, the imaging control unit 71 is configured to change the X-ray conditions and increase the X-ray irradiation amount so that the amount of change in noise is equal to or less than the first predetermined value.

[0038] More specifically, when the change in noise, i.e., the change in the first number of pixels determined to be an object in an extracted image 11 in the current X-ray image 10, and the change in the second number of pixels determined to be an object in an extracted image 11 in an X-ray image 10 that is older than the current X-ray image 10, exceeds a first predetermined value, the imaging control unit 71 is configured to change the X-ray conditions and increase the X-ray exposure dose so that the change in noise is equal to or less than the first predetermined value.

[0039] Furthermore, the imaging control unit 71 is configured to control the X-ray conditions so that the amount of change in noise is equal to or less than a first predetermined value and equal to or greater than a second predetermined value that is smaller than the first predetermined value. Specifically, when the amount of change in noise between multiple frames of extracted images 11 generated by the image generation unit 72 is less than the second predetermined value, the imaging control unit 71 is configured to change the X-ray conditions and reduce the X-ray exposure dose so that the amount of change in noise is equal to or less than the first predetermined value and equal to or greater than the second predetermined value.

[0040] More specifically, when the change in noise between the first number of pixels determined to be an object in the extracted image 11 in the current X-ray image 10 and the second number of pixels determined to be an object in the extracted image 11 in the X-ray image 10 that is older than the current X-ray image 10 is less than a second predetermined value, the imaging control unit 71 is configured to change the X-ray conditions and reduce the X-ray exposure dose so that the change in noise is less than the first predetermined value and greater than or equal to a second predetermined value.

[0041] The following describes an example of control for changing the X-ray conditions for the (n+1)th frame X-ray image 10 (not shown) based on the amount of change in noise between the (n-1)th frame extracted image 11 and the (n)th frame extracted image 11. In this embodiment, the imaging control unit 71 is configured to perform control for changing the X-ray conditions every time an X-ray image 10 is generated.

[0042] As shown in Figures 3 and 6 to 8, when the X-ray irradiation unit 2 starts irradiating X-rays, the image generation unit 72 generates an X-ray image 10 including multiple frames based on the X-rays detected by the X-ray detection unit 3.

[0043] Furthermore, the image generation unit 72 generates an extracted image 11 from the generated X-ray image 10 based on the trained model 80. The extracted image 11 is generated for each generated X-ray image 10. Specifically, the image generation unit 72 acquires position information (coordinates) of the device 200 included in the X-ray image 10 by detecting the position of the device 200 in the generated X-ray image 10. The image generation unit 72 distinguishes, based on the acquired position information, between the region of the device 200 and a background region other than the device 200 in the X-ray image 10. Then, based on the result of distinguishing between the region of the device 200 and the background region other than the device 200, the image generation unit 72 generates an extracted image 11 in which the object detected from the X-ray image 10 is extracted.

[0044] In addition, the image generation unit 72 is configured to calculate the amount of change in noise between each of the multiple extracted images 11 generated based on the trained model 80.

[0045] Specifically, the image generation unit 72 is configured to acquire the number of pixels determined to be in the area of ​​the device 200 in each of the extracted images 11 generated based on the trained model 80. The image generation unit 72 acquires a second number of pixels determined to be in the area of ​​the device 200 in the extracted image 11 of the (n-1)th frame. The image generation unit 72 also acquires a first number of pixels determined to be in the area of ​​the device 200 in the extracted image 11 of the (n)th frame. In this embodiment, the amount of change in noise between the extracted images 11 of multiple frames means the difference between the second number of pixels and the first number of pixels. In other words, the amount of change in noise between the extracted images 11 of multiple frames is the fluctuation (fluctuation) in the number of pixels determined to be in the area of ​​the device 200.

[0046] A first predetermined value and a second predetermined value smaller than the first predetermined value are stored in the storage unit 8. A range equal to or smaller than the first predetermined value and equal to or larger than the second predetermined value is a range of values ​​that are considered appropriate as the difference between the second pixel count and the first pixel count.

[0047] FIG. 6 shows an example of an X-ray image 10 and an extracted image 11 in which the amount of change between the second pixel count and the first pixel count exceeds a first predetermined value. In the example shown in FIG. 6, the amount of change (difference) between the second pixel count in the extracted image 11 of the (n-1)th frame and the first pixel count in the extracted image 11 of the (n)th frame exceeds the first predetermined value. That is, there is a large variation between the second pixel count in the extracted image 11 of the (n-1)th frame and the first pixel count in the extracted image 11 of the (n)th frame. In this case, the amount of X-rays irradiated from the X-ray irradiator 2 in the X-ray image 10 is small, resulting in a variation in the signal-to-noise ratio (SN ratio). Therefore, the shape of the object in the extracted image 11 generated based on the trained model 80 is unclear. Consequently, the shape of the object in the enhanced image 12 generated based on the trained model 80 is also unclear. Note that the black dots shown in the extracted image 11 in Figure 6 are pixels that have been determined to be in the area of ​​the device 200 based on the position information obtained based on the trained model 80.

[0048] FIG. 7 shows an example of an X-ray image 10 and an extracted image 11 in which the amount of change between the second pixel count and the first pixel count is less than a second predetermined value. In the example shown in FIG. 7 , the amount of change (difference) between the second pixel count in the extracted image 11 of the (n-1)th frame and the first pixel count in the extracted image 11 of the (n)th frame is less than the second predetermined value. That is, there is almost no variation between the second pixel count in the extracted image 11 of the (n-1)th frame and the first pixel count in the extracted image 11 of the (n)th frame. In this case, the amount of X-rays irradiated from the X-ray irradiator 2 in the X-ray image 10 is large, so there is almost no variation in the signal-to-noise ratio. Therefore, the shape of the object in the extracted image 11 generated based on the trained model 80 is clear. Furthermore, although the shape of the object in the enhanced image 12 generated based on the trained model 80 is also clear, the radiation exposure dose of the subject 101 is slightly increased.

[0049] FIG. 8 shows an example of an X-ray image 10 and an extracted image 11 in which the amount of change between the second pixel count and the first pixel count is less than a first predetermined value and greater than a second predetermined value. In the example shown in FIG. 8 , the amount of change (difference) between the second pixel count in the extracted image 11 of the (n-1)th frame and the first pixel count in the extracted image 11 of the (n)th frame is less than a first predetermined value and greater than a second predetermined value. That is, although there is a slight variation between the second pixel count in the extracted image 11 of the (n-1)th frame and the first pixel count in the extracted image 11 of the (n)th frame, it is within an appropriate range. In this case, because the X-ray dose irradiated from the X-ray irradiator 2 in the X-ray image 10 is appropriate, the shape of the object in the extracted image 11 generated based on the trained model 80 is clear. Furthermore, the shape of the object in the enhanced image 12 generated based on the trained model 80 is also clear, and the radiation exposure dose to the subject 101 is reduced. Note that the black dots shown in the extracted image 11 in Figure 8 are pixels that have been determined to be in the area of ​​the device 200 based on the position information obtained based on the trained model 80.

[0050] (Control of change of X-ray conditions) When the amount of change in noise between multiple frames of extracted images 11 exceeds a first predetermined value, the imaging control unit 71 is configured to change the X-ray conditions and increase the X-ray exposure dose so that the amount of change in noise is equal to or less than the first predetermined value, and when the amount of change in noise between multiple frames of extracted images 11 is less than a second predetermined value, to change the X-ray conditions and decrease the X-ray exposure dose so that the amount of change in noise is equal to or less than the first predetermined value and equal to or greater than the second predetermined value.

[0051] The X-ray conditions are changed by changing at least one value of the tube voltage, the tube current, the pulse width of the X-rays irradiated from the X-ray irradiator 2, and the thickness of the soft ray removal filter.

[0052] The change in the X-ray conditions when increasing the X-ray exposure dose is, for example, at least one of increasing the tube voltage, increasing the tube current, extending the pulse width, and changing to a soft-ray removal filter with a smaller thickness, while the change in the X-ray conditions when decreasing the X-ray exposure dose is, for example, at least one of decreasing the tube voltage, decreasing the tube current, shortening the pulse width, and changing to a soft-ray removal filter with a larger thickness.

[0053] 6 , when the amount of change between the first number of pixels and the second number of pixels exceeds a first predetermined value, that is, when the amount of change in noise between multiple frames of extracted images 11 is large, the imaging control unit 71 is configured to change the X-ray conditions to increase the X-ray exposure amount so that the amount of change in noise becomes equal to or less than the first predetermined value, and to cause the X-ray irradiator 2 to irradiate X-rays based on the changed X-ray conditions. Then, the image generator 72 generates the X-ray image 10 based on the X-rays detected by the X-ray detector 3 under the changed X-ray conditions.

[0054] 7 , when the change amount between the first pixel count and the second pixel count is less than a second predetermined value, that is, when the change amount of noise between the extracted images 11 of multiple frames is small, the imaging control unit 71 is configured to change the X-ray conditions to reduce the X-ray exposure amount so that the change amount of noise is equal to or less than the first predetermined value and equal to or greater than the second predetermined value, and to cause the X-ray irradiator 2 to irradiate X-rays based on the changed X-ray conditions. Then, the image generator 72 generates the X-ray image 10 based on the X-rays detected by the X-ray detector 3 under the changed X-ray conditions.

[0055] 8 , the imaging control unit 71 is configured to cause the X-ray irradiator 2 to irradiate X-rays while maintaining the X-ray conditions when the amount of change between the first pixel count and the second pixel count is equal to or less than a first predetermined value and equal to or greater than a second predetermined value, that is, when the amount of change in noise between multiple frames of extracted images 11 is within a predetermined range. Then, the image generator 72 generates an X-ray image 10 based on the X-rays detected by the X-ray detector 3.

[0056] (Control flow of change of X-ray conditions) The flow of control of change of X-ray conditions by the control unit 7 will be described with reference to Fig. 9. The control of change of X-ray conditions by the control unit 7 is performed sequentially every time an X-ray image 10 is generated by the image generation unit 72. Note that the order of each step can be reversed or can be executed simultaneously as long as there is no mutual contradiction.

[0057] In step S1, the image generating unit 72 generates the X-ray image 10 based on the X-rays detected by the X-ray detection unit 3. Then, the process proceeds to step S2.

[0058] In step S2, the image generator 72 generates an extracted image 11 from the X-ray image 10 based on the trained model 80 generated by machine learning. Then, the process proceeds to step S3.

[0059] In step S3, the image generation unit 72 acquires a first pixel count of pixels determined to be in the area of ​​the device 200 in the extracted image 11 generated based on the trained model 80, and calculates the amount of change between the first pixel count and the second pixel count. Then, the process proceeds to step S4.

[0060] In step S4, the imaging control unit 71 determines whether the amount of change between the first number of pixels and the second number of pixels exceeds a first predetermined value. If the amount of change between the first number of pixels and the second number of pixels exceeds the first predetermined value (Yes in step S4), the imaging control unit 71 proceeds to step S5. If the amount of change between the first number of pixels and the second number of pixels does not exceed the first predetermined value (No in step S4), the imaging control unit 71 proceeds to step S6.

[0061] In step S5, the imaging control unit 71 changes the X-ray conditions and increases the X-ray irradiation dose so that the amount of change in noise becomes equal to or less than a first predetermined value. Then, the process ends.

[0062] In step S6, the imaging control unit 71 determines whether the amount of change between the first and second pixel counts is less than a second predetermined value. If the amount of change between the first and second pixel counts is less than the second predetermined value (Yes in step S6), the imaging control unit 71 proceeds to step S7. If the amount of change between the first and second pixel counts is not less than the second predetermined value (No in step S6), the imaging control unit 71 proceeds to step S8.

[0063] In step S7, the imaging control unit 71 changes the X-ray conditions to reduce the X-ray irradiation dose so that the amount of change in noise is equal to or less than a first predetermined value and equal to or greater than a second predetermined value. Then, the process ends.

[0064] In step S8, the imaging control unit 71 maintains the X-ray conditions without changing them, and then the process ends.

[0065] The imaging control unit 71 may be configured to, for example, change the X-ray conditions to reduce the pulse width of the X-rays irradiated from the X-ray irradiator 2 or reduce the X-ray irradiation dose when the blur of the object in the extracted image 11 in which the object is extracted based on the trained model 80 is large, and to, for example, change the X-ray conditions to increase the pulse width of the X-rays irradiated from the X-ray irradiator 2 or increase the X-ray irradiation dose when the blur of the object in the extracted image 11 is small. The blur of the object in the extracted image 11 can be acquired as a value indicating how many pixels the object in the current extracted image 11 has moved relative to the object in the previous extracted image 11.

[0066] The imaging control unit 71 may also be configured to change the X-ray conditions to increase the frame rate when the movement amount of the object in the extracted image 11 in which the object is extracted based on the trained model 80 is large due to a fast movement speed of the moving unit 4, and to change the X-ray conditions to decrease the frame rate when the movement amount of the object in the extracted image 11 in which the object is extracted based on the trained model 80 is small due to a slow movement speed of the moving unit 4. The frame rate is, for example, the number of frames of the X-ray image 10 generated per second by the image generation unit 72.

[0067] (Effects of this embodiment) In this embodiment, the following effects can be obtained.

[0068] In the X-ray imaging apparatus 100 of this embodiment, the image generation unit 72 generates a plurality of extracted images 11 by extracting the medical device 200 from each of the plurality of X-ray images 10, and calculates the amount of change in noise between each of the generated extracted images 11. The imaging control unit 71 controls the X-ray conditions so that the amount of change in noise is equal to or less than a first predetermined value. By controlling the X-ray conditions so that the amount of change in noise between each of the plurality of extracted images 11 is equal to or less than the first predetermined value, it is possible to suppress fluctuations in the amount of change in noise between each of the plurality of extracted images 11. This improves the visibility of the medical device 200 in the X-ray image 10. Therefore, improving the visibility of the medical device 200 in the X-ray image 10 improves the accuracy of positioning and placement of the medical device 200 in a blood vessel.

[0069] Furthermore, the X-ray imaging apparatus 100 according to the above embodiment has the following configuration, thereby providing the following additional effects.

[0070] That is, in this embodiment, as described above, the image generation unit 72 is configured to generate a plurality of extracted images 11 from a plurality of X-ray images 10 based on the trained model 80 generated by machine learning, and the imaging control unit 71 controls the X-ray conditions so that the amount of change in noise in each of the plurality of extracted images 11 is equal to or less than a first predetermined value. As a result, the extracted images 11 in which the medical devices 200 as the objects are extracted are generated based on the trained model 80, so that the devices 200 can be extracted with high accuracy in the X-ray images 10, and the X-ray conditions can be appropriately controlled so that the amount of change in noise in the extracted images 11 in which the devices 200 are accurately extracted is equal to or less than the first predetermined value.

[0071] Furthermore, in this embodiment, as described above, the imaging control unit 71 is configured to change the X-ray conditions and increase the X-ray exposure dose when the amount of noise change between the multiple extracted images 11 exceeds a first predetermined value so that the amount of noise change is equal to or less than the first predetermined value. Here, when the amount of noise change between the extracted images 11 is large, fluctuations in the S / N ratio occur due to an insufficient X-ray dose. When the amount of noise change between the multiple extracted images 11 exceeds the first predetermined value, the X-ray conditions are changed to increase the X-ray exposure dose so that the amount of noise change is equal to or less than the first predetermined value, thereby suppressing fluctuations in the S / N ratio due to an insufficient X-ray dose. Therefore, the visibility of the medical device 200 in the X-ray image 10 can be appropriately improved.

[0072] Furthermore, in this embodiment, as described above, the imaging control unit 71 is configured to control the X-ray conditions so that the amount of change in noise is equal to or less than a first predetermined value and equal to or greater than a second predetermined value that is smaller than the first predetermined value, and to change the X-ray conditions and reduce the X-ray exposure dose when the amount of change in noise between the plurality of extracted images 11 is less than the second predetermined value. Here, when the amount of change in noise between the extracted images 11 is small, the amount of X-rays irradiated from the X-ray irradiator 2 in the X-ray image 10 is large, so that there is almost no fluctuation in the S / N ratio. When the amount of change in noise between the plurality of extracted images 11 is less than the second predetermined value, the X-ray conditions are changed to reduce the X-ray exposure dose so that the amount of change in noise is equal to or less than the first predetermined value and equal to or greater than the second predetermined value, thereby suppressing an increase in the radiation exposure dose of the subject 101 while ensuring the visibility of the medical device 200.

[0073] Furthermore, in this embodiment, as described above, when the amount of change in noise between the first number of pixels determined to be the medical device 200 as the object in the extracted image 11 of the current X-ray image 10 and the second number of pixels determined to be the medical device 200 as the object in the extracted image 11 of the X-ray image 10 that is older than the current X-ray image 10 exceeds a first predetermined value, the imaging control unit 71 is configured to change the X-ray conditions and increase the X-ray exposure dose so that the amount of change in noise is equal to or less than the first predetermined value. This makes it possible to easily obtain the amount of change in noise between the first number of pixels determined to be the medical device 200 in the extracted image 11 of the current X-ray image 10 and the second number of pixels determined to be the medical device 200 in the extracted image 11 of the previous X-ray image 10. Therefore, when the change amount between the first pixel count and the second pixel count exceeds a first predetermined value, the visibility of the medical device 200 can be easily improved by changing the X-ray conditions and increasing the X-ray irradiation amount so that the change amount of noise is equal to or less than the first predetermined value.

[0074] Furthermore, in this embodiment, as described above, when the change in noise between the first number of pixels determined to represent the medical device 200 as the object in the extracted image 11 of the current X-ray image 10 and the second number of pixels determined to represent the medical device 200 as the object in the extracted image 11 of the X-ray image 10 that is older than the current X-ray image 10 is less than a second predetermined value, the imaging control unit 71 is configured to change the X-ray conditions and reduce the X-ray exposure dose so that the change in noise is less than or equal to the first predetermined value and greater than or equal to the second predetermined value. This makes it possible to easily obtain the change in noise between the first number of pixels and the second number of pixels as the change in noise. Therefore, by changing the X-ray conditions and reducing the X-ray exposure dose so that the change in the first number of pixels and the second number of pixels is less than or equal to the first predetermined value and greater than or equal to the second predetermined value, it is possible to effectively suppress an increase in the radiation exposure dose of the subject 101 while further ensuring the visibility of the medical device 200.

[0075] Furthermore, in this embodiment, as described above, the imaging control unit 71 is configured to maintain the X-ray conditions when the change in noise between the first number of pixels and the second number of pixels is equal to or less than a first predetermined value and equal to or greater than a second predetermined value. Thus, when the change in noise between the first number of pixels and the second number of pixels is equal to or less than the first predetermined value and equal to or greater than the second predetermined value, the S / N ratio varies slightly but is within an appropriate range, so the X-ray conditions are not changed. Therefore, the X-ray conditions are deemed appropriate, and the medical device 200 can continue to be clearly displayed.

[0076] [Modifications] The embodiments disclosed herein should be considered to be illustrative in all respects and not restrictive. The scope of the present invention is defined by the claims, not by the description of the above-mentioned embodiments, and further includes all modifications (modifications) within the meaning and scope of the claims.

[0077] For example, in the above embodiment, the image generation unit is configured to generate extracted images in which a medical device is extracted as an object detected in an X-ray image based on a trained model generated by machine learning, and the imaging control unit controls the X-ray conditions so that the amount of change in noise between each of the extracted images is equal to or less than a first predetermined value. However, the present invention is not limited to this. For example, the image generation unit may be configured to acquire position information of blood vessels included in an X-ray image of a subject administered with a contrast agent based on a trained model that detects position information of blood vessels different from the trained model, based on a trained model generated by machine learning, and generate extracted images in which the subject's blood vessels are extracted as an object detected in the X-ray image. The imaging control unit may be configured to control the X-ray conditions so that the amount of change in noise between each of the extracted images in which the subject's blood vessels are extracted based on the trained model that detects position information of blood vessels is equal to or less than a first predetermined value.

[0078] The image generation unit may also be configured to generate an extracted image in which both the medical device and the subject's blood vessels as objects detected in the X-ray image are extracted based on a trained model generated by machine learning, and the imaging control unit may be configured to control the X-ray conditions so that the amount of change in noise between each of the multiple extracted images is equal to or less than a first predetermined value.

[0079] In the above embodiment, the image generation unit is configured to generate an extracted image in which a medical device is extracted as an object detected in an X-ray image based on a trained model generated by machine learning. However, the present invention is not limited to this. For example, the image generation unit may be configured to generate an extracted image in which a medical device is extracted as an object detected in an X-ray image based on a region of interest set by an operator in the X-ray image or a region of interest automatically set by a marker attached to the device in the X-ray image. The method of generating the extracted image is not particularly limited.

[0080] In the above embodiment, the imaging control unit is configured to change the X-ray conditions and reduce the X-ray irradiation dose when the amount of change in noise between the plurality of extracted images is less than the second predetermined value so that the amount of change in noise is less than the first predetermined value and greater than or equal to the second predetermined value, but the present invention is not limited to this. For example, the imaging control unit does not need to control the change in the X-ray conditions when the amount of change in noise between the plurality of extracted images is less than the second predetermined value.

[0081] In the above embodiment, the amount of change in noise is the amount of change between the first number of pixels and the second number of pixels, but the present invention is not limited to this. For example, the amount of change in noise does not have to be the amount of change between the first number of pixels and the second number of pixels. For example, the image generation unit may be configured to calculate the amount of change in noise by directly detecting noise from the extracted image.

[0082] In the above embodiment, the X-ray conditions are changed by changing at least one of the values ​​of the tube voltage, the tube current, the pulse width of the X-rays irradiated from the X-ray irradiator, and the thickness of the soft ray removal filter, but the present invention is not limited to this. For example, the X-ray conditions may be changed by a known method other than those described above.

[0083] Aspects It will be appreciated by those skilled in the art that the exemplary embodiments described above are examples of the following aspects.

[0084] an X-ray irradiation unit that irradiates a subject with X-rays; an X-ray detection unit that detects X-rays that have passed through the subject; an image generation unit that generates a plurality of X-ray images based on the X-rays detected by the X-ray detection unit; and an imaging control unit that controls X-ray conditions for the X-rays irradiated from the X-ray irradiation unit, wherein each of the plurality of X-ray images includes at least one of a medical device inside the subject's body and a blood vessel of the subject, the image generation unit generates a plurality of extracted images by extracting at least one of the medical device and the blood vessel in each of the plurality of X-ray images, and calculates a change in noise between each of the generated plurality of extracted images, and the imaging control unit controls the X-ray conditions so that the change in noise is equal to or less than a first predetermined value.

[0085] (Item 2) The X-ray imaging device according to Item 1, wherein the image generation unit is configured to generate the plurality of extracted images from the plurality of X-ray images based on a trained model generated by machine learning, and the imaging control unit is configured to control the X-ray conditions so that the amount of change in the noise between each of the plurality of extracted images is equal to or less than the first predetermined value.

[0086] (Item 3) The X-ray imaging device according to Item 2, wherein the imaging control unit is configured to, when a change in the noise between the plurality of extracted images exceeds the first predetermined value, change the X-ray conditions to increase the X-ray irradiation amount so that the change in the noise becomes equal to or less than the first predetermined value.

[0087] (Item 4) The X-ray imaging device according to Item 3, wherein the imaging control unit further controls the X-ray conditions so that the amount of change in noise is equal to or less than the first predetermined value and equal to or greater than a second predetermined value that is smaller than the first predetermined value, and when the amount of change in noise between the plurality of extracted images is less than the second predetermined value, changes the X-ray conditions to reduce the X-ray exposure dose so that the amount of change in noise is equal to or less than the first predetermined value and equal to or greater than the second predetermined value.

[0088] (Item 5) The X-ray imaging device according to Item 3, wherein the imaging control unit is configured to, when a change in the noise between a first number of pixels determined to be at least one of the medical device and the blood vessel in the extracted image in the current X-ray image and a second number of pixels determined to be at least one of the medical device and the blood vessel in the extracted image in the X-ray image earlier than the current X-ray image, exceeds a first predetermined value, change the X-ray conditions to increase the X-ray exposure dose so that the change in the noise is equal to or less than the first predetermined value.

[0089] (Item 6) The X-ray imaging device according to Item 4, wherein the imaging control unit is configured to, when a change in the noise between a first number of pixels determined to represent at least one of the medical device and the blood vessel in the extracted image in the current X-ray image and a second number of pixels determined to represent at least one of the medical device and the blood vessel in the extracted image in the X-ray image earlier than the current X-ray image, is less than the second predetermined value, change the X-ray conditions to reduce the X-ray exposure dose so that the change in the noise is less than the first predetermined value and greater than or equal to the second predetermined value.

[0090] (Item 7) The X-ray imaging device according to Item 6, wherein the imaging control unit is configured to maintain the X-ray conditions when the change amount between the first number of pixels and the second number of pixels as the change amount of the noise is equal to or less than the first predetermined value and equal to or greater than the second predetermined value.

[0091] 2 X-ray irradiation unit 3 X-ray detection unit 10 X-ray image 11 Extracted image 71 Imaging control unit 72 Image generation unit 80 Trained model 100 X-ray imaging device 101 Subject 200 Device

Claims

1. An X-ray imaging apparatus comprising: an X-ray irradiation unit that irradiates a subject with X-rays; an X-ray detection unit that detects X-rays that have passed through the subject; an image generation unit that generates a plurality of X-ray images based on the X-rays detected by the X-ray detection unit; and an imaging control unit that controls the X-ray conditions for the X-rays irradiated from the X-ray irradiation unit, wherein each of the plurality of X-ray images includes at least one of a medical device inside the subject's body and a blood vessel of the subject, the image generation unit generates a plurality of extracted images by extracting at least one of the medical device and the blood vessel from each of the plurality of X-ray images, and calculates a change in noise between each of the generated plurality of extracted images, and the imaging control unit controls the X-ray conditions so that the change in noise is equal to or less than a first predetermined value.

2. The X-ray imaging device of claim 1, wherein the image generation unit is configured to generate the plurality of extracted images from the plurality of X-ray images based on a trained model generated by machine learning, and the imaging control unit is configured to control the X-ray conditions so that the amount of change in noise between each of the plurality of extracted images is equal to or less than the first predetermined value.

3. The X-ray imaging device of claim 2, wherein the imaging control unit is configured to change the X-ray conditions and increase the X-ray exposure dose when the amount of change in noise between the multiple extracted images exceeds the first predetermined value so that the amount of change in noise is equal to or less than the first predetermined value.

4. The X-ray imaging device of claim 3, wherein the imaging control unit further controls the X-ray conditions so that the amount of change in noise is less than the first predetermined value and greater than or equal to a second predetermined value that is smaller than the first predetermined value, and when the amount of change in noise between the plurality of extracted images is less than the second predetermined value, changes the X-ray conditions to reduce the X-ray exposure dose so that the amount of change in noise is less than the first predetermined value and greater than or equal to the second predetermined value.

5. The X-ray imaging device of claim 3, wherein the imaging control unit is configured to change the X-ray conditions and increase the X-ray exposure dose so that the amount of change in noise is equal to or less than the first predetermined value when the amount of change in noise, i.e., a first number of pixels determined to be at least one of the medical device and the blood vessel in the extracted image in the current X-ray image and a second number of pixels determined to be at least one of the medical device and the blood vessel in the extracted image in the X-ray image earlier than the current X-ray image, exceeds the first predetermined value.

6. The X-ray imaging device of claim 4, wherein the imaging control unit is configured to, when the change in the noise between a first number of pixels determined to be at least one of the medical device and the blood vessel in the extracted image in the current X-ray image and a second number of pixels determined to be at least one of the medical device and the blood vessel in the extracted image in the X-ray image earlier than the current X-ray image, is less than the second predetermined value, change the X-ray conditions to reduce the X-ray exposure dose so that the change in the noise is less than the first predetermined value and greater than or equal to the second predetermined value.

7. The X-ray imaging device of claim 6, wherein the imaging control unit is configured to maintain the X-ray conditions when the change in the noise between the first number of pixels and the second number of pixels is less than the first predetermined value and greater than or equal to the second predetermined value.

Images