JP7312611B2 - X-ray diagnostic equipment - Google Patents

Description

An embodiment of the invention relates to an X-ray diagnostic apparatus.

2. Description of the Related Art Conventionally, medical institutions such as hospitals use X-ray diagnostic apparatuses for diagnosing subjects such as patients. For example, in a gastrointestinal imaging examination, X-rays are irradiated and photographed at a timing at which irregularities on the surface of the organ are easily visible, while controlling the degree of adhesion of a contrast medium to the surface of the organ by fluoroscopy. In this case, the contrast agent is controlled by controlling the tilt angle of the bed or instructing the subject to move the body, so knowledge and experience are required to irradiate the X-ray at the appropriate timing.

Further, conventionally, a technique has been proposed in which the pixel values of a monitoring image set with respect to reference image data displayed in real time are measured to automatically perform X-ray irradiation at the timing when a contrast medium flows into a diagnostic target site. However, in timing control based on image data, there is a possibility that a deviation may occur between the timing determined from the pixel values and the actual timing of X-ray irradiation.

Japanese Patent Application Laid-Open No. 2006-136500

The problem to be solved by the present invention is to support the determination of the timing of X-ray irradiation in an X-ray diagnostic apparatus.

An X-ray diagnostic apparatus according to an embodiment includes an X-ray generation unit, a detection unit, a generation unit, a reception unit, an acquisition unit, a determination unit, and a control unit. The X-ray generator generates X-rays. The detection unit detects X-rays that have passed through the subject. The generator generates an image based on the X-rays detected by the detector. The reception unit receives an operation for instructing the start of shooting. The acquisition unit acquires operation information representing the operation status of the own device. The determination unit determines the timing to start shooting based on the output result obtained by inputting the operation information acquired by the acquisition unit to a trained model that receives the input of the motion information and outputs the appropriateness of the timing to start shooting. The control unit controls the X-ray generation unit so that, if the reception unit receives the operation before the timing for starting imaging is determined by the determination unit, the X-ray generation unit is irradiated with X-rays at the timing of receiving the operation, and if the timing for starting imaging is determined by the determination unit before the reception unit receives the operation, the X-ray generation unit is controlled to irradiate the object with X-rays at the timing.

FIG. 1 is a diagram showing a configuration example of an X-ray diagnostic apparatus according to an embodiment. FIG. 2 is a diagram for explaining a method of generating a trained model according to the embodiment. FIG. 3 is a diagram illustrating an example of processing during learning of a trained model according to the embodiment. FIG. 4 is a diagram illustrating an example of processing during operation of a trained model according to the embodiment. FIG. 5 is a diagram for explaining an example of the operation of the imaging timing determination function according to the embodiment; FIG. 6 is a flowchart illustrating an example of imaging processing executed by the X-ray diagnostic apparatus according to the embodiment; FIG. 7 is a diagram showing a configuration example of an X-ray diagnostic apparatus according to Modification 1. As shown in FIG.

An embodiment of an X-ray diagnostic apparatus according to an embodiment will be described below with reference to the drawings.

FIG. 1 is a diagram showing a configuration example of an X-ray diagnostic apparatus according to this embodiment. As shown in FIG. 1, the X-ray diagnostic apparatus 1 includes a high voltage control unit 11, a high voltage generation unit 12, an X-ray generation unit 13, a mechanism control unit 14, an X-ray detection unit 15, an image calculation/storage unit 16, a display unit 17, an operation unit 18, and a system control unit 19.

The high-voltage controller 11 sets X-ray irradiation conditions such as tube current, tube voltage, and irradiation time in the high-voltage generator 12 according to an instruction signal from the system controller 19 . The high voltage generator 12 generates a high voltage to be applied between the anode and the cathode in order to accelerate thermoelectrons generated from the X-ray generator 13 .

The X-ray generator 13 has an X-ray tube 13a and an X-ray restrictor 13b. The X-ray tube 13a is a vacuum tube that generates X-rays, and accelerates electrons with a high voltage supplied from the high-voltage generator 12 to collide with a tungsten target to generate X-rays. The X-ray diaphragm 13b is positioned between the X-ray tube 13a and the subject P placed on the bed 2, and shapes the X-ray beam emitted from the X-ray tube 13a to form an X-ray beam with a desired solid angle.

The bed 2 is a bed on which the subject P is placed (mounted), and is arranged between an X-ray generator 13 and an X-ray detector 15 fixed at a predetermined distance by the C-arm 3 . The bed 2 is capable of moving the subject P in the vertical direction and longitudinal direction, rotating it upside down, and the like, in order to perform imaging of a predetermined portion of the subject P. As shown in FIG. Further, a configuration may be adopted in which a compression tube for compressing the abdomen of the subject P or the like is provided in association with the bed 2 . The movement amount, movement timing, movement speed, etc. of the bed 2, the C-arm 3, and the compression tube are controlled by a mechanism control section 14, which will be described later.

The mechanism control section 14 is an example of a mechanism section. The mechanism control section 14 has an image system movement mechanism section 14a, a bed movement mechanism section 14b, and a mechanism control circuit 14c. The imaging system moving mechanism section 14a is integrated with the C-arm 3 that supports the X-ray generating section 13 and the X-ray detecting section 15 (imaging system), and has a mechanism for rotating around the bed 2 and moving the subject P in the body axis direction.

The bed moving mechanism part 14b is integrated with the top plate of the bed 2, and has a mechanism for moving, tilting and rotating the bed 2 with the subject P placed thereon. Further, the mechanism control circuit 14c is a circuit for controlling the operations of the imaging system movement mechanism section 14a and the bed movement mechanism section 14b, and outputs control signals to each mechanism section. When a compression tube is provided in association with the bed 2, the bed moving mechanism 14b is assumed to have a mechanism for moving the compression tube (for example, moving between the retracted position and the pressing position).

The X-ray detector 15 is an example of a detector. The X-ray detector 15 has a flat panel detector 15a. The flat panel detector 15a is an FPD (Flat Panel Detector) and detects X-rays that have passed through the subject P. FIG. For example, the flat panel detector 15a has detection elements arranged in a matrix. Each detection element converts the X-rays that have passed through the subject P into an electric signal, accumulates the electric signal, and transmits the accumulated electric signal to the image calculation/storage unit 16 .

The image calculation/storage unit 16 is an example of a generation unit. The image calculation/storage unit 16 has an image calculation circuit 16a, an image data storage circuit 16b, and a display processing circuit 16c. The image calculation circuit 16a generates image data from the electrical signals accumulated by the flat panel detector 15a. The image data storage circuit 16b stores the image data generated by the image calculation circuit 16a. The display processing circuit 16c generates display image data by performing image processing for assisting human vision on the image data generated by the image calculation circuit 16a or the image data stored in the image data storage circuit 16b. Such image processing includes, for example, recursive filtering, gamma correction, dynamic range compression, and the like.

The display unit 17 displays the display image data generated by the display processing circuit 16c. The display unit 17 is implemented by, for example, a display device such as a liquid crystal monitor or a CRT (Cathode Ray Tube) monitor.

The operation unit 18 has a user interface 18a, an X-ray irradiation button 18b, a foot switch 18c, a microphone 18d, an imaging preparation detection unit 18e, and the like.

The user interface 18a is configured by a display device similar to the display unit 17, a touch panel display, or the like, and displays a GUI (Graphical User Interface) or the like for receiving instructions from the operator. The user interface 18a may be implemented by the display unit 17. FIG.

In the user interface 18a, the operator inputs the information of the subject P, the optimal X-ray irradiation conditions for the diagnosis target region of the subject P, the distance between the X-ray tube focus and the X-ray detector, the shape of the X-ray cone beam, the incident angle of the X-ray beam with respect to the subject P, various imaging conditions such as the movement speed of the bed 2 and the C-arm 3, and the movement control of the mechanism control unit 14. These setting signals and command signals are sent to each unit via the system control section 19 .

Subject information includes inspection sites, inspection methods, subject physiques, past diagnosis history, and the like. The X-ray irradiation conditions include the tube voltage applied to the X-ray tube 13a, the tube current, the X-ray irradiation time, and the like.

In addition, the operator inputs the inspection area of the subject P to be imaged via the user interface 18a. As the inspection area, the one specified in the guideline or the like is used. For example, in the examination of the upper gastrointestinal tract, the following 16 examination areas are sequentially set automatically or manually.
Esophagus: 2 segments (1) Standing 1st oblique (upper): Upper esophagus (2) Standing 1st oblique (lower): Lower esophagus to gastric cardia Stomach: 14 segments (3) Supine front: Body to posterior wall of anterior pylorus (4) Supine 1st oblique: Greater curvature to posterior wall to anterior pylorus (5) Supine second oblique: Lesser body to greater posterior pylorus (6) Prone Front (head low): Mid-body to anterior wall of the pylorus (7) Prone second oblique position (head low): Anterior wall near the greater curve of the body to anterior wall near the lesser curve of the pylorus (8) First oblique position in prone position: Cardia to upper stomach (upper body and vault) anterior wall (9) Right lateral position: Anterior and posterior wall centering on the lesser curvature of the cardia (10) Semi-recumbent second oblique position: Cardia to upper posterior wall of the body (1) 1) Supine 2nd oblique position (distribution): Upper body posterior wall lesser curve (12) Standing 1st oblique position: Upper body anteroposterior wall greater curve and duodenal bulb (13-16) Compression in standing position 4 areas (body, stomach, anterior floor of pylorus, pylorus)

The X-ray irradiation button 18b is an example of a receiving unit that receives an operator's operation (pressing). When the X-ray irradiation button 18b receives a pressing operation from the operator, the X-ray irradiation button 18b outputs to the system control unit 19 an imaging start signal instructing the start of imaging, that is, the start of X-ray irradiation. The system control unit 19 starts X-ray irradiation by controlling the high voltage control unit 11, the X-ray generation unit 13, the X-ray detection unit 15, and the like in response to an imaging start signal, as will be described later. Hereinafter, the photographing by the photographing start signal is also referred to as actual photographing. Further, the image data captured by the actual shooting is also called a captured image.

The foot switch 18c is a switch that is operated by being stepped on by the operator. For example, the foot switch 18c is used to operate the bed 2 and the C-arm 3 to move and rotate.

The microphone 18d is an example of a sound pickup unit that picks up the voice of the operator. The sound picked up by the microphone 18 d is output to the system control section 19 . Also, the sound picked up by the microphone 18d is output from a speaker provided in the room where the bed 2 is placed. For example, when the operator instructs the subject P to move the body, the operator gives the instruction via the microphone 18d.

The imaging preparation detection unit 18e is an example of a state detection unit that detects the state of the operator who operates the X-ray irradiation button 18b. Specifically, the imaging preparation detection unit 18e detects that the operator is in a state in which the X-ray irradiation button 18b can be operated (hereinafter referred to as an imaging preparation state). As an example, the imaging preparation detection unit 18e is implemented by a touch sensor provided on the X-ray irradiation button 18b. In this case, the imaging preparation detector 18e outputs to the system controller 19 a signal indicating the imaging preparation state while the operator's finger is in contact with the X-ray irradiation button 18b.

As another example, the imaging preparation detection unit 18e is implemented by an imaging device that captures an image of the vicinity of the X-ray irradiation button 18b, a recognition device that recognizes a human action from an image (video) captured by the imaging device, or the like. In this case, the imaging preparation detection unit 18e recognizes from the image captured by the imaging device whether or not the operator puts his or her finger on the X-ray irradiation button 18b. While the operator's finger is in contact with the X-ray irradiation button 18b, the imaging preparation detector 18e outputs to the system controller 19 a signal indicating the imaging preparation state.

The system control unit 19 has a storage circuit 19a and a processing circuit 19b. The storage circuit 19 a stores various programs and data related to the operation of the X-ray diagnostic apparatus 1 . Specifically, the storage circuit 19a stores a learned model M1, which will be described later. Such a learned model M1 is prepared for each inspection area described above and stored in association with identification information for identifying the inspection area. The storage circuit 19a is realized by, for example, a RAM (Random Access Memory), a semiconductor memory device such as a flash memory, a hard disk, or an optical disk.

The processing circuit 19 b controls the operation of the X-ray diagnostic apparatus 1 . Specifically, the processing circuit 19b controls the operation of each unit of the X-ray diagnostic apparatus 1 based on various information input by the operator via the operation unit 18 and various control programs and various data read from the storage circuit 19a.

The processing circuit 19 b also executes an acquisition function 191 , an examination area identification function 192 , an imaging timing determination function 193 and an imaging control function 194 . Here, the acquisition function 191 is an example of an acquisition unit. Inspection area identifier 192 is an example of an identifier. The imaging timing determination function 193 is an example of a determination unit. The shooting control function 194 is an example of a control unit.

For example, each processing function executed by an acquisition function 191, an inspection area identification function 192, an imaging timing determination function 193, and an imaging control function 194, which are components of the processing circuit 19b, is recorded in the storage circuit 19a in the form of a computer-executable program. The processing circuit 19b is a processor that reads out each program from the storage circuit 19a and executes it, thereby realizing functions corresponding to each program. In other words, the processing circuit 19b in a state where each program is read has each function shown in the processing circuit 19b of FIG.

In the present embodiment, it is assumed that each processing function described below is realized by a single processing circuit 19b, but a processing circuit may be configured by combining a plurality of independent processors, and the functions may be realized by each processor executing a program.

The acquisition function 191 acquires various types of information (hereinafter also referred to as operation information) representing the operation status of imaging from each unit of the X-ray diagnostic apparatus 1 . For example, the acquisition function 191 acquires information indicating an examination area to be imaged, which is input from the operation unit 18 (user interface 18a). The acquisition function 191 also acquires an imaging start signal input from the operation unit 18 (X-ray irradiation button 18b). Also, the acquisition function 191 acquires the operator's uttered voice input from the operation unit 18 (microphone 18d). The acquisition function 191 also acquires a shooting preparation signal input from the operation unit 18 (shooting preparation detection unit 18e).

Also, the acquisition function 191 acquires a photographed image or a fluoroscopic image from the image calculation/storage unit 16 . Here, the fluoroscopic image is image data obtained by imaging (provisional imaging) with an X-ray dose lower than that of the main imaging. The fluoroscopic image is processed by the image calculation/storage unit 16 and displayed on the display unit 17 in the same manner as the photographed image. Temporary imaging is performed continuously prior to actual imaging, and is used for positioning the imaging position, confirming the position of the contrast agent injected into the subject P, and the like. When applying the perspective image to the learning data or the trained model M1, it is preferable to use the image data before being processed by the display processing circuit 16c as the perspective image in order to avoid the influence of the processing delay by the display processing circuit 16c.

The acquisition function 191 also acquires, from the mechanism control unit 14, information indicating the operating states of the bed 2 and the C-arm 3, and information indicating the relative position of the X-ray generator 13 (X-ray tube 13a) with respect to the bed 2. Further, for example, when a compression cylinder is provided for the bed 2 , the acquisition function 191 acquires information indicating the position and operation state of the compression cylinder from the mechanism control unit 14 .

The operation information described above is input from each unit of the X-ray diagnostic apparatus 1 at any time, and the acquisition function 191 acquires the operation information at the input timing. Note that the acquisition function 191 may be configured to store a series of motion information related to imaging of the subject P for each examination area by storing each piece of motion information described above in association with information such as a time stamp indicating the timing at which the motion information was acquired.

The examination area identification function 192 identifies an examination area of the subject P to be imaged. Here, various methods can be adopted for the identification method for the inspection area. As an example, the inspection area identification function 192 may identify an inspection area to be imaged based on information indicating the inspection area among the operation information acquired by the acquisition function 191 . In this case, the inspection area identification function 192 identifies the inspection area to be imaged based on the most recently acquired information indicating the inspection area.

As another example, the inspection area identification function 192 may recognize the organ, the imaging position, the imaging angle, etc., represented in the fluoroscopic image from the fluoroscopic image acquired by the acquisition function 191, and identify the inspection area based on this recognition result. Furthermore, the examination area identification function 192 may identify an examination area from the information indicating the operating states of the bed 2 and the C-arm 3 acquired by the acquisition function 191 .

Note that the identification of the examination area based on the fluoroscopic image described above may be performed using, for example, a known technique related to image recognition. Further, identification of inspection areas based on the fluoroscopic image and motion states of the bed 2 and C-arm 3 may be performed using a model (learned model) generated by machine-learning the characteristics of the motion information. In this case, the machine learning model is functioned to receive these motion information inputs and output the inspection area. The inspection area identification function 192 inputs the fluoroscopic image acquired by the acquisition function 191 and the motion states of the bed 2 and the C-arm 3 into the model, thereby identifying the inspection area from the output result of the learned model.

Further, for example, when the examination areas are switched in a predetermined order as in the examination of the upper gastrointestinal tract described above, the examination area identification function 192 may be configured to automatically switch the examination area to be identified each time the main imaging is performed.

The imaging timing determination function 193 determines the timing (imaging timing) of actual imaging based on the operation information sequentially acquired by the acquisition function 191 . Specifically, the imaging timing determination function 193 determines the imaging timing of the subject P using the learned model M1 stored in the storage circuit 19a.

The trained model M1 will be described below. The trained model M1 is a model generated by using part or all of a series of motion information acquired by the acquisition function 191 during past imaging as data for learning, and by using as teaching data the result of judging the quality of the pressing timing of the X-ray irradiation button 18b based on the quality of the captured image obtained during the imaging. Such learning data is time-series data in which the elements included in the motion information are arranged in the order of acquisition timing of the elements.

Note that the generation of the learned model may be performed by the X-ray diagnostic apparatus 1 or may be performed by an apparatus other than the X-ray diagnostic apparatus 1 . In the following description, it is assumed that the X-ray diagnostic apparatus 1 (processing circuit 19b) generates a learned model.

FIG. 2 is a diagram for explaining a method of generating a trained model M1 according to this embodiment. FIG. 2 shows an example in which the fluoroscopic image, the voice of the operator (operator voice), the information indicating the motion of the bed 2 (bed position information), and the timing of pressing the X-ray irradiation button 18b (timing of pressing the X-ray irradiation button) among the operation information acquired by the acquisition function 191 are used as learning data. Also, the horizontal axis indicates the passage of time.

In FIG. 2, as the bed position information, the vertical movement, longitudinal movement, tilting rotation of the bed 2, the relative position of the X-ray tube 13a with respect to the bed 2 (X-ray tube-detector position), and the compression tube position are represented by binary values (operating or stopped, retracted position or compression position), but not limited to this, parameters such as coordinates, operation speed, and acceleration may be used.

A hatched portion in the fluoroscopic image represents a contrast agent injected into the stomach. The operator of the X-ray diagnostic apparatus 1 controls the adherence of the contrast medium to the surface of the organ by instructing the subject P to move or moving the bed 2 by voice based on the fluoroscopic image displayed on the display unit 17. Then, the operator presses the X-ray irradiation button 18b at a timing at which the unevenness of the surface of the organ is easily visible, thereby performing actual imaging.

For example, in FIG. 2, the operator speaks at the timing of time t4, and the X-ray irradiation button 18b is pressed at the timing of time t7. However, X-ray irradiation is not performed immediately after the X-ray irradiation button 18b is pressed, and X-ray irradiation is started at the timing of time t11. It should be noted that the fluoroscopic image capturing (provisional capturing) is generally interrupted when the X-ray irradiation button 18b is pressed. Therefore, the fluoroscopic image in the dashed frame shown from time t8 to time t11 indicates a provisional fluoroscopic image that will be obtained if provisional imaging continues even after the X-ray irradiation button 18b is pressed.

As described above, in the X-ray diagnostic apparatus 1, a lag (delay time) of time tD occurs from the timing when the X-ray irradiation button 18b is pressed (imaging timing) until the X-ray irradiation is performed, so the actually captured image represents the state at time t11. Such a delay time is a characteristic value unique to the X-ray diagnostic apparatus 1 due to factors such as the signal path of the X-ray diagnostic apparatus 1 .

Therefore, even if the operator presses the X-ray irradiation button 18b while viewing a fluoroscopic image, there is a possibility that a photographed image in an appropriate state cannot be obtained due to the above-described delay time. As described above, in the X-ray diagnostic apparatus 1, in addition to the movement of the bed 2 and the guidance of the subject P by voice, there is also the influence of the above-described delay time inherent in the X-ray diagnostic apparatus 1. Therefore, experience and learning are required to irradiate X-rays at appropriate timing.

The learned model M1 according to the present embodiment is a learned model for supporting the determination of shooting timing, and is generated through the learning process shown in FIG. Here, FIG. 3 is a diagram showing an example of processing during learning of the trained model M1.

As shown in FIG. 3, during learning, the processing circuit 19b inputs the fluoroscopic image obtained during imaging, the operator's voice, the bed position information, and the pressing timing of the X-ray irradiation button 18b in chronological order as learning data (example data). In addition, the processing circuit 19b inputs, as teacher data, the judgment result of the appropriateness of pressing timing (imaging timing) of the X-ray irradiation button 18b determined by the judgment result of the propriety of the captured image. A plurality of data sets of learning data and teacher data are prepared for each inspection area.

The processing circuit 19b generates a learned model M1 for each inspection area by executing machine learning using the data set described above. The trained model M1 can be configured by, for example, a neural network. A neural network is a network that has a structure in which adjacent layers arranged in layers are connected, and information propagates from the input layer side to the output layer side.

For example, the processing circuitry 19b inputs the datasets described above to a neural network. Here, in a neural network, information propagates in one direction from the input layer side to the output layer side while connecting only between adjacent layers. A multi-layer neural network is composed of, for example, an input layer, a plurality of intermediate layers (hidden layers), and an output layer. Arbitrary functions can be expressed in such a neural network by adjusting the parameters.

For example, the neural network can express a logistic curve that shows the relationship between the input learning data and the probability that the photographed image was taken correctly, that is, the probability that the photograph was taken at an appropriate timing. In this case, the neural network can receive input of learning data and perform binary classification that indicates whether the shooting timing is appropriate.

Then, the processing circuit 19b adjusts the parameters of the neural network so that the neural network can output preferable results when learning data, that is, various kinds of information acquired by the acquisition function 191 are input. As a result, the processing circuit 19b receives the input of the motion information (perspective image, operator's voice, bed position information) acquired by the acquisition unit, and can generate the learned model M1 that has the function of classifying whether the imaging timing is appropriate.

Although the trained model M1 is described as being composed of a neural network, the embodiment is not limited to this. That is, the trained model M1 may be generated by a machine learning method other than the neural network. For example, the processing circuit 19b may generate a learned model M1 that is functionalized to output imaging timing from information acquired by the acquisition unit by other machine learning techniques such as SVM (support vector machine) and deep learning. In particular, in deep learning, an image (perspective image) itself can be input and processed, so processing such as extracting feature amounts from the perspective image in advance is unnecessary, and the trained model M1 can be efficiently generated.

In addition, in the present embodiment, the data for learning is the fluoroscopic image, the operator's voice, the bed position information, and the timing of pressing the X-ray irradiation button. However, at least the fluoroscopic image and the timing of pressing the X-ray irradiation button are preferably included in the learning data.

In addition, the learning data acquired in this embodiment is a plurality of time-series data composed of fluoroscopic images and operation information such as X-ray irradiation button press timing, but the period targeted for machine learning is not particularly limited. For example, machine learning may be performed using the acquired learning data for all periods, or may be performed using learning data for a part of the period.

In the case of a partial period, for example, machine learning may be performed using learning data acquired during the period from the timing when the bed position information meets a predetermined condition to the timing when the X-ray irradiation button is pressed. Further, for example, machine learning may be performed using learning data acquired during a period from the timing when the operator utters a predetermined voice (such as holding his breath) to the timing when the X-ray irradiation button 18b is pressed.

As another example, machine learning may be performed using learning data acquired at the timing when the X-ray irradiation button 18b is pressed or at timings before and after the X-ray irradiation button 18b is pressed. In the former case, for example, machine learning is performed based on motion information such as a single transmission image acquired at the timing of pressing the X-ray irradiation button 18b. In the latter case, machine learning is performed based on operation information such as two transmission images acquired before and after the X-ray irradiation button 18b is pressed. When using a plurality of chronologically continuous fluoroscopic images as learning data, a difference image indicating the difference between the chronologically consecutive fluoroscopic images may be generated as preprocessing, and machine learning may be performed using the generated difference image.

Next, an example of processing during operation will be described with reference to FIG. Here, FIG. 4 is a diagram showing an example of processing during operation of the trained model M1.

First, the imaging timing determination function 193 selects a learned model M1 corresponding to the inspection area identified by the inspection area identification function 192 from among the learned models M1 stored in the storage circuit 19a.

The imaging timing determination function 193 sequentially inputs the fluoroscopic image, the operator's voice, and the bed position information among the motion information acquired by the acquisition function 191 to the learned model M1. Then, the imaging timing determination function 193 determines the imaging timing based on the suitability of the imaging timings sequentially output by the learned model M1. An operation example of the imaging timing determination function 193 will be described below with reference to FIG.

FIG. 5 is a diagram for explaining an example of the operation of the imaging timing determination function 193. As shown in FIG. Here, FIG. 5 shows an operation example when the same inspection area as in FIG. 2 is imaged. Note that the horizontal axis means the passage of time, as in FIG.

First, the imaging timing determination function 193 inputs the fluoroscopic image, the operator's voice, and the bed position information among the motion information acquired by the acquisition function 191 to the learned model M1. For example, in the example of FIG. 5, the information obtained from time t21 to time t27 is sequentially input.

The learned model M<b>1 outputs information (signal) indicating whether or not the imaging timing is appropriate each time information is input by the imaging timing determination function 193 . In FIG. 5, whether or not shooting timing is appropriate is indicated by ON and OFF. For example, between times t21 and t26, an OFF signal is output indicating that the imaging timing is inappropriate, and an ON signal is output indicating that the imaging timing is appropriate at time t27.

When the ON signal is detected, the imaging timing determination function 193 notifies the imaging control function 194 of imaging start, thereby determining imaging timing. Here, the output timing of the ON signal is inferred from the delay time specific to the X-ray diagnostic apparatus 1 described above and the relationship between a series of operation information related to the imaging operation. Therefore, if the X-ray irradiation is started at the timing of the ON signal, it is possible to obtain an appropriate photographed image in consideration of the delay time.

Note that the fluoroscopic image in the dashed frame shown from time t28 to time t31, like the fluoroscopic image from time t8 to time 11 in FIG.

Returning to FIG. 1, the imaging control function 194 controls the high voltage controller 11, the X-ray generator 13, the X-ray detector 15, and the image calculation/storage unit 16, and captures a fluoroscopic image or a photographic image. Specifically, the imaging control function 194 performs the following controls. First, the imaging control function 194 controls the high voltage controller 11 and the X-ray generator 13 to irradiate the subject P with X-rays. The imaging control function 194 then controls the image calculation/storage unit 16 to generate a fluoroscopic image or a captured image.

Further, the shooting control function 194 starts actual shooting of the shot image in response to a shooting start signal from the operation unit 18 or the shooting timing determination function 193 . Here, the imaging control function 194 performs exclusive control of the imaging start signal so that the actual imaging is performed once for each inspection area identified by the inspection area identification function 192 .

For example, if the acquisition function 191 acquires the start signal from the operation unit 18 before the shooting start signal is notified from the shooting timing determination function 193, the shooting control function 194 starts the actual shooting based on the start signal from the operation unit 18. Further, if the shooting timing determination function 193 notifies the shooting control function 194 of the start of shooting before the start signal is input from the operation unit 18, the shooting control function 194 starts the main shooting based on this notification.
However, when the actual imaging is started in response to an instruction from either the operation unit 18 or the imaging timing determination function 193, the imaging control function 194 performs exclusive control so that the actual imaging is not performed twice in the same examination area even if the other instructs to start imaging.

The photographing control function 194 validates the notification from the photographing timing determination function 193 only while the photographing preparation signal is input from the operation unit 18, and invalidates the notification from the photographing timing determination function 193 while the photographing preparation signal is not input even if the photographing start is notified from the photographing timing determination function 193.例文帳に追加As a result, even if the operator in the operation preparation state makes a mistake in operating the X-ray irradiation button 18b by carelessness, the subject P can be photographed at the photographing timing determined by the photographing timing determining function 193, so that the photographing timing can be prevented from being missed. Further, since the imaging timing determined by the imaging timing determination function 193 is invalidated while the imaging preparation signal is not input, it is possible to prevent the subject P from being imaged at the timing unintended by the operator.

Next, an operation example of the X-ray diagnostic apparatus 1 will be described with reference to FIG. Here, FIG. 6 is a flowchart showing an example of imaging processing executed by the X-ray diagnostic apparatus 1. As shown in FIG. As a premise of this process, it is assumed that the acquisition function 191 sequentially acquires motion information (step S11).

First, the examination area identification function 192 identifies an examination area of the subject P to be imaged based on the motion information and the like acquired by the acquisition function 191 (step S12). The imaging timing determination function 193 determines whether or not the inspection area identified in step S12 is the initial inspection area or the changed inspection area changed from the previous inspection area (step S13).

Here, if the inspection area is the first inspection area or a changed inspection area that has been changed from the previous inspection area (step S13; Yes), the imaging timing determination function 193 selects the learned model M1 corresponding to the inspection area identified in step S12 (step S14), and proceeds to step S15. If the inspection area identified in step S12 is neither the initial inspection area nor the changed inspection area changed from the previous inspection area (step S13; No), the imaging timing determination function 193 immediately proceeds to step S15.

Subsequently, the imaging timing determination function 193 inputs the motion information acquired by the acquisition function 191 to the learned model M1 (step S15), and determines whether the imaging timing is appropriate based on the output of the learned model M1 (step S16). Here, when it determines with it being unsuitable (step S16; No), it transfers to step S17.

In step S17, the imaging control function 194 determines whether or not an instruction to start imaging has been notified from the operation unit 18. If an instruction to start imaging has been notified (step S17; Yes), the process proceeds to step S19. It should be noted that if the shooting start instruction has not been notified (step S17; No), the shooting control function 194 returns the process to step S11.

Further, when the imaging timing determination function 193 determines that the imaging timing is appropriate in step S16 (step S16; Yes), it notifies the imaging control function 194 to start imaging. The shooting control function 194 that has received the shooting start notification from the shooting timing determination function 193 determines whether or not the operator is ready for shooting based on the state of the shooting preparation signal acquired by the acquisition function 191 (step S18). Here, when the imaging control function 194 determines that the imaging control function 194 is not in the imaging preparation state (step S18; No), the process returns to step S11.

On the other hand, if it is determined that the imaging is ready (step S18; No), the imaging control function 194 determines whether it is the first imaging in this inspection area (step S19). If shooting has already been performed (step S19; No), the shooting control function 194 returns the process to step S11 without shooting, thereby preventing multiple shots from being taken.

Further, when it is determined that it is the first shooting in step S19 (step S19; Yes), the shooting control function 194 starts shooting (actual shooting) (step S20) and returns to step S11.

The above-described processing is, for example, continuously executed until imaging is performed in all inspection areas, and ends when imaging is completed in the final inspection area.

In this way, the X-ray diagnostic apparatus 1 determines the timing to start imaging (imaging timing) based on the output result obtained by inputting the motion information acquired by the acquisition function 191 to the learned model M1 that receives input of motion information and outputs the appropriateness of the timing to start imaging. As a result, the X-ray diagnostic apparatus 1 starts X-ray irradiation based on the automatically determined imaging timing, thereby imaging the subject P at an appropriate timing in consideration of the delay time inherent in the apparatus itself. Therefore, since even an inexperienced operator can obtain a photographed image with high diagnostic performance, the X-ray diagnostic apparatus 1 can assist in determining the timing of X-ray irradiation.

It should be noted that the above-described embodiment can be appropriately modified and implemented by changing a part of the configuration or functions of the X-ray diagnostic apparatus 1 . Therefore, hereinafter, some modifications of the above-described embodiment will be described as other embodiments. In the following description, points different from the above-described embodiment will be mainly described, and detailed description of points common to the contents already described will be omitted. Further, the modifications described below may be implemented individually or in combination as appropriate.

(Modification 1)
In the above-described embodiment, a configuration in which an inspection area is specified and input via the user interface 18a of the operation unit 18 has been described, but the method of specifying the inspection area is not limited to this.

For example, the operation unit 18 may be provided with a dedicated user interface for instructing the examination area. FIG. 7 is a diagram showing a configuration example of the X-ray diagnostic apparatus 1 according to Modification 1. As shown in FIG. In the X-ray diagnostic apparatus 1 of FIG. 7, the operation unit 18 is provided with an examination area display/input unit 18f as a dedicated user interface for designating an examination area.

The inspection area display/input unit 18f is configured by, for example, a display device, a keyboard, a pointing device, a touch panel display, and the like. The examination area display/input unit 18f, for example, displays each examination area that can be handled by the X-ray diagnostic apparatus 1, and is configured so that a desired examination area can be selected. The inspection area selected via the inspection area display/input unit 18 f is output to the system control unit 19 . Further, the inspection area display/input unit 18f displays the currently set inspection area in a visible state.

By preparing a dedicated user interface for designating an examination area in this way, the operator of the X-ray diagnostic apparatus 1 can efficiently select and instruct an examination area. In addition, by displaying the currently set inspection area in a visible state, the operator can be made to recognize the inspection area being imaged, thereby supporting the imaging work.

(Modification 2)
In the above-described embodiment, the function of the system control unit 19 assists the timing of X-ray irradiation (imaging timing). However, the function does not need to be operated all the time, and the function may be switched between enabled and disabled.

For example, it may be possible to switch between enabling and disabling of the imaging timing determination function 193 via the user interface 18 a of the operation unit 18 . As a result, for example, when an operator skilled in operating the X-ray diagnostic apparatus 1 performs imaging, by disabling the imaging timing determination function 193, actual imaging can be performed only by operating the X-ray irradiation button 18b.

In the above-described embodiment, an example in which the functional configuration of the X-ray diagnostic apparatus 1 is implemented by the processing circuit 19b has been described, but the embodiment is not limited to this. For example, the functional configuration in this specification may be implemented by hardware alone or by a mixture of hardware and software.

In addition, the term "processor" used in the above description includes, for example, a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), or an application specific integrated circuit (ASIC), a programmable logic device (e.g., Simple Programmable Logic Device (SPLD), Complex Programmable Logic Device (CPLD), and Field Programmable Gate Array (FPGA)) and other circuits. means The processor implements its functions by reading and executing a program stored in the storage circuit 19a. Note that instead of storing the program in the memory circuit 19a, the program may be configured to be directly installed in the circuit of the processor. In this case, the processor implements the function by reading and executing the program embedded in the circuit. Moreover, the processor of the present embodiment is not limited to being configured as a single circuit, and may be configured as one processor by combining a plurality of independent circuits to realize its functions.

Here, the program executed by the processor is pre-installed in a ROM (Read Only Memory), a storage circuit, or the like and provided. In addition, this program is a computer-readable storage medium such as CD (Compact Disk)-ROM, FD (Flexible Disk), CD-R (Recordable), DVD (Digital Versatile Disk), etc. as a file in a format that can be installed in these devices or in an executable format. It may be provided. Also, this program may be provided or distributed by being stored on a computer connected to a network such as the Internet and downloaded via the network. For example, this program is composed of modules including each functional unit described above. As actual hardware, the CPU reads out a program from a storage medium such as a ROM and executes it, so that each module is loaded onto the main storage device and generated on the main storage device.

According to the embodiments described above, the determination of the timing of X-ray irradiation can be supported in the X-ray diagnostic apparatus.

While several embodiments of the invention have been described, these embodiments have been presented by way of example and are not intended to limit the scope of the invention. These embodiments can be implemented in various other forms, and various omissions, replacements, and modifications can be made without departing from the scope of the invention. These embodiments and their modifications are included in the scope and spirit of the invention, as well as the scope of the invention described in the claims and equivalents thereof.

1 X-ray diagnostic apparatus 19 System control unit 191 Acquisition function 192 Examination area identification function 193 Imaging timing determination function 194 Imaging control function M1 Learned model

Claims (7)

an X-ray generator that generates X-rays;
a detection unit that detects X-rays that have passed through the subject;
a generation unit that generates an image based on the X-rays detected by the detection unit;
a reception unit that receives an operation instructing the start of shooting;
an acquisition unit that acquires operation information representing the operation status of the own device;
a determination unit that determines the timing to start shooting based on an output result obtained by inputting the motion information acquired by the acquisition unit to a trained model that receives input of the motion information and outputs whether the timing to start shooting is appropriate;
a control unit for controlling the X-ray generation unit to irradiate the subject with X-rays at the timing of receiving the operation when the reception unit receives the operation before the timing for starting imaging is determined by the determination unit, and for controlling the X-ray generation unit to irradiate the subject with X-rays at the timing when the timing for starting imaging is determined by the determination unit before the reception unit receives the operation;
An X-ray diagnostic device comprising: an X-ray generator that generates X-rays;
a detection unit that detects X-rays that have passed through the subject;
a generation unit that generates an image based on the X-rays detected by the detection unit;
a reception unit that receives an operation instructing the start of shooting;
an acquisition unit that acquires operation information representing the operation status of the own device;
a determination unit that determines the timing to start shooting based on an output result obtained by inputting the motion information acquired by the acquisition unit to a trained model that receives input of the motion information and outputs whether the timing to start shooting is appropriate;
a control unit that controls the X-ray generation unit to irradiate the subject with X-rays at the timing when the reception unit receives the operation or at the timing determined by the determination unit;
a state detection unit that detects a state of an operator who operates the reception unit ;
with
The X-ray diagnostic apparatus, wherein the control unit validates the timing determined by the determination unit when the state of the operator detected by the state detection unit is in a predetermined state. an X-ray generator that generates X-rays;
a detection unit that detects X-rays that have passed through the subject;
a generation unit that generates an image based on the X-rays detected by the detection unit;
a reception unit that receives an operation instructing the start of shooting;
an acquisition unit that acquires operation information representing the operation status of the own device;
a determination unit that determines the timing to start shooting based on an output result obtained by inputting the motion information acquired by the acquisition unit to a trained model that receives input of the motion information and outputs whether the timing to start shooting is appropriate;
a control unit that controls the X-ray generation unit to irradiate the subject with X-rays at the timing when the reception unit receives the operation or at the timing determined by the determination unit;
with
The learned model is prepared for each inspection area of the subject,
The control unit controls the X-ray generation unit to irradiate the subject with X-rays at the timing when the reception unit receives the operation or the timing determined by the determination unit so that the subject is irradiated with X-rays once for each examination area. an X-ray generator that generates X-rays;
a detection unit that detects X-rays that have passed through the subject;
a generation unit that generates an image based on the X-rays detected by the detection unit;
a reception unit that receives an operation instructing the start of shooting;
a sound pickup unit that picks up a sound uttered by an operator who operates the reception unit ;
an acquisition unit that acquires operation information representing the operation status of the own device;
a determination unit that determines the timing to start shooting based on an output result obtained by inputting the motion information acquired by the acquisition unit to a trained model that receives input of the motion information and outputs whether the timing to start shooting is appropriate;
a control unit that controls the X-ray generation unit to irradiate the subject with X-rays at the timing when the reception unit receives the operation or at the timing determined by the determination unit;
with
The acquisition unit is an X-ray diagnostic apparatus that sequentially acquires sounds picked up by the sound pickup unit as the operation information. Further comprising an identification unit that identifies the inspection area,
4. The X-ray diagnostic apparatus according to claim 3, wherein the determination unit determines timing to start imaging using the learned model corresponding to the examination area identified by the identification unit. The X-ray diagnostic apparatus according to any one of claims 1 to 4, wherein the acquisition unit sequentially acquires, as the operation information, transmission images generated by the generation unit using X-rays with a dose lower than that of X-rays irradiated when imaging the subject. further comprising a mechanism unit for moving the bed on which the subject is mounted;
The X-ray diagnostic apparatus according to any one of claims 1 to 4, wherein the acquisition unit sequentially acquires information related to movement of the bed by the mechanical unit as the operation information.

Images