JP7412178B2 - X-ray diagnostic equipment and medical image processing equipment - Google Patents

Description

Embodiments of the present invention relate to an X-ray diagnostic device and a medical image processing device.

In the field of X-ray diagnostic equipment, automatic X-ray condition control (hereinafter also referred to as AEC), which automatically sets the X-ray conditions to be used according to the thickness of the subject, is a technology to improve the visibility of X-ray images. technology is known. In conventional AEC, X-ray conditions are not necessarily such that the visibility of the object of interest is high.

Special Publication No. 2009-504221

Ian Goodfellow and two others, “Chapter 9 Convolutional Networks,” Deep learning, MIT press, 2016, p. 330-372, Internet <URL: http://www.deeplearningbook.org> Aufrichtig R, Wilson DL, "X-ray fluoroscopy spatio-temporal filtering with object detection.", IEEE Trans. Med. Imaging, 1995:14(4):733-746 Michitaka Honda, Kunio Shiraishi, "Detection method of linear shadows by principal component analysis and its application to real-time fluoroscopic image processing", Journal of the Society of Medical Imaging and Information Science, 2004, Vol. 21, No. 3, p. 239-251

One of the problems that the embodiments disclosed in this specification and drawings are intended to solve is to obtain appropriate X-ray conditions for improving the visibility of X-ray images.

Further, one of the problems that the embodiments disclosed in this specification and the drawings are intended to solve is to improve the visibility of an X-ray image in which a pseudo linear shadow is captured.

However, the problems to be solved by the embodiments disclosed in this specification and the drawings are not limited to the above problems. Problems corresponding to the effects of each configuration shown in the embodiments described later can also be positioned as other problems.

The X-ray diagnostic apparatus according to the embodiment includes an imaging section, a determining section, and a control section.
The imaging unit irradiates the subject with X-rays and captures an X-ray image.
The determination unit determines the contribution of the pixel to the control of the X-ray conditions based on the analysis result of an X-ray image captured by X-ray irradiation with multiple energies using tube voltage switching.
The control unit controls X-ray conditions in imaging by single-energy X-ray irradiation without using the tube voltage switching, based on the determination result of the contribution.

FIG. 1 is a block diagram showing the configuration of an X-ray diagnostic apparatus according to a first embodiment. FIG. 2 is a block diagram showing the configuration of a console device and a medical image processing device in the X-ray diagnostic apparatus according to the first embodiment. FIG. 3 is a schematic diagram for explaining an example of a trained model according to the first embodiment. FIG. 4 is a flowchart for explaining the operation in the first embodiment. FIG. 5 is a flowchart for explaining the operation of step ST30 in the first embodiment. FIG. 6 is a sequence diagram and a schematic diagram for explaining the operation in the first embodiment. FIG. 7 is a schematic diagram of an original image and a spectral image for explaining the operation in the first embodiment. FIG. 8 is a schematic diagram showing an example of an original image for explaining the operation in the first embodiment. FIG. 9 is a schematic diagram showing an example of a bone image and a bone map image for explaining the operation in the first embodiment. FIG. 10 is a schematic diagram showing another example of the original image for explaining the operation in the first embodiment. FIG. 11 is a schematic diagram showing another example of a bone map image for explaining the operation in the first embodiment. FIG. 12 is a schematic diagram showing still another example of a bone map image for explaining the operation in the first embodiment. FIG. 13 is a block diagram showing the configuration of a console device and a medical image processing device in an X-ray diagnostic apparatus according to the second embodiment. FIG. 14 is a flowchart for explaining the operation in the second embodiment. FIG. 15 is a schematic diagram showing an example of an original image for explaining the operation in the second embodiment. FIG. 16 is a schematic diagram showing an example of a bone image for explaining the operation in the second embodiment. FIG. 17 is a schematic diagram showing an example of a bone map image for explaining the operation in the second embodiment.

Each embodiment will be described below with reference to the drawings.

<First embodiment>
FIG. 1 is a block diagram showing the configuration of an X-ray diagnostic apparatus according to the first embodiment, and FIG. 2 is a block diagram showing the configuration of a console device and a medical image processing device in the X-ray diagnostic apparatus. FIG. 3 is a schematic diagram for explaining an example of a learned model.

Here, the X-ray diagnostic apparatus 1 includes an imaging device 10, a bed device 50, a console device 70, and a monitor 80. The imaging device 10 includes a high voltage generator 11, an X-ray generator 12, an X-ray detector 13, a C-arm 14, and a C-arm controller 142. The imaging device 10 is an example of an imaging unit that irradiates a subject with X-rays and captures an X-ray image. Specifically, the imaging device 10 is an example of an imaging unit that captures an X-ray image of a subject by irradiating X-rays with a single energy or multiple energies.

The high voltage generator 11 generates a high voltage to be applied between an anode and a cathode and outputs it to the X-ray tube in order to accelerate thermoelectrons generated from the cathode of the X-ray tube.

The X-ray generator 12 includes an X-ray tube that irradiates the subject P with X-rays, and a function that limits the X-ray irradiation field and attenuates the X-rays in a part of the irradiation field. and an X-ray diaphragm.

X-ray tubes generate X-rays. Specifically, an X-ray tube is a vacuum tube that holds a cathode that generates thermoelectrons and an anode that generates X-rays by receiving the thermoelectrons flying from the cathode. For example, there is a rotating anode type X-ray tube that generates X-rays by irradiating a rotating anode with thermoelectrons. The X-ray tube is connected to a high voltage generator 11 via a high voltage cable. A tube voltage is applied between the cathode and the anode by a high voltage generator 11. Application of tube voltage causes thermoelectrons to fly from the cathode to the anode. Tube current flows as thermoelectrons fly from the cathode to the anode. By applying a high voltage and supplying filament current from the high voltage generator 11, thermoelectrons fly from the cathode to the anode, and when the thermoelectrons collide with the anode, X-rays are generated.

The X-ray diaphragm is located between the X-ray tube and the X-ray detector 13 and typically includes aperture blades, an additional filter, and a compensation filter. The X-ray diaphragm narrows down the X-rays generated by the X-ray tube so that only the region of interest of the subject P is irradiated by blocking X-rays outside the aperture area. For example, an X-ray aperture has aperture blades made of four lead plates, and by sliding these aperture blades, the area where X-rays are blocked can be adjusted to an arbitrary size. The aperture blades of the X-ray aperture are driven by a drive device (not shown) in accordance with the region of interest input by the operator through the input interface 73. Further, the X-ray diaphragm is configured such that an additional filter for adjusting the total filtration of X-rays can be inserted through the slit. Furthermore, the X-ray diaphragm is designed such that a lead mask and a compensation filter used during X-ray inspection can be inserted through the accessory insertion port. Note that the compensation filter may include a ROI (Region Of Interest) filter that has a function of attenuating or reducing the irradiated X-ray dose.

The X-ray detector 13 detects X-rays that have passed through the subject P. As such an X-ray detector 13, it is possible to use one that directly converts X-rays into electric charges, and one that converts X-rays into light and then converts them into electric charges.Here, the former will be explained as an example, but the latter can be used. It doesn't matter. That is, the X-ray detector 13 includes, for example, a two-dimensional image sensor using a CMOS (Complementary Metal Oxide) transistor, and a planar FPD (FPD) that converts X-rays transmitted through the subject P into charges and accumulates them. The FPD includes a flat panel detector) and a gate driver that generates drive pulses for reading out the charges accumulated in this FPD. This FPD may also be called a CMOS-FPD. The FPD is constructed by arranging minute detection elements two-dimensionally in the column and line directions. Each detection element includes a photoelectric film that senses X-rays and generates charges according to the amount of incident X-rays, a photodiode (PD) that accumulates the charges generated in the photoelectric film, and an amplifier circuit that amplifies the charges. It also includes an A/D converter that converts the amplified charge into a digital signal. The digital signals are sequentially read out by driving pulses supplied by the gate driver.

A projection data generation circuit (not shown) is provided downstream of the X-ray detector 13. The projection data generation circuit includes a parallel-serial converter that converts digital signals read out in parallel from the FPD row by row or column by column into time-series serial signals (time-series projection data). The time-series projection data is output from the projection data generation circuit and supplied to the medical image processing device 75.

The C-arm 14 can perform X-ray imaging of the subject P on the top plate 53 by holding the X-ray generator 12 and the X-ray detector 13 so as to face each other with the subject P and the top plate 53 in between. It has a configuration that can be used. In the following description, a ceiling hanging type C-arm will be described as an example, but the present invention is not limited thereto, and, for example, a floor-standing type C-arm may be used.

Specifically, the C-arm 14 is movable along the long axis direction and the short axis direction of the top plate 53. Further, the C-arm 14 is supported by a support arm via a holding portion. The support arm has a substantially arcuate shape, and its base end is attached to a moving mechanism relative to a rail provided on the ceiling. The C-arm 14 is held by a holding part so as to be rotatable about an axis in the X direction that is perpendicular to both the Y direction perpendicular to the top plate 53 and the Z direction along the long axis direction of the top plate 53. . Further, the C-arm 14 has a substantially arc shape centered on the axis in the Z direction, and is held by the holding portion so as to be slidable along the substantially arc shape. That is, the C-arm 14 can perform a sliding motion around the axis in the Z direction as the center of rotation. In addition, the C-arm 14 can rotate around the holding part and around an axis in the This makes it possible to observe X-ray images from any direction. Further, the C-arm 14 can also rotate about an axis in the Y direction, so that, for example, the rotation center axis of the above-mentioned sliding operation can be set in the X direction. Note that the imaging axis passing through the X-ray focal point of the X-ray generator 12 and the center of the detection surface of the X-ray detector 13 intersects the rotation center axis of the slide operation and the rotation center axis of the main rotation operation at one point. It is designed to. The intersection point is generally called the isocenter. The isocenter is not displaced even if the C-arm 14 performs the above-mentioned sliding movement or main rotation movement. Therefore, when the region of interest is located at the isocenter, it becomes easy to observe the region of interest in the moving image of the medical image obtained by the sliding motion or main rotation motion of the C-arm 14.

Such a C-arm 14 is equipped with a support arm under the rail, and a plurality of power sources at appropriate locations for realizing operations related to the X-direction axis, Y-direction axis, and Z-direction axis. There is. These power sources are controlled by a C-arm controller 142. The C-arm control device 142 reads the drive signal from the system control function 741 and causes the C-arm 14 to slide, rotate, and linearly move. Furthermore, each C-arm 14 is equipped with a state detector (not shown) that detects information about its angle, posture, or position. The state detector includes, for example, a potentiometer that detects the rotation angle and the amount of movement, an encoder that is a position detection sensor, and the like. As the encoder, a so-called absolute encoder such as a magnetic type, brush type, or photoelectric type can be used. Furthermore, as the state detector, various types of position detection mechanisms can be used as appropriate, such as a rotary encoder that outputs rotational displacement as a digital signal or a linear encoder that outputs linear displacement as a digital signal.

The bed device 50 is a device on which the subject P is placed and moved, and includes a base 51, a bed driving device 52, a top plate 53, and a support frame 54.

The base 51 is a casing that is installed on the floor and supports the support frame 54 movably in the vertical direction (Y direction).

The bed driving device 52 is housed in the casing of the bed device 50 and includes a motor or an actuator that moves the top plate 53 on which the subject P is placed in the longitudinal direction (Z direction) of the top plate 53. The bed driving device 52 reads a drive signal from the system control function 741 and moves the top plate 53 horizontally or vertically with respect to the floor surface.

The top plate 53 is a plate provided on the upper surface of the support frame 54 and on which the subject P is placed.

The support frame 54 movably supports the top plate 53 on which the subject P is placed. Specifically, the support frame 54 is provided on the upper part of the base 51 and supports the top plate 53 so as to be slidable along its longitudinal direction.

As shown in FIG. 2, the console device 70 includes a memory 71, a display 72, an input interface 73, and a processing circuit 74.

The memory 71 includes a memory body that records electrical information such as a ROM (Read Only Memory), a RAM (Random Access Memory), an HDD (Hard Disk Drive), and an image memory, and a memory controller, a memory interface, etc. attached to the memory body. peripheral circuits. The memory 71 stores, for example, programs executed by the processing circuit 74, projection data received from the X-ray detector 13, medical images generated by the processing circuit 74, data used for processing by the processing circuit 74, various tables, and processing. Intermediate data, processed data, etc. are stored. Examples of medical images include normal X-ray images, two-dimensional projection data (X-ray images) obtained by sequentially saving projection data, high-energy images, low-energy images, bone images, soft tissue images, and bone maps. There are images etc.

Here, the normal X-ray image is an X-ray image obtained by imaging a subject by irradiating X-rays with a single energy without using tube voltage switching. Note that "tube voltage switching" is not intended to be "adjustment of tube voltage by AEC" but to "control to alternately switch a plurality of tube voltages" in dual energy technology.

A high-energy image is an X-ray image taken using the higher energy (higher tube voltage) among the X-ray images taken of the subject by X-ray irradiation with multiple energies using tube voltage switching. .

A low energy image is an X-ray image taken using the lower energy (lower tube voltage) among the X-ray images taken of the subject by X-ray irradiation with multiple energies using tube voltage switching. .

A bone image is an X-ray image that is created by subjecting a high-energy image and a low-energy image to material discrimination processing, and clearly represents the bone portion of the bone portion and non-bone portion (soft tissue). As the bone image, for example, an X-ray image obtained by weighted subtraction of a low energy image and a high energy image so as to suppress the contrast of non-bone parts from the low energy image can be used as appropriate. Further, as the bone image, a bone thickness image, which is an image whose pixel value is the thickness of the bone, may be used.

A soft tissue image is an X-ray image that is created by subjecting a high-energy image and a low-energy image to material discrimination processing, and clearly represents a non-bone part (soft tissue) of a bone part and a non-bone part. As the soft tissue image, for example, an X-ray image obtained by weighted subtraction of a high-energy image and a low-energy image so as to suppress the contrast of bone parts from the high-energy image can be used as appropriate. Further, as the soft tissue image, a soft tissue thickness image, which is an image whose pixel value is the thickness of the soft tissue, may be used.

The bone map image is an image representing the result of discriminating bone parts and non-bone parts, for example, by subjecting a bone image to threshold processing. Note that instead of the bone map image, it is also possible to use an image representing the result of discriminating bone parts and non-bone parts, for example, by applying threshold processing to a soft tissue image.

In addition, as shown in FIG. 3, the memory 71 also stores a trained model Md2 obtained by training the machine learning model Md1 using the high energy image gHE, the low energy image gLE, and the bone map image gMp. good. The memory 71 may, for example, store a learned model Md2 in advance before the X-ray diagnostic apparatus 1 is shipped from the factory, or may store a learned model Md2 acquired from a server device (not shown) after the X-ray diagnostic apparatus 1 is shipped from the factory. Md2 may be stored. This also applies to each of the embodiments below. The trained model Md2 outputs the results of discriminating bone parts and non-bone parts from the X-ray image (e.g. bone map image gMp) based on the X-ray image taken by X-ray irradiation with multiple energies. It is designed to do so.

Such a trained model Md2 can be created as a trained model, which is a trained machine learning model, by causing the machine learning model Md1 to perform machine learning based on the learning data. Here, the learning data uses a high energy image gHE and a low energy image gLE, which are X-ray images captured by X-ray irradiation with multiple energies, as input data, and This is a set of input data and output data in which the bone map image gMp, which is the result of discrimination, is used as output data. The machine learning model is a parameterized composite function in which a plurality of functions are combined, which inputs the high energy image gHE and the low energy image gLE and outputs the bone map image gMp. A parameterized composite function is defined by a combination of multiple tunable functions and parameters. The machine learning model according to this embodiment may be any parameterized composite function that satisfies the above requirements, but is assumed to be a multilayer network model (hereinafter referred to as a multilayer network). The trained model Md2 using the multilayer network includes an input layer that inputs the high-energy image gHE and the low-energy image gLE, an output layer that outputs the bone map image gMp, and at least one layer that is provided between the input layer and the output layer. It has one intermediate layer. The learned model Md1 is assumed to be used as a program module that is part of artificial intelligence software. As such a multilayer network, for example, a deep neural network (DNN), which is a multilayer neural network that is a target of deep learning, is used. As the DNN, for example, a recurrent neural network (RNN) may be used for moving images, and a convolutional neural network (CNN) may be used for still images. This type of CNN is also called DCNN (Deep CNN). In this embodiment, DCNN is used as a trained model. Regarding CNN, for example, the aforementioned ``Ian Goodfellow and two others,'' ``Chapter 9 Convolutional Networks,'' deep learning, and MIT press. ), 2016, p.330-372, Internet <URL: http://www.deeplearningbook.org>. The RNN may also include long short-term memory (LSTM). The above description regarding the multilayered network also applies to all the machine learning models Md1 and learned models Md2 below.

For example, the program provides a computer with a determination function that determines the contribution of a pixel to the control of X-ray conditions based on the analysis result of an X-ray image taken by X-ray irradiation with multiple energies, and This realizes a control function for controlling X-ray conditions including single energy. Supplementally, as such a program, for example, a program that is installed in advance on a computer from a network or a non-transitory computer-readable storage medium and causes the computer to implement each function of the medical image processing device 75 is used. . Memory 71 is an example of a storage section.

The display 72 consists of a display main body that displays various information such as medical images, an internal circuit that supplies display signals to the display main body, and peripheral circuits such as connectors and cables that connect the display main body and the internal circuit. There is. The internal circuit generates display data by superimposing incidental information such as object information and projection data generation conditions on the image data supplied from the processing circuit 74, and performs D/A conversion and TV formatting on the obtained display data. It is converted and displayed on the display itself. For example, the display 72 outputs a medical image generated by the processing circuit 74, a GUI (Graphical User Interface) for accepting various operations from an operator, and the like. For example, the display 72 is a liquid crystal display or a CRT (Cathode Ray Tube) display. Further, the display 72 is an example of a display section. Further, the display 72 may be of a desktop type, or may be configured of a tablet terminal or the like that can communicate wirelessly with the main body of the console device 70. The display 72 is an example of a display section.

The input interface 73 performs input of subject information, setting of X-ray conditions, input of various command signals, and the like. The subject information includes, for example, subject ID, subject name, date of birth, age, weight, sex, examination site, and the like. Note that the subject information may include the height of the subject. The input interface 73 includes, for example, a trackball for instructing the movement of the C-arm 14, setting a region of interest (ROI), etc., a switch button, a mouse, a keyboard, a touch pad for performing input operations by touching the operation surface, and This is realized by a touch panel display or the like in which a display screen and a touch pad are integrated. The input interface 73 is connected to the processing circuit 74 , converts input operations received from the operator into electrical signals, and outputs the electrical signals to the processing circuit 74 . Furthermore, the input interface 73 may be configured with a tablet terminal or the like that can communicate wirelessly with the main body of the console device 70. Furthermore, in this specification, the input interface 73 is not limited to one that includes physical operation parts such as a mouse and a keyboard. For example, an electrical signal processing circuit that receives an electrical signal corresponding to an input operation from an external input device provided separately from the device and outputs this electrical signal to the processing circuit 74 is also included in the example of the input interface 73. .

The processing circuit 74 is a processor that implements a system control function 741, an image processing function 742, an analysis function 743, a determination function 744, and a display control function 745 corresponding to the program by calling and executing the program in the memory 71. Although the system control function 741, image processing function 742, analysis function 743, determination function 744, and display control function 745 are realized by a single processing circuit 74 in FIG. A processing circuit may be configured by combining processors, and each function may be realized by each processor executing a program. Furthermore, the system control function 741, image processing function 742, analysis function 743, determination function 744, and display control function 745 may be respectively referred to as a system control circuit, an image processing circuit, an analysis circuit, a determination circuit, and a display control circuit. It may be implemented as a hardware circuit.

For example, the system control function 741 temporarily stores information such as a command signal input by an operator through the input interface 73 and various initial setting conditions, and then transmits this information to each processing function of the processing circuit 74.

Further, the system control function 741 controls the C-arm control device 142 and the bed driving device 52 using, for example, information regarding the driving of the C-arm 14 and the top plate 53 inputted from the input interface 73. For example, the system control function 741 controls movement and rotation of the imaging device 10, movement and tilt of the bed device 50, and the like.

Further, the system control function 741 reads information set in the memory 71, for example, and controls X-ray conditions such as tube voltage, tube current, and irradiation time in the high voltage generator 11. The X-ray conditions may include the product of tube current and irradiation time (mAS).

Further, the system control function 741 determines the X-ray conditions for imaging by single-energy X-ray irradiation without using tube voltage switching, based on the determination result of the contribution of the pixel to the control of the X-ray conditions by the determination function 744, which will be described later. control. Such system control function 741 is an example of a control unit.

For example, the image processing function 742 performs image processing such as filtering processing on the projection data in the memory 71 to generate X-ray image data, and stores the X-ray image data in the memory 71. Examples of the X-ray image data generated from the projection data include medical image data such as a normal X-ray image, high energy gHE, and low energy image gLE.

The analysis function 743 analyzes an X-ray image captured by X-ray irradiation with multiple energies using tube voltage switching, and analyzes the results of discriminating bone parts and non-bone parts from the X-ray image. get as. For example, the analysis function 743 performs material discrimination processing and image calculations (subtraction processing, weighted subtraction processing, threshold processing) between the high-energy image gHE and the low-energy image gLE captured by X-ray irradiation with multiple energies, The obtained X-ray image data such as bone images, soft tissue images, and bone map images are stored in the memory 71. The bone map image may be called a "discrimination result" or an "analysis result". The analysis function 743 may be realized by a method using a program that describes an algorithm for predetermined material separation processing or image calculation processing, or may be realized by a method using the learned model Md described above. In the former case, for example, by analyzing an X-ray image captured by X-ray irradiation with multiple energies, a bone image with the contrast of non-bone parts suppressed is generated from the X-ray image, and the bone image is subjected to threshold processing. A program may be used to obtain the discriminated results by applying the following. In the latter case, for example, the X-ray image is input to a trained model for outputting the discriminated result based on the X-ray image captured by X-ray irradiation with multiple energies, and the discriminated result is input. You may also use a method of obtaining the analysis results by outputting . The analysis function 743 is an example of an analysis section.

The determination function 744 determines the contribution of a pixel to the control of X-ray conditions based on the analysis result of an X-ray image captured by X-ray irradiation with multiple energies using tube voltage switching. Note that "contribution of a pixel to control of X-ray conditions" indicates how much pixel value of which pixel is used for feedback of X-ray conditions. In other words, "determining the contribution of pixels to the control of X-ray conditions" involves selecting pixels to be used for calculating statistical values for feedback to X-ray conditions from among the pixels that make up the X-ray image. This also includes determining a weighting coefficient for each pixel when calculating statistical values for feedback to the X-ray conditions from the pixel values of each pixel constituting the X-ray image. In addition, "determining the contribution of pixels to the control of X-ray conditions" involves selecting pixels to be used for calculating statistical values for feedback to X-ray conditions, and furthermore selecting a weighting coefficient for each selected pixel. This includes determining the As the statistical value for feedback to the above-mentioned X-ray conditions, pixel values obtained by statistical methods such as simple average value calculation or weighted average value calculation can be used as appropriate. The pixel value obtained by the statistical method is not limited to this, and any value such as an extracted value, mode value, median value, maximum value, etc. can be used as appropriate. In any case, the decision function 744 uses the results of the multi-energy X-ray image analysis to determine the pixel's contribution to the X-ray condition feedback.

Here, when the determination function 744 obtains the result of discriminating bone parts and non-bone parts from the X-ray image as an analysis result, it determines whether or not the imaged device overlaps the pixels of the bone part. The contribution may be determined based on. "Imaged device" may also be read as "detected device" or "identified device."

Further, the determination function 744 may determine the contribution based on each pixel of the bone part among the pixels in the region of interest of the X-ray image when the device overlaps the pixel of the bone part. . At this time, if there are no pixels of the bone part within the region of interest, the determination function 744 moves the region of interest to include at least a part of the device, and each pixel of the bone part within the region of interest after the movement. The contribution may be determined based on.

Further, the determination function 744 may determine the contribution based on each pixel of the non-bone part among the pixels in the region of interest of the X-ray image when the device does not overlap the pixel of the bone part. good. At this time, if there are no pixels of the non-bone part within the region of interest, the determination function 744 moves the region of interest to include at least a part of the device, and determines the size of the non-bone part within the region of interest after the movement. The contribution may be determined based on each pixel. Note that "the case where no device overlaps the pixel of the bone" may be read as "the case where there is no device in the pixel of the bone". In any case, such determination function 744 is an example of a determination unit.

The display control function 745 performs controls such as displaying display data such as medical image data in the memory 71 on the display 72 and the monitor 80 . For example, the display control function 745 reads a signal from the system control function 741, acquires desired medical image data from the memory 71, and performs control such as displaying it on the display 72 and the monitor 80. The display control function 745 is an example of a display control section.

The monitor 80 is a display having a larger display surface than the display 72, and includes a display main body that displays various information such as medical images, an internal circuit that supplies display signals to the display main body, and a display main body and internal circuit. It consists of peripheral circuits such as connectors and cables that connect the The internal circuit generates display data by superimposing incidental information such as object information and projection data generation conditions on the image data supplied from the processing circuit 74, and performs D/A conversion and TV formatting on the obtained display data. It is converted and displayed on the display itself. The monitor 80 can display the same or different content as the display 72 under control from the display control function 745 of the processing circuit 74 .

These memory 71, display 72, input interface 73, image processing function 742, analysis function 743, determination function 744, and display control function 745 of the processing circuit 74 constitute a medical image processing device 75. Accordingly, the description regarding the image processing function 742, analysis function 743, determination function 744, and display control function 745 of the memory 71, display 72, input interface 73, and processing circuit 74 is the same as that of the X-ray diagnostic apparatus 1 and the medical image processing apparatus 75. Each of these is explained. The medical image processing device 75 may be built into the X-ray diagnostic device 1, or may be provided outside the X-ray diagnostic device 1 as a device separate from the X-ray diagnostic device 1.

Next, the operation of the X-ray diagnostic apparatus configured as described above will be explained using the flowcharts of FIGS. 4 and 5 and the schematic diagrams of FIGS. 6 to 12.

First, prior to collecting X-ray images, the operator operating the X-ray diagnostic apparatus 1 operates the input interface 73 to input subject information, and then performs Conditions, image data generation conditions, and image data display conditions are set, and these input information and setting information are stored in the memory 71. When this initial setting is completed, the operator moves/rotates the top plate 53 on which the subject P is placed and the C-arm 14 of the imaging device 10 in a predetermined direction, thereby allowing X-rays to be directed to the subject P. Set the imaging position and imaging direction for fluoroscopic imaging. After such a preparation stage, step ST10 is started.

In step ST10, the X-ray diagnostic apparatus 1 collects and displays normal X-ray images. For example, the processing circuit 74 of the X-ray diagnostic apparatus 1 sets a normal image acquisition sequence in response to the operation of the input interface 73 by the operator, and sets X-ray conditions including single energy based on the normal image acquisition sequence. By controlling, X-ray fluoroscopic imaging is started via the imaging device 10. Thereby, for example, an X-ray image of the torso of the subject P is obtained as a moving image. This X-ray image is a live image captured using a single energy, and is sequentially collected from the X-ray detector 13 to the medical image processing device 75 during X-ray fluoroscopic imaging. The collected X-ray images are stored in the memory 71 and displayed on the display 72 and monitor 80. However, immediately after the start of X-ray fluoroscopic imaging, no device such as a guide wire is inserted into the subject P, and the device does not appear in the X-ray image. After that, the device is inserted into the subject P.

After step ST10, in step ST20, the X-ray diagnostic apparatus 1 searches for a device from the X-ray image and detects the device. For device detection, a rule-based detection algorithm such as those in Non-Patent Documents 2 and 3 may be used, or a machine learning algorithm such as the CNN mentioned above may be used, and various device detection algorithms may be used. It is possible.

After step ST20, in step ST30, the X-ray diagnostic apparatus 1 collects and displays a spectral image using multiple energies in accordance with the operation of the input interface 73 by the operator. This step ST30 is executed like steps ST31 to ST36 as shown in FIG. 5, for example.

First, in step ST31, the processing circuit 74 sets a spectral image acquisition sequence according to the operation of the input interface 73 by the operator.

After step ST31, in steps ST32 and ST33, the processing circuit 74 collects spectral images by controlling the imaging device 10 based on the spectral image collection sequence. In other words, the imaging device 10 captures an X-ray image using multiple energies, and the processing circuit 74 analyzes the captured X-ray image. For example, as shown in FIG. 6(a), the processing circuit 74 controls the high voltage generator 11 and switches the tube voltage during one pulse from low kV to high kV, thereby generating multiple energies in one X-ray pulse. Switch to take an image. Imaging in which multiple energies are switched may be called dual-energy imaging or multi-energy imaging.

At this time, as shown in FIG. 6(b), charges are accumulated in the X-ray detector 13 that detects the X-rays transmitted through the subject P for each pixel of the FPD. Note that this FPD uses a CMOS type image sensor that can be sampled and held many times and can be read non-destructively.

Therefore, as shown in FIG. 6(c), the processing circuit 74 controls the X-ray detector 13 and uses the first readout signal, which is a drive pulse for reading out the X-ray image according to the low kV pulse. Accordingly, first projection data corresponding to the X image (SH1) is read from the FPD. The first projection data is collected by the medical image processing device 75 and sequentially stored in the memory 71, thereby generating an X-ray image (SH1) as two-dimensional first projection data. The X-ray image (SH1) is also referred to as a low energy image gLE.

Similarly, as shown in FIG. 6(d), in response to the second readout signal, which is a drive pulse for reading out the X-ray image corresponding to the high kV pulse, the second readout signal corresponding to the X-ray image (SH2) is Read projection data from FPD. The second projection data is collected by the medical image processing device 75 and sequentially stored in the memory 71, thereby generating an X-ray image (SH2) as two-dimensional second projection data. The processing circuit 74 of the medical image processing device 75 generates a high-energy image gLH by processing this X-ray image (SH2) and the previous X-ray image (SH1), and collects it in the memory 71. As this arithmetic processing, for example, subtraction processing (SH2-SH1) can be used.

The processing circuit 74 generates a spectral image gSP based on these low energy image gLE and high energy image gLH.

After that, as shown in FIG. 6(e), a reset signal is sent from the gate driver to the FPD, and the accumulated charge amount of the FPD pixel is reset. This completes the collection of the spectral image gSP for one X-ray pulse (one frame). Similarly, step ST32 is repeatedly executed for each frame.

Here, the acquisition of the spectral image gSP and the material discrimination processing in steps ST32 to ST33 will be supplementarily described. Collection of the spectral image gSP and material discrimination processing are performed in parallel.
For example, as shown in FIG. 7, the processing circuit 74 performs material discrimination processing on an original image gE such as a low energy image gLE and a high energy image gLH to produce a spectral image gSP such as a bone image gB and a soft tissue image gST. generate.

In the substance discrimination process, for example, the output signal ratio of the X-ray detector 13 corresponding to a pixel of an energy image captured with a certain energy E, with and without a subject, is expressed by equation (1).

However, I/I ₀ : output signal ratio of the X-ray detector 13 with and without a subject;
E: energy [keV],
N(E): number of photons (spectrum) at energy E,
μ _bone (E): Linear attenuation coefficient of bone at energy E [cm ^-1 ],
μ _soft (E): Linear attenuation coefficient of soft tissue at energy E [cm ^-1 ],
d _bone : bone thickness [cm],
d _soft : Thickness of soft tissue [cm].

Here, based on Equation (1), Equation (2) for the X-ray spectrum due to low energy E _L and Equation (3) for the X-ray spectrum due to high energy E _H are created.

However, I _EL /I _{0_EL} : The output signal ratio of the X-ray detector 13 with and without the object when using low energy _EL ,
I _EH /I _{0_EH} : Output signal ratio of the X-ray detector 13 with and without the object when using high energy E _H.

In equations (2) and (3), the two unknowns are the bone thickness d _bone and the soft tissue thickness d _soft . Therefore, by solving the simultaneous equations of equations (2) and (3), the bone thickness d _bone and the soft tissue thickness d _soft are calculated. According to the discrimination method using two energies as described above, devices such as guide wires are mainly classified into bones with similar linear attenuation coefficients. At the pixel where the device is detected in ST20, the bone thickness d _bone may be determined by interpolating the bone thickness d _bone at surrounding pixels. Alternatively, the bone thickness d _bone is corrected by subtracting the bone thickness corresponding to a typical device from the bone thickness d _bone calculated based on equations (2) and (3). You may. A bone image gB and a soft tissue image gST can be created based on the bone thickness d _bone and the soft tissue thickness d _soft at the pixels of the energy image. Bone image gB is an X-ray image in which the contrast of soft tissue is suppressed and clearly represents a bone region. The soft tissue image gST is an X-ray image in which the contrast of the bone region is suppressed and clearly represents the soft tissue. In this way, substance discrimination processing is performed.

Note that the bone image gB and the soft tissue image gST are not limited to the method of creating the material discrimination processing described above, but may be created using dual energy subtraction processing, which is another method of material discrimination. In this case, instead of the substance discrimination process described above, dual energy subtraction processing using the low energy image gLE and the high energy image gHE is executed. For example, pixels representing soft tissue are selected at the same position in each of the low energy image gLE and the high energy image gHE. Here, the soft tissue of the low energy image gLE is erased based on the value of the pixel representing the soft tissue of the high energy image gHE and the value of the pixel representing the soft tissue of the low energy image gLE. The high energy image gHE is weighted subtracted from gLE. A bone image gB is generated by appropriately correcting the result of this weighted subtraction. As described above, the bone image gB is an X-ray image in which the contrast of soft tissue is suppressed and clearly represents a bone region.

Similarly, for example, pixels indicating a bone are selected at the same position in each of the low energy image gLE and the high energy image gHE. Here, based on the pixel value indicating the bone part of the high-energy image gHE and the value of the pixel indicating the bone part of the low-energy image gLE, the high-energy image The low energy image gLE is weighted subtracted from gHE. A soft tissue image gST is generated by appropriately correcting the result of this weighted subtraction. As described above, the soft tissue image gST is an X-ray image in which the contrast of the bone region is suppressed and clearly represents the soft tissue.

In either material discrimination processing or dual energy subtraction processing, once a spectral image gSP such as a bone image gB and a soft tissue image gST is generated, steps ST32 to ST33 for one frame are completed. Note that, as the bone image gB, for example, a bone thickness image whose pixel value is the thickness of the bone may be used. Further, as the soft tissue image gST, for example, a thickness image of a soft tissue whose pixel value is the thickness of the soft tissue may be used.

After steps ST32 and ST33, in step ST34, the processing circuit 74 determines whether the displayed image is a spectral image gSP in accordance with the operation of the input interface 73 by the operator.

As a result of the determination in step ST34, if the displayed image is a spectral image, the processing circuit 74 displays the bone image gB and the soft tissue image gST on the display 72 and the monitor 80 in step ST35.

On the other hand, if the displayed image is not a spectral image as a result of the determination in step ST34, the processing circuit 74 causes the display 72 and monitor 80 to display the low energy image gLE and the high energy image gHE in step ST36.

With the above steps, step ST30 consisting of steps ST31 to ST36 is completed.

After step ST30, returning to FIG. 4, in step ST40, the processing circuit 74 performs threshold processing on the bone image gB, thereby displaying a bone image representing the result of discriminating bone parts and non-bone parts (soft tissue). Create a map image. As a supplementary note, although the bone image gB is an X-ray image that clearly shows bone parts, there are areas where the distinction between bone parts and non-bone parts is not clear. On the other hand, in the bone map image, by subjecting the bone image gB to threshold processing, bone parts and non-bone parts in the bone image gB can be clearly distinguished. The bone map image is, for example, an image obtained by maintaining the pixel values of bone parts in the bone image gB and changing the pixel values of non-bone parts to set values. The setting value is preferably a value such as 0 (zero value) that makes it easy to identify pixels of non-bone parts. Note that since the bone map image is not an image for display but an image for internal calculation, there is no need to use values that bring about visual effects such as coloring or patterning as setting values. Such a bone map image clearly distinguishes and represents bone parts and non-bone parts. In any case, according to steps ST30 and ST40, it is possible to obtain an analysis result of an X-ray image captured by X-ray irradiation with multiple energies. Specifically, in steps ST32, ST33, and ST40, the results of discriminating bone parts and non-bone parts (bone A map image gMp) can be obtained as an analysis result. Specifically, in steps ST32, ST33, and ST40, a bone image in which the contrast of non-bone parts is suppressed is generated from the X-ray image by analyzing an X-ray image captured by X-ray irradiation with multiple energies. By applying threshold processing to the bone image, a discriminated result can be obtained. Note that the processing circuit 74 inputs the X-ray image to the trained model Md2 for outputting the discrimination result based on the X-ray image captured by X-ray irradiation with multiple energies, and outputs the discrimination result. The analysis results may be obtained by outputting the results.

Thereafter, the processing circuit 74 determines the contribution of the pixel to the X-ray condition control (AEC) based on the analysis result of the X-ray image captured by X-ray irradiation with multiple energies (steps ST50 to ST120). The explanation will be given below in order.

After step ST40, in step ST50, the processing circuit 74 determines whether a device such as a guide wire is present in the bone. This step ST50 is a process of determining the contribution based on whether or not the device overlaps the pixels of the bone part, when the result of discriminating bone parts and non-bone parts from the X-ray image is obtained as an analysis result. This is an example. In the example shown in FIG. 8, it is assumed that in the original image gE, the guide wire Wg is located in a bone region and is difficult to visually recognize. Further, it is assumed that the region of interest ROI is set at a position that does not include the guide wire Wg.

At this time, as shown in FIG. 9, the guide wire Wg is visible in the bone image gB. Furthermore, according to the bone map image gMp in which bone and non-bone parts of the bone image gB are distinguished, it is found that the guide wire Wg is located in a bone part. That is, in the case of the example shown in FIGS. 8 and 9, the processing circuit 74 determines that the device is in the bone (ST50: Yes).

On the other hand, in the example shown in FIG. 10, it is assumed that the guide wire Wg is located in a non-bone part in the original image gE and is difficult to visually recognize. Further, it is assumed that the region of interest ROI is set at a position that does not include the guide wire Wg. In other words, it is assumed that the region of interest ROI is located in an area where the image level of the site where the guide wire is placed is less reflected.

At this time, as shown in FIG. 11, according to the bone map image gMp in which the bone and non-bone parts of the bone image gB are distinguished, it is found that the guide wire Wg is located in the non-bone part. That is, in the case of the example shown in FIGS. 10 and 11, the processing circuit 74 determines that the device is in a non-bone region (ST50: No).

Here, the processing of steps ST60 to ST80, which is carried out in the case of step ST50: Yes, and the processing of steps ST90 to ST110, which is carried out in the case of step ST50: No, will be described in order.

As a result of the determination in step ST50, if the device is located in a bone region (ST50: Yes), in step ST60, the processing circuit 74 determines whether there are pixels that can be used for X-ray condition control (AEC) within the region of interest ROI. Determine whether or not. Note that the pixels that can be used for AEC in step ST60 are those of the bone region in order to make it easier to see the device located in the bone region.

As a result of the determination in step ST60, if there are no usable pixels, the process moves to step ST70. In step ST70, the processing circuit 74 moves the region of interest ROI to the vicinity of the device. As a result, the region of interest ROI includes pixels of the bone near the device. Note that pixels within the region of interest ROI are used for AEC. Further, in step ST70, if there are no pixels of the bone within the region of interest, the region of interest is moved to include at least a part of the device, and based on each pixel of the bone within the region of interest after the movement. This is an example of a process for determining contribution. After step ST70, the process moves to step ST80.

On the other hand, as a result of the determination in step ST60, if there are available pixels, the process moves to step ST80. In step ST80, the processing circuit 74 excludes pixels of non-bone parts from among the pixels in the region of interest ROI, and uses the remaining pixels of the bone part as pixels in the region of interest ROI for AEC. Furthermore, steps ST60 and ST80 are an example of a process of determining the contribution (increasing the contribution rate) of pixels that overlap with the detected device among the pixels of the bone within the region of interest ROI. . As a supplement, when the device is located in a bone region, the basic process is to add and average the pixels of the bone region within the region of interest ROI (simple average value calculation) to obtain the AEC signal level within the ROI. As a variation, the pixel values of the pixels in the bone area where the device is placed are subjected to averaging processing, and a weighted calculation (weighted average value calculation) is performed to obtain the signal level for AEC within the ROI. May be executed. After step ST80, the process moves to step ST120.

The above is the process of steps ST60 to ST80 that is proceeded to when step ST50: Yes.

On the other hand, as a result of the determination in step ST50, if the device is not in the bone region (ST50: No), in step ST90, the processing circuit 74 determines that the pixels that can be used for X-ray condition control (AEC) are located in the region of interest ROI. Determine whether it is within the range. Note that the pixels that can be used for AEC in step ST90 are pixels in non-bone areas (soft tissue) in order to make it easier to see devices that are not in bone areas.

As a result of the determination in step ST90, if there are no usable pixels (ST90: No), the process moves to step ST100. In step ST100, the processing circuit 74 moves the region of interest ROI to the vicinity of the device, as shown in FIG. As a result, the region of interest ROI includes pixels of the non-bone part near the device. Note that pixels of non-bone parts within the region of interest ROI are used for AEC. Further, in step ST100, if there are no pixels of the non-bone part within the region of interest, the region of interest is moved so as to include at least a part of the device, and each pixel of the non-bone part within the region of interest after the movement is This is an example of a process for determining contribution based on . After step ST100, the process moves to step ST110.

On the other hand, as a result of the determination in step ST90, if there are available pixels, the process moves to step ST110. In step ST110, the processing circuit 74 excludes pixels in the bone part from among the pixels in the region of interest ROI, and sets the remaining pixels in the non-bone part as pixels in the region of interest ROI. Note that pixels of non-bone parts within the region of interest ROI are used for AEC. In addition, in steps ST90 and ST110, when the pixels of the bone part do not overlap with the device, the pixels of the bone part are excluded from each pixel in the region of interest of the X-ray image, and the pixels of the remaining non-bone part are removed. This is an example of a process for determining contribution based on each pixel. After step ST110, the process moves to step ST120. The above is the process of steps ST90 to ST110 to which the process proceeds in the case of step ST50: No.

Next, in step ST120, the processing circuit 74 executes calculation of pixel values within the region of interest ROI. As this calculation, for example, any one of the following calculations (a) to (c) can be used as appropriate.

(a) A pixel value is calculated according to the bone thickness d _bone calculated in step ST33.

(b) A simple average value calculation may be performed on the remaining pixels in the region of interest ROI after ST80 or ST110.

(c) Based on the bone thickness d _bone calculated in step ST33, arithmetic processing is performed in which a pixel with a bone thickness d _bone closer to the bone thickness d _bone at a pixel near the device is given a larger weight (e.g., Weighted average value calculation) may also be performed.

Step ST120 ends by executing any one of the calculations (a) to (c) above. Note that the obtained calculation results of pixel values within the region of interest ROI are used for AEC.

After step ST120, in step ST130, the X-ray diagnostic apparatus 1 collects and displays a normal X-ray image that is a live image captured using a single energy, similarly to step ST10 described above. However, as the tube voltage in the normal image acquisition sequence that is set, the value of the tube voltage adjusted by AEC based on the calculation result in step ST120 is used. Such step ST130 is an example of a process of controlling X-ray conditions including single energy based on the determination result of contribution.

In step ST140, the X-ray diagnostic apparatus 1 searches for a device from the X-ray image and detects the device, similarly to step ST20 described above.

After step ST140, in step ST150, the processing circuit 74 determines whether or not to update the bone map image gMp, for example, in accordance with the operation of the input interface 73 by the operator. For example, if the device in the X-ray image is difficult to see, the bone map image gMp is updated by an operator's operation. Furthermore, if the device in the X-ray image is easy to see, the bone map image gMp is not updated. Note that the present invention is not limited to this, and the processing circuit 74 may update the bone map image gMp when the X-ray image changes. The change in the X-ray image may be, for example, a change in the device position within the X-ray image, or a change in the imaging range of the X-ray image.

As a result of the determination in step ST150, if the bone map image gMp is not updated, the processing circuit 74 returns to step ST130 and continues the processing in steps ST130 to ST150.

On the other hand, if the bone map image gMp is to be updated as a result of the determination in step ST150, the processing circuit 74 returns to step ST30 and continues the processing in steps ST30 to ST150. Note that during execution of the above processing, when an instruction to end imaging is input, the processing is ended.

As described above, according to the first embodiment, an X-ray image of the subject is captured based on X-ray conditions including single energy or multiple energies, and the X-ray image captured by X-ray irradiation with the multiple energies is Based on the image analysis result, the contribution of the pixel to the control of the X-ray conditions is determined, and based on the determination result of the contribution, the X-ray conditions including single energy are controlled.

Therefore, it is possible to obtain appropriate X-ray conditions for improving the visibility of X-ray images taken of subjects having different X-ray absorption differences. Moreover, comprehensive optimization can be expected. As a result, it can be expected to improve image quality and reduce exposure dose by selecting appropriate X-ray conditions.

As a supplement, there is room for improvement in the prior art in that appropriate X-ray conditions for improving visibility cannot be obtained for X-ray images taken of subjects having different X-ray absorption differences. Specifically, for example, in cardiovascular angiography, X-ray images are taken of multiple areas with different X-ray absorption differences, such as the lung field where X-ray absorption is low and the vertebrae where X-ray absorption is high. In images, the difference in signal image level is large and the dynamic range is wide. Therefore, in the conventional technology, when a guide wire is located above a vertebral part that absorbs a lot of X-rays and there are few vertebral parts within the region of interest for evaluating the image level of AEC, it is difficult to clearly display the guide wire. Appropriate X-ray conditions cannot be obtained. In addition, in the conventional technology, on the other hand, appropriate X-ray conditions cannot be obtained even when the guide wire is located above a lung field with low X-ray absorption and there are few lung fields within the region of interest. .

On the other hand, according to the first embodiment, as described above, appropriate X-ray conditions for improving visibility can be obtained for X-ray images taken of subjects having different X-ray absorption differences.

Further, by analyzing an X-ray image captured by X-ray irradiation with multiple energies, the analysis result may be a result of discriminating bone parts and non-bone parts from the X-ray image. In this case, it is possible to obtain appropriate X-ray conditions for improving the visibility of an X-ray image taken of a subject consisting of bone and non-bone parts having different X-ray absorption differences.

As a supplement, using an X-ray spectral imaging method that can generate images of only the intended substance based on multiple X-ray energy information, it is possible to detect high-absorption areas such as bones and other low-absorption areas equivalent to water in the acquired image area. Generate a differential mapping image of the soft tissue site of absorption. Automatic X-ray condition control and image processing can be performed based on the created mapping image.

Further, the contribution may be determined based on whether or not pixels of the bone portion overlap the device. In this case, even when it is difficult to see the device overlapping the bone, appropriate X-ray conditions can be obtained to improve the visibility of the device.

Furthermore, when pixels of the bone region overlap the device, the contribution may be determined based on each pixel of the bone region among the pixels within the region of interest of the X-ray image. In this case, appropriate X-ray conditions for improving the visibility of the device can be obtained based on each pixel of the bone within the region of interest.

In addition, if there are no pixels of the bone within the region of interest, the region of interest is moved to include at least a part of the device, and the contribution is determined based on each pixel of the bone within the region of interest after the movement. may be determined. In this case, even if there are no pixels of the bone within the region of interest, the region of interest can be moved to include pixels of the bone, so the operation for determining the contribution of pixels to the control of X-ray conditions is Reliability can be improved.

Furthermore, when pixels of the bone region do not overlap the device, the contribution may be determined based on each pixel of the non-bone region among the pixels within the region of interest of the X-ray image. In this case, appropriate X-ray conditions for improving the visibility of the device can be obtained based on each pixel of the non-bone part within the region of interest.

In addition, if there are no pixels of the non-bone part within the region of interest, the region of interest is moved so as to include at least a part of the device, and based on each pixel of the non-bone part within the region of interest after the movement, The contribution may be determined. In this case, even if there are no pixels of the non-bone part in the region of interest, the region of interest can be moved to include pixels of the non-bone part in the region of interest, so the contribution of pixels to the control of the X-ray conditions can be determined. Operation reliability can be improved.

In addition, by analyzing X-ray images captured by X-ray irradiation with multiple energies, bone images with suppressed contrast of non-bone parts are generated from the X-ray images, and by applying threshold processing to the bone images, discrimination can be achieved. You may also obtain the same result. In this case, an analysis result of the X-ray image can be obtained mainly using an image processing method.

In addition, by inputting the X-ray image to a trained model for outputting the results of discrimination based on the X-ray images captured by X-ray irradiation with multiple energies, and outputting the results of the discrimination, , an analysis result may be obtained. In this case, an analysis result of the X-ray image can be obtained using a neural network.

The effects of the first embodiment as described above can also be appropriately expressed as in [10] to [15] below.
[10] X-ray conditions can be controlled by using bone images and soft tissue images obtained by spectral image collection.

[11] Among the material discrimination images (bone images, soft tissue images) obtained in [10] above, bone images can be used to create a bone map.

[12] Using [11] above, it is possible to determine whether a separately identified target device is on the bone map.

[13] As a result of the judgment in [12] above, when the target device is on the bone map, non-bone X-ray conditions can be controlled by excluding pixels for which it has been determined that Further, when the target device is not on the bone map, the X-ray conditions can be controlled by excluding pixels determined to be bones from the AEC_ROI set on the original image.

[14] In [13] above, if there is no corresponding pixel, the X-ray conditions can be controlled by moving the AEC ROI to a nearby area.

[15] In the above [13], when controlling the X-ray conditions when the target device is on the bone map, the value of the set tube voltage can be controlled according to the thickness of the bone.

<Second embodiment>
FIG. 13 is a block diagram showing the configuration of a console device and a medical image processing device included in the X-ray diagnostic apparatus according to the second embodiment, and the same parts as in FIG. will be omitted, and we will mainly discuss the different parts here.

The second embodiment is a modification of the first embodiment, and is a form that improves visibility in real time for an X-ray image in which many pseudo linear shadows are captured. Specifically, instead of the determination function 744 shown in FIG. 2, the processing circuit 74 includes a detection function 746 and an emphasis function 747 as shown in FIG. Note that the term "real-time" does not strictly mean a process that improves visibility at the moment an X-ray image is taken, but a process that improves visibility sequentially from the moment an X-ray image is taken. This means that the processing for

Here, the detection function 746 of the processing circuit 74 detects a device based on an analysis result of an X-ray image captured by the above-described imaging apparatus 10 by irradiating X-rays with multiple energies using tube voltage switching. As a supplement, the detection function 746 uses the analysis results of X-ray images using multiple energies to detect devices.

In addition, when the above-described analysis function 743 has obtained a result of discriminating bone parts and non-bone parts from the X-ray image, the detection function 746 detects the difference between the bone part and the non-bone part in the X-ray image. , the device may be detected by searching for the device from each pixel of the bone. Note that, as described above, the analysis function 743 inputs the X-ray image to the trained model Md2 for outputting the discrimination result based on the X-ray image captured by X-ray irradiation with multiple energies. However, the analysis result may be obtained by outputting the discriminated result. The detection function 746 is an example of a detection unit.

The enhancement function 747 of the processing circuit 74 generates an enhanced image by executing enhancement processing of the device. As the enhancement process, any image processing such as contrast enhancement, edge enhancement, and color display can be used. Further, in the device enhancement process, the entire device within the region of interest may be emphasized, or a portion of the device within the region of interest may be emphasized. Furthermore, the device enhancement process is not limited to emphasizing the pixels of the device, but may also emphasize pixels around the device. The emphasis function 747 is an example of an emphasis section.

Other configurations are similar to the first embodiment.

Next, the operation in the second embodiment will be explained using the flowchart of FIG. 14 and the schematic diagrams of FIGS. 15 to 17. First, after the preparatory steps such as the above-mentioned initial settings are performed, step ST210 is started.

In step ST210, a normal X-ray image is collected and displayed, similar to step ST10 described above.

After step ST10 ends, steps ST220 to ST240 are executed in the same manner as steps ST31 to ST33 described above. As a result, original images gE such as low energy images gLE and high energy images gHE, and spectral images gSP such as bone images gB and soft tissue images gST are collected by the medical image processing device 75 of the X-ray diagnostic apparatus 1. In the collected original image gE, as shown in an example in FIG. 15, it is assumed that many linear shadows are captured in addition to the guide wire on the right side. In the bone image gB corresponding to the original image gE, as shown in FIG. 16, the guide wire is imaged to overlap with the bone on the right side.

After step ST240, step ST250 is executed similarly to step ST40 described above. At this time, the processing circuit 74 creates a bone map image gMp representing the result of discriminating bone parts and non-bone parts (soft tissue) as shown in FIG. 17 by, for example, performing threshold processing on the bone image gB. do. Thereby, the result of discriminating bone parts and non-bone parts can be obtained as an analysis result.

After step ST250, the processing circuit 74 detects a device based on the analysis result (ST260 to ST270). For example, when a result of discriminating the bone part and the non-bone part is obtained as an analysis result, the processing circuit 74 searches for a device from each pixel of the bone part of the bone part and the non-bone part. By this, the device is detected (ST260 to ST270). The explanation will be given below in order.

In step ST260, the processing circuit 74 sets each pixel of the bone part of the bone part and the non-bone part as a search area of the device. In the example shown in FIG. 17, the bone portion has a gray area that is less than half of the bone map image gMp. That is, in FIG. 17, the search area of the device is set as an area less than half of the bone map image gMp.

After step ST260, in step ST270, the processing circuit 74 detects the device by searching for the device within the device search area.

After step ST270, in step ST280, the processing circuit 74 determines whether to display the bone image gB or the soft tissue image gST in accordance with the operation of the input interface 73 by the operator.

If the result of the determination in step ST280 is NO, in step ST290, the processing circuit 74 displays the normal X-ray image with device emphasis. That is, the processing circuit 74 generates an enhanced image by executing a device enhancement process in a normal X-ray image, and causes the display 72 and the monitor 80 to display this enhanced image. After step ST290 ends, the process moves to step ST330.

Further, if the determination result in step ST280 is to display the bone image gB or the soft tissue image gST, in step ST300, the processing circuit 74 displays the bone image gB in accordance with the operation of the input interface 73 by the operator. Determine whether or not to do so.

If the result of the determination in step ST300 is NO, in step ST310, the processing circuit 74 displays the soft tissue image gST with device emphasis. That is, the processing circuit 74 generates an enhanced image by executing enhancement processing of the device in the soft tissue image gST, and displays this enhanced image on the display 72 and the monitor 80. After step ST310 ends, the process moves to step ST330.

On the other hand, as a result of the determination in step ST300, if the bone image gB is to be displayed, in step ST320, the processing circuit 74 displays the bone image gB with device emphasis. That is, the processing circuit 74 generates an enhanced image by executing enhancement processing of the device in the bone image gB, and causes the display 72 and the monitor 80 to display this enhanced image. After step ST320 ends, the process moves to step ST330.

In step ST330, the processing circuit 74 determines whether or not to update the bone map image gMp in accordance with the operation of the input interface 73 by the operator, as described above.

As a result of the determination in step ST330, if the bone map image gMp is not updated, the processing circuit 74 returns to step ST280 and continues the processing in steps ST280 to ST330.

On the other hand, if the bone map image gMp is to be updated as a result of the determination in step ST330, the processing circuit 74 returns to step ST220 and continues the processing in steps ST220 to ST330. Note that during execution of the above processing, when an instruction to end imaging is input, the processing is ended.

As described above, according to the second embodiment, an X-ray image is captured using multiple energies, a device is detected based on the analysis result of the captured X-ray image, and an enhancement process for the device is executed. A highlighted image is generated.

Therefore, the visibility of an X-ray image in which many pseudo linear shadows are captured can be improved in real time. Furthermore, it is possible to expect an improvement in image quality due to improved precision in image processing.

As a supplement, the conventional technology has room for improvement in that it is not possible to improve the visibility in real time for an X-ray image in which many pseudo linear shadows are captured. Specifically, for example, image processing that searches an X-ray image for a linear shadow indicating a guide wire and highlights the guide wire must be performed in real time because the X-ray image is a moving image such as a fluoroscopic image. There is. On the other hand, since the position of the guide wire within the X-ray image is unknown, it is necessary to search evenly from one end of the X-ray image to the other. Therefore, in the prior art, in order to perform highlighting in real time, high demands are placed on the performance of hardware that implements image processing. In addition, the conventional technology is difficult to detect only the guide wire in an X-ray image where many pseudo linear shadows are captured, such as in the lung field, so it is difficult to detect only the guide wire in real time. I can't.

On the other hand, according to the second embodiment, as described above, visibility can be improved in real time for an X-ray image in which many pseudo linear shadows are captured.

As a further supplement, according to the second embodiment, the linear shadow of the guide wire is captured and used for enhancement through image processing. In the original image gE, there are many linear shadows other than the guide wire. On the other hand, when a bone image gB is created by material discrimination processing, a device (guide wire) whose main material is Ni, Cr, etc. is depicted as a bone part. Therefore, by using the bone map image gMp, the guidewire search region is limited to the bone region, and linear shadows other than the guidewire (in non-bone regions) can be suppressed.

Further, by analyzing the captured X-ray image, a result of discriminating bone parts and non-bone parts from the X-ray image may be obtained as an analysis result. At this time, the device may be detected by searching for the device from each pixel of the bone portion of the bone portion and the non-bone portion. In this case, since the search area for the device is limited to each pixel of the bone area, the device can be detected more easily and faster than when searching for the device from the entire image including bone and non-bone areas. be able to.

In addition, the X-ray image is input to a trained model for outputting the discriminated result based on the X-ray image captured by the X-ray irradiation of the multiple energies, and the discriminated result is output. The analysis result may be obtained by doing so. In this case, as described above, the analysis results of the X-ray image can be obtained using a neural network.

Note that the second embodiment has a configuration in which a device is detected based on the analysis result of an X-ray image using multiple energies, and an enhanced image is generated by executing enhancement processing for the device. , there is no need to control the X-ray conditions. Therefore, the second embodiment can be implemented not only as an X-ray diagnostic apparatus but also as a medical image processing apparatus.

Further, the effects of the second embodiment as described above can also be appropriately expressed as in [20] and [21] below.
[20] Image processing control can be performed by using bone images and soft tissue images obtained by spectral image collection.

[21] Among the material discrimination images (bone images, soft tissue images) obtained in [20] above, only a part of the region of the bone map image created using the bone images is set as the search range. , it is possible to perform processing to recognize linear shadows.

According to at least one embodiment described above, it is possible to obtain appropriate X-ray conditions for improving the visibility of X-ray images taken of subjects having different X-ray absorption differences.

The term "processor" used in the above description refers to, for example, a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), an Application Specific Integrated Circuit (ASIC), a programmable logic device (for example, Refers to circuits such as Simple Programmable Logic Device (SPLD), Complex Programmable Logic Device (CPLD), and Field Programmable Gate Array (FPGA).A processor is a memory circuit. The functions are realized by reading and executing the program stored in the processor.Instead of storing the program in the memory circuit, the program may be directly incorporated into the processor circuit.In this case, the processor Functions are realized by reading and executing programs built into the circuit. Note that each processor in this embodiment is not limited to being configured as a single circuit for each processor, but may be configured as multiple independent circuits. They may be combined to form one processor to realize the function.Furthermore, a plurality of components shown in FIG. 2 or 13 may be integrated into one processor to realize the function. .

Although several embodiments of the present invention have been described, these embodiments are presented as examples and are not intended to limit the scope of the invention. These embodiments can be implemented in various other forms, and various omissions, substitutions, and changes can be made without departing from the gist of the invention. These embodiments and their modifications are included within the scope and gist of the invention as well as within the scope of the invention described in the claims and its equivalents.

1 X-ray diagnostic device 10 Imaging device 11 High voltage generator 12 X-ray generator 13 X-ray detector 14 C-arm 142 C-arm control device 50 Bed device 51 Base 52 Bed driving device 53 Top plate 54 Support frame 70 Console device 71 Memory 72 Display 73 Input interface 74 Processing circuit 741 System control function 742 Image processing function 743 Analysis function 744 Determination function 745 Display control function 746 Detection function 747 Emphasis function 75 Medical image processing device Md2 Learned model gE Original image gHE High energy image gLE Low energy image gB Bone image gST Soft tissue image gSP Spectral image

Claims (13)

an imaging unit that irradiates the subject with X-rays and captures an X-ray image;
a determining unit that determines the contribution of a pixel to the control of X-ray conditions based on an analysis result of an X-ray image captured by X-ray irradiation with multiple energies using tube voltage switching;
An X-ray diagnostic apparatus comprising: a control unit that controls X-ray conditions in imaging by single-energy X-ray irradiation without using the tube voltage switching, based on the determination result of the contribution. The apparatus further includes an analysis unit that obtains, as the analysis result, a result of discriminating bone parts and non-bone parts from the X-ray image by analyzing the X-ray image taken by the X-ray irradiation of the plural energies. The X-ray diagnostic apparatus according to claim 1. The X-ray diagnostic apparatus according to claim 2, wherein the determining unit determines the contribution based on whether or not the imaged device overlaps a pixel of the bone portion. The determining unit determines the contribution based on each pixel of the bone part out of each pixel in the region of interest of the X-ray image when the device overlaps the pixel of the bone part. Item 3. The X-ray diagnostic device according to item 3. If there are no pixels of the bone within the region of interest, the determination unit moves the region of interest to include at least a portion of the device, and determines each pixel of the bone within the region of interest after the movement. The X-ray diagnostic apparatus according to claim 4, wherein the contribution is determined based on. The determination unit determines the contribution based on each pixel of a non-bone part of each pixel in a region of interest of the X-ray image when the device does not overlap a pixel of the bone part. The X-ray diagnostic apparatus according to claim 3. If there are no pixels of the non-bone part within the region of interest, the determining unit moves the region of interest to include at least a part of the device, and determines the size of the non-bone part within the region of interest after the movement. The X-ray diagnostic apparatus according to claim 6, wherein the contribution is determined based on each pixel. The analysis unit generates a bone image in which the contrast of non-bone parts is suppressed from the X-ray image by analyzing the X-ray image captured by the X-ray irradiation with the multiple energies, and performs threshold processing on the bone image. The X-ray diagnostic apparatus according to any one of claims 2 to 7, wherein the discriminated result is obtained by performing. The analysis unit inputs the X-ray image to a trained model for outputting the discriminated result based on the X-ray image captured by the multiple-energy X-ray irradiation, and outputs the discriminated result. The X-ray diagnostic apparatus according to any one of claims 2 to 8, wherein the analysis result is obtained by outputting. an imaging unit that captures an X-ray image by irradiating X-rays with multiple energies using tube voltage switching;
a detection unit that detects a device based on an analysis result of the captured X-ray image;
By analyzing the captured X-ray image, a bone image with suppressed contrast of non-bone parts is generated from the X-ray image, and by applying threshold processing to the bone image, an analysis unit that obtains a bone map image representing a result of discriminating bone parts and non-bone parts as the analysis result;
Equipped with
The detection unit detects the device by searching for the device from each pixel of the bone part of the bone part and the non-bone part in the bone map image . The analysis unit inputs the X-ray image to a trained model for outputting the discriminated result based on the X-ray image captured by the multiple-energy X-ray irradiation, and outputs the discriminated result. The X-ray diagnostic apparatus according to claim 10 , wherein the analysis result is obtained by outputting. The X-ray diagnostic apparatus according to claim 10 or 11 , further comprising an enhancement section that generates an enhanced image by executing enhancement processing of the device. Generating a bone image with suppressed contrast of non-bone parts from the X-ray image by analyzing an X-ray image obtained by irradiating X-rays with multiple energies using tube voltage switching, and performing threshold processing on the bone image. an analysis unit that obtains, as an analysis result, a bone map image representing the result of discriminating bone parts and non-bone parts from the X-ray image;
a detection unit that detects a device based on the analysis result;
an enhancement unit that generates an enhanced image by executing enhancement processing of the device ;
The detection unit is a medical image processing apparatus, wherein the detection unit detects the device by searching for the device from each pixel of the bone part of the bone part and the non-bone part in the bone map image .