X-ray diagnostic apparatus, medical image processing apparatus, and program

Abstract

To determine parameters appropriate for multifrequency processing in accordance with an element included in an imaging visual field.SOLUTION: An X-ray diagnostic apparatus according to an embodiment comprises a detection unit, a determination unit, and an image processing unit. The detection unit detects an element from X-ray image data obtained by imaging a subject. The determination unit determines parameters for multifrequency processing on the basis of a detection result of the element. The image processing unit executes the multifrequency processing for the X-ray image data and / or another piece of X-ray image data obtained by imaging after the X-ray image data, on the basis of the determined parameter.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The embodiments disclosed in this specification and the drawings relate to an X-ray diagnostic apparatus, a medical image processing apparatus, and a program.

Background Art

[0002] Conventionally, as image processing in an X-ray diagnostic apparatus, multi-frequency processing is known. In multi-frequency processing, a band-pass signal of a difference between an original image and a plurality of unsharp images is extracted, and a coefficient is multiplied by each band-pass signal and added to calculate an enhancement signal, and free enhancement characteristics can be realized by independently enhancing a plurality of frequency band signals.

[0003] The parameters used in multi-frequency processing differ in optimal values depending on elements included in an imaging field of view and the like. For this reason, for example, when the same parameters are applied in multi-frequency processing despite changes in elements included in the imaging field of view during a procedure by a doctor due to movement of an X-ray irradiation region or movement of a device position or the like, X-ray image data of appropriate image quality may not be obtained.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] One of the problems to be solved by the embodiments disclosed in this specification and the drawings is to determine appropriate parameters in multi-frequency processing according to elements included in an imaging field of view, for example. However, the problems to be solved by the embodiments disclosed in this specification and the drawings are not limited to the above problems. It is also possible to position problems corresponding to respective effects of respective configurations shown in the embodiments described later as other problems.

Means for Solving the Problems

[0006] The X-ray diagnostic apparatus according to the embodiment includes a detection unit, a determination unit, and an image processing unit. The detection unit detects an element from the X-ray image data obtained by imaging a subject. Type and number Based on the detection result of the element, the determination unit determines the parameters for multi-frequency processing. The image processing unit executes multi-frequency processing on at least one of the X-ray image data and other X-ray image data captured after the X-ray image data based on the determined parameters. Multi-frequency processing includes frequency separation processing that generates a plurality of frequency band data separated for each of a plurality of frequency bands from at least one of X-ray image data and other X-ray image data. The parameter includes the cut-off frequency of the low-pass filter used for the frequency separation processing. The determination unit determines the cut-off frequency according to the type and number of the detected elements. The image processing unit separates the plurality of frequency band data based on the cut-off frequency.

Brief Description of the Drawings

[0007]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Figure 13

Figure 14

DETAILED DESCRIPTION OF THE INVENTION

[0008] Hereinafter, embodiments of an X-ray diagnostic apparatus, a medical image processing apparatus, and a program will be described in detail with reference to the drawings.

[0009] (First Embodiment) FIG. 1 is a block diagram showing an example of the configuration of an X-ray diagnostic apparatus 100 according to the first embodiment. The X-ray diagnostic apparatus 100 generates X-ray image data obtained by imaging a subject P by irradiating the subject P with X-rays. Note that the subject P is not included in the X-ray diagnostic apparatus 100. The X-ray diagnostic apparatus 100 is used, for example, during examinations and treatments such as those for the circulatory system, digestive tract, urinary system, orthopedics, and interventional radiology (IVR). Note that the use of the X-ray diagnostic apparatus 100 is not limited to these.

[0010] As shown in FIG. 1, the X-ray diagnostic apparatus 100 includes an X-ray generation unit 1, an X-ray detection unit 2, a mechanism unit 3, a high-voltage generation unit 4, a holding arm 5, a mechanism control unit 6, an image calculation and storage unit 7, a display device 8, an operation unit 9, a system control unit 10, and a hospital bed 17.

[0011] In addition, the X-ray generation unit 1 includes an X-ray tube 15 and an X-ray collimator 16. The X-ray detection unit 2 includes an image data generation unit 20, a flat panel detector (FPD) 21, and a gate driver 22. The mechanism unit 3 includes a holding arm movement mechanism 41 and a bed movement mechanism 42. The image data generation unit 20 includes a charge-voltage converter 23, an A / D (Analog / Digital) converter 24, and a parallel-serial converter 25.

[0012] The high voltage generation unit 4 is a high voltage power supply that generates a high voltage under the control of the system control unit 10 and supplies the generated high voltage to the X-ray tube 15.

[0013] The X-ray tube 15 generates X-rays using the high voltage supplied from the high voltage generation unit 4.

[0014] The X-ray collimator 16 narrows down the X-rays generated by the X-ray tube 15 so that they are selectively irradiated onto the region of interest of the subject P.

[0015] The holding arm 5 holds the X-ray generation unit 1 and the X-ray detection unit 2. The holding arm 5 supports the X-ray generation unit 1 and the X-ray detection unit 2 at both ends, and is also called a C-arm because of its shape similar to the letter C. In FIG. 1, the X-ray diagnostic apparatus 100 includes one holding arm 5, but may also have a biplane configuration including an Ω-arm.

[0016] The mechanism control unit 6 controls the holding arm movement mechanism 41 and the bed movement mechanism 42 under the control of the system control unit 10 to adjust the rotation and movement of the holding arm 5 and the movement of the bed 17.

[0017] The holding arm movement mechanism 41 is a mechanism that rotates or moves the holding arm 5 and includes a motor and an actuator (not shown), etc.

[0018] The bed movement mechanism 42 is a mechanism that moves the bed 17 and includes a motor and an actuator (not shown), etc.

[0019] The examination table 17 places the subject P thereon. The examination table 17 can be moved in the vertical direction, the front-rear direction, and the tilt direction by the examination table moving mechanism 42 while the subject P is placed thereon.

[0020] The X-ray detection unit 2 detects the X-rays that have passed through the subject P and generates X-ray image data based on the detection result.

[0021] Specifically, the flat panel detector 21 detects the X-rays that have passed through the subject P and transmits the detection result to the image data generation unit 20. The flat panel detector 21 includes, for example, a detection film, a pixel capacitance unit, a TFT (Thin Film Transistor), etc. The flat panel detector 21 is an example of the X-ray detector in the present embodiment.

[0022] The gate driver 22 supplies a driving voltage to the gate terminal of the TFT in order to read out the charges accumulated in the flat panel detector 21 as X-ray image signals under the control of the system control unit 10.

[0023] The image data generation unit 20 generates X-ray image data from the detection signals detected by the flat panel detector 21 and stores the generated X-ray image data in the image data storage circuit 13. For example, the image data generation unit 20 performs current-voltage conversion, A / D conversion, and parallel-serial conversion on the detection signals detected by the flat panel detector 21 to generate X-ray image data.

[0024] Specifically, the charge-voltage converter 23 converts the charges read out from the flat panel detector 21 into voltage. The A / D converter 24 converts the output of the charge-voltage converter 23 into a digital signal (digital data). The parallel-serial converter 25 converts the detection signal converted into a digital signal into time-series data elements.

[0025] The image arithmetic and storage unit 7 corrects and stores the X-ray image data generated by the image data generation unit 20. In the present embodiment, when distinguishing the X-ray image data before and after correction, the X-ray image data generated by the image data generation unit 20 is referred to as the original image data, and the data obtained by correcting the original image data in the image arithmetic and storage unit 7 is referred to as the display X-ray image data.

[0026] The image arithmetic and storage unit 7 includes a storage circuit 11, an image arithmetic circuit 12, and an image data storage circuit 13.

[0027] The storage circuit 11 stores programs corresponding to various functions read and executed by the image arithmetic circuit 12. Also, the storage circuit 11 stores data used in various processes executed by the image arithmetic circuit 12. For example, the storage circuit 11 stores information indicating the on / off status of the automatic setting function of the parameters for multi-frequency processing, and learned models and the like.

[0028] The storage circuit 11 is realized by, for example, a semiconductor memory element such as a RAM (Random Access Memory), a flash memory, a hard disk, an optical disk, or the like. The storage circuit 11 is an example of a storage unit.

[0029] The image arithmetic circuit 12 generates display X-ray image data by performing image processing on the original image data generated by the image data generation unit 20, and stores the generated display X-ray image data in the image data storage circuit 13.

[0030] In the present embodiment, the image processing performed by the image arithmetic circuit 12 is multi-frequency processing. Note that the image arithmetic circuit 12 may further perform image processing other than multi-frequency processing on the original image data. Also, the image arithmetic circuit 12 of the present embodiment has an automatic setting function for parameters of multi-frequency processing according to elements included in the imaging field of view (Field Of View: FOV).

[0031] More specifically, the image arithmetic circuit 12 includes an acquisition function 120, a detection function 121, a determination function 122, a frequency separation function 123a, an enhancement function 123b, and a synthesis function 123c. Also, the frequency separation function 123a, the enhancement function 123b, and the synthesis function 123c are collectively referred to as a multi-frequency processing function 123. The acquisition function 120 is an example of an acquisition unit. The detection function 121 is an example of a detection unit. The determination function 122 is an example of a determination unit. The multi-frequency processing function 123 is an example of an image processing unit and a multi-frequency processing unit. The frequency separation function 123a is an example of a frequency separation unit. The enhancement function 123b is an example of an enhancement function unit. The synthesis function 123c is an example of a synthesis unit. Details of each function will be described later.

[0032] The image arithmetic circuit 12 is a processor that realizes functions corresponding to each program by, for example, reading and executing a program from the storage circuit 11. In other words, each circuit in the state of having read each program has a function corresponding to the read program.

[0033] The display device 8 includes a display image memory 31, a D / A (Digital / Analog) converter 32, a display control circuit 33, and a monitor 34.

[0034] The display image memory 31 temporarily stores the display X-ray image data generated by the image arithmetic circuit 12 that has been read by the display control circuit 33.

[0035] The D / A converter 32 performs D / A conversion on the display X-ray image data.

[0036] The display control circuit 33 is a processor that controls the monitor 34. It reads the display X-ray image data generated by the image arithmetic circuit 12 from the image data storage circuit 13, causes it to be converted by the D / A converter 32, and then displays it on the monitor 34. The display control circuit 33 is an example of a display control unit. Also, the display control circuit 33 may display various GUIs (Graphical User Interfaces) on the monitor 34.

[0037] The monitor 34 displays an X-ray image based on display X-ray image data and a GUI for receiving instructions from the operator. It is realized by a liquid crystal display, an organic EL (Organic Electro-Luminescence: OEL) display, or the like. The monitor 34 is an example of a display unit.

[0038] The operation unit 9 receives various instructions and information inputs from the operator. The operation unit 9 is realized by, for example, a trackball, a switch button, a mouse, a keyboard, a touch pad that performs an input operation by touching an operation surface, a touch screen in which a display screen and a touch pad are integrated, a non-contact input circuit using an optical sensor, and a voice input circuit. When the operation unit 9 is a touch screen, the monitor 34 and the touch pad may be integrated.

[0039] The operation unit 9 is connected to the system control unit 10, converts the input operation received from the operator into an electrical signal, and outputs it to the system control unit 10. For example, the operation unit 9 receives an on / off operation of the automatic setting function of the parameters of the multi-frequency processing by the operator. When the operation unit 9 receives an on / off operation of the automatic setting function of the parameters of the multi-frequency processing, the operation unit 9 sends the received operation content to the system control unit 10.

[0040] In addition, the operation unit 9 receives input operations such as imaging conditions and inspection protocols by the operator. The operation unit 9 sends the received operation content to the system control unit 10. Further, the system control unit 10 sends various operation contents acquired from the operation unit 9 to the image calculation circuit 12.

[0041] The imaging conditions include settings related to the imaging system, the imaging field of view, and the magnification.

[0042] The imaging system is defined items or information regarding the positional relationship between the devices used for imaging and the subject P, and the positional relationship between the devices used for imaging. The positional relationship between the devices used for imaging and the subject P, and the positional relationship between the devices used for imaging are also referred to as imaging geometry. The devices used for imaging are, for example, the X-ray tube 15 and the flat panel detector 21.

[0043] The imaging system includes, for example, the source image distance (SID), SSD (Source Skin Distance), the height of the bed 17, and the rotation amount of the holding arm 5.

[0044] The magnification is specified by the operator, for example, by a function called "LiveZoom". LiveZoom is a function that enlarges or reduces the X-ray image drawn on the monitor 34 by the user operating the operation unit 9.

[0045] The examination protocol is information indicating the examination procedure in the X-ray diagnostic apparatus 100, and the imaging target site and the execution order of various imaging are defined. For example, a plurality of examination protocols are stored in advance in the storage circuit 11, and the operator may select the examination protocol used when imaging the subject P by operating the operation unit 9.

[0046] Note that in this specification, the operation unit 9 is not limited to only those equipped with physical operation components 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 X-ray diagnostic apparatus 100 and outputs this electrical signal to the control circuit is also included in the example of the operation unit 9. The operation unit 9 is also referred to as an input interface. The operation unit 9 is an example of the reception unit in the present embodiment.

[0047] The system control unit 10 controls the imaging process by the X-ray diagnostic apparatus 100. The system control unit 10 includes, for example, a processing circuit 101 and a storage circuit 102.

[0048] The processing circuit 101 is a processor that executes imaging processing performed by the X-ray diagnostic apparatus 100. Further, the processing circuit 101 controls the entire X-ray diagnostic apparatus 100 by controlling various components included in the X-ray diagnostic apparatus 100. For example, the processing circuit 101 sends various operation contents received by the operation unit 9 from the operator to the image calculation circuit 12.

[0049] The storage circuit 102 stores programs corresponding to various functions read and executed by the processing circuit 101. The storage circuit 102 is realized by, for example, a semiconductor memory element such as a RAM or a flash memory, a hard disk, an optical disk, or the like.

[0050] In the above description, an example has been described in which the "processor" reads out and executes programs corresponding to each function from the storage circuits 11 and 102. However, the embodiment is not limited to this. The term "processor" means, for example, a circuit such as a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), an application specific integrated circuit (ASIC), or a programmable logic device (for example, a simple programmable logic device (SPLD), a complex programmable logic device (CPLD), and a field programmable gate array (FPGA)). When the processor is, for example, a CPU, the processor realizes its function by reading out and executing the program stored in the storage circuits 11 and 102. On the other hand, when the processor is an ASIC, instead of storing the program in the storage circuits 11 and 102, the function is directly incorporated as a logic circuit in the circuit of the processor. Note that each processor of the present embodiment is not limited to being configured as a single circuit for each processor, and a plurality of independent circuits may be combined to be configured as one processor to realize its function. Further, a plurality of components in FIG. 1 may be integrated into one processor to realize its function.

[0051] Next, each function included in the image arithmetic circuit 12 of the present embodiment will be described.

[0052] The acquisition function 120 acquires the original image data obtained by imaging the subject P from the image data storage circuit 13.

[0053] The detection function 121 detects elements from the original image data obtained by imaging the subject P.

[0054] In this embodiment, an element is an object depicted in X-ray image data, specifically, a body tissue of a subject P or a medical device. Medical devices depicted in the X-ray image data include, for example, devices such as catheters, guidewires, and stents used in IVR. Body tissues depicted in the X-ray image data include, for example, bones, blood vessels, diaphragms, lung fields, and the like.

[0055] More specifically, the detection function 121 detects the type of element depicted on the original image data acquired by the acquisition function 120 and the image region where the element is depicted. In this embodiment, the detection function 121 uses a learned model to obtain a segmentation result of the original image data for each element.

[0056] FIG. 2 is a diagram showing an example of segmentation of the original image data 81 according to the first embodiment. As shown in FIG. 2, when the original image data 81 is input to the learned model 90, a label indicating the type of element depicted in the original image data 81 and the image region where each element is depicted are output. In FIG. 2, the segmentation result of the original image data 81 is illustrated as the region-segmented image data 82.

[0057] The learned model 90 is a model learned by associating a plurality of learning X-ray image data with the segmentation results for each element corresponding to the plurality of learning X-ray image data. The learned model 90 is, for example, a learned model generated by deep learning (deep neural network) such as a neural network or other machine learning. As deep learning techniques, deep convolutional neural network (DCNN), convolutional neural network (CNN), recurrent neural network (RNN), and the like can be applied, but are not limited thereto. The learned model 90 is composed of, for example, a neural network and learned parameter data.

[0058] Assume that the learned model 90 is stored in the memory circuit 11, for example. The detection function 121 reads the learned model 90 from the memory circuit 11 and inputs the original image data 81. Alternatively, the learned model 90 may be incorporated in the detection function 121.

[0059] The learned model 90 may be generated by an information processing device other than the X-ray diagnostic apparatus 100, or the X-ray diagnostic apparatus 100 may be provided with a learning function for generating the learned model 90.

[0060] In addition, the learned model 90 in the present embodiment includes a "self-learning model" that further updates the internal algorithm of the learned model 90 when the user gives feedback on the products output by these learned models 90.

[0061] In the example shown in FIG. 2, a Guiding catheter, a Catheter, a Guide wire, and a Vertebra are detected as elements.

[0062] The range where the guiding catheter is depicted on the original image data 81 is illustrated as the image region 70a on the region-segmented image data 82. The range where the catheter is depicted is illustrated as the image region 70b on the region-segmented image data 82. The range where the guide wire is depicted is illustrated as the image region 70c on the region-segmented image data 82. The range where the vertebra is depicted is illustrated as the image region 70d on the region-segmented image data 82. Hereinafter, when not particularly distinguishing the image regions 70a to 70d where individual elements are depicted, they are simply referred to as the image region 70.

[0063] In addition, the region where no element is detected on the original image data 81 is referred to as the background region 60.

[0064] Returning to FIG. 1, the determination function 122 determines the parameters of the multi-frequency processing based on the detection result of the elements by the detection function 121.

[0065] Multi-frequency processing is a process of adjusting the enhancement characteristics for each frequency band of the spatial frequency. The multi-frequency processing includes a frequency separation process and an enhancement characteristic adjustment process.

[0066] The frequency separation process is a process of generating a plurality of frequency band data separated for each of a plurality of frequency bands from the X-ray image data. The frequency separation process is a process of applying a low pass filter (LPF) step by step to the X-ray image data and generating a plurality of frequency band data each including a different frequency band and background data by taking the difference from the LPF processed image of the previous step.

[0067] The enhancement characteristic adjustment process is a process of enhancing or suppressing the plurality of frequency band data by multiplying each of the plurality of frequency band data by a coefficient.

[0068] The parameters of the multi-frequency processing include the threshold used in the frequency separation process and the coefficient used in the enhancement characteristic adjustment process. The threshold used in the frequency separation process is, for example, the cut-off frequency of the low pass filter used for the separation of the frequency band.

[0069] More specifically, the determination function 122 determines the parameters of the multi-frequency processing based on the type of the element detected from the original image data 81 and the size of the image area 70 where the element is detected.

[0070] For example, generally in X-ray image data, the larger the change in the image or the finer the pattern of the image, the more it corresponds to a higher frequency band. Therefore, the smaller the image area 70 occupies on the original image data 81, the more it corresponds to a higher frequency area, and the larger the image area 70 occupies on the original image data 81, the more it corresponds to a lower frequency area.

[0071] On the premise of such characteristics of the frequency band data, the determination function 122 calculates, for each element, the ratio that the image area 70 in which the element is drawn occupies on the original image data 81, and determines the cut-off frequency of the low-pass filter based on the ratio.

[0072] FIG. 3 is a diagram showing an example of the frequency separation process according to the first embodiment. As shown in FIG. 3, the determination function 122 calculates the ratio of the area of each image area 70 on the region-divided image data 82. The ratio of the area of each image area 70 is the ratio that the number of pixels included in each image area 70 occupies in the total number of pixels of the region-divided image data 82. In the example shown in FIG. 3, the image area 70d of Vertebra occupies 32%, the image area 70b of Catheter occupies 7%, the image area 70a of Guiding catheter occupies 6%, the image area 70c of Guide wire occupies 5%, and the other background area 60 occupies 50%. From the ratio, it can be seen that most of the original image data 81 is occupied by the image area 70d of Vertebra and the background area 60, and there are a plurality of image areas 70b, 70a, 70c with relatively small areas.

[0073] The graph G1 in FIG. 3 shows the spatial frequency on the horizontal axis and the frequency response on the vertical axis. In the example shown in FIG. 3, the determination function 122 separates the frequency band data f0 to f5 and the background data b1 by applying a low-pass filter in six steps. Note that the number of divisions of the frequency band data f0 to f5 is not limited to this.

[0074] The determination function 122 determines the cut-off frequency of the low-pass filter so that, for example, the more image regions 70 corresponding to a high frequency region, the more finely the frequency band data f0 to f5 are separated in the high frequency band. In the example shown in FIG. 3, the number of frequency band data f0 to f5 existing in the high frequency region to the right of half of the horizontal axis of the graph G1 is large. This is because the determination function 122 sets many cut-off frequencies for separating the respective frequency band data f0 to f5 on the high frequency side. By separating the frequency band data f0 to f5 with a fine granularity on the high frequency side in this way, it becomes possible to finely adjust the degree of emphasis of the object on the high frequency side, that is, the small image region 70, in the X-ray image data.

[0075] Note that depending on the type of detected element, it may be possible to estimate the corresponding frequency band. For example, generally, since a catheter, a guiding catheter, and a guide wire have an elongated shape, the image region depicted on the X-ray image data is small and corresponds to a high frequency band. Therefore, the determination function 122 may determine the cut-off frequency according to the type and number of detected elements. When adopting this configuration, the storage circuit 11 may store a table associating the type of element with the frequency band.

[0076] Also, the determination function 122 determines a coefficient for emphasizing or suppressing each of the frequency band data f0 to f5 and the background data b1 according to the type of detected element. In multi-frequency processing, since different values of coefficients can be multiplied by the frequency band data f0 to f5 and the background data b1 respectively, the determination function 122 can determine the coefficients of the number of frequency band data f0 to f5 and background data b1 separated by a stepwise low-pass filter.

[0077] FIG. 4 is a diagram showing an example of the enhancement characteristic adjustment process according to the first embodiment. In the graph G2 of FIG. 4, the frequency band data f0 to f5 and the background data b1 in the state before being multiplied by the coefficient, which are generated from the original image data 81, are illustrated by solid lines. Further, the corrected frequency band data f00, f10, and the background data b10 that are enhanced or suppressed by being multiplied by the coefficient are illustrated by broken lines.

[0078] As shown in the region-divided image data 82 shown in FIG. 4, when bones such as Vertebra are depicted in the X-ray image data, if the bone overlaps with a device such as a catheter, the visibility of the device in the overlapping region decreases.

[0079] In such a case, the determination function 122 suppresses the enhancement of the display of the image region 70d corresponding to Vertebra by making the coefficient on the low-frequency side less than 1. In the example shown in the graph G2 of FIG. 4, the frequency response of the background data b10 multiplied by the coefficient is smaller than that of the background data b1 before adjustment. That is, the determination function 122 determines the coefficient according to the combination of the types of the detected elements.

[0080] Further, when a thin device such as a guide wire is detected from the original image data 81, the determination function 122 determines the coefficient to be multiplied by each of the frequency band data f0 to f5 so as to enhance the higher-frequency side of the frequency band data f0 to f5 more. In the example shown in FIG. 4, the determination function 122 makes the coefficient multiplied by the first frequency band data f0 from the high-frequency side the largest, and the coefficient multiplied by the second frequency band data f1 from the high-frequency side the second largest.

[0081] Note that the determination function 122 may specify the frequency band to be enhanced according to the type of the detected element, or may specify the frequency band to be enhanced based on the ratio occupied by each image region 70 on the original image data 81.

[0082] The automatic setting process of the parameters for multi-frequency processing by the detection function 121 and the determination function 122 is executed when the automatic setting function of the parameters for multi-frequency processing is set to on. The on / off state of the automatic setting function of the parameters for multi-frequency processing is switched by an operation by an operator received by the operation unit 9 described later. The on / off status of the automatic setting function of the parameters for multi-frequency processing is stored, for example, in the storage circuit 11. The detection function 121 and the determination function 122 refer to the storage circuit 11 to determine whether the automatic setting function of the parameters for multi-frequency processing is on or off, and when it is on, execute the above-described element detection process and parameter determination process.

[0083] Returning to FIG. 1, the multi-frequency processing function 123 executes multi-frequency processing on the original image data 81 based on the determined parameters. As described above, the multi-frequency processing function 123 includes a frequency separation function 123a, an enhancement function 123b, and a synthesis function 123c.

[0084] The frequency separation function 123a separates a plurality of frequency band data f0 to f5 and background data b1 based on the parameters determined by the determination function 122. More specifically, the frequency separation function 123a applies a low-pass filter step by step using the cut-off frequencies of the frequency band data f0 to f5 and the number of background data b1 to be separated determined by the determination function 122, thereby separating the plurality of frequency band data f0 to f5 and the background data b1.

[0085] Also, the enhancement function 123b multiplies the plurality of frequency band data f0 to f5 and the background data b1 separated by the frequency separation function 123a by the coefficients determined by the determination function 122, thereby enhancing or suppressing each frequency band data f0 to f5 and the background data b1.

[0086] The composite function 123c generates display X-ray image data by combining a plurality of frequency band data f00, f10, f2 to f5 and background data b10, for which emphasis characteristic adjustment processing has been performed by the emphasis function 123b. The composite function 123c stores the generated display X-ray image data in the image data storage circuit 13.

[0087] Next, the flow of processing executed by the X-ray diagnostic apparatus 100 configured as described above will be described.

[0088] FIG. 5 is a flowchart showing an example of the flow of multi-frequency processing according to the first embodiment. The processing of this flowchart starts when imaging processing by irradiating the subject P with X-rays is started under the control of the system control unit 10.

[0089] First, the image data generation unit 20 generates original image data 81 from the detection signal detected by the planar detector 21 (S1). The acquisition function 120 acquires the original image data 81 generated by the image data generation unit 20.

[0090] Next, the detection function 121 determines whether or not the automatic setting function of the parameters for multi-frequency processing is set to on (S2).

[0091] When the automatic setting function of the parameters for multi-frequency processing is on (S2 “Yes”), the detection function 121 uses the learned model 90 to detect elements from the original image data 81 acquired by the acquisition function 120 (S3).

[0092] Next, the determination function 122 determines the parameters for multi-frequency processing based on the type of elements detected from the original image data 81 and the size of the image area 70 where the elements are detected (S4).

[0093] Then, the multi-frequency processing function 123 generates display X-ray image data by performing multi-frequency processing on the original image data 81 using the determined parameters (S5).

[0094] Next, the display control circuit 33 causes the generated X-ray image data for display to be displayed on the monitor 34 (S6).

[0095] Also, when the automatic setting function of the multi-frequency processing parameters is off (S2 “No”), the processes of S3 and S4 by the detection function 121 and the determination function 122 are not executed. In this case, in the process of S6, the multi-frequency processing function 123 generates the X-ray image data for display by performing multi-frequency processing on the original image data 81 using predetermined parameters. The predetermined parameters are stored, for example, in the storage circuit 11.

[0096] Then, when the imaging of the subject P continues (S7 “No”), the processes of S1 to S6 are repeatedly executed. In the present embodiment, for example, the acquisition function 120 repeatedly acquires the original image data 81 of a new frame. The detection function 121 repeatedly performs element detection on the newly acquired original image data 81 each time the original image data 81 of a new frame is acquired. Also, the determination function 122 repeatedly performs parameter determination along with the element detection. Then, the multi-frequency processing function 123 repeatedly performs multi-frequency processing based on the repeatedly determined parameters. In this way, each functional unit repeatedly executes the process each time the original image data 81 of a new frame is acquired, so that the multi-frequency processing function 123 can be applied to the original image data 81 during imaging in real time.

[0097] Then, when the imaging of the subject P ends (S7 “Yes”), the processing of this flowchart ends.

[0098] As described above, the X-ray diagnostic apparatus 100 according to the present embodiment detects elements from the original image data 81 in which the subject P is imaged, determines parameters for multi-frequency processing based on the detection results of the elements, and executes multi-frequency processing on the original image data 81 based on the determined parameters. Therefore, according to the X-ray diagnostic apparatus 100 of the present embodiment, appropriate parameters in multi-frequency processing can be determined according to the elements included in the imaging field of view.

[0099] For example, the parameters used in multi-frequency processing have different optimal values depending on elements included in the imaging field of view and the like. Therefore, for example, if the same parameters are applied in multi-frequency processing even though the elements included in the imaging field of view during a procedure by a doctor change according to the movement of the X-ray irradiation area or the movement of the position of the device, etc., it may not be possible to obtain X-ray image data for display with appropriate image quality. In contrast, the X-ray diagnostic apparatus 100 of the present embodiment can perform multi-frequency processing using the parameters determined according to the changed elements even when the elements depicted in the original image data 81 change due to a change in the imaging area or the movement of the position of the device, and thus can maintain the image quality of the X-ray image data for display.

[0100] In particular, in the case of an examination such as IVR that displays in real time an X-ray image taken during a procedure by a doctor, the value of the parameter suitable for the display of the device may change due to the movement of the X-ray irradiation area during imaging or the movement of the position of a device such as a catheter within the imaging field of view due to the doctor's procedure. In such a case, according to the X-ray diagnostic apparatus 100 of the present embodiment, by automatically updating the parameter to an appropriate value according to the elements included in the imaging field of view, the visibility of the device on the X-ray image can be maintained without the user having to adjust the parameter each time.

[0101] Also, in the present embodiment, the multi-frequency processing includes a frequency separation process that generates a plurality of frequency band data f0 to f5 separated for each of a plurality of frequency bands from the original image data 81. The parameters of the multi-frequency processing include the threshold value used for the frequency separation process. The X-ray diagnostic apparatus 100 of the present embodiment separates the plurality of frequency band data f0 to f5 based on the determined threshold value. According to the X-ray diagnostic apparatus 100 of the present embodiment, since frequency separation can be appropriately performed according to the elements depicted in the original image data 81, the image quality of the original image data 81 can be improved.

[0102] Also, the frequency separation process is a process that generates a plurality of frequency band data f0 to f5 including different frequency bands by gradually applying a low-pass filter to the original image data 81. The X-ray diagnostic apparatus 100 of the present embodiment determines the cut-off frequency in the low-pass filter based on the detection result of the element. Therefore, according to the X-ray diagnostic apparatus 100 of the present embodiment, the frequency band corresponding to the frequency band data f0 to f5 can be adjusted according to the elements depicted in the original image data 81.

[0103] Also, in the present embodiment, the multi-frequency processing includes an emphasis characteristic adjustment process that emphasizes or suppresses the plurality of frequency band data f0 to f5 by multiplying each of the plurality of frequency band data f0 to f5 by a coefficient. According to the X-ray diagnostic apparatus 100 of the present embodiment, based on the detection result of the element, by determining the coefficient used for the emphasis characteristic adjustment process, the frequency band data f0 to f5 can be individually emphasized or suppressed according to the elements depicted in the original image data 81.

[0104] Further, the X-ray diagnostic apparatus 100 according to the present embodiment detects the type of elements drawn on the original image data 81 and the image area 70 where the elements are drawn, and determines parameters based on the type of detected elements and the size of the image area 70 where the elements are detected. Therefore, according to the X-ray diagnostic apparatus 100 of the present embodiment, the cut-off frequencies for separating the frequency band data f0 to f5 appropriate for improving the image quality of the display X-ray image data, and the frequency band data f0 to f5 to be emphasized or suppressed can be specified with high accuracy according to the frequency characteristics of the elements drawn on the original image data 81.

[0105] Further, the X-ray diagnostic apparatus 100 according to the present embodiment calculates, for each element, the ratio of the image area 70 where the element is drawn to the entire original image data 81, and determines a threshold value used for the frequency separation process based on the ratio. Therefore, according to the X-ray diagnostic apparatus 100 of the present embodiment, the frequency band corresponding to the element drawn on the original image data 81 can be separated more finely than the frequency band corresponding to the background area 60, and the frequency band data f0 to f5 corresponding to the frequency band corresponding to the element can be emphasized. By such processing, the X-ray diagnostic apparatus 100 according to the present embodiment can improve the visibility of each element in the display X-ray image data.

[0106] Further, the X-ray diagnostic apparatus 100 according to the present embodiment inputs the original image data 81 into a learned learned model 90 together with a plurality of learning X-ray image data and the segmentation results of the elements included in the plurality of learning X-ray image data, and obtains the segmentation results output from the learned model 90. Therefore, according to the X-ray diagnostic apparatus 100 of the present embodiment, the image area 70 where the element is drawn on the original image data 81 can be recognized with high accuracy.

[0107] Note that "determining the parameters of the multi-frequency processing" in the present embodiment includes selecting an appropriate one from among the presets of image processing including multi-frequency processing having different parameters. That is, not only directly selecting the parameters of the multi-frequency processing, but also indirectly determining the parameters of the multi-frequency processing by selecting the preset of the image processing is included in "determining the parameters of the multi-frequency processing". For example, in X-ray image data, various image processes such as filter processing may be performed in addition to the multi-frequency processing. The determination function 122 of the X-ray diagnostic apparatus 100 may select one parameter set from among a plurality of preset parameter sets including the multi-frequency processing and such various image processes.

[0108] (Second Embodiment) In the above-described first embodiment, the parameters of the multi-frequency processing were determined based on the ratio of the area of the image region 70 in which each element was drawn on the original image data 81. In contrast, in this second embodiment, the parameters of the multi-frequency processing are determined according to the combination of the overlapping image regions 70.

[0109] The X-ray diagnostic apparatus 100 of the present embodiment has the same configuration as that of the first embodiment described with reference to FIG. 1.

[0110] The image arithmetic circuit 12 of the present embodiment includes an acquisition function 120, a detection function 121, a determination function 122, a frequency separation function 123a, an enhancement function 123b, and a synthesis function 123c, in the same manner as in the first embodiment. The acquisition function 120, the detection function 121, the frequency separation function 123a, the enhancement function 123b, and the synthesis function 123c have the same functions as those in the first embodiment. Also, other configurations included in the X-ray diagnostic apparatus 100 have the same functions as those in the first embodiment.

[0111] The determination function 122 of the present embodiment recognizes a location where a plurality of image regions 70 in which different types of elements are drawn overlap based on the detection result of the elements by the detection function 121. Then, when the plurality of image regions 70 overlap, the determination function 122 determines the parameters of the multi-frequency processing according to the types of the elements corresponding to the overlapping image regions 70. For example, the determination function 122 of the present embodiment determines the overlap of the elements, and optimizes the parameters of the multi-frequency processing applied to the entire original image data 81 in the direction of optimizing the visibility of the image region 70 where the elements overlap.

[0112] FIG. 6 is a diagram showing an example of adjustment of parameters of multi-frequency processing according to the second embodiment. The determination function 122 recognizes, by image processing, a location where two or more image regions 70 overlap on the region-divided image data 82 segmented by the detection function 121.

[0113] In the graphs G3 to G5 shown in FIG. 6, the frequency band data f0 to f5 and the background data b1 in the state before multiplying by the coefficient are shown by solid lines, and the corrected frequency band data f10 to f50 emphasized or suppressed by the coefficient and the background data b10 are shown by broken lines.

[0114] In the example shown in FIG. 6, an image region 70c in which a guide wire is drawn and an image region 70d in which a vertebra is drawn overlap in an overlapping region A1. When an image region 70 in which a body tissue such as a vertebra or a diaphragm is drawn overlaps with an image region 70 in which a device such as a guide wire is drawn among the elements, the visibility of the device on the X-ray image data decreases.

[0115] In such a case, among the frequency band data f0 to f5 and the background data b1, the low-frequency side is suppressed and the high-frequency side is emphasized, so that the vertebra is suppressed and the device is emphasized and displayed.

[0116] Graph G3 shows an example of a state in which the background data b1 on the low-frequency side and the frequency band data f4 and f5 are suppressed to suppress the display of the Vertebra. In the example shown in FIG. 6, the determination function 122 sets the coefficient corresponding to the low-frequency side data to be suppressed among the frequency band data f0 to f5 and the background data b1 to a value less than 1. The determination function 122 determines the value of each coefficient so that, for example, the lower the frequency, the smaller the coefficient value. The value of each coefficient is, for example, associated with the element to be suppressed and is stored in advance in the storage circuit 11.

[0117] Further, graph G4 shows an example of a state in which the high-frequency side frequency band data f0 to f4 is emphasized to emphasize the guide wire. The determination function 122 sets the coefficient corresponding to the high-frequency side data to be emphasized among the frequency band data f0 to f5 to a value greater than 1. The determination function 122 determines the value of each coefficient so that, for example, the higher the frequency, the larger the coefficient value. The value of each coefficient is, for example, associated with the element to be emphasized and is stored in advance in the storage circuit 11.

[0118] Graph G5 shows an example of the result of synthesizing the coefficients shown in graph G3 and graph G4. For example, for the coefficient of the frequency band data f4 with a medium level of spatial frequency height, different magnitude values are applied in both graph G3 and graph G4, but the determination function 122 may determine the average value of these values as the coefficient of the frequency band data f4. For example, when the storage circuit stores a set of coefficients associated with the elements to be suppressed and a set of coefficients associated with the elements to be emphasized, the determination function 122 synthesizes the set of coefficients associated with the elements to be suppressed and the set of coefficients associated with the elements to be emphasized to determine the value of the coefficient commonly used for the entire original image data 81. Note that the method of synthesizing different coefficients is not limited to taking the average value, and various operations can be employed.

[0119] In addition, in FIG. 6, an example is illustrated in which the background data b1 is suppressed and the frequency band data f0 to f4 on the high-frequency side is emphasized. However, depending on the combination of the types of overlapping elements, the objects of emphasis and suppression are different.

[0120] For example, when the image region 70 in which the lung field is depicted and the image region 70 in which the device is depicted overlap, since the lung field is clearly depicted on the X-ray image data, artifacts may occur due to the overlap with the device. Therefore, when the image region 70 in which the lung field is depicted and the image region 70 in which the device is depicted overlap, the determination function 122 suppresses the frequency band data corresponding to the frequency of the lung field among the frequency band data f0 to f4, thereby ensuring the visibility of the device on the X-ray image data.

[0121] The multi-frequency processing function 123 of the present embodiment generates display X-ray image data by performing multi-frequency processing on the original image data 81 based on the parameters determined by the determination function 122, in the same manner as in the first embodiment. Further, the display control circuit 33 causes the generated display X-ray image data to be displayed on the monitor 34, in the same manner as in the first embodiment.

[0122] As described above, the X-ray diagnostic apparatus 100 of the present embodiment recognizes a location where a plurality of image regions 70 in which different types of elements are depicted overlap based on the detection results of the elements, and determines the parameters of the multi-frequency processing according to the types of the overlapping elements in the image region 70. Therefore, according to the X-ray diagnostic apparatus 100 of the present embodiment, in addition to the same effects as in the first embodiment, it is possible to reduce the decrease in visibility due to the overlap between the elements.

[0123] In addition, the X-ray diagnostic apparatus 100 of the present embodiment determines the parameters of the multi-frequency processing that are commonly used for the entire original image data 81. Therefore, according to the X-ray diagnostic apparatus 100 of the present embodiment, by using parameters unified for the entire image, it is possible to simplify the image processing and adjust to improve the visibility of the entire image.

[0124] (Third Embodiment) In the above-described first and second embodiments, multi-frequency processing was performed by applying parameters common to the entire original image data 81. In this third embodiment, multi-frequency processing with different parameters is performed for each image region 70 in which each element is drawn.

[0125] The X-ray diagnostic apparatus 100 of the present embodiment has the same configuration as that of the first embodiment described with reference to FIG. 1.

[0126] The image arithmetic circuit 12 of the present embodiment includes an acquisition function 120, a detection function 121, a determination function 122, a frequency separation function 123a, an enhancement function 123b, and a synthesis function 123c, as in the first embodiment. The acquisition function 120, the detection function 121, the frequency separation function 123a, the enhancement function 123b, and the synthesis function 123c have the same functions as those in the first embodiment. In addition, other configurations included in the X-ray diagnostic apparatus 100 also have the same functions as those in the first embodiment.

[0127] The determination function 122 of the present embodiment determines parameters corresponding to the type of the drawn element for each image region 70 in which the element is drawn on the original image data 81 based on the detection result of the element by the detection function 121.

[0128] More specifically, the determination function 122 recognizes the image region 70 in which the element is drawn on the original image data 81 as an ROI (Region Of Interest).

[0129] FIG. 7 is a diagram showing an example of an ROI according to the third embodiment. In the example shown in FIG. 7, on the region-divided image data 82, the image region 70a in which the guiding catheter is drawn is recognized as ROI #1, the image region 70b in which the catheter is drawn is recognized as ROI #2, the image region 70c in which the guide wire is drawn is recognized as ROI #4, and the image region 70d in which the vertebra is drawn is recognized as ROI #4. The number of ROIs corresponds to the number of detected elements. Also, the background region 60 is a region that does not correspond to any of the ROIs.

[0130] The memory circuit 11 of this embodiment stores multi-frequency processing parameters corresponding to the types of elements. More specifically, the memory circuit 11 stores a table in which the types of elements are associated with a group of coefficients used in the enhancement characteristic adjustment process. Note that the group of coefficients is a set of a plurality of coefficients corresponding to the frequency band data f0 to f5 and the background data b1. Note that the memory circuit 11 may further store a table in which the types of elements are associated with a group of cut-off frequencies for separating the frequency band data f0 to f5 and the background data b1.

[0131] The determination function 122 of this embodiment selects, from the memory circuit 11, parameters corresponding to the types of elements drawn for each image region 70 in which an element is drawn on the original image data 81.

[0132] The group of coefficients corresponding to the type of element will be described with reference to FIGS. 8 to 10.

[0133] FIG. 8 is a diagram showing an example of the frequency band data f0 to f5 and the background data b1 to which the group of coefficients corresponding to the catheter according to the third embodiment is applied. In the graph G6 shown in FIG. 8, the frequency band data f0 to f5 and the background data b1 in the state before being multiplied by the coefficients are shown by solid lines, and the corrected frequency band data f00 to f50 enhanced or suppressed by the coefficients are shown by broken lines. In the group of coefficients corresponding to the image region 70b where the catheter is drawn, that is, ROI#2, as shown in FIG. 8, the coefficients increase so as to enhance more on the high-frequency side.

[0134] Further, FIG. 9 is a diagram showing an example of frequency band data f0 to f5 and background data b1 to which a coefficient group corresponding to the guide wire according to the third embodiment is applied. In the graph G7 shown in FIG. 9, the frequency band data f0 to f5 and the background data b1 in the state before being multiplied by the coefficient are shown by solid lines, and the corrected frequency band data f00 to f40 emphasized or suppressed by the coefficient are shown by broken lines. In the coefficient group corresponding to the image region 70c where the guide wire is drawn, that is, ROI#3, as shown in FIG. 9, the coefficient becomes larger so as to emphasize more on the higher frequency side than ROI#2. Generally, a guide wire is a thinner device than a catheter, and the size of the image region 70c drawn in the original image data 81 also becomes smaller. Therefore, in ROI#3, the visibility of the image region 70c is improved by further emphasizing the higher frequency side than ROI#2.

[0135] Further, FIG. 10 is a diagram showing an example of frequency band data f0 to f5 and background data b1 to which a coefficient group corresponding to the bone according to the third embodiment is applied. In FIG. 10, a vertebra is illustrated as an example of the bone.

[0136] In the graph G8 shown in FIG. 10, the frequency band data f0 to f5 and the background data b1 in the state before being multiplied by the coefficient are shown by solid lines, and the corrected background data b10, frequency band data f40, f50 emphasized or suppressed by the coefficient are shown by broken lines.

[0137] As shown in FIG. 10, in the coefficient group corresponding to the image region 70d where the vertebra is drawn, that is, ROI#4, among the frequency band data f0 to f5 and the background data b1, the coefficient becomes smaller so as to suppress more on the lower frequency side. Therefore, even when other ROIs where devices such as a guide wire are drawn overlap ROI#4, the display of ROI#4 is not emphasized, and thus the visibility of the device can be maintained.

[0138] Note that the determination function 122 may perform coefficient weighting within the ROI in order to reduce the visual discontinuity of the boundaries of each ROI on the display X-ray image data due to differences in coefficients. For example, different coefficient groups may be applied step by step within one ROI such that the difference from the coefficient groups applied to other ROIs becomes smaller as it approaches the boundary adjacent to other ROIs. By reducing the difference between the groups of coefficients at the boundaries of the ROIs in this way, the discomfort felt by the user viewing the X-ray image can be reduced.

[0139] Also, in this embodiment, although an example in which the parameters corresponding to the elements are stored in the storage circuit 11 has been described, the determination function 122 may calculate the parameters corresponding to each element according to the segmentation result of the original image data 81.

[0140] Also, for the background region 60 which is a region not corresponding to any ROI, the parameters pre-stored in the storage circuit 11 may be applied, or other image processing different from the multi-frequency processing may be applied.

[0141] The multi-frequency processing function 123 of this embodiment executes multi-frequency processing individually for each ROI based on the parameters determined for each ROI by the determination function 122. The multi-frequency processing function 123 generates display X-ray image data by integrating each ROI subjected to multi-frequency processing individually and the background region 60.

[0142] Also, the display control circuit 33 causes the generated display X-ray image data to be displayed on the monitor 34 in the same manner as in the first embodiment.

[0143] In this way, the X-ray diagnostic apparatus 100 of this embodiment determines the parameters corresponding to the type of the depicted element for each image region 70 where the element is depicted on the original image data 81. Therefore, according to the X-ray diagnostic apparatus 100 of this embodiment, in addition to having the effects of the first embodiment, appropriate multi-frequency processing can be performed for each image region 70 where each element is depicted.

[0144] More specifically, the X-ray diagnostic apparatus 100 of the present embodiment includes a storage circuit 11 that stores parameters corresponding to the types of elements. For each image region 70 in which an element is depicted on the original image data 81, the apparatus selects, from the storage circuit 11, the parameter corresponding to the type of the depicted element. Therefore, according to the X-ray diagnostic apparatus 100 of the present embodiment, it is possible to easily apply parameters corresponding to the type of element to each image region 70.

[0145] (Modification 1) In the above-described embodiment, the X-ray diagnostic apparatus 100 determines the parameters of the multi-frequency processing based on the detection result of the element depicted in the original image data 81. The X-ray diagnostic apparatus 100 may further determine the parameters of the multi-frequency processing according to the imaging conditions and the inspection protocol.

[0146] For example, the determination function 122 of the present modification determines the parameters based on at least one of the inspection protocol used when imaging the X-ray image data and the imaging conditions. As described in the first embodiment, the imaging conditions include settings related to the imaging system, the imaging field of view, and the magnification. Also, as described in the first embodiment, the imaging system is a definition item or information regarding the positional relationship between the device used for imaging and the subject P, and the positional relationship between the devices used for imaging, and includes SID, SSD, the height of the bed 17, and the rotation amount of the holding arm 5. The determination function 122 determines the parameters based on, for example, at least any one of the inspection protocol used for imaging the subject P, the imaging field of view, the magnification, and the positional relationship between the device used for imaging and the subject P.

[0147] Also, for example, when determining the parameters based on the inspection protocol and the imaging conditions, the storage circuit 11 of the present modification stores a table in which the inspection protocol, the imaging conditions, and the parameters of the multi-frequency processing are associated with each other.

[0148] FIG. 11 is a diagram showing an example of a table 111 in which parameters of multi-frequency processing according to Modification 1 are registered. As shown in FIG. 11, in the table 111, a parameter set No., an inspection protocol, imaging conditions, an offset frequency group, and a coefficient group are registered in association with each other.

[0149] The offset frequency group is a set of a plurality of offset frequencies that separate frequency band data f0 to f5 and background data b1. The coefficient group is a set of a plurality of coefficients corresponding to the frequency band data f0 to f5 and the background data b1. A set of an offset frequency group and a coefficient group corresponding to a combination of one inspection protocol and imaging conditions is called a parameter set. The parameter set No. is identification information for identifying each parameter set.

[0150] Note that the configuration of the table 111 shown in FIG. 11 is an example and is not limited thereto. For example, in FIG. 11, an example in which a plurality of parameter sets are registered in one table 111 is illustrated, but one table may be provided for each parameter set. Also, in FIG. 11, both the offset frequency group and the coefficient group are registered in the table 111, but only one of them may be associated with the inspection protocol and the imaging conditions.

[0151] Also, in FIG. 11, both the inspection protocol and the imaging conditions are associated with the parameters, but only one of them may be associated with the parameters. Further, other information may be associated with the parameters and registered in the table 111.

[0152] The determination function 122 of this modification reads a parameter set corresponding to the inspection protocol and imaging conditions used for imaging the subject P from the table 111 stored in the storage circuit 102, and determines the parameters included in the parameter set as parameters for multi-frequency processing on the original image data 81.

[0153] FIG. 12 is a diagram showing an example of frequency band data f0 to f5 to which a parameter set according to a first modification is applied, and background data b1. Further, FIG. 13 is a diagram showing an example of frequency band data f0 to f5 to which a parameter set different from that in FIG. 12 is applied, and background data b1. As shown in graphs G9 and G10 in FIGS. 12 and 13, the results of multi-frequency processing are different depending on each parameter set.

[0154] For example, depending on the inspection protocol and imaging conditions, the types and positions of the elements included in the imaging field of view change. Therefore, by storing in advance parameters for improving the image quality of the display X-ray image data for each inspection protocol and imaging conditions, it becomes possible to specify parameters according to the elements included in the imaging field of view.

[0155] More specifically, the types and positions of the elements included in the imaging field of view change depending on the positional relationship between the device used for imaging and the subject P, that is, the imaging geometry. The positional relationship between the device used for imaging and the subject P is defined by, for example, SID, the height of the bed 17, and the rotation amount of the holding arm 5. Therefore, the determination function 122 in this modification determines parameters based on SID, the height of the bed 17, or the rotation amount of the holding arm 5 included in the imaging conditions.

[0156] Further, the determination function 122 may further change the parameter set read from the table 111 based on the elements detected from the original image data 81. For example, the determination function 122 may determine the parameters by correcting the parameters corresponding to the inspection protocol and imaging conditions by the methods described in the first to third embodiments above.

[0157] In this modification, a method of specifying parameters corresponding to the inspection protocol and imaging conditions by reading the parameter set registered in the table 111 has been described, but other methods may be adopted. For example, the determination function 122 may specify parameters corresponding to the inspection protocol and imaging conditions by a mathematical formula or an algorithm.

[0158] For example, based on the imaging conditions, the determination function 122 may estimate the positional relationship between the device used for imaging and the subject P, that is, the imaging geometry, and calculate appropriate parameters according to the estimated imaging geometry.

[0159] (Modification Example 2) In addition, in each of the above-described embodiments, the segmentation result of the original image data 81 has been used for internal processing for determining the parameters of the multi-frequency processing, but it may also be used for display. For example, the display control circuit 33 may cause the monitor 34 to display a label indicating the type of element detected from the original image data 81, an ROI set for each image region 70 in the third embodiment, and the like.

[0160] FIG. 14 is a diagram showing an example of the display on the monitor 34 according to Modification Example 2. In the example shown in FIG. 14, the display control circuit 33 causes the monitor 34 to display a display image 83 in which a label indicating the type of detected element and a boundary line of the image region 70 are superimposed on the display X-ray image data. By thus displaying the segmentation result of the original image data 81, the user can easily grasp which part of the display X-ray image data has been detected as what kind of element.

[0161] (Modification Example 3) In addition, in the first embodiment described above, each time new original image data 81 of a frame is acquired, the detection function 121 and the determination function 122 determine the parameters of the multi-frequency processing according to the latest imaging state. However, the update frequency of the parameters is not limited to this. For example, the same parameters may be continuously used while the imaging conditions have not changed.

[0162] More specifically, the determination function 122 determines the parameters of the multi-frequency processing based on the original image data 81 for several frames from the start of imaging, and thereafter, the same parameters may be used unless the imaging system, FOV, or magnification is changed by the user.

[0163] Alternatively, the determination function 122 may update the parameters of the multi-frequency processing every predetermined number of frames or time intervals. The multi-frequency processing function 123 executes the multi-frequency processing using the parameters determined at the time of the past update until the update.

[0164] In addition, the determination function 122 may change the update frequency of the parameters according to the imaging target site. The imaging target site can be specified, for example, by a set inspection protocol. For example, when the same imaging system continues and the imaging target site is the head or lower limb region where the subject P moves less, the determination function 122 may continue to use the parameters applied in the past frame. Further, the determination function 122 may determine the parameters by comprehensively combining the element detection results of a plurality of frames instead of only the element detection results based on one frame.

[0165] In addition, in an imaging site where the subject P is expected to make periodic movements, such as the heart region, the determination function 122 may store the parameters determined based on a plurality of original image data 81 corresponding to one cardiac cycle in the storage circuit 11. In this case, the multi-frequency processing function 123 may read the parameters from the storage circuit 11 in electrocardiogram synchronization according to the heartbeat and use them for multi-frequency processing.

[0166] (Modification 4) Regarding the processing in which the learned model 90 is used in each of the above embodiments, a method other than the learned model 90 may be used. For example, the detection function 121 may detect elements from the original image data 81 by image recognition processing that does not use deep learning.

[0167] (Modification 5) In each of the above embodiments, the case where the X-ray image data to be segmented for element detection and the X-ray image data to be subjected to multi-frequency processing are the same X-ray image data (original image data) was exemplified. However, the original image data to be segmented and the original image data to be subjected to multi-frequency processing do not have to be the same.

[0168] For example, when the X-ray diagnostic apparatus 100 continuously captures original image data and executes element detection, parameter determination, and multi-frequency processing in real time, while the processes of segmentation and parameter determination for a certain original image data are being executed, other original image data is captured. In this case, the multi-frequency processing function 123 of the X-ray diagnostic apparatus 100 may execute multi-frequency processing on other original image data captured after the original image data to be segmented, based on the parameters detected from the original image data to be segmented. The other original image data is an example of the other X-ray image data in this modified example.

[0169] That is, the multi-frequency processing function 123 of this modified example executes multi-frequency processing on at least one of "the original image data to be segmented" and "other original image data captured after the said original image data" based on the parameters determined by the determination function 122.

[0170] The other X-ray image data to be subjected to multi-frequency processing may be the original image data captured immediately after the original image data to be segmented, or may be the original image data captured even later.

[0171] (Modified Example 6) The processes described as being executed by the X-ray diagnostic apparatus 100 in each of the above embodiments may be executed by an information processing apparatus different from the X-ray diagnostic apparatus 100. Examples of the information processing apparatus different from the X-ray diagnostic apparatus 100 include a PC (Personal Computer), a tablet terminal, a server apparatus, a workstation, and the like. These information processing apparatuses are examples of the medical image processing apparatus in this modification.

[0172] For example, the medical image processing apparatus may include an image arithmetic circuit 12 having an acquisition function 120, a detection function 121, a determination function 122, a frequency separation function 123a, an enhancement function 123b, and a synthesis function 123c, a storage circuit 11, a display control circuit 33, a monitor 34, and an operation unit 9.

[0173] Note that various data handled in this specification are typically digital data.

[0174] According to at least one of the embodiments described above, appropriate parameters in multi-frequency processing can be determined according to the elements included in the imaging field of view.

[0175] Although several embodiments have been described, these embodiments are 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, changes, and combinations of the embodiments can be made without departing from the gist of the invention. These embodiments and their modifications are included in the scope and gist of the invention, and are also included in the invention described in the claims and its equivalent scope.

[0176] Regarding the above embodiments, the following supplementary notes are disclosed as one aspect and selective features of the invention.

[0177] (Supplementary Note 1) A detection unit that detects elements from the X-ray image data of the subject that has been imaged, A determination unit that determines parameters for multi-frequency processing based on the detection result of the elements An image processing unit that executes the multi-frequency processing on at least one of the X-ray image data and other X-ray image data captured after the X-ray image data based on the determined parameters; An X-ray diagnostic apparatus comprising the same.

[0178] (Appendix 2) The X-ray diagnostic apparatus further comprises an acquisition unit that repeatedly acquires X-ray image data of the subject; The detection unit repeatedly executes the detection of the elements on the newly acquired X-ray image data; The determination unit repeatedly executes the determination of the parameters along with the detection of the elements; The image processing unit may repeatedly execute the multi-frequency processing based on the repeatedly determined parameters.

[0179] (Appendix 3) The multi-frequency processing may include a frequency separation process that generates a plurality of frequency band data separated for each of a plurality of frequency bands from at least one of the X-ray image data and the other X-ray image data; The determined parameters of the multi-frequency processing may include a threshold value used for the frequency separation process; The image processing unit may separate the plurality of frequency band data based on the threshold value.

[0180] (Appendix 4) The frequency separation process may be a process that generates a plurality of frequency band data including different frequency bands by gradually applying a low-pass filter to at least one of the X-ray image data and the other X-ray image data; The threshold value may be a cut-off frequency in the low-pass filter.

[0181] (Appendix 5) The multi-frequency processing may include an emphasis characteristic adjustment process of emphasizing or suppressing the plurality of frequency band data by multiplying each of the plurality of frequency band data by a coefficient. The determined parameters of the multi-frequency processing may include the coefficient.

[0182] (Appendix 6) The detection unit may detect the type of element drawn on the X-ray image data and the image area where the element is drawn. The determination unit may determine the parameters based on the type of the detected element and the size of the image area where the element is detected.

[0183] (Appendix 7) The determination unit may calculate, for each element, the ratio that the image area where the element is drawn occupies on the X-ray image data, and determine the threshold value based on the ratio.

[0184] (Appendix 8) The detection unit may input the X-ray image data into a trained trained model together with a plurality of learning X-ray image data and segmentation results of elements included in the plurality of learning X-ray image data, and obtain segmentation results for each of the elements included in the X-ray image data output from the trained model.

[0185] (Appendix 9) The determination unit may recognize a location where a plurality of image areas in which different types of the elements are drawn overlap based on the detection result of the elements, and determine the parameters according to the types of the elements whose image areas overlap.

[0186] (Appendix 10) The determination unit may determine the parameters that are commonly used for the entire plurality of continuously captured X-ray image data including the X-ray image data and the other X-ray image data.

[0187] (Appendix 11) The determination unit may determine the parameter for each image region in which the element is depicted on the X-ray image data.

[0188] (Appendix 12) The X-ray diagnostic apparatus may further include a storage unit that stores the parameter corresponding to the type of the element. The determination unit may select, from the storage unit, the parameter corresponding to the type of the depicted element for each image region in which the element is depicted on the X-ray image data.

[0189] (Appendix 13) The determination unit may further determine the parameter based on at least any one of an examination protocol, an imaging field of view, a magnification ratio, and a positional relationship between the device used for imaging and the subject, which are used when the X-ray image data is captured.

[0190] (Appendix 14) The X-ray diagnostic apparatus a bed on which the subject is placed, an X-ray detector that detects X-rays that have passed through the subject, and an arm that supports the X-ray detector, may be provided. The determination unit may determine the parameter based on the distance between the X-ray source and the image receptor surface, the height of the bed, or the amount of rotation of the arm.

[0191] (Appendix 15) a detection unit that detects an element from X-ray image data in which a subject is imaged, a determination unit that determines a parameter for multi-frequency processing based on the detection result of the element, an image processing unit that performs the multi-frequency processing on at least one of the X-ray image data and other X-ray image data captured after the X-ray image data based on the determined parameter, A medical image processing apparatus comprising the same.

[0192] (Appendix 16) A detection step of detecting elements from X-ray image data in which a subject has been imaged; A determination step of determining parameters for multi-frequency processing based on the detection results of the elements; An image processing step of performing the multi-frequency processing on at least one of the X-ray image data and other X-ray image data imaged after the X-ray image data based on the determined parameters; A program for causing a computer to execute the above.

Explanation of Signs

[0193] 5 Holding arm 7 Image operation and storage unit 8 Display device 9 Operation unit 10 System control unit 11,102 Memory circuit 12 Image operation circuit 13 Image data storage circuit 17 Bed 20 Image data generation unit 33 Display control circuit 34 Monitor 60 Background area 70,70a~70d Image area 81 Original image data 82 Region-segmented image data 83 Display image 90 Trained model 100 X-ray diagnostic apparatus 101 Processing circuit 111 Table 120 Acquisition function 121 Detection function 122 Determination function 123 Multi-frequency processing function 123a Frequency separation function 123b Enhancement function 123c Synthesis function b1,b10 Background data f0~f5,f00,f10,f20,f30,f40,f50 Each frequency band data Graphs G1 to G10 P Subject

Claims

1. A detection unit that detects the type and number of elements from X-ray image data in which a subject has been imaged; A determination unit that determines parameters for multi-frequency processing based on the detection result of the elements; An image processing unit that executes the multi-frequency processing on at least one of the X-ray image data and other X-ray image data imaged after the X-ray image data based on the determined parameters; Comprising: The multi-frequency processing includes a frequency separation process that generates a plurality of frequency band data separated for each of a plurality of frequency bands from at least one of the X-ray image data and the other X-ray image data; The parameters include the cut-off frequency of a low-pass filter used for the frequency separation process; The determination unit determines the cut-off frequency according to the type and number of the detected elements; The image processing unit separates the plurality of frequency band data based on the cut-off frequency; An X-ray diagnostic apparatus.

2. Further comprising an acquisition unit that repeatedly acquires X-ray image data in which the subject has been imaged; The detection unit repeatedly executes detection of the elements on the newly acquired X-ray image data; The determination unit repeatedly executes determination of the parameters along with the detection of the elements; The X-ray diagnostic apparatus according to claim 1, wherein the image processing unit repeatedly executes the multi-frequency processing based on the repeatedly determined parameters.

3. The frequency separation process is a process that generates a plurality of frequency band data including different frequency bands by gradually applying a low-pass filter to at least one of the X-ray image data and the other X-ray image data; The X-ray diagnostic apparatus according to claim 1 or 2.

4. The multi-frequency processing includes an enhancement characteristic adjustment process that enhances or suppresses the plurality of frequency band data by multiplying each of the plurality of frequency band data by a coefficient; The determined parameters of the multi-frequency processing include the coefficient; The X-ray diagnostic apparatus according to any one of claims 1 to 3.

5. The detection unit detects an image region in which the elements are depicted; The determination unit further determines the parameters based on the size of the image region in which the elements are detected; The X-ray diagnostic apparatus according to any one of claims 1 to 4.

6. The determination unit calculates, for each of the elements, the ratio that the image area in which the element is drawn occupies on the X-ray image data, and determines the cut-off frequency based on the ratio. The X-ray diagnostic apparatus according to any one of claims 1 to 5. **Claim 7** The detection unit inputs the plurality of learning X-ray image data and the segmentation results of the elements included in the plurality of learning X-ray image data into a learned model, inputs the X-ray image data, and obtains the segmentation results for each of the elements included in the X-ray image data output from the learned model. The X-ray diagnostic apparatus according to any one of claims 1 to 6. **Claim 8** The determination unit recognizes, based on the detection result of the element, a location where a plurality of image areas in which different types of the elements are drawn overlap, and determines the parameter according to the types of the elements for which the image areas overlap. The X-ray diagnostic apparatus according to any one of claims 1 to 7. **Claim 9** The determination unit determines the parameter that is commonly used for a plurality of continuously captured X-ray image data including the X-ray image data and the other X-ray image data. The X-ray diagnostic apparatus according to any one of claims 1 to 8. **Claim 10** The determination unit determines the parameter for each image area in which the element is drawn on the X-ray image data. The X-ray diagnostic apparatus according to any one of claims 1 to 9. **Claim 11** Further comprising a storage unit that stores the parameter corresponding to the type of the element, The determination unit selects, from the storage unit, the parameter corresponding to the type of the element drawn for each image area in which the element is drawn on the X-ray image data. The X-ray diagnostic apparatus according to claim 10. **Claim 12** The determination unit further determines the parameter based on at least any one of an inspection protocol, an imaging field of view, a magnification factor, and a positional relationship between the device used for imaging and the subject used when imaging the X-ray image data. The X-ray diagnostic apparatus according to any one of claims 1 to 11. **Claim 13** A bed on which the subject is placed, An X-ray detector that detects X-rays that have passed through the subject, An arm that supports the X-ray detector, and The determination unit determines the parameter based on the distance between the X-ray source and the image receptor surface, the height of the bed, or the amount of rotation of the arm. The X-ray diagnostic apparatus according to any one of claims 1 to 12.

14. A detection unit that detects the type and number of elements from X-ray image data in which a subject has been imaged; A determination unit that determines parameters for multi-frequency processing based on the detection result of the elements; An image processing unit that executes the multi-frequency processing on at least one of the X-ray image data and other X-ray image data imaged after the X-ray image data based on the determined parameters; Comprising: The multi-frequency processing includes a frequency separation process that generates a plurality of frequency band data separated for each of a plurality of frequency bands from at least one of the X-ray image data and the other X-ray image data; The parameter includes a cut-off frequency of a low-pass filter used for the frequency separation process; The determination unit determines the cut-off frequency according to the type and number of the detected elements; A medical image processing apparatus.

15. A detection step of detecting the type and number of elements from X-ray image data in which a subject has been imaged; A determination step of determining parameters for multi-frequency processing based on the detection result of the elements; An image processing step of executing the multi-frequency processing on at least one of the X-ray image data and other X-ray image data imaged after the X-ray image data based on the determined parameters, including: The multi-frequency processing includes a frequency separation process that generates a plurality of frequency band data separated for each of a plurality of frequency bands from at least one of the X-ray image data and the other X-ray image data; The parameter includes a cut-off frequency of a low-pass filter used for the frequency separation process; The determination step determines the cut-off frequency according to the type and number of the detected elements; A program for causing a computer to execute the process.

Images