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

Abstract

To improve the visibility of selected objects in X-ray images. [Solution] The X-ray diagnostic apparatus according to this embodiment includes: an acquisition unit that sequentially acquires a plurality of X-ray images in a time series; a detection unit that detects a plurality of object candidates, which are candidates for a plurality of objects included in the acquired plurality of X-ray images; an evaluation unit that calculates an evaluation value for each of the plurality of object candidates based on the plurality of X-ray images; a display unit that displays the evaluation value in association with the plurality of object candidates; a reception unit that accepts the selection of at least one of the plurality of object candidates; and a corrected image generation unit that generates a plurality of corrected images by applying a correction process to the plurality of X-ray images to align the position of the object corresponding to the selected object candidate with the reference position, using the position of the object detected in the reference image among the plurality of X-ray images and selected from the plurality of object candidates as the reference position.

Description

TECHNICAL FIELD

[0001] Embodiments disclosed in the present specification and drawings relate to an X-ray diagnostic apparatus, a medical image processing apparatus, a medical image processing method, and a medical image processing program. BACKGROUND ART

[0002] Intravascular interventional therapy is a treatment method in which a therapeutic instrument (device) called a catheter is inserted into a blood vessel to treat an affected part occurring in the heart, brain, liver or the like. For example, in intravascular interventional therapy, a doctor inserts a balloon catheter to a stenotic site. Then, the doctor injects a liquid into the balloon through the catheter, for example, to inflate the balloon. As a result, the stenotic site is mechanically dilated, and blood flow is restored. After the liquid in the balloon is aspirated, the balloon catheter is pulled out of the body by the doctor.

[0003] Furthermore, intravascular interventional therapy using a balloon catheter in which a metal mesh (stent) is closely attached to the outside of the balloon is also performed to prevent restenosis of the stenotic site dilated by the balloon. In this treatment method, the doctor expands the balloon to dilate the stent, then aspirates the liquid in the balloon and pulls the catheter out of the body. As a result, the dilated stent is left indwelling at the stenotic site, and the restenosis rate of the stenotic site can be reduced.

[0004] In intravascular interventional therapy, it is necessary to accurately move the device inserted into the blood vessel to the treatment target site. Normally, positioning of the device is performed with reference to an X-ray image generated and displayed in real time by an X-ray diagnostic apparatus. For this reason, as markers indicating the positions of the balloon and the stent, for example, two (or sometimes one) radiopaque metals are attached to the device, and the doctor refers to the markers depicted in the X-ray image displayed on the monitor to perform positioning of the device.

[0005] However, when performing endovascular interventions on organs that constantly beat, such as the heart, or on blood vessels of organs that move due to beating, the position of the device on the X-ray image is constantly shifting. Therefore, positioning the device by referring to the X-ray image is an extremely difficult task for physicians.

[0006] Therefore, conventionally, there is a known technique for displaying a device as if it were virtually stationary by tracking markers depicted in sequentially generated X-ray images and transforming the images so that the position of the markers in each X-ray image is the same as in previous images. Furthermore, as a post-processing step, there is a known technique for highlighting the device with high contrast by, for example, averaging multiple frames of images in which the marker positions have been corrected to be the same. [Prior art documents] [Patent Documents]

[0007] [Patent Document 1] Japanese Patent Publication No. 2018-171297 [Overview of the project] [Problems that the invention aims to solve]

[0008] One of the problems that the embodiments disclosed herein and in the drawings aim to solve is to improve the visibility of a selected object in an X-ray image. However, the problems that the embodiments disclosed herein and in the drawings aim to solve are not limited to the above problem. Problems corresponding to the effects of each configuration shown in the embodiments described later can also be positioned as other problems. [Means for solving the problem]

[0009] The X-ray diagnostic apparatus according to this embodiment includes an acquisition unit, a detection unit, a display unit, an evaluation unit, a reception unit, and a corrected image generation unit. The acquisition unit sequentially acquires a plurality of X-ray images in a time series. The detection unit detects a plurality of object candidates, which are candidates for a plurality of objects included in the acquired plurality of X-ray images. The evaluation unit calculates an evaluation value for each of the plurality of object candidates based on the plurality of X-ray images. The display unit displays the evaluation value in association with the plurality of object candidates. The reception unit accepts the selection of at least one of the plurality of object candidates. The corrected image generation unit generates a plurality of corrected images by applying a correction process to the plurality of X-ray images, using the position of the object corresponding to the selected object candidate as a reference position, and aligning the position of the object corresponding to the selected object candidate with the reference position. [Brief explanation of the drawing]

[0010] [Figure 1] Figure 1 shows an example of the configuration of an X-ray diagnostic apparatus according to an embodiment. [Figure 2] Figure 2 is a diagram illustrating the processing performed by the detection function according to this embodiment. [Figure 3] Figure 3 is a diagram illustrating an example of the Learning mode according to the embodiment. [Figure 4] Figure 4 is a diagram illustrating an example of tracking multiple target candidates across multiple frames, relating to an embodiment. [Figure 5] Figure 5 is a diagram illustrating the processing by the corrected image generation function according to an embodiment. [Figure 6] Figure 6 is a diagram illustrating an example of a Tracking mode according to the embodiment. [Figure 7] Figure 7 shows an example of an embodiment in which two balloons are used as multiple objects. [Figure 8] Figure 8 shows an example of a list of trajectories according to the embodiment. [Figure 9]Figure 9 shows an example of a marker selection screen corresponding to a candidate object, relating to an embodiment. [Figure 10] Figure 10 is a diagram illustrating an example of a selection screen displayed on a tablet according to an embodiment. [Figure 11] Figure 11 is a diagram illustrating an example of another selection screen related to an embodiment. [Figure 12] Figure 12 is a flowchart showing an example of the flow of the object selection tracking process according to the embodiment. [Modes for carrying out the invention]

[0011] Hereinafter, embodiments of the X-ray diagnostic apparatus, medical image processing apparatus, medical image processing method, and medical image processing program will be described in detail with reference to the attached drawings. In the embodiments described below, the X-ray diagnostic apparatus according to the present application will be used as an example. Furthermore, the medical image processing apparatus and X-ray diagnostic apparatus according to the present application are not limited to the embodiments described below. In the following embodiments, parts with the same reference numerals perform similar operations, and redundant explanations will be omitted as appropriate.

[0012] (Embodiment) The overall configuration of the X-ray diagnostic apparatus according to the embodiment will now be described. Figure 1 is a diagram showing an example of the configuration of the X-ray diagnostic apparatus 100 according to the embodiment. As shown in Figure 1, the X-ray diagnostic apparatus 100 according to the embodiment includes a high-voltage generator 11, an X-ray tube 12, a collimator 13, a top plate 14, a C-arm 15, an X-ray detector 16, a C-arm rotation / movement mechanism 17, a top plate movement mechanism 18, a C-arm / top plate mechanism control circuit 19, an aperture control circuit 20, a processing circuit 21, an input circuit 22, a display 23, an image data generation circuit 24, a storage circuit 25, and an image processing circuit 26.

[0013] In the X-ray diagnostic apparatus 100 shown in Figure 1, each processing function is stored in the storage circuit 25 in the form of a program executable by a computer. The C-arm and tabletop mechanism control circuit 19, the aperture control circuit 20, the processing circuit 21, the image data generation circuit 24, and the image processing circuit 26 are processors that realize the functions corresponding to each program by reading out the program from the storage circuit 25 and executing it. In other words, each circuit in a state where each program is read out has the function corresponding to the read-out program.

[0014] The term "processor" used in the above description 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 (e.g., a Simple Programmable Logic Device (SPLD), a Complex Programmable Logic Device (CPLD), and a Field Programmable Gate Array (FPGA)).

[0015] The processor realizes the functions by reading out and executing the program stored in the storage circuit 25. Instead of storing the program in the storage circuit 25, the program may be directly embedded in the circuit of the processor. In this case, the processor realizes the functions by reading out and executing the program embedded in the circuit. 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 configure one processor to realize its functions.

[0016] The high voltage generator 11 generates a high voltage under the control of the processing circuit 21, and supplies the generated high voltage to the X-ray tube 12. The X-ray tube 12 generates X-rays using the high voltage supplied from the high voltage generator 11.

[0017] The collimator 13 narrows down the X-rays generated by the X-ray tube 12 under the control of the diaphragm control circuit 20 so that the X-rays are selectively irradiated to the region of interest of the subject P. For example, the collimator 13 has four slidable diaphragm blades. The collimator 13 slides these diaphragm blades under the control of the diaphragm control circuit 20, thereby narrowing down the X-rays generated by the X-ray tube 12 and irradiating the subject P with the X-rays. The top panel 14 is a bed on which the subject P is placed, and is arranged on a couch not shown. Note that the subject P is not included in the X-ray diagnostic apparatus 100.

[0018] The X-ray detector 16 detects X-rays that have passed through the subject P. For example, the X-ray detector 16 has detection elements arranged in a matrix. Each detection element converts the X-rays transmitted through the subject P into an electric signal and accumulates the electric signal, and transmits the accumulated electric signal to the image data generation circuit 24.

[0019] The C-arm 15 holds the X-ray tube 12, the collimator 13, and the X-ray detector 16. The X-ray tube 12, the collimator 13, and the X-ray detector 16 are arranged by the C-arm 15 so as to face each other with the subject P interposed therebetween. Note that although FIG. 1 illustrates an example in which the X-ray diagnostic apparatus 100 is of a single-plane type, the embodiment is not limited to this, and may be of a bi-plane type.

[0020] The C-arm rotation / movement mechanism 17 is a mechanism for rotating and moving the C-arm 15. The C-arm rotation / movement mechanism 17 can also change SID (Source Image receptor Distance), which is the distance between the X-ray tube 12 and the X-ray detector 16. The C-arm rotation / movement mechanism 17 can also rotate the X-ray detector 16 held by the C-arm 15. The top panel moving mechanism 18 is a mechanism for moving the top panel 14.

[0021] The C-arm / top plate mechanism control circuit 19 controls the rotation and movement of the C-arm 15 and the movement of the top plate 14 by controlling the C-arm rotation / movement mechanism 17 and the top plate movement mechanism 18 under the control of the processing circuit 21. The aperture control circuit 20 controls the irradiation range of the X-rays irradiated onto the subject P by adjusting the opening of the aperture blades of the collimator 13 under the control of the processing circuit 21.

[0022] The image data generation circuit 24 generates image data using electrical signals converted from X-rays by the X-ray detector 16, and stores the generated image data in the memory circuit 25. For example, the image data generation circuit 24 performs current-to-voltage conversion, A (Analog) / D (Digital) conversion, and parallel-to-serial conversion on the electrical signals received from the X-ray detector 16 to generate image data (projection data). The image data generation circuit 24 then stores the generated image data in the memory circuit 25.

[0023] The memory circuit 25 receives and stores the image data generated by the image data generation circuit 24. The memory circuit 25 also stores programs corresponding to various functions that are read out and executed by each circuit shown in Figure 1. For example, the memory circuit 25 stores programs corresponding to the control function 211, the detection function 212, the evaluation function 213, the corrected image generation function 214, and the display control function 215, all of which are read out and executed by the processing circuit 21.

[0024] The image processing circuit 26 generates an X-ray image by performing various image processing operations on the image data stored in the memory circuit 25, under the control of the processing circuit 21 described later. Alternatively, the image processing circuit 26 directly acquires image data from the image data generation circuit 24 under the control of the processing circuit 21 described later, and generates an X-ray image by performing various image processing operations on the acquired image data. The image processing circuit 26 can also store the processed X-ray image in the memory circuit 25. For example, the image processing circuit 26 can perform various processing operations using image processing filters such as moving average (smoothing) filters, Gaussian filters, median filters, recursive filters, and bandpass filters.

[0025] The input circuit 22 is implemented by a trackball, switch buttons, mouse, keyboard, etc., for setting areas (e.g., regions of interest), and a foot switch, etc., for performing X-ray irradiation. The input circuit 22 is connected to the processing circuit 21 and converts the input operations received from the operator into electrical signals and outputs them to the processing circuit 21. The input circuit 22 accepts various operations from the operator. The input circuit 22 may also be called the input unit, operation unit, or reception unit.

[0026] The display 23 displays a GUI (Graphical User Interface) for receiving operator instructions and various images generated by the image processing circuit 26. The display 23 can be, for example, a liquid crystal display (LCD), a cathode ray tube (CRT), an organic electroluminescent display (OELD), a plasma display, or any other suitable display. The display 23 may be a desktop type, or it may be composed of a tablet terminal capable of wireless communication with the processing circuit 21, etc. The display 23 corresponds to the display unit.

[0027] The processing circuit 21 controls the operation of the entire X-ray diagnostic apparatus 100. Specifically, the processing circuit 21 performs various processes by reading and executing programs corresponding to control functions 211 for controlling the entire apparatus from the storage circuit 25. The processing circuit 21 may also be called a processing unit.

[0028] For example, the processing circuit 21 controls the high-voltage generator 11 according to the operator's instructions transmitted from the input circuit 22 via the control function 211, and adjusts the voltage supplied to the X-ray tube 12, thereby controlling the amount of X-rays irradiated to the subject P and the ON / OFF status. Also, for example, the control function 211 controls the C-arm / top plate mechanism control circuit 19 according to the operator's instructions, adjusting the rotation and movement of the C-arm 15 and the movement of the top plate 14. Furthermore, for example, the control function 211 controls the aperture control circuit 20 according to the operator's instructions, adjusting the opening of the aperture blades of the collimator 13, thereby controlling the irradiation range of the X-rays irradiated to the subject P.

[0029] Furthermore, the control function 211 controls the image data generation process by the image data generation circuit 24, the image processing process by the image processing circuit 26, or the analysis process, according to the operator's instructions. The control function 211 also controls the display 23 to display the GUI for receiving operator instructions and images stored in the memory circuit 25. The processing circuit 21 that implements the control function 211 may also be called the control unit.

[0030] As shown in Figure 1, the processing circuit 21 executes a detection function 212, an evaluation function 213, a corrected image generation function 214, and a display control function 215. Details of the processing realized by the detection function 212, the evaluation function 213, the corrected image generation function 214, and the display control function 215 will be described later.

[0031] The image processing circuit 26 and / or image data generation circuit 24 described above are examples of acquisition units that sequentially acquire multiple X-ray images in a time series. The detection function 212 is an example of a detection unit. The evaluation function 213 is an example of an evaluation unit. The corrected image generation function 214 is an example of a corrected image generation unit. The display control function 215 is an example of a display control unit.

[0032] The overall configuration of the X-ray diagnostic apparatus 100 has been described above. With this configuration, the X-ray diagnostic apparatus 100 according to this embodiment makes it possible to select multiple objects included in the X-ray image and improve the visibility of the selected objects. For example, the X-ray diagnostic apparatus 100 according to this embodiment makes it possible to display and fix the selected objects on the X-ray image. Specifically, the X-ray diagnostic apparatus 100 makes it possible to display a moving image in which an object (a therapeutic instrument (device)) corresponding to a selected object candidate selected by the operator appears to be virtually stationary. The object is, for example, an instrument inserted into the subject P. An instrument inserted into the subject P is, for example, a therapeutic device such as a stent, a marker (characteristic object), or a wire. In other words, the object is at least one of the therapeutic device inserted into the subject P and a characteristic object (a marker pair (a pair of markers) described later) attached to the therapeutic device. The therapeutic device may also have multiple characteristic objects.

[0033] For example, when a physician performs an endovascular intervention using a balloon catheter with a stent to a narrowed area in the cardiovascular system of subject P, the physician positions the device by referring to the X-ray image generated and displayed by the X-ray diagnostic device 100. However, as mentioned above, when performing an endovascular intervention on the blood vessels of organs that are constantly beating, such as the heart, or organs that move due to beating, the position of the device on the X-ray image will shift. Therefore, positioning the device by referring to the X-ray image is a highly skilled task for the physician.

[0034] Therefore, the X-ray diagnostic device 100 tracks multiple markers depicted in sequentially generated X-ray images and performs image correction so that the positions of the pair of markers in each X-ray image are the same as in past images, thereby creating a video display in which the device appears virtually stationary. For example, the X-ray tube 12 irradiates the subject P's region of interest (e.g., the heart) with X-rays, and the X-ray detector 16 sequentially detects the X-rays that have passed through the region of interest. Based on the data continuously detected by the X-ray detector 16, the X-ray diagnostic device 100 performs image processing so that the devices included in the X-ray images generated sequentially in a time series appear virtually stationary, and displays them as a video in real time.

[0035] As a result, the X-ray diagnostic device 100 can display X-ray images that improve the visibility of devices displayed during intravascular interventional treatment, which is performed by referring to X-ray images, and facilitate the positioning of devices. However, with the above-described technology, image processing was applied so that the device desired by the user would appear virtually stationary, making real-time video display impossible.

[0036] Therefore, the X-ray diagnostic apparatus 100 according to the present invention, using a processing circuit 21 described in detail below, performs image processing on a pair of markers—one selected by the user from among multiple point markers and another marker linked to that marker—so that the device appears virtually stationary, thereby enabling real-time video display. As a result, the X-ray diagnostic apparatus 100 according to the present invention makes it possible to select multiple objects included in the X-ray image and improves the visibility of the selected objects.

[0037] The following describes the process for displaying a moving image in which the device appears virtually stationary. This process involves, for example, performing image processing on the collected X-ray image to detect multiple candidate markers. Next, the process identifies multiple pairs of markers (multiple pairs of markers) from among the multiple candidate markers and tracks the identified pairs over multiple frames. This selects the most plausible pair of stent markers. Subsequently, the process calculates a shift amount so that the selected pair of markers is displayed in the center of the screen, and displays the image with the stent markers at the center.

[0038] The description will focus on the case where the processing circuit 21 performs various functions to control the image processing circuit 26, but the processing circuit 21 may also perform the same processing as the image processing circuit 26.

[0039] Specifically, when displaying a moving image in which the device appears virtually stationary, the detection function 212 controls the image processing circuit 26 to identify multiple candidate objects, which are candidates for multiple objects related to the medical device inserted into the body of the subject P, using a group of image data sequentially generated by the image data generation circuit 24 over a predetermined period. Based on the identification results, the detection function 212 detects the positions of the multiple candidate objects in the newly generated X-ray image. In other words, the detection function 212 controls the image processing circuit 26 to detect multiple objects included in the X-ray image generated from the image data. Here, the predetermined period for object detection and the predetermined objects to be detected only need to be determined by the time the detection process starts, for example, before the generation of the image data group, during the generation of the image data group, or after the generation of the image data group.

[0040] For example, the detection function 212 detects the coordinates of the stent marker attached to the stent in the new image each time a new X-ray image is stored. That is, the detection function 212 detects the coordinates of the stent marker in the sequentially generated X-ray images based on information about the stent marker depicted in the image. To give one example, the detection function 212 detects the coordinates of the stent marker in the sequentially generated X-ray images based on information about the stent marker specified by the operator, or on a training image of the stent marker.

[0041] Specifically, the detection function 212 generates frequency images containing predetermined frequency components from sequentially generated X-ray images and detects the coordinates of multiple target object candidates contained in the generated frequency images. Specifically, the detection function 212 generates high-frequency images containing high-frequency components from sequentially generated X-ray images and detects the coordinates of stent markers in the generated high-frequency images. That is, the predetermined frequency components are frequency components that include components corresponding to multiple objects, and the detection function 212 generates a frequency image in which the predetermined object is emphasized and detects the coordinates of the predetermined object. Here, the predetermined frequency components in the frequency images only need to be determined by the time the detection process starts, for example, before the generation of the image data group, during the generation of the image data group, or after the generation of the image data group.

[0042] Furthermore, the detection function 212 generates low-frequency images of the X-ray images by performing a smoothing process on the X-ray images. The detection function 212 then detects the coordinates of the stent markers in the generated high-frequency images. For example, the detection function 212 generates a high-frequency image for each X-ray image by performing the above-described process on each sequentially generated X-ray image, and then detects the coordinates of the stent markers contained in each of the generated high-frequency images.

[0043] Specifically, the detection function 212 generates a high-frequency image by subtracting a low-frequency image from the X-ray image to remove the low-frequency component. Next, the detection function 212 performs binarization on the high-frequency image. Subsequently, the detection function 212 detects the coordinates of multiple candidate objects by removing wireframe images (large connected regions). At this time, the detection function 212 calculates the reliability of the multiple candidate objects based on the templates of the multiple candidate objects and the pixel values ​​at the coordinates of the multiple candidate objects. Specifically, the detection function 212 calculates the marker-likeness corresponding to the reliability of the multiple candidate objects based on the marker templates and the pixel values ​​of the multiple markers. The calculation of marker-likeness can be achieved using known methods, so the explanation is omitted.

[0044] At this time, the detection function 212 compares the threshold value stored in the memory circuit 25 with the marker likelihood and identifies (selects) the coordinates of markers whose likelihood exceeds the threshold value. The threshold value is set in advance and stored in the memory circuit 25. Note that the calculation of marker likelihood may be performed by the evaluation function 213. The selected coordinates correspond to marker likelihood that exceeds the threshold value. The coordinates identified (selected) by the detection function 212 correspond to the coordinates of multiple target object candidates.

[0045] The detection function 212 selects, for example, pairs of candidates (multiple target object candidates) that fall within a predetermined range of stent length. Then, using the center coordinates of the selected pairs, the detection function 212 tracks the pairs between time-series adjacent X-ray images (between adjacent frames) in multiple X-ray images. Note that the generation of high-frequency images is not limited to the example described above, and may be performed by any method, such as processing using a bandpass filter.

[0046] The following describes the process for displaying a video where the device appears virtually stationary, using the detection of the coordinates of two stent markers as an example. Note that the following also describes the processing after the high-frequency image has been generated.

[0047] Figure 2 is a diagram illustrating the processing by the detection function 212 according to the embodiment. For example, the display control function 215, which will be described later, controls the display 23 to display the X-ray image (first frame) that was initially generated and stored in the memory circuit 25, as shown in Figure 2(A). The operator (such as a doctor) who has referenced the first frame specifies the two stent markers in the first frame via the input circuit 22, as shown in Figure 2(A). As a result, the detection function 212 recognizes the display pattern of the stent markers in the X-ray image (such as the shape of the stent markers and brightness information) and detects the coordinates of each of the two stent markers in the first frame.

[0048] Subsequently, as shown in Figure 2(A), the detection function 212 sets a rectangle centered on the coordinates of each of the two stent markers specified in the first frame as an ROI (Region of Interest). Then, the detection function 212 extracts patterns similar to the pattern within the set ROI for each newly generated image, for example, using the cross-correlation method, and detects the coordinates with the highest cross-correlation value as the coordinates of the stent markers.

[0049] In Figure 2(A), the case in which two stent markers are specified by the operator is described, but this embodiment is not limited to this, and the case in which only one stent marker is specified by the operator is also possible. In this case, the detection function 212 also performs a cross-correlation method using the ROI set from the coordinates of the specified stent marker in the first frame to detect the coordinates of the other stent marker in the first frame.

[0050] Alternatively, the detection function 212 detects the coordinates of a stent marker using a training image that shows the shape and brightness characteristics of a stent marker attached to a stent actually used in treatment, as seen in an X-ray image. For example, as shown in Figure 2(B), an X-ray image of a stent marker is stored separately as a training image, and the detection function 212 extracts a pattern similar to the training image for each new image, searches for the region with the highest similarity from the extracted candidate regions of the stent marker, and detects the coordinates of the stent marker.

[0051] Here, when the detection function 212 detects the coordinates of the stent marker from sequentially generated X-ray images, it first identifies (specifies) the stent marker using multiple X-ray images. That is, the detection function 212 uses a group of sequentially generated X-ray images to identify multiple objects that are inserted into the body of the subject P and depicted in the X-ray images, and detects the coordinates of the multiple objects included in the newly generated X-ray images based on the identification results. For example, the detection function 212 uses a stent marker specified by the operator or a stent marker based on a training image to extract all regions similar to the stent marker for each of the multiple X-ray images over a predetermined period. Then, the detection function 212 comprehensively extracts the region that is most likely to be a stent marker from the regions extracted in each of the multiple X-ray images as the stent marker.

[0052] Hereinafter, the process of detecting and identifying (specifying) stent markers as described above will be referred to as "Learning mode". The detection function 212, for example, in the case of stent marker detection in Learning mode, detects multiple candidate objects, each of which is a candidate object included in multiple acquired X-ray images.

[0053] Figure 3 is a diagram illustrating an example of a Learning mode according to the embodiment. Figure 3 shows a Learning mode using n frames of X-ray images generated by the image processing circuit 26. For example, the detection function 212 extracts all regions (coordinates) similar to the stent marker in the entire area of ​​the first frame shown in Figure 3.

[0054] The processing circuit 21 calculates evaluation values ​​for multiple target candidates based on multiple X-ray images using the evaluation function 213. For example, the evaluation function 213 forms pairs using all extracted coordinates and calculates evaluation points for each pair based on similarity, distance between the two coordinates, etc. The evaluation function 213 calculates and assigns evaluation points to the pair of coordinates 51 and 52. Although only coordinates 51 and 52 are shown in Figure 3, if the stent marker contains similar regions (coordinates), those coordinates are also detected, and pairs are formed with coordinates 51, 52, or other coordinates, and evaluation points are calculated.

[0055] For example, the evaluation function 213 uses evaluation points to select a pair of candidate markers that fall within the range of the stent length from among 10 combinations of marker candidates that exceed a threshold for marker likelihood. The evaluation function 213 uses the center coordinates (gx, gy) of the selected pair to track the selected pair between frames. The evaluation function 213 creates multiple candidate pairs (multiple target object candidates) from multiple candidate marker points in 100 frames (100 X-ray images that are consecutive in time series). The candidate pairs consist of, for example, 40 frames. The evaluation function 213 tracks the multiple pairs (multiple target object candidates) over multiple frames in a time series, generates a time-series trajectory (Track) of the pairs, and extends it over multiple frames. The evaluation function 213 calculates an evaluation value for the extended trajectory for each of the multiple pairs.

[0056] The evaluation function 213 calculates an evaluation value using, for example, the distance between the end of a pair connected across multiple frames in the trajectory and a newly connected pair, the number of frames skipped during the connection of pairs related to trajectory generation, and the frame number from which trajectory generation began. In other words, the evaluation function 213 calculates an evaluation value using at least one of the following: the frequency of detection of multiple object candidates in multiple X-ray images and the time-series continuity of detection of multiple object candidates.

[0057] Figure 4 shows an example of tracking multiple target candidates across multiple frames. The circles in Figure 4 correspond to the center coordinates of the selected multiple target candidates. The straight lines connecting the circles between frames indicate the trajectory created by tracking the pairs. As shown in Figure 4, the evaluation function 213 tracks the pairs and generates and extends the trajectory. At this time, the evaluation function 213 calculates an evaluation value for the trajectory such that there are no interruptions in the trajectory between frames and the longer the trajectory is connected, the larger the evaluation value becomes.

[0058] Based on the above, the evaluation function 213 calculates evaluation values ​​for each of the multiple target object candidates based on multiple X-ray images. Note that trajectory tracking and evaluation value calculation are performed not only in Learning Mode, but also during the acquisition of X-ray images from subject P by fluoroscopy, etc. (Tracking Mode, described later).

[0059] For example, since the beating of the heart and the expansion and contraction of the lungs are regular (periodic), stent markers that move in conjunction with them will also exhibit regular (periodic) movements. In the Learning mode described above, stent markers that move regularly (periodicly) are comprehensively detected using X-ray images over a predetermined period, and the one that looks most like a stent marker is identified as a stent marker.

[0060] As described above, the detection function 212 first identifies (specifies) stent markers in the X-ray image using Learning mode and extracts the region that includes the coordinates the stent markers can take. The detection function 212 can improve detection accuracy by detecting stent markers mainly in the extracted region.

[0061] The processing circuit 21, using the correction image generation function 214, uses the position of the object corresponding to the selected object candidate as the reference position in the reference image among the multiple X-ray images, and applies a correction process to the multiple X-ray images to align the position of the object corresponding to the selected object candidate with the reference position. This correction process ensures that, for example, the position of the object and the reference position coincide in the corrected images. For example, the correction process aligns the position of the object corresponding to the selected object candidate with the reference position. The reference image is, for example, the image in which the most object candidates were detected in Learning mode, or the LIH (Last Image Hold) image.

[0062] For example, the corrected image generation function 214 controls the image processing circuit 26 to use the coordinates of the stent markers already detected by the detection function 212 as reference coordinates, and generates a corrected image by performing image transformation processing such as affine transformation on the new image so that the coordinates of the stent markers detected by the detection function 212 in the new image are aligned with the reference coordinates. Here, image transformation processing includes processing that does not include image stretching, and includes processing consisting only of image movement processing such as translation and rotation.

[0063] Figure 5 is a diagram illustrating the processing performed by the corrected image generation function 214. In Figure 5, the processing is shown for a new image in which the coordinates of the stent marker have been detected based on the results of the Learning mode processing, after the Learning mode processing by the detection function 212 has finished. In other words, the first frame shown in Figure 5 is the first X-ray image generated after the Learning mode has finished.

[0064] For example, the detection function 212 first performs Learning mode processing using 40 frames of images, and then, for the first and second frames generated after the completion of Learning mode, it detects the coordinates of the stent marker using the results of the Learning mode processing, as shown in Figure 5(A). For example, the detection function 212 extracts regions similar to the stent marker, centering on the region extracted by Learning mode, and detects the region that is most likely to be a stent marker as the stent marker.

[0065] When the coordinates of the stent marker are detected by the detection function 212, the correction image generation function 214 generates a correction image 2 from the second frame by image deformation, as shown in Figure 5(A), so that the coordinates of the stent marker detected in the second frame X-ray image, which is generated as a new image, are aligned with the coordinates (reference position) of the stent marker already detected in the first frame.

[0066] The correction image generation function 214 then generates a correction image for new images from the third frame onward, using the coordinates of the stent marker in the correction image it generated from the X-ray image generated immediately before the new image as the reference coordinates. For example, as shown in Figure 5(B), the correction image generation function 214 generates a correction image 3 from the third frame by image deformation so that the coordinates of the stent marker detected in the third frame are aligned with the coordinates of the stent marker in the correction image 2 generated from the second frame.

[0067] In this embodiment, the case in which the coordinates of the stent marker in the corrected image generated from the frame immediately preceding the new image are used as the reference coordinates has been described. However, the embodiment is not limited to this, and the coordinates of the stent marker detected in the first frame may be aligned with the reference coordinates, and the corrected image may be generated from the new image from the second frame onward. However, as will be described later, the corrected image is used to generate a display image used when displaying a video, so the corrected image may also be generated from the new image using the previous corrected image.

[0068] As described above, the correction image generation function 214 generates a correction image in which the coordinates of the stent markers detected by the detection function 212 are aligned between images. In other words, the correction image generation function 214 identifies the stent markers in Learning mode and uses the processing results of Learning mode to generate a correction image in which the coordinates of the stent markers detected from subsequent X-ray images are aligned between images. Hereinafter, the correction image generation process described above will be referred to as "Tracking mode".

[0069] Figure 6 is a diagram illustrating an example of the Tracking mode according to the embodiment. For example, in Tracking mode, as shown in Figure 6, a corrected image is generated in which the coordinates of the stent marker detected are aligned with the region extracted by Learning mode. That is, the corrected image generation function 214 generates a corrected image targeting the X-ray image in which the detection function 212 detected the stent marker after Learning mode.

[0070] The display control function 215 causes the corrected images generated by the corrected image generation function 214 to be displayed as a video on the display 23. Specifically, the display control function 215 controls the system so that each newly generated corrected image is displayed sequentially on the display 23 as a display image. In other words, the display control function 215 controls the system so that the display image, with the coordinates of the stent marker aligned, is displayed as a video. This allows for the display of an X-ray image as a video, for example, where the background area other than the stent appears blurred, but the stent itself remains still.

[0071] Here, the display control function 215 controls the image processing circuit 26 to perform various filtering processes on the corrected image and then displays the resulting image as a video. For example, the display control function 215 controls the image processing circuit 26 to perform high-frequency noise reduction filtering using a recursive filter on the corrected image and generate a display image. A recursive filter is a filter that reduces high-frequency noise by adding the pixel values ​​of pixels in past frames, which are weighted according to a predetermined weight, to the pixel values ​​of pixels in the frame being processed.

[0072] In the corrected image, since the coordinates of the stent markers are aligned, it is possible to reduce high-frequency noise in the stent portion and improve the visibility of the stent in the corrected image by using a recursive filter that uses past frames. Here, the predetermined weighting in the recursive filter only needs to be determined at the time the filtering process is performed, and can be determined before, during, or after the generation of the corrected image.

[0073] In other words, the display control function 215 sequentially applies a recursive filter using past corrected images to the sequentially generated corrected images, thereby generating a display image with improved visibility for the device and displaying it as a video. The display control function 215 can also generate a display image by simply adding the sequentially generated corrected images together.

[0074] The above describes the processing involved in displaying a video in which a device appears virtually stationary. The X-ray diagnostic apparatus 100 improves the image quality when displaying a video in which the device appears virtually stationary. As described above, when displaying a video in which a device is virtually stationary, the apparatus detects feature points (such as stent markers) of the device included in the X-ray image and virtually stops the movement of the device by roughly aligning the positions of the detected feature points.

[0075] In the above explanation, the set of markers located in the center of the X-ray image is the two points that were ultimately selected. When multiple markers exist in the X-ray image, the marker desired by the user may not be selected. Also, in the above explanation, a marker other than the one the user wants to see may be displayed in the center of the X-ray image, and the position of the device the user actually wants to see may move due to pulsation or other factors.

[0076] This is because improved marker detection accuracy has made it easier to detect multiple markers, leading to a higher likelihood of cases where multiple marker pairs with high evaluation values ​​exist. For example, balloons may be used interchangeably during treatment or used in conjunction with stents. Different balloons are used depending on the procedure, and for example, multiple balloons may be used interchangeably, resulting in multiple balloons being present in the blood vessel.

[0077] Figure 7 shows an example in which two balloons are used as multiple targets. The circles in Figure 7 are markers. In the blood vessel BV shown in Figure 7, blood flow is from left to right. As shown in Figure 7, plaque PL is formed before and after the bifurcation of blood vessel BV. Before the first balloon BAL1 expands the plaque PL, the second balloon BAL2 is positioned downstream of the bifurcation of blood vessel BV and expanded to prevent a portion of the plaque PL (thrombus) from flowing downstream of the bifurcation. Next, the first balloon BAL1 expands the plaque PL. Subsequently, the first balloon BAL1 and the second balloon BAL2 are positioned near the plaque PL located in the larger blood vessel upstream of the bifurcation.

[0078] In the case shown in Figure 7, when the second balloon BAL2 is positioned downstream of the bifurcation of blood vessel BV, the user desires that the second balloon BAL2 be displayed in the center of the X-ray image as the object. Furthermore, after the second balloon BAL2 has been expanded, when the first balloon BAL1 is positioned at the location of the plaque PL, the user desires that the first balloon BAL1 be displayed in the center of the X-ray image as the object. Moreover, when the first balloon BAL1 and the second balloon BAL2 are positioned near the plaque PL located in a large blood vessel upstream of the bifurcation, the user desires that the first balloon BAL1 be displayed in the center of the X-ray image as the object during its movement, and that the second balloon BAL2 be displayed in the center of the X-ray image as the object during its movement. Thus, as shown in Figure 7, the user may desire to change the object of focus during the procedure.

[0079] In the above description, when a marker is detected and a trajectory (Track) is generated, other trajectories (devices) that were not selected as display targets to be virtually fixed are not selectable by the user. Therefore, in this embodiment, from among the multiple detected markers (multiple target object candidates), pairs of markers other than the trajectory with the highest evaluation value are stored in the memory circuit 25, and selectable marker pairs are selected from the other stored pairs of markers, providing an operation that allows the user to arbitrarily select a marker pair.

[0080] Specifically, marker pairs (multiple target candidates) that exceed a threshold for marker likelihood are stored in the memory circuit 25 as a track list, along with their marker likelihood values, evaluation values, coordinates, etc. At this time, the target candidate with the highest evaluation value in the track list is flagged. In addition, multiple target candidates in the track list are each assigned an identifier that identifies them. This identifier can be arbitrarily set as a name, number, abbreviation, etc., by user instruction via the input circuit 22.

[0081] Figure 8 shows an example of a trajectory list TL. The trajectory list TL is generated, for example, by the evaluation function 213 upon completion of the Learning mode and stored in the memory circuit 25. As shown in Figure 8, the trajectory list TL shows multiple target candidates sorted in order of evaluation value.

[0082] The processing circuit 21, using the display control function 215, arranges the trajectory evaluation values ​​based on the display and displays them on the display 23. This allows the user to easily change the marker to be displayed in the center of the X-ray image by selecting the desired target object candidate via the input circuit 22, for example, when the device to be viewed changes during the procedure, or when the balloon is moved and used differently during the procedure, as shown in Figure 7. The operation of selecting a target object candidate can be performed, for example, on the fluoroscopic image, the captured image, the LIH display, the operation screen in Tracking mode, the acquired video image on the tablet, and on still images.

[0083] Figure 9 shows an example of a marker selection screen SI corresponding to a candidate object. The marker selection screen SI has an X-ray image 91 and a list of markers (list display of markers) 93. For example, a reference image is used as the X-ray image 91 in the marker selection screen SI. As shown in Figure 9, the selected marker pair SMP is displayed on the display 23 with a highlight. This highlight can be, for example, a line type such as a solid or dotted line, a hue such as a dark or light color, a change in size, or a border.

[0084] In other words, the display 23 highlights the selected object candidate from among multiple object candidates. Also, as shown in Figure 9, selectable marker pairs are displayed in order of evaluation value in the marker list 93 on the selection screen SI. At this time, the object to be selected is moved by operating the button (toggle TG) in the marker list 93, and the object is confirmed. Furthermore, when the mouse MS touches a marker (object candidate) in the marker list 93, the display control function 215 highlights the marker that the mouse MS touched, either by making it larger or by blinking.

[0085] Figure 10 shows an example of a selection screen SI displayed on a tablet. The marker selection screen SI includes an X-ray image 101 and a marker list 103. As shown in Figure 10, when the marker selection mode is turned ON in the marker list 103, the display control function 215 displays the currently selected pair and the candidate pairs that can be selected in color. That is, as shown in Figure 10, the currently selected marker pair (target candidate) SMP and the selectable marker pairs are displayed in highlight.

[0086] The display mode in Figure 10 is the same as in Figure 9. In Figure 10, when the vicinity of a marker pair is touched or operated with a mouse, the display control function 215 highlights the marker pair NMP in the vicinity of that operation. Also, as shown in Figure 10, the marker list 103 displays a list of target object candidates in order of evaluation value, and toggle selection is possible using the button TG. In this case, the display mode of the target object candidates in toggle selection is linked to the selection state in the X-ray image 101 and the marker list 103.

[0087] Figure 11 shows an example of another selection screen OSI. The other selection screen OSI has an X-ray image 111 showing the areas of the marker and the treatment device (stent in Figure 11). As shown in Figure 11, the surrounding areas of multiple target candidate objects are highlighted with closed curves, rectangles, etc., using line types, hues, etc., according to the evaluation value. At this time, as shown in Figure 11, an identifier that identifies the marker pair may be displayed near the surrounding area. A target candidate object is selected by selecting the surrounding area. The display control function 215 may display the surrounding area when the evaluation value and / or the marker-likeness value is small. Also, as shown in Figure 11, the display 23 may display identifiers (names, numbers, etc.) that can identify multiple target candidate objects.

[0088] Note that the set of multiple object candidates, i.e., marker candidates, displayed on the selection screen SI and other selection screens OSI, is not limited to two points. For example, if there are three or more marker candidates, the center point of all markers will be tracked. Specifically, for example, in the case of a device such as a stent or balloon with four markers, the detection function 212 calculates the center point (centroid, etc.) of the coordinates of the four markers and uses that center point to track the device.

[0089] Furthermore, if a long, continuous trajectory is not present in the latest frame (LIH image), the display control function 215 may display multiple candidate objects appearing in frames preceding the LIH image frame in the LIH image on the selection screen SI and other selection screens OSI. In addition, to search for the preceding frame, the display control function 215 may, for example, use an X-ray image corresponding to the end of diastole acquired with electrocardiogram synchronization.

[0090] For example, if the timing of selecting a marker corresponding to a candidate object is during the LIH image, the Tracking mode is immediately reflected in the next fluoroscopy. That is, as shown in Figure 10, without any operation to turn on the marker selection mode, the Tracking mode is implemented for the selected marker according to the marker selection. It should be noted that candidate objects can be received even during fluoroscopy or imaging. In this case, markers located anywhere other than the center of the X-ray image are likely to be moving due to the pulsation of the subject P, but as shown in Figures 9 and 10, marker selection is possible by operating the toggle TG.

[0091] The configuration of the X-ray diagnostic apparatus 100 according to this embodiment has been described above. Below, the process of selecting one target candidate from a plurality of target candidate and executing the Tracking mode (hereinafter referred to as the target selection tracking process) will be explained with reference to Figure 12.

[0092] Figure 12 is a flowchart illustrating an example of the object selection tracking process flow. It is assumed that the Learning mode is performed prior to the object selection tracking process. Furthermore, it is assumed that multiple object candidates have a reliability (marker-likeness) that exceeds a threshold and are stored in the memory circuit 25 as a list of trajectories TL, as shown in Figure 8. The list of trajectories TL, as shown in Figure 8, is an arrangement of multiple trajectories with evaluation values ​​above a certain value, sorted by evaluation value.

[0093] (Object selection tracking process) (Step S1) An operation to turn on the marker selection mode is input via the input circuit 22. In response to this operation, the display control function 215 displays evaluation values ​​on the display 23 in association with multiple target candidate objects in the marker lists 93 and 103, as shown in Figure 9 or Figure 10. For example, the display control function 215 displays the selection screen SI on the display 23. As a result, the display 23 displays evaluation values ​​in association with multiple target candidate objects in the marker lists 93 and 103, as shown in Figure 9. At this time, the display 23 further displays multiple target candidate objects in the reference images (X-ray images 91 and 101). Note that the display 23 may also display multiple target candidate objects in a list in the marker lists 93 and 103, as shown in Figures 9 and 10. Furthermore, the display 23 may further display multiple identifiers that can identify multiple target candidate objects in the X-ray image 111, as shown in Figure 11.

[0094] (Step S2) The input circuit 22 accepts the selection of at least one object candidate from among several object candidates through user operation. That is, the input circuit 22 accepts the selection of at least one object candidate from among several object candidates. For example, the input circuit 22 accepts the selection of at least one object candidate from among the several object candidates displayed on the reference image. At this time, the display 23 highlights the selected object candidate from among the multiple object candidates.

[0095] Furthermore, the input circuit 22 may accept the selection of at least one of multiple target candidates in response to the operation of the toggle button TG, which indicates the selection of multiple target candidates in the list displayed on the selection screen SI. Also, as shown in Figure 11, if multiple identifiers that can identify multiple target candidates are displayed in the X-ray image 111, the input circuit 22 may accept the selection of at least one of the multiple identifiers. In addition, as shown in Figure 11, if the selection of a target candidate is accepted for another selection screen OSI, the processing in step S1 is unnecessary.

[0096] (Step S3) The processing circuit 21, using the evaluation function 213, assigns a flag to the selected target candidate or increases its evaluation value. For example, the evaluation function 213 assigns a flag to the selected target candidate in the trajectory list TL. Specifically, the evaluation function 213 changes the "selected flag" for the selected target candidate in the trajectory list TL from 0 to 1. Subsequently, the evaluation function 213 updates the trajectory list TL and stores it in the memory circuit 25.

[0097] Alternatively, the evaluation function 213 recalculates the evaluation value of the selected object candidate. The evaluation function 213 recalculates the evaluation value of the selected object candidate using, for example, neighboring values ​​from the object candidate with the highest evaluation value, and / or the marker-likeness (Trustness) used when selecting marker candidate points in the final (latest) frame (e.g., LIH image). At this time, it is also possible to temporarily add (boost) the evaluation value to continue tracking the trajectory with a higher evaluation than the object candidate with the highest evaluation value. The evaluation function 213 changes the evaluation value before recalculation to the recalculated evaluation value in the trajectory list TL. Subsequently, the evaluation function 213 updates the trajectory list TL and stores it in the memory circuit 25.

[0098] When using the nearest values ​​from the object candidate with the highest evaluation value, the evaluation function 213 recalculates the evaluation value using, for example, the following formula (1). Re-evaluation value = Evaluation value + α × (1 - (Distance to the object candidate with the highest evaluation value / Maximum distance on screen)) ... (1) The constant α in equation (1) is a weighting and can be adjusted as appropriate (variable) according to the situation, such as image quality.

[0099] When assigning marker characteristics, the evaluation function 213 recalculates the evaluation value using, for example, the following formula (2). Re-evaluation value = Evaluation value + β × Marker-likeness in the final frame (LIH image) ... (2) The constant β in equation (2) is a weighting and can be adjusted as appropriate (variable) according to the situation, such as image quality.

[0100] If the evaluation value of the selected target candidate is to be increased, the evaluation function 213 recalculates the evaluation value using, for example, the following formula (3). Re-evaluation value = Evaluation value + Baseline increase value ... (3) In equation (3), the boost value is set to a value greater than (maximum evaluation value - minimum evaluation value) on the trajectory list TL. Also, if the evaluation value has been recalculated, the boost value in equation (3) is set to a value greater than (maximum re-evaluation value - minimum re-evaluation value).

[0101] (Step S4) If there are any previously selected object candidates (Yes in step S4), that is, if there are any previously selected object candidates in the trajectory list TL, the process in step S5 is executed. If there are no previously selected object candidates (No in step S4), that is, if there are no previously selected object candidates in the trajectory list TL, the process in step S6 is executed.

[0102] (Step S5) The processing circuit 21, using the evaluation function 213, removes the flag of a previously selected target candidate or the boost for a previously selected target candidate. Specifically, the evaluation function 213 changes the "selected flag" of a previously selected target candidate in the trajectory list TL from 1 to 0. The previously selected target candidate is a different target candidate from the one selected in step S2. The evaluation function 213 changes the evaluation value of a previously selected target candidate in the trajectory list TL to the evaluation value before the boost. Subsequently, the evaluation function 213 updates the trajectory list TL and stores it in the memory circuit 25.

[0103] (Step S6) The processing circuit 21 uses the evaluation function 213 to identify selected target candidates from the updated trajectory list using a flag or an enhanced evaluation value. When using a flag, the evaluation function 213 identifies target candidates in the updated trajectory list whose selected flag is "1". When using an enhanced evaluation value, the evaluation function 213 identifies the target candidate with the highest evaluation value in the updated trajectory list.

[0104] (Step S7) The processing circuit 21 performs correction processing on the X-ray image using the center coordinates of the identified target candidate, via the correction image generation function 214. This generates a corrected image. For example, when fluoroscopy is performed on subject P, multiple corrected images are generated until the operation is completed.

[0105] (Step S8) The processing circuit 21, using the display control function 215, causes the generated corrected image to be displayed on the display 23. As a result, the display 23 displays the corrected image.

[0106] (Step S9) If the selection mode is turned ON by the user's instruction to the input circuit 22 (Yes in step S9), the process from step S1 onwards is repeated. If the selection mode is not turned ON (No in step S9), the object selection tracking process ends. If, for example, a candidate for the target part is selected by operating the toggle TG without activating the selection mode, the process from step S3 onwards is repeated.

[0107] The X-ray diagnostic apparatus 100 according to the embodiment described above sequentially acquires a plurality of X-ray images in a time series, detects a plurality of object candidates which are multiple object candidates included in the acquired plurality of X-ray images, calculates an evaluation value for each of the plurality of object candidates based on the plurality of X-ray images, displays the calculated evaluation value in association with the plurality of object candidates, accepts the selection of at least one of the plurality of object candidates, uses the position of the object corresponding to the selected object candidate in the reference image among the plurality of X-ray images as the reference position, and generates a plurality of corrected images by applying a correction process to the plurality of X-ray images to align the position of the object corresponding to the selected object candidate with the reference position. As a result, the X-ray diagnostic apparatus 100 according to the embodiment can virtually fix and display the selected object candidate at the center of the X-ray image according to the user's wishes. For this reason, the X-ray diagnostic apparatus 100 according to the embodiment can improve the visibility of the selected object in the X-ray image.

[0108] Furthermore, the X-ray diagnostic apparatus 100 according to the embodiment calculates the evaluation value using at least one of the frequency of detection of multiple target object candidates in multiple X-ray images and the time-series continuity of said detection. As a result, the X-ray diagnostic apparatus 100 according to the embodiment can efficiently evaluate multiple target object candidates desired by the user.

[0109] Furthermore, in the X-ray diagnostic apparatus 100 according to the embodiment, the object is at least one of a treatment device inserted into the subject P and a characteristic object attached to the treatment device. Also, in the X-ray diagnostic apparatus 100 according to the embodiment, the treatment device comprises a plurality of characteristic objects. As a result, the X-ray diagnostic apparatus 100 according to the embodiment can virtually fix and display a treatment device or a characteristic object attached to the treatment device selected according to the user's wishes at the center of the X-ray image, thereby improving the visibility of the selected treatment device or the characteristic object attached to the treatment device in the X-ray image.

[0110] Furthermore, the X-ray diagnostic apparatus 100 according to this embodiment highlights the selected target object candidate from among the multiple target object candidates. As a result, with the X-ray diagnostic apparatus 100 according to this embodiment, the user can easily identify the target object candidate that they have selected.

[0111] Furthermore, the X-ray diagnostic apparatus 100 according to this embodiment displays a plurality of target object candidates in the reference image and accepts the selection of at least one of the plurality of target object candidates displayed in the reference image. As a result, according to the X-ray diagnostic apparatus 100 according to this embodiment, the user can easily select a desired target object candidate from the plurality of target object candidates.

[0112] Furthermore, the X-ray diagnostic apparatus 100 according to this embodiment displays a list of multiple target object candidates and accepts the selection of at least one of the multiple target object candidates in response to the operation of a toggle button TG indicating the selection of multiple target object candidates in the list. Thus, according to the X-ray diagnostic apparatus 100 according to this embodiment, a desired target object candidate can be selected at any time by operating the toggle button TG.

[0113] Furthermore, the X-ray diagnostic apparatus 100 according to the embodiment displays a plurality of identifiers capable of identifying a plurality of target object candidates, and accepts the selection of at least one of the plurality of identifiers. Thus, according to the X-ray diagnostic apparatus 100 according to the embodiment, a desired target object candidate can be selected by selecting a preset identifier.

[0114] Based on these considerations, the X-ray diagnostic device 100 according to this embodiment allows the user to select the desired marker position according to the treatment process and procedure, for example, when performing treatment using multiple balloons or stents in the cardiovascular field. Therefore, the X-ray diagnostic device 100 according to this embodiment can improve the effect of displaying a device selected by the user virtually fixed at the center of the image. Furthermore, with the X-ray diagnostic device 100 according to this embodiment, even if the marker of the object to be displayed and fixed moves out of the imaging field, it becomes possible to select another marker pair around that object, and by continuously performing the Tracking mode, the risk of interrupting the procedure can be reduced.

[0115] When the technical concept of this embodiment is realized in a medical image processing device, the medical image processing device comprises: an acquisition unit that sequentially acquires a plurality of X-ray images in a time series; a detection unit that detects a plurality of object candidates, which are candidates for a plurality of objects included in the acquired plurality of X-ray images; an evaluation unit that calculates an evaluation value for each of the plurality of object candidates based on the plurality of X-ray images; a display unit that displays the evaluation value in association with the plurality of object candidates; a reception unit that accepts the selection of at least one of the plurality of object candidates; and a corrected image generation unit that generates a plurality of corrected images by applying a correction process to the plurality of X-ray images to align the position of the object corresponding to the selected object candidate with the reference position, using the position of the object detected in the reference image among the plurality of X-ray images as the reference position.

[0116] Medical image processing devices can be implemented on various servers or network-based information processing devices. Furthermore, medical image processing devices may be mounted on X-ray diagnostic equipment. The acquisition unit in the medical image processing device is mounted on a processing circuit as an acquisition function. In this case, the acquisition function sequentially acquires multiple X-ray images from the X-ray diagnostic equipment in a time-series manner. The acquisition function stores the sequentially acquired X-ray images in a memory circuit. The hardware configuration, functions, and processing details of the detection unit, evaluation unit, display unit, reception unit, and corrected image generation unit in the medical image processing device are the same as those in the embodiment, and therefore their description is omitted. Also, the procedure and effects of the object selection tracking process implemented by the medical image processing device are the same as those in the embodiment, and therefore their description is omitted.

[0117] When the technical concept of this embodiment is realized by a medical image processing method, the medical image processing method sequentially acquires multiple X-ray images in a time series, detects multiple object candidates which are multiple object candidates included in the acquired multiple X-ray images, calculates an evaluation value for each of the multiple object candidates based on the multiple X-ray images, displays the evaluation value in association with the multiple object candidates, accepts the selection of at least one of the multiple object candidates, uses the position of the object corresponding to the object candidate detected in the reference image among the multiple X-ray images as the reference position, and generates multiple corrected images by applying a correction process to the multiple X-ray images to align the position of the object corresponding to the selected object candidate with the reference position. The procedure and effects of the object selection tracking process realized by the medical image processing method are the same as in the embodiment, so a description is omitted.

[0118] When the technical concept in the embodiment is realized in a medical image processing program, the medical image processing program enables the computer to sequentially acquire multiple X-ray images in a time series, detect multiple object candidates which are multiple object candidates included in the acquired multiple X-ray images, calculate an evaluation value for each of the multiple object candidates based on the multiple X-ray images, display the evaluation value in association with the multiple object candidates, accept the selection of at least one of the multiple object candidates, use the position of the object detected in the reference image among the multiple X-ray images and corresponding to the selected object candidate as the reference position, and generate multiple corrected images by applying a correction process to the multiple X-ray images to align the position of the object corresponding to the selected object candidate with the reference position.

[0119] For example, object selection tracking can be implemented by installing a medical image processing program on a computer and loading the medical image processing program into memory. In this case, the program that allows the computer to execute the object selection tracking process can also be stored and distributed on storage media such as magnetic disks (hard disks, etc.), optical disks (CD-ROMs, DVDs, etc.), and semiconductor memory. Furthermore, the distribution of the medical image processing program is not limited to the above media, and may also be distributed using telecommunications functions, such as downloading via the internet. The procedure and effects of the object selection tracking process implemented by the medical image processing program are the same as in the embodiment, so a description will be omitted.

[0120] According to the embodiments described above, the visibility of the selected object in the X-ray image can be improved.

[0121] While embodiments have been described, these embodiments are presented as examples only and are not intended to limit the scope of the invention. These embodiments can be implemented in various other forms, and various omissions, substitutions, modifications, and combinations of embodiments can be made without departing from the spirit of the invention. These embodiments and their variations are included in the scope and spirit of the invention, as well as in the claims and their equivalents. [Explanation of Symbols]

[0122] 11. High-voltage generator 12 X-ray tube 13 Collimator 14 Top plate 15 C-arm 16 X-ray detectors 17 C-arm rotation and movement mechanism 18. Tabletop moving mechanism 19 C-arm / top plate mechanism control circuit 20 Aperture control circuit 21 Processing Circuit 22 Input Circuits 23 displays 24 Image Data Generation Circuit 25 Memory circuit 26 Image Processing Circuit 91 X-ray image List of 93 markers 100 X-ray diagnostic equipment 101 X-ray image List of 103 markers 111 X-ray image 211 Control Functions 212 Detection Function 213 Evaluation function 214 Corrected Image Generation Function 215 Display control function

Claims

1. An acquisition unit that sequentially acquires multiple X-ray images in a time series, A detection unit that detects multiple candidate objects, which are multiple candidate objects included in the multiple X-ray images acquired, An evaluation unit that calculates an evaluation value for each of the multiple candidate objects based on the multiple X-ray images, A display unit that displays the evaluation value in association with the plurality of target candidate objects, A receiving unit that accepts the selection of at least one of the aforementioned multiple candidate objects, A correction image generation unit generates multiple correction images by detecting an object in a reference image among the multiple X-ray images, using the position of the object corresponding to the selected object candidate as the reference position among the multiple object candidates, and performing a correction process on the multiple X-ray images to align the position of the object corresponding to the selected object candidate with the reference position. An X-ray diagnostic device equipped with [specific features / features].

2. The evaluation unit calculates the evaluation value using at least one of the frequency of detection of the plurality of target object candidates in the plurality of X-ray images and the time-series continuity of the detection. The X-ray diagnostic apparatus according to claim 1.

3. The aforementioned object is at least one of the following: a treatment device inserted into the subject, and a characteristic object attached to the treatment device. The X-ray diagnostic apparatus according to claim 1.

4. The treatment device comprises a plurality of the aforementioned features. The X-ray diagnostic apparatus according to claim 3.

5. The display unit highlights the selected object candidate from among the plurality of object candidates. The X-ray diagnostic apparatus according to claim 1 or 2.

6. The display unit further displays the plurality of target object candidates in the reference image, The reception unit accepts the selection of at least one of the multiple target object candidates displayed in the reference image. The X-ray diagnostic apparatus according to claim 1.

7. The display unit displays the multiple candidate objects in a list, The receiving unit accepts the selection of at least one of the multiple target candidates in the list in response to the operation of a toggle button indicating the selection of the multiple target candidates. The X-ray diagnostic apparatus according to claim 1.

8. The display unit further displays a plurality of identifiers capable of identifying the plurality of target candidate objects, The receiving unit accepts the selection of at least one of the plurality of identifiers. The X-ray diagnostic apparatus according to claim 1.

9. An acquisition unit that sequentially acquires multiple X-ray images in a time series, A detection unit that detects multiple candidate objects, which are multiple candidate objects included in the multiple X-ray images acquired, An evaluation unit that calculates an evaluation value for each of the multiple candidate objects based on the multiple X-ray images, A display unit that displays the evaluation value in association with the plurality of target candidate objects, A receiving unit that accepts the selection of at least one of the aforementioned multiple candidate objects, A correction image generation unit generates multiple correction images by detecting an object in a reference image among the multiple X-ray images, using the position of the object corresponding to the selected object candidate as the reference position among the multiple object candidates, and performing a correction process on the multiple X-ray images to align the position of the object corresponding to the selected object candidate with the reference position. A medical image processing device equipped with [a specific feature].

10. Multiple X-ray images are acquired sequentially in a time series, Each of the multiple candidate objects, which are candidates for multiple objects included in the multiple X-ray images acquired, is detected. Based on the aforementioned multiple X-ray images, an evaluation value is calculated for each of the aforementioned multiple candidate objects. The aforementioned evaluation values ​​are displayed in association with the plurality of candidate objects. The system accepts the selection of at least one of the aforementioned multiple candidate objects. Multiple corrected images are generated by applying a correction process to the multiple X-ray images, where the object is detected in the reference image among the multiple object candidates, the position of the object corresponding to the selected object candidate is used as the reference position, and the position of the object corresponding to the selected object candidate is aligned to the reference position. A medical image processing method comprising the following features.

11. On the computer, Multiple X-ray images are acquired sequentially in a time series, Multiple candidate objects, which are candidates for objects included in the acquired multiple X-ray images, are detected. Based on the aforementioned multiple X-ray images, an evaluation value is calculated for each of the aforementioned multiple candidate objects. The aforementioned evaluation values ​​are displayed in association with the plurality of candidate objects. The system accepts the selection of at least one of the aforementioned multiple candidate objects. The process involves detecting an object in a reference image among the multiple X-ray images, using the position of the object corresponding to the selected object candidate as the reference position among the multiple object candidates, and generating multiple corrected images by applying a correction process to the multiple X-ray images to align the position of the object corresponding to the selected object candidate with the reference position. A medical image processing program that makes this possible.

Images