Blood vessel subtraction image generation method and device, medical imaging equipment and storage medium

Abstract

The invention discloses a blood vessel subtraction image generation method and device, medical imaging equipment and a storage medium. The method comprises the following steps: firstly, acquiring a target angiography image and a preliminary matching mask image matched with the motion law of the target angiography image; then, processing is carried out according to the preliminary matching mask image, and a target matching mask image with the background tending to be the same as that of the target angiography image is obtained; and finally, generating a blood vessel subtraction image corresponding to the target angiography image based on the target matching mask image and the target angiography image. By acquiring the preliminary matching mask image matched with the motion law of the target angiography image, the conditions of low frame rate acquisition or dysphoria of a patient and the like can be better handled. The blood vessel subtraction image corresponding to the target angiography image is generated based on the target matching mask image with the background tending to be the same as that of the target angiography image and the target angiography image, background interference in the target angiography image can be better eliminated, and therefore the quality of the blood vessel subtraction image is improved.

Description

Technical Field

[0001] The present invention relates to the field of image processing technology, and in particular to a method and device for generating a vascular subtraction image, a medical imaging device and a storage medium. Background Art

[0002] Digital subtraction uses digital processing and subtraction technology to highlight the contrast agent in the blood vessels and improve the visibility of the vascular structure by comparing X-ray images before and after the injection of contrast agent, thereby improving the accuracy of medical diagnosis.

[0003] During actual shooting, due to the influence of the patient's breathing, heartbeat, etc., the background of the X-ray image before and after the injection of the contrast agent cannot be exactly the same, and artifacts will appear in the subtraction image, interfering with the display of the blood vessels. Summary of the invention

[0004] The embodiments of this specification are intended to solve at least one of the technical problems in the related art to a certain extent. To this end, the embodiments of this specification propose a method, device, medical imaging device and storage medium for generating a vascular subtraction image.

[0005] The present specification provides a method for generating a vascular subtraction image, the method comprising:

[0006] Acquire a target angiography image and a preliminary matching mask image that matches the motion law of the target angiography image;

[0007] Processing is performed according to the preliminary matching mask image to obtain a target matching mask image having a background similar to that of the target angiography image;

[0008] A blood vessel subtraction image corresponding to the target angiography image is generated based on the target matching mask image and the target angiography image.

[0009] In one embodiment, the preliminary matching mask image is determined by:

[0010] Get the mask image sequence;

[0011] Determining the target phase stage of the target contrast image according to the phase of the target contrast image and the phase of the specified contrast image set; wherein at least part of the specified contrast image set is located before the target contrast image, or the specified contrast image set is located after the target contrast image;

[0012] The preliminary matching mask image is determined in the mask image sequence according to the target phase stage and the motion law data of the target angiography image.

[0013] In one embodiment, the mask image sequence corresponds to a plurality of motion cycles; and determining the preliminary matching mask image in the mask image sequence according to the motion law data of the target phase stage and the target angiography image comprises:

[0014] Determining in the mask image sequence a plurality of frames of mask images located within the target phase stage in each motion cycle;

[0015] Determine, from among the multiple frames of mask images located in the target phase stage in each motion cycle, a reference mask image set whose similar data to the designated angiography image set meets a preset similarity screening condition;

[0016] In the mask image sequence, a mask image that is located within the motion cycle of the reference mask image set and matches the motion law data of the target angiography image is determined as the preliminary matching mask image.

[0017] In one embodiment, determining a reference mask image set whose similar data to the specified angiography image set meets a preset similarity screening condition from among the multiple mask image frames located in the target phase stage in each motion cycle includes:

[0018] According to the motion law data of the specified contrast image set, matching is performed in multiple mask images located in the target phase stage in each motion cycle to obtain a mask set to be screened in each motion cycle;

[0019] The reference mask image set that is most similar to the designated contrast image set is determined in the mask image sets to be screened in each of the plurality of motion cycles.

[0020] In one embodiment, the preliminary matching mask images are multiple, and the multiple preliminary matching mask images constitute a preliminary matching mask set. The preliminary matching mask image is determined in the mask image sequence according to the target phase stage and the motion law data of the target angiography image, including:

[0021] Determining, in the mask image sequence, a plurality of frames of mask images located within the target phase stage;

[0022] According to the motion law data of the target angiography image, matching is performed in multiple frames of mask images located in the target phase stage to obtain the preliminary matching mask set.

[0023] In one embodiment, the preliminary matching mask images are multiple, and the multiple preliminary matching mask images constitute a preliminary matching mask set. The target matching mask image is obtained by fusion processing based on the preliminary matching mask images in the preliminary matching mask set; the processing based on the preliminary matching mask images to obtain a target matching mask image having a background similar to that of the target contrast image includes:

[0024] Key point positioning and pixel value calculation are performed according to the preliminary matching mask images in the preliminary matching mask set to obtain the target matching mask image.

[0025] In one embodiment, the preliminary matching mask set includes a first mask image and a second mask image; performing key point positioning and pixel value calculation according to the preliminary matching mask image in the preliminary matching mask set to obtain the target matching mask image includes:

[0026] Determining first position data corresponding to a key point in the first mask image and second position data corresponding to a key point in the second mask image; wherein the key point in the first mask image matches the key point in the second mask image;

[0027] Performing interpolation processing using the first phase data of the first mask image, the second phase data of the second mask image, the third phase data of the target contrast image, the first position data, and the second position data to obtain target position data of key points in the target matching mask image;

[0028] Performing interpolation processing based on the pixel data of the first mask image, the pixel data of the second mask image, the first position data, and the second position data to obtain the pixel value of the key point in the target matching mask image;

[0029] The target matching mask image is obtained based on the target position data and pixel values ​​of the key points in the target matching mask image.

[0030] In one embodiment, the preliminary matching mask set has two frames of images; before determining the first position data corresponding to the key point in the first mask image, the method further includes:

[0031] Determine, from the preliminary matching mask set, a preliminary matching mask image that is closest to the motion law data of the target angiography image as the first mask image;

[0032] The preliminary matching mask images other than the first mask image in the preliminary matching mask set are used as the second mask images; wherein the second position data is determined on the second mask image based on the first position data in a template matching manner.

[0033] In one embodiment, generating a vascular subtraction image corresponding to the target angiography image based on the target matching mask image and the target angiography image includes:

[0034] Performing registration based on the target matching mask image and the target angiography image to obtain a registered mask image; subtracting the registered mask image from the target angiography image to obtain the vascular subtraction image; or

[0035] The target matching mask image is subtracted from the target angiography image to obtain the vascular subtraction image.

[0036] In one embodiment, the preliminary matching mask images are multiple, and the multiple preliminary matching mask images constitute a preliminary matching mask set; the preliminary matching mask set is determined by the following method:

[0037] Get the mask image sequence;

[0038] Determine third position data of key points of the target contrast image and fourth position data of key points of each mask image frame in the mask image sequence;

[0039] Determining image similarity data between each mask image frame in the mask image sequence and the target contrast image according to the third position data and the fourth position data;

[0040] The preliminary matching mask set is determined in the mask image sequence according to the image similarity data.

[0041] The present specification provides a device for generating a vascular subtraction image, the device comprising:

[0042] An image acquisition module, used to acquire a target contrast image and a preliminary matching mask image that matches the motion law of the target contrast image;

[0043] An image processing module, used for processing the preliminary matching mask image to obtain a target matching mask image having a background similar to that of the target angiography image;

[0044] A subtraction image generation module is used to generate a blood vessel subtraction image corresponding to the target angiography image based on the target matching mask image and the target angiography image.

[0045] An embodiment of the present specification provides a medical imaging device, which includes: a memory, and one or more processors communicatively connected to the memory; the memory stores instructions executable by the one or more processors, and the instructions are executed by the one or more processors to enable the one or more processors to implement the steps of the method described in any of the above embodiments.

[0046] The embodiments of this specification provide a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the method described in any of the above embodiments are implemented.

[0047] An embodiment of the present specification provides a computer program product, wherein the computer program product includes instructions, and when the instructions are executed by a processor of a computer device, the computer device is enabled to perform the steps of the method described in any one of the above embodiments.

[0048] In the above-mentioned embodiment of the specification, first, a target angiography image and a preliminary matching mask image matching the motion law of the target angiography image are obtained. Then, the target matching mask image is processed according to the preliminary matching mask image to obtain a target matching mask image with the same background as the target angiography image. Finally, a vascular subtraction image corresponding to the target angiography image is generated based on the target matching mask image and the target angiography image. By obtaining a preliminary matching mask image matching the motion law of the target angiography image, the requirements for the quality of the mask image are reduced, and the situation of low frame rate acquisition or patient agitation is better dealt with, thereby improving the robustness and reliability of the vascular subtraction image generation method. By processing the preliminary matching mask image matching the motion law of the target angiography image, a target matching mask image with the same background as the target angiography image is obtained, and the similarity between the background of the mask image used to generate the vascular subtraction image and the target angiography image is improved, so that the target matching mask image and the target angiography image are more visually unified and realistic. Therefore, generating a vascular subtraction image corresponding to the target angiography image based on the target matching mask image and the target angiography image helps to better eliminate background interference in the target angiography image, thereby highlighting the morphology and contour of the blood vessels, thereby improving the quality of the vascular subtraction image. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1a A flow chart of a method for generating a vascular subtraction image provided in an embodiment of this specification;

[0050] Figure 1b A schematic diagram of the flow chart of the method for generating a vascular subtraction image provided in an embodiment of this specification;

[0051] Figure 1c A schematic diagram of a respiratory gating output signal and corresponding time provided in an embodiment of this specification;

[0052] Figure 2 A schematic diagram of the flow chart of the method for generating a vascular subtraction image provided in an embodiment of this specification;

[0053] Figure 3a A schematic diagram of a process for determining a preliminary matching mask set provided in an embodiment of this specification;

[0054] Figure 3b A schematic diagram of determining a preliminary matching mask set provided in an embodiment of this specification;

[0055] Figure 4a A schematic diagram of a process for determining a preliminary matching mask set provided in an embodiment of this specification;

[0056] Figure 4b A schematic diagram of determining a preliminary matching mask set provided in an embodiment of this specification;

[0057] Figure 5a A schematic diagram of a process for determining a reference mask image set provided in an embodiment of this specification;

[0058] Figure 5b A schematic diagram of determining a reference mask image set provided in an embodiment of this specification;

[0059] Figure 6 A schematic diagram of a process for determining a preliminary matching mask set provided in an embodiment of this specification;

[0060] Figure 7 A schematic diagram of a process for obtaining a target matching mask image provided in an embodiment of this specification;

[0061] Figure 8a A schematic diagram of a process for determining a first mask image and a second mask image provided in an embodiment of this specification;

[0062] Figure 8b A schematic diagram of determining a first mask image and a second mask image provided in an embodiment of this specification;

[0063] Figure 9a A schematic diagram of a vascular subtraction image generated by registering a fixed mask image with a first frame of angiography image provided in an embodiment of this specification;

[0064] Figure 9b A schematic diagram of a vascular subtraction image generated by registering a fixed mask image with a second frame of angiography image provided in an embodiment of this specification;

[0065] Fig.9cA schematic diagram of a vascular subtraction image generated by registering a fixed mask image with a third frame of angiography image provided in an embodiment of this specification;

[0066] Figure 9d A schematic diagram of a vascular subtraction image generated by registering a first frame of angiography image and its corresponding target matching mask image provided in an embodiment of this specification;

[0067] Fig.9e A schematic diagram of a vascular subtraction image generated by registering a second frame of angiography image and its corresponding target matching mask image provided in an embodiment of this specification;

[0068] Figure 9f A schematic diagram of a vascular subtraction image generated by registering a third frame of angiography image and its corresponding target matching mask image provided in an embodiment of this specification;

[0069] Fig.10 A schematic diagram of a process for determining a preliminary matching mask set provided in an embodiment of this specification;

[0070] Fig.11 A schematic diagram of the flow chart of the method for generating a vascular subtraction image provided in an embodiment of this specification;

[0071] Fig.12 A schematic diagram of a vascular subtraction image generating device provided in an embodiment of this specification. DETAILED DESCRIPTION

[0072] Embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present invention, and should not be construed as limiting the present invention.

[0073] A vascular machine is a medical imaging device that assists doctors in conducting examinations or surgeries. It uses X-rays to dynamically display tissue images of the patient's examination site, especially blood vessel images. Since blood vessels are not clearly distinguished from other tissues under X-ray irradiation, contrast agents are usually injected into the blood vessels to improve the display contrast of blood vessels in the image. Then, using the digital subtraction method, the image acquired after the injection of contrast agent (contrast image) and the image acquired without the injection of contrast agent (mask image) are subtracted to obtain a subtraction image in which only the blood vessels are clearly displayed. The premise of digital subtraction is that the position of the patient's examination site in the contrast image and the mask image is the same, so that the image after subtraction can subtract the same background on the contrast image and the mask image, leaving only the contrast agent-enhanced blood vessel image. However, in actual examinations, due to the influence of the patient's breathing, heartbeat, movement and other movements, the background of the contrast image and the mask image cannot be exactly the same, and more background residues will appear in the obtained subtraction image, interfering with the display of blood vessels. Especially when acquiring chest and abdominal images, due to the large amplitude of respiratory movement and the possibility of agitation of the patient, this will cause obvious background residues in the subtraction image. Although doctors often ask patients to hold their breath to reduce movement, this cannot be achieved well for patients with poor lung function or those undergoing general anesthesia.

[0074] Based on the above analysis, the embodiment of the present specification provides a method for generating a vascular subtraction image. First, a target angiography image and a preliminary matching mask image that matches the motion law of the target angiography image are obtained. Then, the target matching mask image is processed according to the preliminary matching mask image to obtain a target matching mask image that is similar to the background of the target angiography image. Finally, a vascular subtraction image corresponding to the target angiography image is generated based on the target matching mask image and the target angiography image. By obtaining a preliminary matching mask image that matches the motion law of the target angiography image, the requirements for the quality of the mask image are reduced, and the situation of low frame rate acquisition or patient agitation is better dealt with, thereby improving the robustness and reliability of the vascular subtraction image generation method. By processing the preliminary matching mask image that matches the motion law of the target angiography image, a target matching mask image that is similar to the background of the target angiography image is obtained, and the similarity between the background of the mask image used to generate the vascular subtraction image and the target angiography image is improved, so that the target matching mask image and the target angiography image are more visually unified and realistic. Therefore, generating a vascular subtraction image corresponding to the target angiography image based on the target matching mask image and the target angiography image helps to better eliminate background interference in the target angiography image, thereby highlighting the morphology and contour of the blood vessels, thereby improving the quality of the vascular subtraction image.

[0075] The vascular subtraction image generation method provided in the embodiments of this specification can be applied to a vascular machine. Figure 1a, the vascular machine subtraction device can include three modules: image acquisition, image processing and image display. The time control of the injection of contrast agent by the syringe is set by the console 114, that is, the time between the start of emitting rays and the injection of contrast agent is set (at least the time including one breathing cycle is set). In the image acquisition module, after the patient is ready, the operator will use a pedal or other control device to trigger the tube 102, and the tube 102 will emit an X-ray beam. In the time period from the start of emitting X-rays to the injection of contrast agent, the X-rays pass through the patient's body and are captured by the detector 104. The detector 104 will convert the received X-rays into digital signals and record imaging information. The digital signal is image reconstructed to generate a mask image sequence. The image memory 106 stores the mask image sequence. The mask image sequence is transmitted to the image processing module in real time. The console 114 in the image processing module controls the mask generation component 108, and the mask generation component 108 judges the motion law of each frame of the mask image and determines the phase of each frame of the mask image. Inject contrast agent, and generate a sequence of contrast images by reconstructing the received digital signals during the time period from the injection of contrast agent to the stop of X-ray emission. The image memory 106 stores the sequence of contrast images. The sequence of contrast images is transmitted to the image processing module in real time. The mask generation component 108 in the image processing module determines the motion law of each frame of contrast image and determines the phase of each frame of contrast image. The target contrast image is any frame of contrast image in the sequence of contrast images. The mask generation component 108 determines a preliminary matching mask set in the mask image sequence according to the phase of the target contrast image, and determines a target matching mask image based on the first mask image closest to the phase of the target contrast image in the preliminary matching mask set and the second mask image other than the first mask image and the target contrast image. The target matching mask image and the target contrast image are transmitted to the subtraction component 110, and the console 114 controls the subtraction component 110. The subtraction component 110 subtracts the target matching mask image from the target contrast image to obtain a vascular subtraction image. The console 114 controls the display 112 to display the vascular subtraction image for doctors to diagnose the patient's condition.

[0076] This specification provides a method for generating a vascular subtraction image. Figure 1b The method for generating a vascular subtraction image may include the following steps:

[0077] S110, acquiring a target angiography image and a preliminary matching mask image that matches the motion pattern of the target angiography image.

[0078] The motion law may be a certain motion change of a significant tissue structure in a medical image, for example, the motion law may be a respiratory phase corresponding to the image, or may be position data of a key point in the image.

[0079] Specifically, after the patient is ready, the operator will use a pedal or other control device to trigger the X-ray emission device to emit an X-ray beam. The X-ray passes through the patient's body and is captured by the detector. The detector converts the received X-ray into a digital signal and records the imaging information. The acquired digital signal is transmitted to the computer system for image reconstruction to generate a mask image. In the time period from the start of X-ray emission to the injection of contrast agent, multiple frames of mask images are generated by reconstructing the received digital signal, and the multiple frames of mask images constitute a mask image sequence. Inject contrast agent, in the time period from the injection of contrast agent to the stop of X-ray emission, multiple frames of contrast images are generated by reconstructing the received digital signal, and the multiple frames of contrast images constitute a contrast image sequence. The target contrast image is any frame of contrast image in the contrast image sequence. In order to obtain a mask image that is more similar to the background of the target contrast image, it is necessary to match the motion law of the target contrast image with the motion law of the mask image in the mask image sequence, and the mask image that meets the standard constitutes a preliminary matching mask image.

[0080] In some embodiments, the method for determining the image motion law can be obtained by using an external respiratory gating device. The respiratory gating technology can output chest amplitude data that changes over time, that is, phase, in real time by fixing the sensor on the patient's chest. These data correspond to the breathing time of the image acquisition, which can be approximately described as follows: Figure 1c As shown in the figure, the horizontal axis is time, and the vertical axis is the chest amplitude data, i.e., phase. When the patient breathes freely, the diaphragm in the image will float up and down, and the red dotted line marks the upper edge of the diaphragm. When the amplitude of the gated signal decreases, it means that the patient exhales, the chest moves downward, and the diaphragm rises; when the amplitude of the gated signal increases, it means that the patient inhales, the chest moves upward, and the diaphragm descends. Therefore, by obtaining the respiratory gating signal, the corresponding respiratory phase can be assigned to the mask image and the contrast image in real time to represent the movement law of the image.

[0081] S120, performing processing according to the preliminary matching mask image to obtain a target matching mask image having the same background as the target angiography image.

[0082] Specifically, processing the preliminary matching mask image may include noise reduction and / or registration processing, or may include fusion processing of multiple preliminary matching mask images as described below. The purpose of processing the preliminary matching mask image is to improve the quality of the matching mask image and eliminate the position difference with the angiogram caused by motion.

[0083] S130 , generating a vascular subtraction image corresponding to the target angiography image based on the target matching mask image and the target angiography image.

[0084] The backgrounds tending to be the same may mean that the background of the target matching mask image and the background of the target contrast image are visually more consistent or similar.

[0085] Specifically, the preliminary matching mask image is processed to coordinate the preliminary matching mask image with the background of the target angiography image, and a target matching mask image that is similar to the background of the target angiography image is obtained. Then, the target matching mask image and the target angiography image are used for subtraction processing to eliminate or weaken the blood vessel signal in the target angiography image, and generate a blood vessel subtraction image corresponding to the target angiography image.

[0086] In the above-mentioned implementation, first, a target angiography image and a preliminary matching mask image matching the motion law of the target angiography image are obtained. Then, the target matching mask image is processed according to the preliminary matching mask image to obtain a target matching mask image with the same background as the target angiography image. Finally, a vascular subtraction image corresponding to the target angiography image is generated based on the target matching mask image and the target angiography image. The implementation of this specification reduces the requirements for the quality of the mask image by obtaining a preliminary matching mask image matching the motion law of the target angiography image, and better copes with situations such as low frame rate acquisition or patient agitation, thereby improving the robustness and reliability of the vascular subtraction image generation method. By processing the preliminary matching mask image matching the motion law of the target angiography image, a target matching mask image with the same background as the target angiography image is obtained, and the similarity between the background of the mask image used to generate the vascular subtraction image and the target angiography image is improved, so that the target matching mask image and the target angiography image are more visually unified and realistic. Therefore, generating a vascular subtraction image corresponding to the target angiography image based on the target matching mask image and the target angiography image helps to better eliminate background interference in the target angiography image, thereby highlighting the morphology and contour of the blood vessels, thereby improving the quality of the vascular subtraction image.

[0087] This specification provides a method for generating a vascular subtraction image. Figure 2 The method for generating a vascular subtraction image may include the following steps:

[0088] S210: Acquire a target angiography image and a set of preliminary matching masks that match the motion pattern of the target angiography image.

[0089] Specifically, during the time period from the start of X-ray emission to the injection of contrast agent, multiple frames of mask images are generated by reconstructing the received digital signals, and the multiple frames of mask images constitute a mask image sequence. Contrast agent is injected, during the time period from the injection of contrast agent to the stop of X-ray emission, multiple frames of contrast images are generated by reconstructing the received digital signals, and the multiple frames of contrast images constitute a contrast image sequence. The target contrast image is any frame of contrast image in the contrast image sequence. In order to obtain a mask image that is more similar to the background of the target contrast image, it is necessary to match the motion law of the target contrast image with the motion law of the mask images in the mask image sequence, and form a preliminary matching mask set with multiple frames of mask images that meet the standards.

[0090] S220, performing fusion processing on the preliminary matching mask images in the preliminary matching mask set to obtain a target matching mask image having the same background as the target angiography image.

[0091] S230 , generating a vascular subtraction image corresponding to the target angiography image based on the target matching mask image and the target angiography image.

[0092] Specifically, the preliminary matching mask images in the preliminary matching mask set are fused so that the fused image can retain the detail information in the preliminary matching mask image and coordinate with the background of the target angiography image, thereby obtaining a target matching mask image that is similar to the background of the target angiography image. Then, the target matching mask image and the target angiography image are used for subtraction processing to eliminate or weaken the vascular signal in the target angiography image, thereby generating a vascular subtraction image corresponding to the target angiography image.

[0093] In the above implementation, first, a target angiography image and a set of preliminary matching masks matching the motion law of the target angiography image are obtained. Then, a fusion process is performed based on the preliminary matching mask images in the preliminary matching mask set to obtain a target matching mask image with the same background as the target angiography image. Finally, a vascular subtraction image corresponding to the target angiography image is generated based on the target matching mask image and the target angiography image. By obtaining a set of preliminary matching masks matching the motion law of the target angiography image, the requirements for the quality of the mask image are reduced, and the situation of low frame rate acquisition or patient agitation is better dealt with, thereby improving the robustness and reliability of the vascular subtraction image generation method. By performing a fusion process on the preliminary matching mask images in the set of preliminary matching masks matching the motion law of the target angiography image, a target matching mask image with the same background as the target angiography image is obtained, and the similarity between the background of the mask image used to generate the vascular subtraction image and the target angiography image is improved, so that the target matching mask image and the target angiography image are more visually unified and realistic. Therefore, generating a vascular subtraction image corresponding to the target angiography image based on the target matching mask image and the target angiography image helps to better eliminate background interference in the target angiography image, thereby highlighting the morphology and contour of the blood vessels, thereby improving the quality of the vascular subtraction image.

[0094] In some embodiments, see Figure 3a , determine the initial matching mask set by:

[0095] S310: Obtain a mask image sequence.

[0096] Specifically, after the patient is ready, the operator will use a pedal or other control device to trigger the X-ray emission device to emit an X-ray beam. The X-rays pass through the patient's body and are captured by the detector. The detector converts the received X-rays into digital signals and records the imaging information. The acquired digital signals are transmitted to the computer system for image reconstruction to generate a mask image. During the period from the start of X-ray emission to the injection of contrast agent, multiple frames of mask images are generated by reconstructing the received digital signals, and the multiple frames of mask images constitute a mask image sequence.

[0097] S320, determining a target phase stage of the target contrast image according to the phase of the target contrast image and the phase of the specified contrast image set.

[0098] At least part of the designated contrast image set is located before the target contrast image, or the designated contrast image set is located after the target contrast image. The target phase stage may be the phase state or stage of the target contrast image, for example, the target phase stage may be an ascending stage or a descending stage.

[0099] Specifically, some rules or standards for determining the specified contrast image set can be pre-set based on phase difference, time information or other relevant factors. According to the pre-set rules or standards, the specified contrast image set is determined with reference to the phase of the target contrast image. At least part of the specified contrast image set is located before the target contrast image, or the specified contrast image set is located after the target contrast image. The phase situation in the specified contrast image set is determined. Then, based on the positional relationship between the specified contrast image set and the target contrast image and the size relationship between the phase of each frame of the contrast image in the specified contrast image set and the phase of the target contrast image, it is determined whether the target phase stage of the target contrast image is a rising stage or a falling stage.

[0100] For example, see Figure 3b The discrete black dots in the curve in the figure are the collected mask images or contrast images. c is the contrast image, and the contrast image I c The first two frames of contrast images are determined as the designated contrast image set. According to the phase of the target contrast image and the phase of each contrast image frame in the designated contrast image set, the target phase stage of the target contrast image is determined to be the rising stage. Among them, the number of contrast image frames in the designated contrast image set can be determined according to the increase or decrease of the acquisition frame rate. The higher the acquisition frame rate, the more frames of contrast images in the designated contrast image set.

[0101] S330 , determining a preliminary matching mask set in the mask image sequence according to the target phase stage and the motion law data of the target angiography image.

[0102] Specifically, the motion law data of the target angiography image is matched with the motion law data of the mask image in the mask image sequence in the target phase stage. According to the matching result, multiple frames of mask images that are relatively similar to the background of the target angiography image are selected to form a preliminary matching mask set.

[0103] In the above-mentioned embodiment, a mask image sequence is obtained, and the target phase stage of the target contrast image is determined according to the phase of the target contrast image and the phase of the specified contrast image set. A preliminary matching mask set is determined in the mask image sequence according to the target phase stage and the motion law data of the target contrast image, so as to provide a data basis for determining a target matching mask image with a background that is similar to that of the target contrast image.

[0104] In some embodiments, a preliminary matching mask image is determined by: acquiring a mask image sequence, determining a target phase stage of the target contrast image based on the phase of the target contrast image and the phase of a specified contrast image set, and determining a preliminary matching mask image in the mask image sequence based on the target phase stage and the motion law data of the target contrast image.

[0105] Specifically, in the time period from the start of X-ray emission to the injection of contrast agent, multiple frames of mask images are generated by reconstructing the received digital signals, and the multiple frames of mask images constitute a mask image sequence. According to a pre-set rule or standard, the specified contrast image set is determined with the phase of the target contrast image as a reference. At least part of the specified contrast image set is located before the target contrast image, or the specified contrast image set is located after the target contrast image. The phase situation in the specified contrast image set is determined. Then, according to the positional relationship between the specified contrast image set and the target contrast image and the size relationship between the phase of each frame of the contrast image in the specified contrast image set and the phase of the target contrast image, it is determined whether the target phase stage of the target contrast image is a rising stage or a falling stage. The motion law data of the target contrast image is matched with the motion law data of the mask image in the mask image sequence within the target phase stage. According to the matching result, a mask image similar to the background of the target contrast image is selected as a preliminary matching mask image.

[0106] In the above-mentioned embodiment, a mask image sequence is obtained, and the target phase stage of the target contrast image is determined according to the phase of the target contrast image and the phase of the specified contrast image set. A preliminary matching mask image is determined in the mask image sequence according to the target phase stage and the motion law data of the target contrast image, so as to provide a data basis for determining a target matching mask image with a background that is similar to that of the target contrast image.

[0107] In some embodiments, see Figure 4a The mask image sequence corresponds to multiple motion cycles. Determining a preliminary matching mask set in the mask image sequence according to the motion law data of the target phase stage and the target contrast image may include the following steps:

[0108] S410, determining in the mask image sequence a plurality of frames of mask images located within a target phase stage in each motion cycle.

[0109] S420, determining a reference mask image set whose similar data to the designated angiography image set meets a preset similarity screening condition from among the multiple mask image frames located in the target phase stage in each motion cycle.

[0110] S430: In the mask image sequence, a plurality of mask image frames that are located within the motion cycle of the reference mask image set and match the motion law data of the target angiography image are determined as a preliminary matching mask set.

[0111] The preset similarity screening condition may be a set of conditions or criteria set when determining a reference mask image set similar to a specified set of contrast images. For example, the preset similarity screening condition may be a similarity measure based on motion law data. The motion cycle may be a periodic change of human motion, such as a breathing cycle or a heartbeat cycle.

[0112] Specifically, after determining the target phase stage, the mask image sequence is analyzed to determine each motion cycle in the mask image sequence and the target phase stage in each motion cycle. All mask images in the mask image sequence that are located in the target phase stage of each motion cycle can be used as multiple mask images located in the target phase stage in each motion cycle. Mask images that are located in the target phase stage of each motion cycle in the mask image sequence and are closest to the motion law data of the specified contrast image set and have the same frame number as the specified contrast image set can also be used as multiple mask images located in the target phase stage in each motion cycle.

[0113] Calculate the similarity data of the multi-frame mask images located in the target phase stage in each motion cycle and the specified contrast image set. By comparing the similarity data, among the multi-frame mask images located in the target phase stage in each motion cycle, determine the multi-frame mask images located in the target phase stage in a certain motion cycle whose similarity data meets the preset similarity screening conditions as the reference mask image set. Then, in the mask image sequence, match the motion law data corresponding to all mask images in the motion cycle where the reference mask image set is located with the motion law data of the target contrast image, and use the mask image closest to the motion law data of the target contrast image as the preliminary matching mask image, and then determine the closest mask image among its adjacent mask images as the preliminary matching mask image. The obtained multi-frame preliminary matching mask images constitute a preliminary matching mask set.

[0114] For example, see Figure 4b , P1 is a reference mask image set. In the mask image sequence, determine the mask image I that is located in the motion cycle of the reference mask image set P1 and is closest to the motion law data of the target angiography image. 1-1 And the mask image I 1-1 Adjacent mask image I 1-2 Constitute a preliminary matching mask set.

[0115] In the above-mentioned embodiment, a plurality of mask image frames located in the target phase stage in each motion cycle are determined in the mask image sequence, and a reference mask image set whose similar data with the specified contrast image set meets the preset similarity screening conditions is determined among the plurality of mask image frames located in the target phase stage in each motion cycle. In the mask image sequence, a plurality of mask image frames located in the motion cycle of the reference mask image set and matching the motion law data of the target contrast image are determined as the preliminary matching mask set, so as to provide a data basis for determining a target matching mask image having a background similar to that of the target contrast image.

[0116] In some embodiments, the mask image sequence corresponds to multiple motion cycles. Determining a preliminary matching mask image in the mask image sequence according to the motion law data of the target phase stage and the target contrast image may include: determining multiple frames of mask images in each motion cycle in the mask image sequence that are within the target phase stage; determining a reference mask image set whose similar data with the specified contrast image set meets a preset similarity screening condition among the multiple frames of mask images in each motion cycle; and determining, in the mask image sequence, a mask image that is within the motion cycle of the reference mask image set and matches the motion law data of the target contrast image as the preliminary matching mask image.

[0117] Specifically, the mask image sequence is analyzed to determine each motion cycle in the mask image sequence and the target phase stage in each motion cycle. All mask images located in the target phase stage of each motion cycle can be used as multiple mask images located in the target phase stage in each motion cycle. Mask images located in the target phase stage of each motion cycle that are closest to the motion law data of the specified contrast image set and have the same frame number as the specified contrast image set can also be used as multiple mask images located in the target phase stage in each motion cycle. Similarity data between the multiple mask images and the specified contrast image set is calculated. By comparing the similarity data, multiple mask images located in the target phase stage in a certain motion cycle whose similarity data meets the preset similarity screening condition are determined as the reference mask image set. Then, in the mask image sequence, the motion law data corresponding to each of all mask images in the motion cycle where the reference mask image set is located is matched with the motion law data of the target contrast image, and the mask image closest to the motion law data of the target contrast image is used as the preliminary matching mask image.

[0118] In the above-mentioned embodiment, a plurality of mask image frames located in the target phase stage in each motion cycle are determined in the mask image sequence, and a reference mask image set whose similar data with the specified contrast image set meets the preset similarity screening condition is determined among the plurality of mask image frames located in the target phase stage in each motion cycle. In the mask image sequence, a mask image located in the motion cycle of the reference mask image set and matching the motion law data of the target contrast image is determined as a preliminary matching mask image, so as to provide a data basis for determining a target matching mask image having a background similar to that of the target contrast image.

[0119] In some embodiments, see Figure 5a , determining a reference mask image set whose similar data to a specified contrast image set meets a preset similarity screening condition from among a plurality of mask image frames located in a target phase stage in each motion cycle, may include the following steps:

[0120] S510 , matching is performed among multiple frames of mask images located in a target phase stage in each motion cycle according to the motion law data of the specified contrast image set, so as to obtain a mask set to be screened in each motion cycle.

[0121] S520 , determining a reference mask image set that is most similar to the designated contrast image set from among the mask image sets to be screened in the respective multiple motion cycles.

[0122] Specifically, after determining the target phase stage, the motion law data corresponding to the mask image in the target phase stage in each motion cycle is matched with the motion law data of the specified contrast image set, and multiple frames of mask images in the target phase stage in each motion cycle that are closest to the motion law data of the specified contrast image set are determined as the mask set to be screened. The similarity between the mask set to be screened and the specified contrast image set of each motion cycle is calculated. The similarity between the mask set to be screened and the specified contrast image set of each motion cycle is compared, and in the mask sets to be screened of each of the multiple motion cycles, the mask set to be screened that is most similar to the specified contrast image set is used as the reference mask image set that is most similar to the specified contrast image set. Among them, the number of frames of the contrast image in the specified contrast image set can be determined according to the increase or decrease of the acquisition frame rate. The higher the acquisition frame rate, the more frames of the contrast image in the specified contrast image set.

[0123] Exemplarily, the target phase stage is determined to be the rising phase. Figure 5b , P c is a specified contrast image set. In each motion cycle, the mask image located in the rising phase is determined to be consistent with the specified contrast image set P cThe multi-frame mask images with the closest phase are used as the mask set P1 and the mask set P2 to be screened. The mask set P1 and the mask set P2 to be screened and the specified contrast image set P are calculated according to the following formula c Similarity:

[0124]

[0125] in, For the specified angiographic image set P c The i-th frame mask image, is the set of masks to be screened P n The i-th mask image of the image set M is a set of M contrast images. n is the set of contrast images P c and the mask set P to be screened n The similarity between .

[0126] S n The smaller the value, the better the motion state matches, and the interference of some sudden motions can be eliminated first. Compare the mask sets P1 and P2 to be screened in each motion cycle with the specified angiographic image set P c By comparing the similarity between them, it can be determined that P1 is the reference mask image set that is most similar to the specified angiography image set.

[0127] In the above implementation, according to the motion law data of the specified contrast image set, matching is performed among the multiple frames of mask images located in the target phase stage in each motion cycle to obtain a set of mask images to be screened for each motion cycle. In the mask sets to be screened for each of the multiple motion cycles, a set of reference mask images that is most similar to the specified contrast image set is determined, thereby providing a data basis for the subsequent determination of the first mask image and the second mask image, thereby determining a target matching mask image that has a background that is similar to the target contrast image.

[0128] In some embodiments, see Figure 6 The preliminary matching mask images are multiple, and the multiple preliminary matching mask images constitute a preliminary matching mask set. Determining the preliminary matching mask image in the mask image sequence according to the target phase stage and the motion law data of the target contrast image may include the following steps:

[0129] S610: Determine a plurality of frames of mask images located in a target phase stage in a mask image sequence.

[0130] S620: According to the motion law data of the target angiography image, matching is performed in multiple frames of mask images located in the target phase stage to obtain a preliminary matching mask set.

[0131] Specifically, the mask image sequence is analyzed, and all mask images located in the target phase change stage are determined as multiple mask images located in the target phase stage, which are recorded as the same-stage mask set. For example, the multiple mask images located in the target phase stage can be all mask images in the rising stage, or all mask images in the falling stage. Then, the similarity data between the motion law data of the target contrast image and the motion law data of each mask image frame in the same-stage mask set is calculated. Finally, by comparing the similarity data between the target contrast image and each mask image frame in the same-stage mask set, the matching of the multiple mask images located in the target phase stage according to the motion law data of the target contrast image is achieved, and the mask image corresponding to the highest similarity data is used as the preliminary matching mask image. Then, the mask image corresponding to the highest similarity data among the mask images adjacent to the mask image corresponding to the highest similarity data is used as the preliminary matching mask image. The determined multiple preliminary matching mask images constitute the preliminary matching mask set.

[0132] In the above embodiment, multiple frames of mask images located in the target phase stage are determined in the mask image sequence, and matching is performed in the multiple frames of mask images located in the target phase stage based on the motion law data of the target contrast image to obtain a preliminary matching mask set, thereby providing a data basis for determining a target matching mask image with a background that is similar to the target contrast image.

[0133] In some embodiments, there are multiple preliminary matching mask images, and the multiple preliminary matching mask images constitute a preliminary matching mask set. The target matching mask image is obtained by fusion processing based on the preliminary matching mask images in the preliminary matching mask set. Processing based on the preliminary matching mask image to obtain a target matching mask image with a background similar to that of the target contrast image may include: performing key point positioning and pixel value calculation based on the preliminary matching mask image in the preliminary matching mask set to obtain the target matching mask image.

[0134] Among them, key points can represent significant organizational structures of the image, for example, key points can be significant locations such as corners, edges, textures, etc.

[0135] Specifically, the key points of the preliminary matching mask images in the preliminary matching mask set are detected, and the positions with significant changes or features in the preliminary matching mask images are determined to locate the key points. After the key points are determined, the pixel values ​​at the corresponding key point positions in the target matching mask image can be calculated based on the pixel values ​​and positions of the key points in the preliminary matching mask images, thereby obtaining the target matching mask image.

[0136] In the above implementation, key point positioning and pixel value calculation are performed based on the preliminary matching mask image in the preliminary matching mask set to obtain a target matching mask image. By obtaining a target matching mask image with a background that is similar to the target angiography image, a data basis is provided to eliminate background interference in the target angiography image, further highlight the morphology and contour of the blood vessels, and thus improve the quality of the vascular subtraction image.

[0137] In some embodiments, see Figure 7 The preliminary matching mask set includes a first mask image and a second mask image. Performing key point positioning and pixel value calculation according to the preliminary matching mask image in the preliminary matching mask set to obtain a target matching mask image may include the following steps:

[0138] S710: Determine first position data corresponding to a key point in the first mask image and second position data corresponding to a key point in the second mask image.

[0139] The key points in the first mask image are matched with the key points in the second mask image.

[0140] Specifically, the gradient of the first mask image is calculated to obtain a gradient map corresponding to the first mask image. Then, the gradient points that meet specific conditions (such as local maximum) are screened out from the gradient map, and the points that meet the specific conditions are used as key points to locate the key points, and obtain the first position data corresponding to the key points in the first mask image. Then, according to the set matching rules (such as the distance between key points, feature similarity and other criteria), the first position data is used as a reference to determine the second position data corresponding to the key points in the second mask image.

[0141] Exemplarily, a global gradient calculation is performed on the first mask image to obtain a gradient map. Then, the gradient map is divided into a plurality of regions using a threshold segmentation method, and a point with the largest gradient is selected in each region as a key point. Based on the determined key point, first position data corresponding to the key point is determined in the first mask image.

[0142] S720, performing interpolation processing using the first phase data of the first mask image, the second phase data of the second mask image, the third phase data of the target contrast image, the first position data, and the second position data to obtain target position data of key points in the target matching mask image.

[0143] Specifically, a suitable interpolation method (such as bilinear interpolation) is selected according to the actual situation and specific needs. According to the selected interpolation method, the first phase data of the first mask image, the second phase data of the second mask image, the third phase data of the target contrast image, the first position data and the second position data are interpolated, and the data of the unknown position is inferred according to the known position data to obtain more continuous and smooth position data, and the target position data of the key point in the target matching mask image is obtained.

[0144] Exemplarily, the formula for obtaining the target position data of the key points in the target matching mask image using the bilinear interpolation method is as follows:

[0145]

[0146] Among them, A c is the third phase data of the target contrast image, D 1-1 is the first position data, is the first phase data of the first mask image, D 1-2 is the second position data, is the second phase data of the second mask image. m The target position data of the key points in the target matching mask image.

[0147] S730, performing interpolation processing based on the pixel data of the first mask image, the pixel data of the second mask image, the first position data, and the second position data to obtain pixel values ​​of key points in the target matching mask image.

[0148] Specifically, according to the actual situation and specific needs, a suitable interpolation method (such as bilinear interpolation, bicubic interpolation) is selected to estimate the pixel value of the unknown pixel point in the interpolation area. The position data of the key point on the first mask image is determined according to the first position data, and the position data of the key point on the second mask image is determined according to the second position data. Using the selected interpolation method, the pixel data at the key point on the first mask image and the pixel data at the key point on the second mask image are interpolated to obtain the pixel value of the target position data of the key point that is more continuous and smooth in the target matching mask image. Repeat the above steps until the pixel value interpolation processing is completed for all key points.

[0149] S740: Obtain a target matching mask image based on the target position data and pixel values ​​of the key points in the target matching mask image.

[0150] Specifically, using the target position data and pixel values ​​of the key points in the target matching mask image, a portion of the target matching mask image can be generated. The gradient points other than the key points in the first mask image are recorded as non-key points. Then, matching is performed based on the position data corresponding to the non-key points in the first mask image to determine the position data corresponding to the non-key points in the second mask image. Fusion processing is performed using the position data and pixel values ​​of the non-key points to generate the remaining portion of the target matching mask image. The portion of the target matching mask image obtained above is merged with the remaining portion of the target matching mask image to generate a complete target matching mask image.

[0151] Exemplarily, on the first mask image, the first mask image is triangulated based on the key points of the first mask image, and the first mask image is divided into a plurality of triangular regions. For the non-key points in each triangular region, the position of the non-key points needs to be determined according to the key point positions corresponding to the three vertices of the region and the distance relationship between the three vertices. According to the distance relationship between the key points of the first mask image and the second mask image, a weighted interpolation method is adopted, that is, the closer the distance to the triangle vertex, the greater the weight it occupies when determining the position, so as to determine the position and pixel value of the non-key points in the target matching mask image.

[0152] In the above implementation manner, the first position data corresponding to the key point in the first mask image and the second position data corresponding to the key point in the second mask image are determined, and the first phase data of the first mask image, the second phase data of the second mask image, the third phase data of the target angiography image, the first position data and the second position data are used for interpolation processing to obtain the target position data of the key point in the target matching mask image, and the interpolation processing is performed based on the pixel data of the first mask image, the pixel data of the second mask image, the first position data and the second position data to obtain the pixel value of the key point in the target matching mask image, and the target matching mask image is obtained based on the target position data and pixel value of the key point in the target matching mask image. By obtaining a target matching mask image with a background that is similar to that of the target angiography image, a data basis is provided for eliminating background interference in the target angiography image, highlighting the morphology and contour of the blood vessels, and thereby improving the quality of the vascular subtraction image.

[0153] In some embodiments, see Figure 8a , the preliminary matching mask set has two frames of images. Before determining the first position data corresponding to the key point in the first mask image, the method may further include the following steps:

[0154] S810. Determine, in the preliminary matching mask set, a preliminary matching mask image that is closest to the motion law data of the target angiography image as the first mask image.

[0155] S820: Use the preliminary matching mask images other than the first mask image in the preliminary matching mask set as second mask images.

[0156] The second position data is determined on the second mask image based on the first position data in a template matching manner.

[0157] Specifically, the motion law data of the target angiography image is compared with the motion law data of each frame of the preliminary matching mask image in the preliminary matching mask set. According to the comparison result, the preliminary matching mask image closest to the motion law data of the target angiography image is selected as the first mask image. Then, the selected first mask image is excluded from the preliminary matching mask set, and the remaining preliminary matching mask images in the preliminary matching mask set are used as the second mask image to ensure that the motion law of the target angiography image can complement each other, thereby improving the effect and stability of the registration.

[0158] Exemplarily, the preliminary matching mask set includes I 1-1 and I 1-2 . See Figure 8b , compare the phase of the target contrast image with the phase of each frame of the preliminary matching mask image in the preliminary matching mask set, and select the preliminary matching mask image I that is closest to the phase of the target contrast image 1-1 As the first mask image. 1-1 The initial matching mask image I 1-2 as the second mask image.

[0159] In the above embodiment, a preliminary matching mask image that is closest to the motion law data of the target angiography image is determined in the preliminary matching mask set as the first mask image, and the preliminary matching mask images other than the first mask image in the preliminary matching mask set are used as the second mask image to provide a data basis for the subsequent generation of a vascular subtraction image corresponding to the target angiography image.

[0160] In some embodiments, generating a vascular subtraction image corresponding to a target angiography image based on a target matching mask image and a target angiography image may include: performing registration based on the target matching mask image and the target angiography image to obtain a registered mask image; and subtracting the registered mask image from the target angiography image to obtain a vascular subtraction image.

[0161] The registration may be a process of aligning or calibrating the target matching mask image and the target angiography image so that they are consistent or accurately overlapped in space.

[0162] Specifically, an appropriate registration method (such as two-dimensional elastic registration or registration using a deep learning method) is selected according to the specific situation. Then, the target matching mask image and the target angiography image are registered using the selected registration method to obtain a registered mask image, so that the background between the registered mask image and the target angiography image is more similar than the background between the target matching mask image and the target angiography image. Therefore, in order to present the vascular structure more clearly, the pixel value of the corresponding position in the target angiography image is subtracted from the pixel value of the same position in the registered mask image pixel by pixel, ensuring that the background interference is effectively removed at each pixel level, so that the vascular structure can be more clearly displayed, and a vascular subtraction image is obtained.

[0163] In the above implementation, the target matching mask image and the target angiography image are registered to obtain a registered mask image; the target angiography image is used to subtract the registered mask image to obtain a vascular subtraction image, and the target matching mask image with the same background as the target angiography image is used for registration to improve the similarity between the registered mask image and the target angiography image. Then, the target angiography image is used to eliminate the background interference in the target angiography image, so as to highlight the morphology and contour of the blood vessels, thereby improving the quality of the vascular subtraction image.

[0164] In some embodiments, generating a vascular subtraction image corresponding to the target angiography image based on the target matching mask image and the target angiography image may include: subtracting the target matching mask image from the target angiography image to obtain the vascular subtraction image.

[0165] Specifically, since the target matching mask image usually contains background structures that are unrelated to blood vessels, in order to present the vascular structure more clearly, the pixel value of the corresponding position in the target angiography image is subtracted from the pixel value of the same position in the target matching mask image pixel by pixel, ensuring that background interference is effectively removed at each pixel level, so that the vascular structure can be displayed more clearly and a vascular subtraction image is obtained.

[0166] For example, compared with the related art that uses a fixed mask image and aligns all the angiography images with it to generate a vascular subtraction image corresponding to each angiography image, for example, refer to Figure 9a , Figure 9a A vascular subtraction image is generated by registering a fixed mask image with the first frame of angiography. Figure 9b , Figure 9b A vascular subtraction image is generated by registering a fixed mask image with a second angiogram. Fig.9c , Fig.9cA vascular subtraction image is generated by registering a fixed mask image with a third frame of angiography image. In the embodiment of this specification, a target matching mask image corresponding to each frame of angiography image is used to register them to generate a higher quality vascular subtraction image. For example, please refer to Figure 9d , Figure 9d The vascular subtraction image is generated by registering the first frame of angiography image with its corresponding target matching mask image. Fig.9e , Fig.9e The vascular subtraction image is generated by registering the second frame of angiography image with its corresponding target matching mask image. Figure 9f , Figure 9f The vascular subtraction image is generated by registering the third frame of angiography image and its corresponding target matching mask image.

[0167] In the above implementation, the target contrast image is subtracted from the target matching mask image to obtain a vascular subtraction image. By using a target matching mask image having a background similar to that of the target contrast image, background interference in the target contrast image is eliminated, the morphology and contour of the blood vessels are more prominent, thereby improving the quality of the vascular subtraction image.

[0168] In some embodiments, see Fig.10 , there are multiple preliminary matching mask images, and multiple preliminary matching mask images constitute a preliminary matching mask set. The preliminary matching mask set is determined by the following method:

[0169] S1010: Obtain a mask image sequence.

[0170] Specifically, after the patient is ready, the operator will use a pedal or other control device to trigger the X-ray emission device to emit an X-ray beam. The X-rays pass through the patient's body and are captured by the detector. The detector converts the received X-rays into digital signals and records the imaging information. The acquired digital signals are transmitted to the computer system for image reconstruction to generate a mask image. During the period from the start of X-ray emission to the injection of contrast agent, multiple frames of mask images are generated by reconstructing the received digital signals, and the multiple frames of mask images constitute a mask image sequence.

[0171] S1020, determining third position data of key points of the target contrast image and fourth position data of key points of each mask image frame in the mask image sequence.

[0172] Specifically, the gradient calculation is performed on the first mask image in the mask image sequence to obtain the first gradient map corresponding to the first mask image. Then, the gradient points that meet the specific conditions (such as the local maximum) are screened out from the first gradient map, and the gradient points that meet the specific conditions are used as key points to realize the positioning of the key points, and obtain the position data of the key points in the first mask image. Then, according to the set matching rules (such as the distance between key points, feature similarity and other criteria), the position data of the key points in the first mask image is used as a reference to determine the position data of the key points in the second mask image. Through iterative cycles, in each round of iteration, the key point position data in the current mask image is determined according to the key point position data in the previous mask image, so as to determine the fourth position data of the key points in each mask image in the mask image sequence. Then, according to the matching rules, the last mask image in the mask image sequence is used as a reference to determine the position data of the key points in the first contrast image. The iteration cycle is performed again. In each iteration, the key point position data in the current frame of the contrast image is determined according to the key point position data in the previous frame of the contrast image, thereby determining the position data of the key point of each frame of the contrast image in the contrast image sequence. The third position data of the key point of the target contrast image is determined according to the position data of the key point of each frame of the contrast image in the contrast image sequence.

[0173] Exemplarily, a global gradient calculation is performed on the first mask image in the mask image sequence to obtain a gradient map. Then, the gradient map is divided into multiple regions using a threshold segmentation method, and the point with the largest gradient in each region is selected as a key point, which can ensure that the number of key points is not too large and not too sparse. Subsequently, according to the inter-frame tracking and template matching method, the gradient key points in the first mask image are tracked in each subsequent mask image frame to determine the fourth position data of the key points of each mask image frame in the mask image sequence. The fourth position data of the key points of each mask image frame in the mask image sequence is determined by the following formula:

[0174] D n = Template matching (M n -M n-1 )+D n-1

[0175] Among them, M n is the nth mask image in the mask image sequence, M n-1 is the n-1th frame mask image in the mask image sequence. n-1 is the fourth position data of the key point K1 in the mask image of the n-1th frame, D n It is the fourth position data of the key point K1 in the mask image of the nth frame.

[0176] Similarly, the third position data of the key point of the target angiography image is determined by the method of inter-frame tracking and template matching. It should be noted that by adopting the method of inter-frame tracking and template matching, the position of the key point can be determined more accurately, avoiding falling into the local minimum, and significantly speeding up the speed of displacement calculation.

[0177] S1030: Determine image similarity data between each mask image frame in the mask image sequence and the target contrast image according to the third position data and the fourth position data.

[0178] S1040: Determine a preliminary matching mask set in the mask image sequence according to the image similarity data.

[0179] The image similarity data may represent the degree of similarity between the background of each mask image frame in the mask image sequence and the target contrast image.

[0180] Specifically, a similarity calculation method (such as cosine similarity, dot product, Euclidean distance, etc.) is used to calculate the similarity between the third position data of the key point of the target contrast image and the fourth position data of the key point of each frame of the mask image in the mask image sequence, so as to determine the image similarity data between each frame of the mask image in the mask image sequence and the target contrast image. The mask image corresponding to the image similarity data representing the highest similarity is used as the preliminary matching mask image. Then, the mask image corresponding to the image similarity data representing the highest similarity in the adjacent mask images of the mask image corresponding to the image similarity data representing the highest similarity is used as the preliminary matching mask image. A preliminary matching mask set is formed based on the determined multiple frames of preliminary matching mask images.

[0181] Exemplarily, the sum of the Euclidean distances between each mask image frame and the target contrast image in the mask image sequence is determined using the Euclidean distance method. The minimum Euclidean distance and the corresponding mask image are used as preliminary matching mask images. Then, the minimum Euclidean distance and the corresponding mask image in the adjacent mask images of the minimum Euclidean distance and the corresponding mask image are used as preliminary matching mask images. A preliminary matching mask set is formed based on the determined multiple frames of preliminary matching mask images.

[0182] In the above implementation, a mask image sequence is acquired, third position data of key points of the target angiography image and fourth position data of key points of each frame of the mask image in the mask image sequence are determined, image similarity data between each frame of the mask image in the mask image sequence and the target angiography image are determined based on the third position data and the fourth position data, and a preliminary matching mask set is determined in the mask image sequence based on the image similarity data, thereby providing a data basis for subsequently improving the quality of vascular subtraction images.

[0183] The embodiment of the present specification also provides a method for generating a vascular subtraction image, wherein the mask image sequence corresponds to multiple motion cycles, and the motion cycle includes a breathing cycle or a heartbeat cycle. The preliminary matching mask set has two frames of images, and the preliminary matching mask set includes a first mask image and a second mask image. For example, refer to Fig.11 The method for generating a vascular subtraction image may include the following steps:

[0184] S1102, acquiring a target contrast image and a mask image sequence.

[0185] S1104 , determining a target phase stage of the target contrast image according to the phase of the target contrast image and the phase of the specified contrast image set.

[0186] Wherein, at least part of the designated contrast image set is located before the target contrast image, or the designated contrast image set is located after the target contrast image.

[0187] S1106: Determine in the mask image sequence a plurality of frames of mask images that are within the target phase stage in each motion cycle.

[0188] S1108. Matching is performed among multiple mask image frames located in the target phase stage in each motion cycle according to the motion law data of the specified contrast image set, so as to obtain a mask set to be screened in each motion cycle.

[0189] S1110 , determining a reference mask image set that is most similar to a specified contrast image set from among the mask image sets to be screened in each of the multiple motion cycles.

[0190] S1112. In the mask image sequence, a plurality of mask image frames that are located within the motion cycle of the reference mask image set and match the motion law data of the target angiography image are determined as a preliminary matching mask set.

[0191] S1114. Determine, in the preliminary matching mask set, a preliminary matching mask image that is closest to the motion law data of the target angiography image as the first mask image.

[0192] S1116. Use the preliminary matching mask images in the preliminary matching mask set except the first mask image as the second mask image.

[0193] The second position data is determined on the second mask image based on the first position data in a template matching manner.

[0194] S1118. Determine first position data corresponding to the key point in the first mask image and second position data corresponding to the key point in the second mask image.

[0195] The key points in the first mask image are matched with the key points in the second mask image.

[0196] S1120, performing interpolation processing using the first phase data of the first mask image, the second phase data of the second mask image, the third phase data of the target contrast image, the first position data, and the second position data to obtain target position data of key points in the target matching mask image.

[0197] S1122: Perform interpolation processing based on the pixel data of the first mask image, the pixel data of the second mask image, the first position data, and the second position data to obtain pixel values ​​of key points in the target matching mask image.

[0198] S1124. Obtain a target matching mask image based on the target position data and pixel values ​​of the key points in the target matching mask image.

[0199] S1126. Subtract the target matching mask image from the target angiography image to obtain a vascular subtraction image.

[0200] This specification provides a vascular subtraction image generation device 1200, see Fig.12 The vascular subtraction image generating device 1200 includes: an image acquisition module 1210 , an image processing module 1220 , and a subtraction image generating module 1230 .

[0201] An image acquisition module 1210 is used to acquire a target angiography image and a preliminary matching mask image that matches the motion law of the target angiography image;

[0202] An image processing module 1220 is used to process the preliminary matching mask image to obtain a target matching mask image having a background similar to that of the target angiography image;

[0203] The subtraction image generation module 1230 is used to generate a blood vessel subtraction image corresponding to the target angiography image based on the target matching mask image and the target angiography image.

[0204] For a detailed description of the vascular subtraction image generating device, reference may be made to the above description of the vascular subtraction image generating method, which will not be described in detail here.

[0205] In some embodiments, a medical imaging device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the method steps in the above embodiments when executing the computer program.

[0206] An embodiment of the present specification provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the method in any of the above embodiments are implemented.

[0207] One embodiment of the present specification provides a computer program product, which includes instructions. When the instructions are executed by a processor of a computer device, the computer device can perform the steps of the method of any of the above embodiments.

[0208] It should be noted that the logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection portion with one or more wirings (electronic device), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or otherwise processing in a suitable manner if necessary, and then stored in a computer memory.

Claims

1. A method for generating a vascular subtraction image, characterized in that: The method comprises: Acquire a target angiography image and a preliminary matching mask image that matches the motion law of the target angiography image; Processing is performed according to the preliminary matching mask image to obtain a target matching mask image having a background similar to that of the target angiography image; A blood vessel subtraction image corresponding to the target angiography image is generated based on the target matching mask image and the target angiography image.

2. The method according to claim 1, characterized in that The preliminary matching mask image is determined by: Get the mask image sequence; Determining the target phase stage of the target contrast image according to the phase of the target contrast image and the phase of the specified contrast image set; wherein at least part of the specified contrast image set is located before the target contrast image, or the specified contrast image set is located after the target contrast image; The preliminary matching mask image is determined in the mask image sequence according to the target phase stage and the motion law data of the target angiography image.

3. The method according to claim 2, characterized in that The mask image sequence corresponds to a plurality of motion cycles; and determining the preliminary matching mask image in the mask image sequence according to the motion law data of the target phase stage and the target angiography image comprises: Determining in the mask image sequence a plurality of frames of mask images located within the target phase stage in each motion cycle; Determine, from among the multiple frames of mask images located in the target phase stage in each motion cycle, a reference mask image set whose similar data to the designated angiography image set meets a preset similarity screening condition; In the mask image sequence, a mask image that is located within the motion cycle of the reference mask image set and matches the motion law data of the target angiography image is determined as the preliminary matching mask image.

4. The method according to claim 3, characterized in that Determining a reference mask image set whose similar data to the designated angiography image set meets a preset similarity screening condition from among the multiple mask image frames located in the target phase stage in each motion cycle comprises: According to the motion law data of the specified contrast image set, matching is performed in multiple mask images located in the target phase stage in each motion cycle to obtain a mask set to be screened in each motion cycle; The reference mask image set that is most similar to the designated contrast image set is determined in the mask image sets to be screened in each of the plurality of motion cycles.

5. The method according to claim 2, characterized in that: The preliminary matching mask images are multiple, and the multiple preliminary matching mask images constitute a preliminary matching mask set. The preliminary matching mask image is determined in the mask image sequence according to the target phase stage and the motion law data of the target angiography image, including: Determining, in the mask image sequence, a plurality of frames of mask images located within the target phase stage; According to the motion law data of the target angiography image, matching is performed in multiple frames of mask images located in the target phase stage to obtain the preliminary matching mask set.

6. The method according to any one of claims 1 to 4, characterized in that The preliminary matching mask images are multiple, and the multiple preliminary matching mask images constitute a preliminary matching mask set. The target matching mask image is obtained by fusion processing based on the preliminary matching mask images in the preliminary matching mask set; the processing based on the preliminary matching mask images to obtain a target matching mask image having a background similar to that of the target contrast image includes: Key point positioning and pixel value calculation are performed according to the preliminary matching mask images in the preliminary matching mask set to obtain the target matching mask image.

7. The method according to claim 6, characterized in that The preliminary matching mask set includes a first mask image and a second mask image; performing key point positioning and pixel value calculation according to the preliminary matching mask image in the preliminary matching mask set to obtain the target matching mask image includes: Determining first position data corresponding to a key point in the first mask image and second position data corresponding to a key point in the second mask image; wherein the key point in the first mask image matches the key point in the second mask image; Performing interpolation processing using the first phase data of the first mask image, the second phase data of the second mask image, the third phase data of the target contrast image, the first position data, and the second position data to obtain target position data of key points in the target matching mask image; Performing interpolation processing based on the pixel data of the first mask image, the pixel data of the second mask image, the first position data, and the second position data to obtain the pixel value of the key point in the target matching mask image; The target matching mask image is obtained based on the target position data and pixel values ​​of the key points in the target matching mask image.

8. The method according to claim 7, characterized in that The preliminary matching mask set has two frames of images; before determining the first position data corresponding to the key point in the first mask image, the method further includes: Determine, from the preliminary matching mask set, a preliminary matching mask image that is closest to the motion law data of the target angiography image as the first mask image; The preliminary matching mask images other than the first mask image in the preliminary matching mask set are used as the second mask images; wherein the second position data is determined on the second mask image based on the first position data in a template matching manner.

9. The method according to any one of claims 1 to 5, characterized in that: The step of generating a vascular subtraction image corresponding to the target angiography image based on the target matching mask image and the target angiography image comprises: Performing registration based on the target matching mask image and the target angiography image to obtain a registered mask image; subtracting the registered mask image from the target angiography image to obtain the vascular subtraction image; or The target matching mask image is subtracted from the target angiography image to obtain the vascular subtraction image.

10. The method according to claim 1, characterized in that The preliminary matching mask images are multiple, and the multiple preliminary matching mask images constitute a preliminary matching mask set; the preliminary matching mask set is determined by the following method: Get the mask image sequence; Determine third position data of key points of the target contrast image and fourth position data of key points of each mask image frame in the mask image sequence; Determining image similarity data between each mask image frame in the mask image sequence and the target contrast image according to the third position data and the fourth position data; The preliminary matching mask set is determined in the mask image sequence according to the image similarity data.

11. A vascular subtraction image generation device, characterized in that: The device comprises: An image acquisition module, used to acquire a target contrast image and a preliminary matching mask image that matches the motion law of the target contrast image; An image fusion module, used for processing the preliminary matching mask image to obtain a target matching mask image having a background similar to that of the target angiography image; A subtraction image generation module is used to generate a blood vessel subtraction image corresponding to the target angiography image based on the target matching mask image and the target angiography image.

12. A medical imaging device, comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 10 are implemented.

13. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 10 are implemented.

Images