Vascular image processing system and apparatus, and storage medium
By obtaining the angiographic image sequence, determining the proximal and distal ends of the vascular stenosis segment, calculating the relative deformation ratio of the target area, solving the problem of low accuracy in vascular deformation calculation in the prior art, and achieving the vascular deformation Accurate quantification and improvement of plaque stability judgment.
Patent Information
- Application Number
- PCT/CN2023/132930
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2023-05-31
- Filing Date
- 2023-11-21
- Publication Date
- 2024-12-05
AI Technical Summary
The vascular deformation calculation method or system based on image registration in the prior art has a problem of low accuracy, which affects the accuracy of plaque stability judgment.
By acquiring angiographic image sequences, the proximal and distal ends of the vascular stenosis segment are determined, and the target area is positioned based on these endpoints, and the relative deformation ratio of the target area is calculated to improve the accuracy of the vascular deformation calculation.
Accurate quantification of vascular deformation is achieved, the accuracy of plaque stability judgment is improved, plaques in blood vessels can be monitored in real time, and safety is enhanced.
Smart Images

Figure CN2023132930_05122024_PF_FP_ABST
Abstract
Description
Vascular image processing system, device and storage medium
[0001] This application claims priority to the Chinese patent application filed with the China Patent Office on May 31, 2023, with application number 202310640919.6, the entire contents of which are incorporated by reference into this application. Technical Field
[0002] The present application relates to the field of image processing, for example, to a vascular image processing system, device and storage medium. Background Art
[0003] Plaques, a yellowish-white mass with a porridge-like texture embedded in the inner layer of arterial walls, are a hallmark of arteriosclerosis. Vascular deformation affects plaque stability; greater deformation leads to more unstable plaques and a greater risk of adverse cardiovascular events.
[0004] Related technologies can obtain vascular images using methods such as intracavitary imaging and then determine the degree of vascular deformation based on image registration, thereby assessing plaque stability. However, image registration can increase errors in vascular deformation calculations. Therefore, related vascular deformation calculation methods or systems based on image registration suffer from low accuracy.
[0005] Summary of the Invention
[0006] The present application provides a vascular image processing system, device and storage medium to solve the problem of low accuracy of vascular deformation calculation methods or systems based on image registration in related technologies.
[0007] According to one aspect of the present application, a blood vessel image processing system is provided, the system comprising:
[0008] A processor configured to execute the following method, comprising:
[0009] Acquiring an angiographic image sequence, the angiographic image sequence including at least two frames of angiographic images, and the at least two frames of angiographic images corresponding to the same projection position;
[0010] For each angiography image, determining a proximal end and a distal end of a stenotic segment of a blood vessel in the current angiography image;
[0011] Locate the target area of the vascular stenosis segment based on the proximal and distal ends;
[0012] The relative deformation ratio of the target area is determined according to the blood vessel diameters of the target area in all angiography images.
[0013] According to another aspect of the present application, a blood vessel image processing device is provided, the device comprising:
[0014] An image acquisition module is configured to acquire an angiographic image sequence, wherein the angiographic image sequence includes at least two frames of angiographic images, and the at least two frames of angiographic images correspond to the same projection position;
[0015] an endpoint determination module configured to determine, for each angiography image, a proximal end and a distal end of a stenotic segment of a blood vessel in a current angiography image;
[0016] A target region module is configured to locate a target region of a stenotic segment of a blood vessel based on the proximal end and the distal end;
[0017] The ratio determination module is configured to determine the relative deformation ratio of the target area according to the blood vessel diameter of the target area in all angiography images.
[0018] According to another aspect of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the computer program implements the following method, including:
[0019] Acquiring an angiographic image sequence, the angiographic image sequence including at least two frames of angiographic images, and the at least two frames of angiographic images corresponding to the same projection position;
[0020] For each angiography image, determining a proximal end and a distal end of a stenotic segment of a blood vessel in the current angiography image;
[0021] Locate the target area of the vascular stenosis segment based on the proximal and distal ends;
[0022] The relative deformation ratio of the target area is determined according to the blood vessel diameters of the target area in all angiography images. BRIEF DESCRIPTION OF THE DRAWINGS
[0023] FIG1 is a structural block diagram of a blood vessel image processing system provided according to an embodiment of the present application;
[0024] FIG2 is a flow chart of a blood vessel image processing method according to an embodiment of the present application;
[0025] FIG3 is a flowchart of another blood vessel image processing method provided according to an embodiment of the present application;
[0026] FIG4 is a structural block diagram of a blood vessel image processing device provided according to an embodiment of the present application;
[0027] FIG5 is a structural block diagram of another blood vessel image processing device provided according to an embodiment of the present application;
[0028] FIG6 is a structural block diagram of another blood vessel image processing device provided according to an embodiment of the present application. DETAILED DESCRIPTION
[0029] It should be noted that the terms "first" and "second" in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in a sequence other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.
[0030] Figure 1 is a block diagram of a vascular image processing system according to an embodiment of the present application. This embodiment is applicable to scenarios where vascular deformation is calculated based on angiographic images. The components shown herein, their connections and relationships, and their functions are provided for illustrative purposes only and are not intended to limit the implementation of the present application as described or claimed herein.
[0031] As shown in Figure 1 , the vascular image processing system 10 includes a processor 11 and memory, such as a read-only memory (ROM) 12 and a random access memory (RAM) 13, communicatively connected to the processor 11. The memory stores computer programs executable by at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer programs stored in the ROM 12 or loaded from a storage unit 18 into the RAM 13. The RAM 13 can also store various programs and data required for the operation of the vascular image processing system 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.
[0032] Multiple components in the vascular image processing system 10 are connected to an I / O interface 15, including an input unit 16, such as a keyboard and mouse; an output unit 17, such as various types of displays and speakers; a storage unit 18, such as a magnetic disk and optical disk; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the vascular image processing system 10 to exchange information or data with other devices via a computer network such as the Internet or various telecommunication networks.
[0033] The processor 11 can be any general-purpose or specialized processing component with processing and computing capabilities. Examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 is configured to execute a vascular image processing method, as shown in FIG2 , which includes:
[0034] S210 , acquiring an angiography image sequence, where the angiography image sequence includes at least two frames of angiography images, and the at least two frames of angiography images correspond to the same projection position.
[0035] The angiographic image sequence may be a two-dimensional or three-dimensional angiographic image obtained based on digital subtraction angiography (DSA), magnetic resonance angiography (MRA) or CT angiography (CTA), or may be data in other formats that can be processed or converted to obtain an angiographic image.
[0036] By processing each image in the angiography image sequence, the geometric features or the contour of the blood vessel can be obtained. For example, the lumen diameter of the blood vessel can be obtained.
[0037] The imaging position is determined by the position of the image intensifier, i.e., the position from which the heart is observed. For example, commonly used imaging positions for coronary angiography include the left anterior oblique, left lateral, and right anterior oblique. Due to individual differences, vascular morphology may vary. Therefore, in practice, the imaging position can be adjusted as needed.
[0038] It is understandable that different frames of angiographic images correspond to angiographic images at different times. Therefore, by comparing and analyzing angiographic images at different times in the same projection position, the vascular deformation corresponding to the same position in the same projection position can be obtained.
[0039] S220 . For each angiography image, determine the proximal end and the distal end of the stenotic segment of the blood vessel in the current angiography image.
[0040] The terms "proximal" and "distal" are not fixed positions but relative. Arteries emanating from the heart gradually branch into capillaries, which then converge into veins returning to the heart. For any two points on a blood vessel, the one closest to the heart is called the proximal end, and the one farther from the heart is called the distal end.
[0041] In one embodiment, the proximal end and the distal end may be any two points within the stenotic segment of the blood vessel. In another embodiment, one of the proximal end and the distal end is located within the stenotic segment of the blood vessel, while the other is located within a normal blood vessel segment connected to the stenotic segment. In yet another embodiment, the proximal end and the distal end are each located within a normal blood vessel segment connected to the stenotic segment of the blood vessel.
[0042] Exemplarily, the proximal and distal ends of the vascular stenosis segment in the angiography image can be determined by manual annotation. Exemplarily, the proximal and distal ends of the vascular stenosis segment in the current angiography image can be determined in response to the user's endpoint selection operation. Alternatively, a neural network model based on at least one of a target detection algorithm and an image segmentation algorithm can be used to obtain an image of the vascular stenosis segment in the angiography image, and the proximal and distal ends can be determined, for example, based on the blood flow direction in the vascular stenosis segment or the distance between the two ends of the vascular stenosis segment and the heart.
[0043] In one embodiment, based on a set vascular stenosis detection algorithm, a bounding box is determined for locating the vascular stenosis segment in the current angiography image; the two vascular endpoints intersecting with the bounding box are designated as the proximal and distal ends, respectively, based on the distance from the heart. The centerline of the bounding box coincides with the centerline of the vascular stenosis segment, and the shape of the centerline of the bounding box can be straight, C-shaped, or S-shaped. Optionally, the target width of each portion of the bounding box is the same, where the target width refers to the width of the bounding box in a direction perpendicular to the centerline of the bounding box.
[0044] The vascular stenosis detection algorithm may be a vision-language pre-training paradigm for boosting scene text detectors (VLPT-STD). Taking a rectangular frame as an example, the angiography image is input into the vascular stenosis detection algorithm to obtain the width, height, and confidence of the vascular stenosis segment in the angiography image. The vascular stenosis segment with a higher confidence level is output as the final detection result. In the angiography image, the two endpoints where the blood vessel intersects with the vascular stenosis are determined based on the direction of the blood vessel. The end closest to the heart is the proximal end, and the end farthest from the heart is the distal end.
[0045] In one embodiment, a segmentation mask is determined for segmenting a stenotic segment of a blood vessel from a current angiographic image; two endpoints of the blood vessel that intersect with the segmentation mask are defined as the proximal end and the distal end, respectively, based on the distance from the heart. Exemplarily, a stenotic segment of a blood vessel is determined in the current angiographic image, and a corresponding segmentation mask is generated; the segmentation mask is multiplied by the angiographic image to obtain a regional image of the stenotic segment of the blood vessel in the angiographic image; and in the angiographic image, two endpoints of the blood vessel that intersect with the segmentation mask are determined, with the end closer to the heart being the proximal end and the end farther from the heart being the distal end.
[0046] Optionally, based on a trained keypoint detection model, the proximal and distal ends of the stenotic segment in the current angiographic image are determined. Keypoints are pixels corresponding to the stenotic segment, or pixels used to segment a normal vessel segment from a stenotic segment. Exemplarily, keypoints are all pixels in the stenotic segment, or pixels along the boundary between the normal vessel segment and the stenotic segment.
[0047] In one embodiment, the keypoint detection model may include a feature extraction network and a prediction network. Exemplarily, the feature extraction network is configured to extract feature data from an angiographic image, input the feature data into the prediction network, and output pixel points corresponding to vascular stenosis segments in the angiographic image or the two endpoints of the vascular stenosis segment, with these pixel points or two endpoints serving as keypoints. The keypoints are then located within the angiographic image, with keypoints closer to the heart serving as proximal ends and those farther from the heart serving as distal ends.
[0048] Exemplarily, determining the proximal end and the distal end of the stenotic segment of the blood vessel in the current angiography image includes:
[0049] Step a1: determining a stenotic segment of a blood vessel in a current angiography image based on a difference between a reference blood vessel lumen and an actual blood vessel lumen.
[0050] The reference blood vessel lumen is the lumen of a theoretically normal blood vessel, and the actual blood vessel lumen is the lumen of the blood vessel in the angiography image.
[0051] The theoretical value of the diameter or width of the blood vessel lumen is determined as the reference diameter; the diameter or width of the blood vessel in the blood vessel image is determined as the actual diameter; the lumen ratio of each pixel in the angiographic image is calculated as (reference diameter - actual diameter) / reference diameter × 100%; a lumen ratio threshold is pre-set. If the lumen ratio is greater than the lumen ratio threshold, the blood vessel at the pixel is considered to be stenotic; if the lumen ratio is less than or equal to the lumen ratio threshold, the blood vessel corresponding to the pixel is considered normal.
[0052] Step a2: The two end points of the stenotic segment of the blood vessel are respectively designated as the proximal end and the distal end according to the distance from the heart.
[0053] For example, based on the distances between the two end points of the stenotic segment and the heart, the end closer to the heart is taken as the proximal end, and the end farther from the heart is taken as the distal end.
[0054] S230: Locate the target area of the stenotic segment of the blood vessel based on the proximal end and the distal end.
[0055] For each frame of angiography, a target region is determined based on the proximal and distal ends. For example, the distal and proximal ends are used as the starting and ending points of the target region of the vascular stenosis segment, respectively. That is, the vascular region between the distal and proximal ends is used as the target region of the vascular stenosis segment.
[0056] S240 : Determine a relative deformation ratio of the target area according to the blood vessel diameters of the target area in all angiography images.
[0057] The relative deformation ratio is a quantitative indicator representing the degree of change in the diameter of blood vessels in the target region, calculated based on the difference between the blood vessel diameter in the target region and the theoretical blood vessel diameter in all angiographic images. For example, the relative deformation ratio is the ratio of the difference between the blood vessel diameter in the target region and the theoretical blood vessel diameter to the theoretical blood vessel diameter.
[0058] Exemplarily, for each frame of angiography image, a related art algorithm is used to determine the vascular contour and vascular centerline of the target region, and the vascular diameter is determined based on the vascular contour and vascular centerline. Exemplarily, the vascular contour of the target region is extracted using the related art algorithm to obtain vascular contour coordinates; for each vascular contour coordinate, the minimum circumscribed rectangle of the vascular contour coordinate is determined, and the edges of the rectangle are translated toward the center of the vessel until the edge of the rectangle intersects with the edge of the vessel at the other end. The distance between the intersection point and the intersection point of the rectangle edge with the vascular contour before the movement is the vascular diameter at that location.
[0059] In one embodiment, the vessel diameter of the target region is determined by the following steps: determining an average vessel width of the target region and using the average vessel width as the vessel diameter of the target region; or determining a minimum vessel width of the target region and using the minimum vessel width as the vessel diameter of the target region. Exemplarily, for each frame of angiographic image, the vessel width of each vessel cross section in the target region is determined, and the average of the vessel widths of each vessel cross section is taken to obtain the average vessel width of the target region and use it as the vessel diameter of the target region; or the minimum of the vessel widths of each vessel cross section is taken to obtain the minimum vessel width of the target region and use it as the vessel diameter of the target region.
[0060] In one embodiment, when the relative deformation ratio is greater than a set deformation threshold, a prompt message indicating that the coronary plaque is prone to detachment is output. It is understandable that when the relative deformation ratio is greater than the set deformation threshold, the coronary plaque is unstable and prone to detachment. Exemplarily, when the relative deformation ratio is greater than 12%, the coronary plaque is determined to be unstable and prone to detachment, and a prompt message indicating that the coronary plaque is prone to detachment is output. The prompt message can be any form of prompt message, which is set to remind the user that the coronary plaque in the target area is prone to detachment. The advantage of this is that it is easier for the user to intervene in the risk in a timely manner and enhance safety.
[0061] In addition, considering that the relative deformation ratio and the risk of coronary plaque shedding may show a positive correlation in some scenarios, a second prompt information different from the above prompt information can be set to remind the user that the coronary plaque in the target area is at a second risk of shedding. Optionally, different deformation thresholds are set to indicate different risks of coronary plaque shedding. When the relative deformation ratio is greater than the first deformation threshold, it indicates that the coronary plaque is at a first risk of shedding, and the first prompt information indicating that the coronary plaque is prone to shedding is output; when the relative deformation ratio is greater than the second deformation threshold and less than or equal to the first deformation threshold, it indicates that the coronary plaque is at a second risk of shedding, and the second prompt information indicating that the coronary plaque is prone to shedding is output. Wherein, the first deformation threshold is greater than the second deformation threshold, and the first risk of shedding is higher than the second risk of shedding.
[0062] The technical solution of this embodiment obtains a sequence of angiographic images, determines the blood vessel diameter of the target area based on the angiographic image sequence, obtains the relative deformation ratio of the blood vessels in the area, and provides prompt information that indicates that coronary plaques are prone to detachment, thereby quantifying the blood vessel deformation in the target area, enabling real-time monitoring of plaques in the blood vessels and improving the accuracy of blood vessel deformation calculation.
[0063] FIG3 is a flowchart of another blood vessel image processing method provided according to an embodiment of the present application. This embodiment shares the same concept as the blood vessel image processing method in the above embodiment and describes, on the basis of the above embodiment, a process for locating a target area of a blood vessel stenosis segment based on the proximal and distal ends.
[0064] As shown in FIG3 , the blood vessel image processing method includes:
[0065] S310 , acquiring an angiography image sequence, where the angiography image sequence includes at least two frames of angiography images, and the at least two frames of angiography images correspond to the same projection position.
[0066] S320 : For each angiography image, determine the proximal end and the distal end of the stenotic segment of the blood vessel in the current angiography image.
[0067] S3301. Determine the length of the vascular stenosis segment.
[0068] Exemplarily, the blood vessel length of the stenotic segment is the distance from the proximal end to the distal end.
[0069] S3302: For the stenotic segment of the blood vessel, remove a blood vessel segment of a first blood vessel length from the proximal end and remove a blood vessel segment of a second blood vessel length from the distal end to obtain a target area.
[0070] The sum of the first blood vessel length and the second blood vessel length is less than the blood vessel length of the stenotic segment of the blood vessel and is greater than or equal to 0.
[0071] Exemplarily, a blood vessel segment between any two points on a stenotic blood vessel segment is taken as a target region, the distance between the two points is greater than 0, and the target region includes at least one pixel.
[0072] It can be understood that the target area may include at least one of the proximal end and the distal end, or may not include the proximal end and the distal end.
[0073] For example, the first blood vessel length from the proximal end can be used as the first endpoint of the target area, and the second blood vessel length from the distal end can be used as the second endpoint of the target area. The sum of the first blood vessel length and the second blood vessel length is less than the blood vessel length of the stenotic segment and is greater than or equal to 0; the blood vessel between the first endpoint and the second endpoint is used as the target area.
[0074] For example, for a stenotic segment of a blood vessel with a length of L, the proximal end of the stenotic segment is point P, the distal end is point D, the length of the first blood vessel is L×N%, the length of the second blood vessel is L×M%, and 0≤(M+N)<100; the point in the stenotic segment that is the first blood vessel length away from point P is recorded as point P1, the point that is the second blood vessel length away from point D is recorded as point D1, and the blood vessel between point P1 and point D1 is used as the target area.
[0075] The advantage of doing this is that the proximal end or distal end of the vascular stenosis segment may be located at the boundary between the normal area of the blood vessel and the vascular stenosis segment, that is, vascular stenosis may not occur at the proximal end or the distal end. Therefore, the vascular segment of the first blood vessel length is removed from the proximal end, and the vascular segment of the second blood vessel length is removed from the distal end, so that the target area is the area where vascular stenosis occurs, thereby improving the accuracy of vascular deformation calculation.
[0076] S340 : Determine a relative deformation ratio of the target area according to the blood vessel diameters of the target area in all angiography images.
[0077] The maximum and minimum values of the blood vessel diameters of the target area in all angiography images are determined, the maximum value minus the minimum value is subtracted to obtain a difference, and the difference is divided by the maximum value to obtain a ratio, which is used as the relative deformation ratio of the target area.
[0078] The technical solution of this embodiment selects a narrowed section of a blood vessel as a target area, and determines the relative deformation ratio according to the blood vessel diameter of the target area, thereby improving the accuracy of blood vessel deformation calculation.
[0079] Figure 4 is a block diagram of a vascular image processing device according to an embodiment of the present application. This embodiment is applicable to scenarios where vascular deformation is calculated based on angiographic images. The device can be implemented using at least one of software and hardware and integrated into a vascular image processing system with application development capabilities.
[0080] As shown in FIG4 , the blood vessel image processing device includes:
[0081] An image acquisition module 401 is configured to acquire an angiography image sequence, where the angiography image sequence includes at least two frames of angiography images, and the at least two frames of angiography images correspond to the same projection position;
[0082] An endpoint determination module 402 is configured to determine, for each angiography image, a proximal end and a distal end of a stenotic segment of a blood vessel in the current angiography image;
[0083] A target region module 403 is configured to locate a target region of a stenotic segment of a blood vessel based on the proximal end and the distal end;
[0084] The ratio determination module 404 is configured to determine the relative deformation ratio of the target area according to the blood vessel diameter of the target area in all angiography images.
[0085] Optionally, the endpoint determination module 402 is configured to:
[0086] determining, based on a set vascular stenosis detection algorithm, a bounding box for locating a vascular stenosis segment in a current angiography image;
[0087] According to the distance from the heart, the two blood vessel endpoints intersecting with the external frame are respectively regarded as the proximal end and the distal end.
[0088] Optionally, the endpoint determination module 402 is further configured to:
[0089] determining a segmentation mask for segmenting a stenotic segment of a blood vessel from a current angiography image;
[0090] According to the distance from the heart, the two blood vessel endpoints intersecting with the segmentation mask are regarded as the proximal end and the distal end respectively.
[0091] Optionally, the endpoint determination module 402 is further configured to determine the proximal end and the distal end of the stenotic segment of the blood vessel in the current angiography image based on a trained key point detection model.
[0092] Optionally, the endpoint determination module 402 is further configured to:
[0093] determining a stenotic segment of a blood vessel in a current angiographic image based on a difference between a reference blood vessel lumen and an actual blood vessel lumen;
[0094] According to the distance from the heart, the two end points of the stenotic segment of the blood vessel are respectively designated as the proximal end and the distal end.
[0095] Optionally, the target area module 403 is configured as:
[0096] Determine the length of the vascular stenosis segment;
[0097] For the stenotic segment of the blood vessel, a blood vessel segment of the first blood vessel length is removed from the proximal end, and a blood vessel segment of the second blood vessel length is removed from the distal end to obtain the target area;
[0098] The sum of the first blood vessel length and the second blood vessel length is less than the blood vessel length of the stenotic segment of the blood vessel and is greater than or equal to 0.
[0099] Optionally, as shown in FIG5 , the apparatus further includes a diameter determination module 405 , and the diameter determination module 405 is configured to:
[0100] Determine the average vessel width in the target area;
[0101] The average vessel width was used as the vessel diameter of the target area;
[0102] or,
[0103] Determine the minimum vessel width in the target area;
[0104] The minimum vessel width was taken as the vessel diameter of the target area.
[0105] Optionally, as shown in FIG6 , the apparatus further includes a shedding prompt module 406 , which is configured to output prompt information indicating that the coronary plaque is prone to shedding when the relative deformation ratio is greater than a set deformation threshold.
[0106] The technical solution of the embodiment of the present application obtains a sequence of angiographic images through the mutual cooperation between multiple modules, determines the blood vessel diameter of the target area based on the angiographic image sequence, obtains the relative deformation ratio of the blood vessels in the area, realizes the quantification of the blood vessel deformation in the target area, and improves the accuracy of the blood vessel deformation calculation.
[0107] The vascular image processing device provided in the embodiments of the present application can execute the vascular image processing method provided in any embodiment of the present application, and has the functional modules and effects corresponding to the execution method.
[0108] In some embodiments, the vascular image processing method can be implemented as a computer program tangibly embodied in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program can be loaded or installed into the vascular image processing system 10 via ROM 12 or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, at least one step of the vascular image processing method described above can be performed. Alternatively, in other embodiments, processor 11 can be configured to execute the vascular image processing method in any other suitable manner (e.g., via firmware).
[0109] Various embodiments of the systems and techniques described herein can be implemented in the following systems or combinations thereof: digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard parts (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, and software. These various embodiments can include being implemented in at least one computer program that is executable or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.
[0110] The computer programs for implementing the methods of the present application may be written in any combination of at least one programming language. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions or operations specified in the flowchart or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.
[0111] In the context of the present application, a computer-readable storage medium can be a tangible medium that can contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared or semiconductor system, device or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium can be a machine-readable storage medium. Examples of machine-readable storage media can include an electrical connection based on at least one line, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
[0112] To provide user interaction, the systems and techniques described herein can be implemented on a vascular image processing system having: a display device (e.g., a cathode ray tube (CRT) or a liquid crystal display (LCD) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the vascular image processing system. Other types of devices can also be used to provide user interaction; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic input, voice input, or tactile input.
[0113] The systems and techniques described herein can be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with embodiments of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.
[0114] A computing system may include a client and a server. The client and server are generally remote from each other and typically interact via a communication network. The client-server relationship arises through computer programs running on the respective computers and establishing a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, a host product within a cloud computing service ecosystem that addresses the management difficulties and limited scalability of traditional physical hosts and virtual private server (VPS) services.
Claims
1. A blood vessel image processing system, comprising a processor, wherein the processor is configured to execute the following method, comprising: Acquire an angiography image sequence, wherein the angiography image sequence includes at least two frames of angiography images, and the at least two frames of angiography images correspond to the same projection position; For each angiography image, determining the proximal end and the distal end of the stenotic segment of the blood vessel in the current angiography image; Locating a target area of the stenotic segment of the blood vessel based on the proximal end and the distal end; The relative deformation ratio of the target area is determined according to the blood vessel diameter of the target area in all the angiography images.
2. The system according to claim 1, wherein: The step of determining the proximal end and the distal end of the stenotic segment of the blood vessel in the current angiography image comprises: Based on a set vascular stenosis detection algorithm, determining a bounding box for locating a vascular stenosis segment in the current angiography image; According to the distance from the heart, two blood vessel endpoints intersecting with the circumscribed frame are respectively used as the proximal end and the distal end.
3. The system according to claim 1, wherein: The step of determining the proximal end and the distal end of the stenotic segment of the blood vessel in the current angiography image comprises: determining a segmentation mask for segmenting the stenotic segment of the blood vessel from the current angiography image; According to the distance from the heart, two blood vessel endpoints intersecting with the segmentation mask are respectively regarded as the proximal end and the distal end.
4. The system according to claim 1, wherein: The step of determining the proximal end and the distal end of the stenotic segment of the blood vessel in the current angiography image comprises: Based on the trained key point detection model, the proximal end and the distal end of the stenotic segment of the blood vessel in the current angiography image are determined.
5. The system according to claim 1, wherein: The step of determining the proximal end and the distal end of the stenotic segment of the blood vessel in the current angiography image comprises: Determine a stenotic segment of a blood vessel in a current angiographic image based on a difference between a reference blood vessel lumen and an actual blood vessel lumen; According to the distance from the heart, the two end points of the stenotic segment of the blood vessel are respectively regarded as the proximal end and the distal end.
6. The system according to claim 1, wherein: The method of locating a target area of the stenosis segment of the blood vessel based on the proximal end and the distal end includes: Determining the blood vessel length of the blood vessel stenosis segment; For the stenotic segment of the blood vessel, a blood vessel segment of a first blood vessel length is removed from the proximal end, and a blood vessel segment of a second blood vessel length is removed from the distal end, so as to obtain a target area; The sum of the first blood vessel length and the second blood vessel length is less than the blood vessel length of the blood vessel stenosis section and is greater than or equal to 0.
7. The system according to claim 1, wherein: The blood vessel diameter of the target area is determined by the following steps, including: determining an average blood vessel width in the target area; Using the average blood vessel width as the blood vessel diameter of the target area; or, determining a minimum blood vessel width in the target area; The minimum blood vessel width is used as the blood vessel diameter of the target area.
8. The system of claim 1, further comprising: When the relative deformation ratio is greater than the set deformation threshold, prompt information indicating that the coronary plaque is prone to fall off is output.
9. A blood vessel image processing device, comprising: An image acquisition module, configured to acquire an angiography image sequence, wherein the angiography image sequence includes at least two frames of angiography images, and the at least two frames of angiography images correspond to the same projection position; An endpoint determination module is configured to determine, for each angiography image, a proximal end and a distal end of a stenotic segment of a blood vessel in a current angiography image; A target region module, configured to locate a target region of the stenotic segment of the blood vessel based on the proximal end and the distal end; The ratio determination module is configured to determine the relative deformation ratio of the target area according to the blood vessel diameter of the target area in all angiography images.
10. A computer-readable storage medium storing a computer program, wherein the computer program enables a processor to implement the following method when executed, comprising: Acquire an angiography image sequence, wherein the angiography image sequence includes at least two frames of angiography images, and the at least two frames of angiography images correspond to the same projection position; For each angiography image, determining the proximal end and the distal end of the stenotic segment of the blood vessel in the current angiography image; Locating a target area of the stenotic segment of the blood vessel based on the proximal end and the distal end; The relative deformation ratio of the target area is determined according to the blood vessel diameter of the target area in all the angiography images.
Citation Information
Patent Citations
Vascular stenosis analysis method and device
CN112288731A
Analysis method and device for angiography image
CN114418976A
Method and device for performing coronary angiography quantitative analysis based on angiography video
CN114418977A
Blood vessel image processing system and device, and storage medium
CN116612102A
Detecting coronary stenosis through spatio-temporal tracking
US20150282777A1
Cited By
Vascular hyperplasia quantitative grading method and device, electronic equipment and storage medium
CN120259408A
Method and device for measuring implantation length of central venous indwelling catheter based on lung CT image
CN122244043A
Creating a vascular tree model
US12354755B2
Enhanced user interface and crosstalk analysis for vascular index measurement
US12446965B2
Three-dimensional sizing tool for cardiac assessment
US12499646B1
