Ultrasonic blood flow imaging method and system based on causal feature registration
By employing a causal feature registration method, the problem of motion artifacts in small vessel imaging was solved, enabling high-definition ultrasound imaging and accurate acquisition of hemodynamic parameters.
Patent Information
- Application Number
- CN202511324935.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-09-17
- Publication Date
- 2025-11-21
AI Technical Summary
Existing technologies are insufficient for effective ultrasound image registration of delicate structures such as small blood vessels, and motion artifacts have a significant impact, leading to a decline in image quality.
A causal feature registration-based method is used to achieve high-resolution imaging of small blood vessels through spatiotemporal matrix decomposition, morphological configuration primitive detection, comprehensive scoring matrix construction, and deformation field calculation.
It improves the imaging quality of fine structures such as small blood vessels, reduces the influence of motion artifacts, and provides higher imaging resolution and hemodynamic parameters.
Smart Images
Figure CN120983077A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of ultrasound blood flow imaging technology, specifically to an ultrasound blood flow imaging method, electronic device, apparatus, system, and computer storage medium based on causal feature registration. Background Technology
[0002] Ultrasound imaging technology has become an indispensable imaging examination tool in clinical diagnosis due to its advantages such as high safety, non-invasiveness, ease of operation, and ability to acquire hemodynamic parameters in real time.
[0003] However, in actual clinical ultrasound imaging applications, motion artifacts can lead to a serious loss of image quality, especially a significant decrease in the imaging effect of small blood vessels, which seriously affects clinical judgment.
[0004] In recent years, the emergence of ultrasonic positioning microscopy technology has greatly improved the resolution and image quality of ultrasonic imaging.
[0005] However, while it can provide more detailed vascular structures and hemodynamic parameters of the imaging area, it also places higher demands on quasi-static ultrasound acquisition, which further amplifies the impact of motion artifacts.
[0006] Previous image registration methods based on similarity or feature point matching could only detect feature points on larger structures, and could not register fine structures such as small blood vessels whose diameter corresponds to only a few pixels. Therefore, how to more effectively register fine structures such as small blood vessels has become an important and challenging problem that needs to be solved in the field of ultrasound blood flow imaging. Summary of the Invention
[0007] To address the aforementioned technical problems, this invention discloses an ultrasound blood flow imaging, electronic device, apparatus, system, and computer storage medium based on causal feature registration.
[0008] Specifically, the ultrasound blood flow imaging method based on causal feature registration includes the following steps: Step 10 involves processing the N frames of ultrasonic echo IQ complex signals acquired from the moving target through spatiotemporal matrix decomposition and wall filtering to obtain the wall-filtered N frames of complex spatiotemporal matrix Z; preferably, N is not less than 500 frames; the composite frame rate of ultrasonic imaging B mode is not less than 500 Hz; and singular value decomposition is used for spatiotemporal matrix decomposition. Step 20 involves taking the modulus of Z frame by frame to construct matrix Y1; Step 30 is responsible for detecting the morphological configuration primitive C in Y frame by frame and recording its structure T and position P; Step 40 is responsible for measuring the morphological configuration primitive structure T in Y frame by frame. i The morphological configuration primitive structure T of the selected quasi-static frame SS Based on the causal strength and topological isomorphism between them, a comprehensive scoring matrix A is constructed. i ; Step 50: Based on the comprehensive scoring matrix A and the position of the morphological configuration primitive P, construct the deformation field F frame by frame, and apply the deformation field of each frame to the corresponding frame in Y to obtain the registered image W. Step 60 involves temporally stitching together all the registered images to obtain high-definition ultrasound imaging results.
[0009] The electronic device for ultrasound blood flow imaging based on causal feature registration includes a processor, a memory storing executable instructions, and a storage medium; wherein, the processor is used to execute a computer program corresponding to the ultrasound blood flow imaging method based on causal feature registration; and the storage medium is responsible for storing the computer program corresponding to the ultrasound blood flow imaging method based on causal feature registration and imaging data.
[0010] The ultrasound blood flow imaging device based on causal feature matching includes: an ultrasound imaging acquisition module S1 for acquiring ultrasound echo IQ complex signals from a moving target; a preprocessing module M1 for performing wall filtering on the N frames of ultrasound echo IQ complex signals acquired from the moving target, and performing frame-by-frame modulus extraction on the filtered Z to construct a matrix Y; a morphological configuration primitive detection module M2 for detecting morphological configuration primitives C in Y and recording their structure T and position P; and a scoring module M3 for measuring the structure T of each frame of morphological configuration primitives in Y. i The morphological configuration primitive structure T of the selected quasi-static frame S S The causal strength and topological isomorphism between the two are used to construct a comprehensive scoring matrix A; the registration module M4 is used to calculate the deformation field F of each frame based on A and P, and apply the deformation field to the corresponding frame in Y to obtain the registered image; the result output module M5 is used to stitch the registration results in time sequence to obtain the registered high-definition ultrasound imaging results.
[0011] The ultrasound blood flow imaging system based on causal feature registration includes: an acquisition device for performing the first method; and the electronic device or imaging device.
[0012] The computer storage medium for ultrasound blood flow imaging based on causal feature registration includes: a computer program and imaging data corresponding to the ultrasound blood flow imaging based on causal feature registration, for the electronic device to execute the ultrasound blood flow imaging method based on causal feature registration. Attached Figure Description
[0013] Figure 1 The diagram shown is a schematic diagram of an ultrasound blood flow imaging method based on causal feature registration provided in an exemplary embodiment of this application.
[0014] Figure 2The diagram shown is a schematic representation of a module of an ultrasound blood flow imaging method based on causal feature matching provided in an exemplary embodiment of this application.
[0015] Figure 3 The diagram shown is a structural schematic of an electronic device provided in an embodiment of this application. Detailed Implementation
[0016] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.
[0017] Figure 1 The diagram shows an exemplary embodiment of the ultrasound blood flow imaging method and system based on causal feature registration provided in this application. It includes the following acquisition and calculation steps: Step 10 involves processing the N frames of ultrasonic echo IQ complex signals acquired from the moving target through spatiotemporal matrix decomposition and wall filtering to obtain the wall-filtered N frames of complex spatiotemporal matrix Z; preferably, N is not less than 500 frames; the composite frame rate of ultrasonic imaging B mode is not less than 500 Hz; and singular value decomposition is used for spatiotemporal matrix decomposition. In this exemplary embodiment, 500 frames of IQ complex signals are acquired and demodulated using 7-angle plane wave coherent composite imaging technology; the composite frame rate of ultrasound imaging B mode is 500 Hz; the IQ complex signals are decomposed using singular value decomposition method, the first 10% of the eigenvalues are removed to filter out stationary tissue signals in the IQ complex signals, and the complex spatiotemporal matrix Z is reconstructed.
[0018] Step 20 involves taking the modulus of Z frame by frame to construct matrix Y; where Y has a size of W×H×N. In this exemplary embodiment, the complex spatiotemporal matrix Z of the 500 frames after wall filtering is moduloed frame by frame to construct the real matrix Y, which is the ultrasound contrast video sequence.
[0019] Step 30 is responsible for detecting the morphological configuration primitive C in Y frame by frame and recording its structure T and position P; In this exemplary embodiment, the Harris corner detection method is used frame by frame to identify the branch points and vascular terminal points of the bleeding flow structure. The amplitude fluctuation of the 5×5 rectangular region centered on the corner point is taken as the structure T; the coordinates corresponding to the corner point are taken as the position P of the morphological configuration primitive.
[0020] Step 40 is responsible for measuring the structure T of the morphological configuration primitives in Y frame by frame. i The morphological configuration primitive structure T of the selected quasi-static frame SS The causal strength and topological isomorphism between them were determined, and a comprehensive scoring matrix A was constructed. i ; In this exemplary embodiment, the starting frame of Y is selected as the frame, and T is calculated using the convergent cross-mapping method and the homeomorphism method, respectively. i The causal strength and topological isomorphism of each morphological configuration primitive in T1 and each morphological configuration primitive in T1 are compared, and the two scores are weighted at a 1:1 ratio to obtain the comprehensive score matrix A. i .
[0021] Step 50 is responsible for constructing the deformation field F frame by frame based on the comprehensive scoring matrix A and the position information P of the morphological configuration primitives, and applying the deformation field to the corresponding frame of Y to obtain the registered image; In this exemplary embodiment, A1 and A are compared frame by frame. i (i = 2, 3, …, N) Hungarian matching is performed, assuming that the two matching morphological configuration primitives correspond to the same blood vessel. Based on the matching results of the morphological configuration primitives and the corresponding position information P, the deformation vectors of the two morphological configuration primitives can be calculated. After all the morphological configuration primitive results are calculated, the deformation field between the two frames can be obtained. Applying the deformation field to the corresponding frame image can obtain the image registered with Y1.
[0022] Step 60 involves temporally stitching together all the registered images to obtain high-definition ultrasound imaging results.
[0023] In this exemplary embodiment, the registration results are sorted and stitched according to timestamps and then smoothed in the time domain to obtain the registered high-definition ultrasound imaging results.
[0024] Figure 2 A schematic diagram of a module for an exemplary embodiment of the ultrasound blood flow imaging method based on causal feature registration provided in this application. It includes: The preprocessing module M1 is responsible for performing wall filtering on the N frames of ultrasonic echo IQ complex signals acquired from the moving target, and performing frame-by-frame modulus extraction on the filtered Z to construct matrix Y; The morphological configuration primitive detection module M2 is responsible for detecting the morphological configuration primitive C in Y frame by frame. i (i = 1, 2, N) and record its structure T i and position P i ; The scoring module M3 is responsible for measuring the structure T of the morphological configuration primitives in Y frame by frame. i The morphological configuration primitive structure T of the selected quasi-static frame S S The causal strength and topological isomorphism between them were determined, and a comprehensive scoring matrix A was constructed. i ; The registration module M4 is responsible for calculating the deformation field F of each frame based on A and P, and applying the deformation field to the corresponding frame in Y to obtain the registered image. The output module M5 is responsible for sequentially stitching together the registration results of each frame to obtain the registered high-definition ultrasound imaging results.
[0025] Below, for reference Figure 3 The electronic device described in this application is described.
[0026] As shown in the figure, the electronic device 70 includes one or more processors 701 and memory 702. The processor 701 may be a central processing unit (CPU) or other form of processing unit with data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device 70 to perform desired functions.
[0027] The memory 702 may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and / or high-level cache. The non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 701 may execute the program instructions to implement the ultrasound blood flow imaging method based on causal feature registration of the various embodiments of this application described above, and / or other desired functions. The computer-readable storage medium may also store various contents such as the complex spatiotemporal matrix Z after wall filtering, matrix Y, morphological configuration primitive C, comprehensive scoring matrix A, deformation field F, high-definition ultrasound blood flow imaging results, etc.
[0028] In one example, the electronic device 70 may also include an input device 703 and an output device 704, which are interconnected via a bus system and / or other forms of connection mechanism (not shown).
[0029] The input device 703 may include, for example, a keyboard, a mouse, etc.
[0030] The output device 704 can output various information to the outside, such as the wall-filtered complex spatiotemporal matrix Z, matrix Y, morphological configuration primitive C, comprehensive scoring matrix A, deformation field F, and high-definition ultrasound blood flow imaging results. The output device 704 may include, for example, a display, speaker, printer, and communication network and its connected remote output devices, etc.
[0031] Of course, for the sake of simplicity, Figure 3This illustration only shows some of the components of the electronic device 70 relevant to this application; components such as buses, input / output interfaces, etc., are omitted. In addition, the electronic device 70 may include any other suitable components depending on the specific application.
[0032] In addition to the methods and apparatus described above, embodiments of this application may also be computer program products comprising computer program instructions that, when executed by a processor, cause the processor to perform the steps in the ultrasound image registration method based on causal feature matching according to various embodiments of this application described above.
[0033] The computer program product can be written in any combination of one or more programming languages to perform the operations of the embodiments of this application. The programming languages include object-oriented programming languages such as Java and C++, as well as conventional procedural programming languages such as C or similar languages. The program code can be executed entirely on the user's computing device, partially on the user's computing device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.
[0034] Furthermore, embodiments of this application may also be computer-readable storage media storing computer program instructions thereon, which, when executed by a processor, cause the processor to perform the steps in ultrasound blood flow imaging based on causal feature registration according to the various embodiments of this application described above.
[0035] The computer-readable storage medium may be any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may, for example, include, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatuses, or devices, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: electrical connections having one or more wires, portable disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.
[0036] The basic principles of this application have been described above with reference to specific embodiments. However, it should be noted that the advantages, benefits, and effects mentioned in this application are merely examples and not limitations, and should not be considered as essential features of each embodiment of this application. Furthermore, the specific details disclosed above are for illustrative and facilitative purposes only, and are not limitations. These details do not limit the application to the necessity of employing the aforementioned specific details for implementation.
[0037] The block diagrams of devices, apparatuses, devices, and systems involved in this application are merely illustrative examples and are not intended to require or imply that they must be connected, arranged, or configured in the manner shown in the block diagrams. As those skilled in the art will recognize, these devices, apparatuses, devices, and systems can be connected, arranged, and configured in any manner. Words such as “comprising,” “including,” “having,” etc., are open-ended terms meaning “including but not limited to,” and are used interchangeably with them. The terms “or” and “and” as used herein refer to the terms “and / or,” and are used interchangeably with them unless the context clearly indicates otherwise. The term “such as” as used herein refers to the phrase “such as but not limited to,” and is used interchangeably with it.
[0038] It should also be noted that in the apparatus, equipment, and methods of this application, the components or steps can be disassembled and / or recombined. These disassemblies and / or recombinations should be considered as equivalent solutions of this application.
[0039] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use this application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein can be applied to other aspects without departing from the scope of this application. Therefore, this application is not intended to be limited to the aspects shown herein, but rather to be accorded the widest scope consistent with the principles and novel features disclosed herein.
[0040] The above description has been given for purposes of illustration and description. Furthermore, this description is not intended to limit the embodiments of this application to the forms disclosed herein. Although numerous exemplary aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, alterations, additions, and sub-combinations thereof.
Claims
1. A high-definition ultrasound blood flow imaging method, characterized in that, Using the causal intensity of typical morphological configuration primitives in the spatiotemporal matrix of the ultrasonic echo IQ complex signal acquired from moving targets as features, the causal intensity and topological isomorphism of multiple configuration primitives in each frame are comprehensively matched to obtain the deformation field corresponding to each frame, ultimately yielding the registered high-definition ultrasonic imaging result; including the following steps: 1) The N frames of ultrasonic echo IQ complex signals acquired from the moving target are subjected to spatiotemporal matrix decomposition and wall filtering to obtain the wall-filtered N frames of complex spatiotemporal matrix Z; wherein, the size of each frame image is W×H, and the size of the IQ complex signal Z is W×H×N; preferably, the spatiotemporal matrix decomposition adopts singular value decomposition. 2) For Z, obtain matrix Y by taking the modulus frame by frame; where the size of Y should be W×H×N; 3) For Y, detect the image Y frame by frame. i Morphological configuration unit C in i j (i = 1, 2, N; j = 1, 2, M) i ); where C i j The structure T of the corresponding primitive i j and its corresponding position P i j M i The number of morphological configuration primitives detected in the i-th frame; 4) Select the S-th frame Y from Y. S As a quasi-static frame, T is measured. S With Y i Medium morphological configuration primitive structure T i The causal strength and topological isomorphism of the two indicators were determined, and a comprehensive scoring matrix A combining the two indicators was obtained. i ; 5) Regarding A i and Y i Position of the morphological configuration unit P i Construct Y i The deformation field F relative to the quasi-static frame i ; 6) The deformation field F i Acting on Y i The selected frame is registered to obtain the image W. i ; 7) Repeat steps 4)-6) for each frame in Y), and register the results of each frame W. i Time-series stitching is performed to obtain the final registered high-definition ultrasound imaging results.
2. The ultrasound blood flow imaging method according to claim 1, characterized in that, For Y, detect image Y frame by frame. i Morphological configuration unit C in i j (i = 1, 2, N; j = 1, 2, M) i The morphological configuration primitive detection methods include edge detection methods, corner detection methods, connected component detection, line detection based on Hough transform, circle detection based on Hough transform, geometry detection based on morphology, blood vessel detection based on Frangi filtering, geometry detection based on graphs, and geometry detection based on neural operators.
3. The ultrasound blood flow imaging method according to claim 1, characterized in that, Select the S-th frame Y from Y. S As a quasi-static frame, T is measured. S With Y i Medium morphological configuration primitive structure T i The causal strength and topological isomorphism of the two indicators were determined, and a comprehensive scoring matrix A combining the two indicators was obtained. i The quasi-static frame selection method includes selecting a start frame, selecting an intermediate frame, selecting an end frame, and a selection method based on cross-correlation; the causal strength measurement method includes Granger causality measurement, transition entropy causality measurement, convergent cross-mapping causality measurement, causal measurement based on a state-space model, and causal measurement based on dynamic mode decomposition; the topological isomorphism measurement method includes persistent homology measurement, Betti number measurement, homeomorphism mapping measurement, homology group measurement, Weisfeiler-Lehman measurement, vascular skeletonization measurement, shape context measurement, and topological measurement based on neural operators.
4. The ultrasound blood flow imaging method according to claim 1, characterized in that, Repeat steps 4)-6) for each frame in Y, and register the results of each frame W. i Time-series stitching is performed to obtain the registered high-definition ultrasound imaging results. The high-definition ultrasound imaging results can be further improved in terms of imaging quality and resolution by combining ultrasound super-resolution strategies. The ultrasound super-resolution strategies include ultrasound diffraction attenuation microscopy, entropy-based radial super-resolution strategy, and trajectory diffusion function-based super-resolution strategy.
5. An electronic device comprising a processor and a computer storage medium storing processor-executable instructions, the processor being configured to execute the executable instructions to implement the method as claimed in any one of claims 1 to 4.
6. An imaging device, characterized in that, The imaging device is used to implement the imaging method of claims 1 to 5, comprising: The preprocessing module M1 is responsible for performing wall filtering on the N frames of ultrasonic echo IQ complex signals acquired from the moving target, and performing frame-by-frame modulus extraction on the filtered Z to construct matrix Y; The morphological configuration primitive detection module M2 is responsible for detecting the morphological configuration primitive C in Y frame by frame. i (i = 1, 2, N) and record its structure T i and position P i ; The scoring module M3 is responsible for measuring the structure T of the morphological configuration primitives in Y frame by frame. i The morphological configuration primitive structure T of the selected quasi-static frame S S The causal strength and topological isomorphism between them were determined, and a comprehensive scoring matrix A was constructed. i ; The registration module M4 is responsible for calculating the deformation field F of each frame based on A and P, and applying the deformation field to the corresponding frame in Y to obtain the registered image. The output module M5 is responsible for sequentially stitching together the registration results of each frame to obtain the registered high-definition ultrasound imaging results.
7. An imaging system, characterized in that, include: The ultrasonic imaging acquisition device S1 is responsible for acquiring the ultrasonic echo IQ complex signal; The electronic device as claimed in claim 5 or the imaging device as claimed in claim 6.
8. A computer storage medium, characterized in that, The computer storage medium is used to store processor-executable instructions so that the processor performs the imaging method according to any one of claims 1 to 4.