A system, method, apparatus, and medium for determining a microcirculatory resistance index
By combining multimodal medical imaging data to construct three-dimensional anatomical structures and Voronoi diagrams for hemodynamic simulation, the invasive nature of microcirculation resistance index detection has been solved, achieving non-invasive, rapid, and accurate detection results.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- RESEARCH INSTITUTE OF TRANSVASCULAR IMPLANTATION EQUIPMENT ZHEJIANG MEDICAL SECOND HOSPITAL BINJIANG DISTRICT HANGZHOU
- Filing Date
- 2026-04-09
- Publication Date
- 2026-07-14
AI Technical Summary
The detection of microcirculation resistance index in existing technologies requires invasive methods, which leads to harm to subjects and high costs, limiting its clinical application.
By combining multimodal medical imaging data, and through data acquisition, automatic segmentation, myocardial flow determination, and coronary blood flow simulation modules, a three-dimensional anatomical structure and Voronoi diagram are constructed to perform hemodynamic simulation and calculate the microcirculation resistance index.
It achieves rapid, accurate, economical, safe, and non-invasive detection of the microcirculation resistance index, reducing the harm caused by invasive testing.
Smart Images
Figure CN122376148A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of non-invasive diagnostic technology for cardiovascular diseases, and in particular to a system, method, device and medium for determining the microcirculation resistance index. Background Technology
[0002] Abnormalities in the function and structure of the coronary microcirculation can lead to myocardial perfusion and ischemic injury. The mechanism may be related to poor remodeling of small arteries and impaired systolic and diastolic function. This condition is usually referred to as coronary microvascular dysfunction, which is an important cause of coronary heart disease.
[0003] The index of microcirculatory resistance (IMR) is an emerging indicator for evaluating coronary microvascular function in recent years and is considered the gold standard for invasive detection of coronary microvascular dysfunction. Related techniques include measuring IMR using invasive pressure guidewires and thermodilution methods. However, these methods require punctures, which may cause harm to the subject and are expensive, thus limiting their large-scale clinical application. Summary of the Invention
[0004] This invention provides a system, method, device, and medium for determining the microcirculation resistance index (IMR). By combining multimodal medical imaging data and comprehensively considering the overall impact of coronary arteries and collateral circulation on downstream myocardial perfusion, it achieves rapid, accurate, economical, safe, and non-invasive IMR detection, effectively reducing the harm caused by invasive detection methods.
[0005] According to one aspect of the present invention, a system for determining the microcirculation resistance index is provided, the system comprising a data acquisition module, an automatic segmentation module, a myocardial flow determination module, a coronary blood flow simulation module, and a parameter calculation module; wherein: The data acquisition module is used to acquire coronary CTA information and myocardial CTP information of the target object, and to perform data preprocessing on the coronary CTA information and myocardial CTP information; The automatic segmentation module is used to determine the three-dimensional anatomical structure based on the pre-trained automatic segmentation model and the pre-processed coronary CTA information; wherein the three-dimensional anatomical structure is used to describe the geometry of the epicardial coronary artery and its downstream perfused myocardium. The myocardial blood flow determination module is used to determine the Voronoi diagram based on the three-dimensional anatomical structure, and to determine the myocardial blood flow supplied by each coronary artery based on the Voronoi diagram and preprocessed myocardial CTP information; wherein, the Voronoi diagram is used to construct a complete segmentation of the three-dimensional myocardium; The coronary blood flow simulation module is used to perform hemodynamic simulation of the epicardial coronary arteries of the target object based on the three-dimensional anatomical structure and the myocardial blood flow supplied by each coronary artery; The parameter calculation module is used to determine the microcirculation resistance index of the target coronary artery segment based on the simulation results and the three-dimensional anatomical structure.
[0006] According to another aspect of the present invention, a method for determining a microcirculation resistance index is provided, the method comprising: The coronary CTA information and myocardial CTP information of the target object are acquired through the data acquisition module, and the coronary CTA information and the myocardial CTP information are preprocessed. The three-dimensional anatomical structure is determined by an automatic segmentation module based on a pre-trained automatic segmentation model and pre-processed coronary CTA information; wherein the three-dimensional anatomical structure is used to describe the geometry of the epicardial coronary artery and its downstream perfused myocardium. The myocardial blood flow determination module determines the Voronoi diagram based on the three-dimensional anatomical structure, and determines the myocardial blood flow supplied by each coronary artery based on the Voronoi diagram and preprocessed myocardial CTP information; wherein, the Voronoi diagram is used to construct a complete segmentation of the three-dimensional myocardium; The coronary blood flow simulation module performs hemodynamic simulation of the epicardial coronary arteries of the target object based on the three-dimensional anatomical structure and the myocardial blood flow supplied by each coronary artery; The microcirculation resistance index of the target coronary artery segment is determined by the parameter calculation module based on the simulation results and the three-dimensional anatomical structure.
[0007] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising: At least one processor; and, A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the method for determining the microcirculation resistance index as described in any embodiment of the present invention.
[0008] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the method for determining the microcirculation resistance index as described in any embodiment of the present invention.
[0009] The technical solution of this invention proposes a system for determining the microcirculation resistance index. This system includes a data acquisition module, an automatic segmentation module, a myocardial flow determination module, a coronary blood flow simulation module, and a parameter calculation module. Specifically: the data acquisition module acquires coronary CTA and myocardial CTP information of the target object and performs data preprocessing on the coronary CTA and myocardial CTP information; the automatic segmentation module determines the three-dimensional anatomical structure based on a pre-trained automatic segmentation model and the preprocessed coronary CTA information; wherein the three-dimensional anatomical structure describes the geometry of the epicardial coronary artery and its downstream perfused myocardium; the myocardial flow determination module determines the Voronoi diagram based on the three-dimensional anatomical structure and determines the myocardial blood flow supplied by each coronary artery based on the Voronoi diagram and the preprocessed myocardial CTP information; wherein the Voronoi diagram is used to construct a complete segmentation of the three-dimensional myocardium; the coronary blood flow simulation module performs hemodynamic simulation of the epicardial coronary artery of the target object based on the three-dimensional anatomical structure and the myocardial blood flow supplied by each coronary artery; and the parameter calculation module determines the microcirculation resistance index of the target coronary artery segment based on the simulation results and the three-dimensional anatomical structure. This technical solution combines multimodal medical imaging data and comprehensively considers the overall impact of coronary arteries and collateral circulation on downstream myocardial perfusion, achieving rapid, accurate, economical, safe, and non-invasive IMR detection, which can effectively reduce the harm caused by invasive detection methods.
[0010] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description
[0011] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0012] Figure 1 This is a schematic diagram of a system for determining the microcirculation resistance index according to an embodiment of the present invention; Figure 2 This is a structural diagram of an automatic segmentation model provided according to an embodiment of the present invention; Figure 3 This is a schematic diagram of a manual segmentation result provided by an embodiment of the present invention; Figure 4 This is a schematic diagram of a Voronoi diagram provided according to an embodiment of the present invention; Figure 5This is a schematic diagram of the matching between the coronary artery outlet and the myocardial region according to an embodiment of the present invention; Figure 6 This is a schematic diagram of myocardial blood flow supplied by a coronary artery, according to an embodiment of the present invention. Figure 7 This is a schematic diagram of a mesh division according to an embodiment of the present invention; Figure 8 This is a schematic diagram of a simulation result provided by an embodiment of the present invention; Figure 9 This is a flowchart of a method for determining a microcirculation resistance index according to an embodiment of the present invention; Figure 10 This is a schematic diagram of the structure of an electronic device that implements a method for determining a microcirculation resistance index according to an embodiment of the present invention. Detailed Implementation
[0013] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.
[0014] It should be noted that the terms "first," "second," "target," etc., used in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.
[0015] Example 1 Figure 1 This is a schematic diagram of a microcirculation resistance index determination system provided in Embodiment 1 of the present invention. This embodiment is applicable to situations where IMR is detected quickly, accurately, economically, and safely using a non-invasive method. The microcirculation resistance index determination system can be implemented in hardware and / or software and can be configured in an electronic device with data processing capabilities.
[0016] like Figure 1 As shown, the system includes a data acquisition module, an automatic segmentation module, a myocardial flow determination module, a coronary blood flow simulation module, and a parameter calculation module. Specifically: the data acquisition module acquires coronary CTA and myocardial CTP information of the target object and performs data preprocessing on these information; the automatic segmentation module determines the three-dimensional anatomical structure based on a pre-trained automatic segmentation model and the preprocessed coronary CTA information; the three-dimensional anatomical structure describes the geometry of the epicardial coronary arteries and their downstream perfused myocardium; the myocardial flow determination module determines the Voronoi diagram based on the three-dimensional anatomical structure and determines the myocardial blood flow supplied by each coronary artery based on the Voronoi diagram and the preprocessed myocardial CTP information; the Voronoi diagram is used to construct a complete segmentation of the three-dimensional myocardium; the coronary blood flow simulation module performs hemodynamic simulation of the epicardial coronary arteries of the target object based on the three-dimensional anatomical structure and the myocardial blood flow supplied by each coronary artery; and the parameter calculation module determines the microcirculation resistance index of the target coronary artery segment based on the simulation results and the three-dimensional anatomical structure.
[0017] CTA (Computed Tomography Angiography) and CTP (Computed Tomography Perfusion) are both used in this invention. It should be noted that the coronary arteries or coronary arteries mentioned in this invention refer to the epicardial coronary arteries. Coronary CTA information refers to image data obtained by performing a CTA scan on the coronary arteries. Myocardial CTP information refers to image data obtained by scanning the myocardium after perfusion. The target subject can be the subject (e.g., a patient) who needs to be assessed for microcirculatory resistance.
[0018] In this embodiment, patient clinical data and laboratory test data can be collected in advance to construct a clinical database. The analysis examines whether there are statistically significant differences in clinical data between patients with normal and impaired microcirculation function in different specific cardiovascular diseases, screens clinical indicators related to microcirculation function, and explores the correlations between these indicators to provide clinical information for the subsequent construction of a precise assessment system. By constructing a clinical database, target patients can be accurately screened, avoiding unnecessary invasive coronary angiography and invasive functional examinations of the large and micro coronary vessels.
[0019] During the data acquisition phase, coronary CTA information and myocardial CTP information of the target subject can be acquired separately through the system's data acquisition module. Coronary CTA information is obtained by performing a coronary CTA scan on the target subject, while myocardial CTP information is obtained by scanning the target subject after myocardial perfusion. Specifically, for coronary CTA scanning, prospective ECG-gated scanning is performed according to a preset scanning protocol (65 ml of contrast agent is injected at a rate of 5.0 ml / s, and 30 ml of normal saline is injected at the same rate). During the scan, adaptive sequence prospective ECG-gated triggering technology is activated. If the target subject's heart rate is ≤70 beats / min, the full-dose window is set within 65%-75% of the RR interval; if the target subject's heart rate is >70 beats / min, the full-dose window is set within 35%-45% of the RR interval. For myocardial perfusion scanning, myocardial perfusion was performed approximately 5 minutes after coronary artery scanning. The scanning program was initiated (50 ml contrast agent, rate 6 ml / s; 40 ml saline, rate 6 ml / s), and the ECG gating trigger point was set at end-systole (this is the optimal systolic phase, approximately 250 ms after the R peak). The dynamic shuttle scanning process lasted approximately 30 seconds. The perfusion image slice thickness was 3 mm, the interval was 2 mm, and the convolution was B25. The scanning parameters were: 2 × 100 kV tube voltage; tube current per rotation 300 mAs; gantry rotation time 0.28 s; collimation 128 × 0.6 mm; Z-axis coverage 73 mm.
[0020] To improve the standardization and quality of the data, after obtaining coronary CTA and myocardial CTP information, data preprocessing is required to reduce the adverse effects caused by inconsistent scanning parameters and smoothing noise. Data preprocessing mainly includes data resampling, signal intensity normalization, and image denoising. This effectively standardizes the image, removes noise, and maintains clear image boundaries, laying the groundwork for subsequent image segmentation.
[0021] The automatic segmentation model can refer to a machine learning model capable of automatically segmenting the coronary arteries and their downstream perfused myocardium based on coronary CTA information. Optionally, the automatic segmentation model is built based on a 3D UNet, such as... Figure 2As shown in the diagram. Here, `input` represents the input, `output` represents the output, `conv n×n` indicates convolution using an n×n kernel, `ReLU` (Rectified Linear Unit) is the activation function, `copy and crop` is a feature fusion technique used to address the mismatch in feature map sizes during downsampling (dimensionality reduction) and upsampling (dimensionality increase), `max pool n×n` indicates max pooling using an n×n window, and `up-conv` represents transposed convolution. It should be noted that due to the significant individual differences in coronary artery structure, the currently used AHA 17-segment myocardial model and bullseye map are insufficient to accurately and individually describe the myocardial regions supplied by the coronary arteries. This invention uses a 3DUNet convolutional neural network to construct an automatic segmentation model. This model can automatically segment the epicardial coronary arteries and their downstream perfused myocardium, generating a target-specific epicardial coronary artery tree and a three-dimensional anatomical model of the downstream perfused myocardium, enabling precise extraction of anatomical information from image data.
[0022] Specifically, the training process of the automatic segmentation model is as follows: (1) Constructing training data: Coronary CTA scans are performed on candidate subjects to obtain candidate coronary CTA information, and the candidate coronary CTA information is preprocessed to obtain training data. Among them, candidate subjects can refer to the subjects participating in model training, and candidate coronary CTA information can refer to the coronary CTA information corresponding to the candidate subjects, specifically in the form of thin-slice DICOM format images. (2) Determining data labels: Cardiovascular radiologists with more than 5 years of clinical experience manually segment the preprocessed coronary CTA images of the coronary arteries and their downstream perfused myocardium. The segmentation results are used as data labels (gold standard), which can be found in [reference]. Figure 3 (3) Building the basic model: Based on the traditional FCN (Fully Convolutional Network), the three-dimensional information of blood vessels is incorporated to improve the segmentation accuracy. Non-local neural network blocks are added to include the correlation information of the characteristics around the blood vessels in the calculation, thereby expanding the receptive area for feature acquisition. It should be noted that the traditional FCN image segmentation method is designed for the segmentation of two-dimensional natural images, which have high resolution and low noise. However, CTA images have low resolution and high noise, so the traditional FCN needs to be improved. (4) Model training: The basic model is trained under supervision based on the training data and data labels, and the trained basic model is determined as the automatic segmentation model.
[0023] In this embodiment, after obtaining the preprocessed coronary CTA information of the target object, the preprocessed coronary CTA information can be used to automatically segment the epicardial coronary artery and its downstream perfused myocardium using the automatic segmentation model deployed in the automatic segmentation module, thereby quickly and accurately generating a three-dimensional anatomical structure to describe the geometry of the epicardial coronary artery and its downstream perfused myocardium.
[0024] The Voronoi diagram consists of a set of continuous polygons formed by the perpendicular bisectors of lines connecting two adjacent points. Given N distinct points in a plane, the plane is divided according to the nearest neighbor principle. Each point is associated with its nearest neighbor region, and each region is called a cell. The core of each cell is a site. When the location of a site is determined, the cell is uniquely determined, such as... Figure 4 As shown. In this embodiment, after obtaining the three-dimensional anatomical structure, the myocardial flow determination module can determine the Voronoi diagram based on the three-dimensional anatomical structure to construct a complete segmentation of the three-dimensional myocardium.
[0025] In this embodiment, optionally, the myocardial flow determination module is further configured to: determine the three-dimensional center point of each coronary artery outlet based on the three-dimensional anatomical structure, and determine the Voronoi unit corresponding to each three-dimensional center point; project each three-dimensional center point onto a four-dimensional parabola to obtain a target projection point set, and determine the four-dimensional convex hull of the target projection point set; project the four-dimensional convex hull of the target projection point set onto three-dimensional space to obtain a Delaunay triangulation; determine the boundary of the Voronoi unit based on the dual surface of the Delaunay triangulation, and determine the Voronoi diagram based on the Voronoi unit and its boundary.
[0026] Specifically, firstly, based on the three-dimensional anatomical structure, a point set corresponding to each coronary artery effluent is determined. Each point set includes multiple points, which together depict a coronary artery effluent. Then, based on each point set, the three-dimensional center point of the corresponding coronary artery effluent is determined, and this three-dimensional center point represents the coronary artery effluent. Thus, all coronary artery effluents can be represented as: ,in, For the first The three-dimensional center point coordinates of each coronary artery exit. This represents the total number of coronary artery exits. For each three-dimensional center point, the corresponding Voronoi element can be determined using the following formula: .in, A point inside the myocardium. Euclidean distance. Voronoi diagram for all. The set of elements constitutes a complete segmentation of the three-dimensional myocardium.
[0027] The Voronoi diagram and Delaunay triangulation are dual to each other, and the boundary of a Voronoi cell can be determined based on this duality. If two points on the coronary artery... and Voronoi elements sharing a face are connected by edges in the Delaunay triangulation. Voronoi diagrams can be efficiently generated by calculating the Delaunay triangulation. Specifically, each 3D center point is first projected onto a 4D parabolic surface. The target projection point set can be obtained from the above. ,in, Then, the QuickHull method is used to calculate the four-dimensional convex hull corresponding to the target projection point set, which can be specifically represented as: .in, The four-dimensional convex hull is a set of points that contain the target projection points. The minimal convex set of all points, where any point within the four-dimensional convex hull can be represented as A weighted average of all points; The weighting coefficients determine the proportion of each coronary artery exit point when synthesizing new points within the four-dimensional convex hull. This, in turn, shapes the four-dimensional convex hull. Projecting back into 3D space yields the Delaunay triangulation. , represented as .in, For each coronary exit point ,That The boundary is determined by the dual face of the Delaunay triangulation, that is: .in, Indicates the coronary exit point corresponding boundary, for The set of nearest neighbors in the Delaunay triangulation. This formula describes how to determine the boundary of a Voronoi cell. The boundary consists of multiple faces, each a set of points equidistant from the exit points of two adjacent coronary arteries. Define all points in the space and points Equal distances on the myocardium A set of.
[0028] After determining the Voronoi diagram, the myocardial blood flow supplied by each coronary artery can be determined based on the Voronoi diagram and preprocessed three-dimensional myocardial CTP information. In this embodiment, optionally, the myocardial flow determination module is further configured to: divide the myocardium into multiple regions based on the Voronoi diagram; determine the correlation between the coronary artery outlet and the myocardial regions based on the region division results; and determine the myocardial blood flow supplied by each coronary artery based on the preprocessed myocardial CTP information and the correlation between the coronary artery outlet and the myocardial regions.
[0029] Specifically, it is necessary to determine each point. To determine which coronary artery effluent Voronoi unit it belongs to, the specific rules are as follows: The Voronoi unit corresponding to the nearest coronary artery effluent point is assigned to that effluent. Points belonging to the same coronary artery effluent point form a plane called the perpendicular bisector, which divides the myocardium into different regions. Each region of the myocardium is connected to its nearest terminal arterial branch, thus assigning all sub-myocardial volumes to different coronary artery effluents, such as... Figure 5 As shown, this allows us to determine the relationship between the coronary artery estuary and the myocardial region. Furthermore, this can be achieved through the formula... The myocardial blood flow supplied by each coronary artery was determined, and the results were as follows: Figure 6 As shown. Among them, Voxel volume (mL) The number of voxels; The myocardial blood flow (mL / min / g) corresponding to the voxel can be obtained from the preprocessed myocardial CTP information.
[0030] Next, the coronary blood flow simulation module can be used to perform hemodynamic simulation of the epicardial coronary arteries of the target object based on the three-dimensional anatomical structure and the myocardial blood flow supplied by each coronary artery, thereby simulating the hemodynamic environment of the coronary arteries. In this embodiment, optionally, the coronary blood flow simulation module is also used to: use the myocardial blood flow supplied by each coronary artery as the target boundary condition; perform mesh generation on the three-dimensional anatomical structure; and solve the target governing equations based on the mesh generation results and the target boundary conditions to obtain the simulation results.
[0031] It should be noted that in fluid dynamics (CFD), blood flow is a classical fluid motion, which can be described by the Navier-Stokes equations. For the sake of simplification, blood flow can be considered as a three-dimensional unsteady, incompressible Newtonian fluid flow, and the target governing equations can be simplified as follows: .in, For the speed of blood flow, For the density of blood, For fluid pressure, The viscosity of blood. The three-dimensional anatomical structure is divided into meshes, such as... Figure 7 As shown. The myocardial blood flow supplied by each coronary artery is used as the target boundary condition. The open-source software Simvascular solver is used to solve the target governing equations based on the mesh generation results and the target boundary conditions to obtain simulation results. Post-processing and visualization are then performed, as shown below. Figure 8 As shown, this allows us to obtain the average pressure value distal to the coronary artery stenosis corresponding to each coronary artery effluent.
[0032] After obtaining the hemodynamic simulation results, the target coronary artery segment can be selected as the region of interest, and the microcirculation resistance index of the target coronary artery segment can be calculated accordingly. In this embodiment, optionally, the parameter calculation module is also used to: determine the anatomical information of the target coronary artery segment based on the three-dimensional anatomical structure; wherein, the anatomical information includes the vessel length and vessel radius; determine the mean pressure distal to the stenosis of the target coronary artery segment based on the simulation results; determine the volume of the target coronary artery segment based on the anatomical information, and determine the ratio of the volume of the target coronary artery segment to the myocardial blood flow it supplies as the target ratio; determine the microcirculation resistance index of the target coronary artery segment based on the product of the target ratio and the mean pressure distal to the stenosis of the target coronary artery segment.
[0033] Specifically, the length and radius of the target coronary artery segment can be directly read based on the three-dimensional anatomical structure, and the mean pressure distal to the stenosis of the target coronary artery segment can be directly read based on the visualization results corresponding to the simulation results. Then, the formula can be used to... Calculate the microcirculation resistance index of the target coronary artery segment, where, and These represent the vessel length and vessel radius of the target coronary artery segment, respectively. The mean pressure distal to the stenosis of the target coronary artery segment. Indicates the volume of the target coronary artery segment. This indicates the myocardial blood flow supplied by the coronary artery to which the target coronary segment belongs (i.e., the myocardial blood flow supplied by the target coronary segment). This represents the target ratio.
[0034] In this embodiment, optionally, the system further includes a parameter correction module, which is used to: acquire reference data, which refers to the microcirculation resistance index of the target coronary artery segment determined based on the invasive pressure guidewire and temperature dilution method; determine whether the microcirculation resistance index of the target coronary artery segment determined by the parameter calculation module meets the accuracy requirements based on the reference data; if it does not meet the accuracy requirements, then correct the microcirculation resistance index of the target coronary artery segment determined by the parameter calculation module based on the reference data.
[0035] In this embodiment, to ensure the accuracy of non-invasive IMR detection, a parameter correction module is also set up in the system to verify and optimize the non-invasive IMR detection. First, the microcirculation resistance index of the target coronary artery segment determined based on invasive pressure guidewire and thermodilution method is obtained as reference data. Specifically, after angiography, a pressure guidewire measurement system can be used for examination, following standard operating procedures, and the average pressure Pa at the coronary ostium and the average pressure Pd distal to the coronary artery stenosis are recorded. The thermodilution method operation steps are as follows: 3 mL of room temperature 0.9% sodium chloride solution is injected. When the sodium chloride solution flows into the coronary ostium, the pressure guidewire axis records the first triggered temperature curve. When the sodium chloride solution flows to the sensor at the tip of the guidewire, the second triggered temperature curve is recorded. This operation is repeated three times to obtain the average conduction time of the two triggered curves. ATP at a dose of 160 μg / kg / min was used to induce maximum myocardial congestion, and Pd under hyperemia was measured. When the coronary arteries exhibit moderate stenosis, collateral circulation perfusion to the myocardium can be temporarily neglected, and a simplified formula can be used for calculation: .
[0036] After obtaining the reference data, the relative error between the reference data and the microcirculation resistance index of the target coronary artery segment determined by the parameter calculation module can be calculated. If the relative error is less than a preset threshold (e.g., 5%), the accuracy requirement is considered met; otherwise, it is considered not to meet the accuracy requirement. Furthermore, if the accuracy requirement is not met, the target control equation can be adjusted, and a new hemodynamic simulation can be performed based on the adjusted target control equation. The IMR is then recalculated based on the new simulation results until the accuracy requirement is met.
[0037] The technical solution of this invention proposes a system for determining the microcirculation resistance index. This system includes a data acquisition module, an automatic segmentation module, a myocardial flow determination module, a coronary blood flow simulation module, and a parameter calculation module. Specifically: the data acquisition module acquires coronary CTA and myocardial CTP information of the target object and performs data preprocessing on the coronary CTA and myocardial CTP information; the automatic segmentation module determines the three-dimensional anatomical structure based on a pre-trained automatic segmentation model and the preprocessed coronary CTA information; wherein the three-dimensional anatomical structure describes the geometry of the epicardial coronary artery and its downstream perfused myocardium; the myocardial flow determination module determines the Voronoi diagram based on the three-dimensional anatomical structure and determines the myocardial blood flow supplied by each coronary artery based on the Voronoi diagram and the preprocessed myocardial CTP information; wherein the Voronoi diagram is used to construct a complete segmentation of the three-dimensional myocardium; the coronary blood flow simulation module performs hemodynamic simulation of the epicardial coronary artery of the target object based on the three-dimensional anatomical structure and the myocardial blood flow supplied by each coronary artery; and the parameter calculation module determines the microcirculation resistance index of the target coronary artery segment based on the simulation results and the three-dimensional anatomical structure. This technical solution combines multimodal medical imaging data and comprehensively considers the overall impact of coronary arteries and collateral circulation on downstream myocardial perfusion, achieving rapid, accurate, economical, safe, and non-invasive IMR detection, which can effectively reduce the harm caused by invasive detection methods.
[0038] Example 2 Figure 9 This is a flowchart of a method for determining the microcirculation resistance index provided in Embodiment 2 of the present invention. This embodiment is applicable to situations where IMR is detected quickly, accurately, economically, and safely using a non-invasive method. This method can be executed by a microcirculation resistance index determination system and has the corresponding beneficial effects of the system.
[0039] like Figure 9 As shown, the method includes: S110, acquire coronary CTA information and myocardial CTP information of the target object through the data acquisition module, and perform data preprocessing on the coronary CTA information and the myocardial CTP information.
[0040] S120 uses an automatic segmentation module to determine the three-dimensional anatomical structure based on a pre-trained automatic segmentation model and pre-processed coronary CTA information.
[0041] Among them, the three-dimensional anatomical structure is used to describe the geometry of the epicardial coronary artery and its downstream perfused myocardium.
[0042] S130, the myocardial blood flow determination module determines the Voronoi diagram based on the three-dimensional anatomical structure, and determines the myocardial blood flow supplied by each coronary artery based on the Voronoi diagram and the preprocessed myocardial CTP information.
[0043] Among them, the Voronoi diagram is used to construct a complete segmentation of the three-dimensional myocardium.
[0044] S140, the coronary blood flow simulation module performs hemodynamic simulation of the epicardial coronary artery of the target object based on the three-dimensional anatomical structure and the myocardial blood flow supplied by each coronary artery.
[0045] S150, the microcirculation resistance index of the target coronary artery segment is determined by the parameter calculation module based on the simulation results and the three-dimensional anatomical structure.
[0046] Optionally, determining the Voronoi diagram based on the three-dimensional anatomical structure includes: The three-dimensional center point of each coronary artery outlet is determined based on the three-dimensional anatomical structure, and the Voronoi unit corresponding to each three-dimensional center point is determined. Project each of the three-dimensional center points onto a four-dimensional parabola to obtain a target projection point set, and determine the four-dimensional convex hull of the target projection point set; The four-dimensional convex hull of the target projection point set is projected onto three-dimensional space to obtain the Delaunay triangulation. The boundaries of the Voronoi elements are determined based on the dual faces of the Delaunay triangulation, and the Voronoi diagram is determined based on the Voronoi elements and their boundaries.
[0047] Optionally, the myocardial blood flow supplied by each coronary artery is determined based on the Voronoi diagram and preprocessed myocardial CTP information, including: Based on the Voronoi diagram, the myocardium is divided into multiple regions, and the correlation between the coronary artery outlet and the myocardial regions is determined according to the region division results. Based on the pre-processed myocardial CTP information and the correlation between the coronary artery outlet and the myocardial region, the myocardial blood flow supplied by each coronary artery was determined.
[0048] Optionally, hemodynamic simulation of the epicardial coronary arteries of the target object is performed based on the three-dimensional anatomical structure and the myocardial blood flow supplied by each coronary artery, including: The myocardial blood flow supplied by each coronary artery is used as the target boundary condition; The three-dimensional anatomical structure is meshed, and the target control equations are solved based on the meshing results and the target boundary conditions to obtain simulation results.
[0049] Optionally, the microcirculation resistance index of the target coronary artery segment is determined based on the simulation results and the three-dimensional anatomical structure, including: The anatomical information of the target coronary artery segment is determined based on the three-dimensional anatomical structure; wherein, the anatomical information includes vessel length and vessel radius; The mean pressure distal to the stenosis of the target coronary artery segment is determined based on the simulation results; The volume of the target coronary artery segment is determined based on the anatomical information, and the ratio of the volume of the target coronary artery segment to the myocardial blood flow it supplies is determined as the target ratio. The microcirculation resistance index of the target coronary artery segment is determined by multiplying the target ratio by the mean pressure distal to the stenosis of the target coronary artery segment.
[0050] Optionally, the method further includes: Reference data is obtained through the parameter correction module. The reference data refers to the microcirculation resistance index of the target coronary artery segment determined based on the invasive pressure guidewire and temperature dilution method. Based on the reference data, determine whether the microcirculation resistance index of the target coronary artery segment determined by the parameter calculation module meets the accuracy requirements; If the conditions are not met, the microcirculation resistance index of the target coronary artery segment determined by the parameter calculation module is corrected based on the reference data.
[0051] Optionally, the automatic segmentation model is built based on 3D UNet.
[0052] The technical solution of this invention first acquires coronary CTA and myocardial CTP information of the target object through a data acquisition module, and preprocesses the coronary CTA and myocardial CTP information. Then, an automatic segmentation module determines the three-dimensional anatomical structure based on a pre-trained automatic segmentation model and the preprocessed coronary CTA information. The three-dimensional anatomical structure is used to describe the geometry of the epicardial coronary artery and its downstream perfused myocardium. Next, a myocardial flow determination module determines the Voronoi diagram based on the three-dimensional anatomical structure, and determines the myocardial blood flow supplied by each coronary artery based on the Voronoi diagram and the preprocessed myocardial CTP information. The Voronoi diagram is used to construct a complete segmentation of the three-dimensional myocardium. Then, a coronary blood flow simulation module performs hemodynamic simulation of the epicardial coronary artery of the target object based on the three-dimensional anatomical structure and the myocardial blood flow supplied by each coronary artery. Finally, a parameter calculation module determines the microcirculation resistance index of the target coronary artery segment based on the simulation results and the three-dimensional anatomical structure. This technical solution, combining multimodal medical imaging data, comprehensively considers the overall impact of coronary arteries and collateral circulation on downstream myocardial perfusion, achieving rapid, accurate, economical, safe, and non-invasive IMR detection, effectively reducing the harm caused by invasive detection methods.
[0053] Example 3 Figure 10 A schematic diagram of an electronic device 10, which can be used to implement embodiments of the present invention, is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.
[0054] like Figure 10 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 can also store various programs and data required for the operation of the electronic device 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.
[0055] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.
[0056] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as the method for determining the microcirculation resistance index.
[0057] In some embodiments, the method for determining the microcirculation resistance index may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the method for determining the microcirculation resistance index described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the method for determining the microcirculation resistance index by any other suitable means (e.g., by means of firmware).
[0058] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.
[0059] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.
[0060] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.
[0061] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; 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 sound input, voice input, or tactile input).
[0062] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.
[0063] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.
[0064] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.
[0065] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.
Claims
1. A system for determining a microcirculation resistance index, characterized in that, The system includes a data acquisition module, an automatic segmentation module, a myocardial flow determination module, a coronary blood flow simulation module, and a parameter calculation module; wherein: The data acquisition module is used to acquire coronary CTA information and myocardial CTP information of the target object, and to perform data preprocessing on the coronary CTA information and myocardial CTP information; The automatic segmentation module is used to determine the three-dimensional anatomical structure based on the pre-trained automatic segmentation model and the pre-processed coronary CTA information; wherein the three-dimensional anatomical structure is used to describe the geometry of the epicardial coronary artery and its downstream perfused myocardium. The myocardial blood flow determination module is used to determine the Voronoi diagram based on the three-dimensional anatomical structure, and to determine the myocardial blood flow supplied by each coronary artery based on the Voronoi diagram and preprocessed myocardial CTP information; wherein, the Voronoi diagram is used to construct a complete segmentation of the three-dimensional myocardium; The coronary blood flow simulation module is used to perform hemodynamic simulation of the epicardial coronary arteries of the target object based on the three-dimensional anatomical structure and the myocardial blood flow supplied by each coronary artery; The parameter calculation module is used to determine the microcirculation resistance index of the target coronary artery segment based on the simulation results and the three-dimensional anatomical structure.
2. The system according to claim 1, characterized in that, The myocardial flow determination module is also used for: The three-dimensional center point of each coronary artery outlet is determined based on the three-dimensional anatomical structure, and the Voronoi unit corresponding to each three-dimensional center point is determined. Project each of the three-dimensional center points onto a four-dimensional parabola to obtain a target projection point set, and determine the four-dimensional convex hull of the target projection point set; The four-dimensional convex hull of the target projection point set is projected onto three-dimensional space to obtain the Delaunay triangulation. The boundaries of the Voronoi elements are determined based on the dual faces of the Delaunay triangulation, and the Voronoi diagram is determined based on the Voronoi elements and their boundaries.
3. The system according to claim 2, characterized in that, The myocardial flow determination module is also used for: Based on the Voronoi diagram, the myocardium is divided into multiple regions, and the correlation between the coronary artery outlet and the myocardial regions is determined according to the region division results. Based on the pre-processed myocardial CTP information and the correlation between the coronary artery outlet and the myocardial region, the myocardial blood flow supplied by each coronary artery was determined.
4. The system according to claim 3, characterized in that, The coronary blood flow simulation module is also used for: The myocardial blood flow supplied by each coronary artery is used as the target boundary condition; The three-dimensional anatomical structure is meshed, and the target control equations are solved based on the meshing results and the target boundary conditions to obtain simulation results.
5. The system according to claim 4, characterized in that, The parameter calculation module is also used for: The anatomical information of the target coronary artery segment is determined based on the three-dimensional anatomical structure; wherein, the anatomical information includes vessel length and vessel radius; The mean pressure distal to the stenosis of the target coronary artery segment is determined based on the simulation results; The volume of the target coronary artery segment is determined based on the anatomical information, and the ratio of the volume of the target coronary artery segment to the myocardial blood flow it supplies is determined as the target ratio. The microcirculation resistance index of the target coronary artery segment is determined by multiplying the target ratio by the mean pressure distal to the stenosis of the target coronary artery segment.
6. The system according to any one of claims 1-5, characterized in that, The system further includes a parameter correction module, which is used for: Obtain reference data, which refers to the microcirculation resistance index of the target coronary artery segment determined based on invasive pressure guidewire and temperature dilution method; Based on the reference data, determine whether the microcirculation resistance index of the target coronary artery segment determined by the parameter calculation module meets the accuracy requirements; If the conditions are not met, the microcirculation resistance index of the target coronary artery segment determined by the parameter calculation module is corrected based on the reference data.
7. The system according to claim 6, characterized in that, The automatic segmentation model is built on 3D UNet.
8. A method for determining a microcirculation resistance index, characterized in that, The method includes: The coronary CTA information and myocardial CTP information of the target object are acquired through the data acquisition module, and the coronary CTA information and the myocardial CTP information are preprocessed. The three-dimensional anatomical structure is determined by an automatic segmentation module based on a pre-trained automatic segmentation model and pre-processed coronary CTA information; wherein the three-dimensional anatomical structure is used to describe the geometry of the epicardial coronary artery and its downstream perfused myocardium. The myocardial blood flow determination module determines the Voronoi diagram based on the three-dimensional anatomical structure, and determines the myocardial blood flow supplied by each coronary artery based on the Voronoi diagram and preprocessed myocardial CTP information; wherein, the Voronoi diagram is used to construct a complete segmentation of the three-dimensional myocardium; The coronary blood flow simulation module performs hemodynamic simulation of the epicardial coronary arteries of the target object based on the three-dimensional anatomical structure and the myocardial blood flow supplied by each coronary artery; The microcirculation resistance index of the target coronary artery segment is determined by the parameter calculation module based on the simulation results and the three-dimensional anatomical structure.
9. An electronic device, characterized in that, The electronic device includes: At least one processor; and, A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the method for determining the microcirculation resistance index as described in claim 8.
10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the method for determining the microcirculation resistance index as described in claim 8.