Method for identifying heart vortex based on spatial domain vorticity deviation

Abstract

The invention discloses a method for identifying hydrodynamic vortexes based on spatial domain vorticity deviation. In the method, heart vortexes are used as demonstration cases. The method comprises the following steps that firstly, blood flow data in the heart are obtained through ultrasonic equipment and nuclear magnetic resonance equipment, the data represent the instantaneous blood flow speed, and the Euler vortex structure in the heart is identified; and then representing a complete Euler vortex structure through the center of the vortex and the boundary of the vortex, extracting vorticity in the boundary after identifying the Euler vortex of each stage, and representing the strength of the Euler vortex by calculating the average value of the vorticity. And finally, parameterizing and describing the evolutionary process of the heart vortex through the calculated Euler vortex strength of each period.

Description

Technical Field

[0001] The present invention relates to the technical field of medical image processing, and more specifically, to a method for identifying cardiac vortices based on spatial domain vorticity deviation. Background Art

[0002] In vivo and in vitro studies have shown that the vortex structure present in the ventricle during the filling and ejection periods is an important mechanism for regulating blood flow in the ventricle. In the early stage of diastolic filling, blood flows from the atrium to the ventricle at a high speed, and flows out of the ventricle during the systolic ejection period, both of which cause the blood to flow in a spiral and form a vortex ring. Studies have found that the spiral flow pattern of blood in the left ventricle is also related to the torsion of the left ventricle. The related torsion deforms the subendocardial fibrous matrix, resulting in the storage of potential energy. Therefore, the formation mechanism of ventricular vortices represents the health of the heart behind the ventricular diastolic and contraction process, and the vortex also plays a vital role in constructing the optimal blood outflow path.

[0003] At present, some progress has been made in the study of vortices in the blood flow process of the left ventricle. Kheradvar et al. studied the velocity series of the left ventricular spatial flow and used vorticity to describe the blood flow. In addition, the eight-point circulation method, the fourth-order central difference approximation method and the three-dimensional finite element interpolation method have been applied to evaluate the distribution of vorticity in the ventricles and atria. However, the above research methods mainly count the overall vortex field in the ventricles and atria, and do not extract features from the vortex area to clarify the influence of the dominant vortex on the flow field state in the heart. Therefore, a method is needed to accurately identify and quantify vortices in the heart in the spatial domain.

[0004] Most existing research methods attempt to identify vortex structures and quantify their strength during cardiac diastole and systole by using local flow information of the flow field. Various criteria based on local flow information of the blood flow field (such as Q-criterion, Ω-criterion, Δ-criterion and λ2-criterion) have been used to identify intracardiac vortices. Although the performance in terms of simplicity is satisfactory, the accuracy of these identification methods is far from satisfactory. However, the detection of vortices using the global flow information of the intracardiac blood flow field is sufficiently objective and accurate. Summary of the invention

[0005] The purpose of the present invention is to overcome the defects of the prior art and provide a method for identifying cardiac vortices based on spatial domain vorticity deviation. The method comprises the following steps:

[0006] First, the blood flow data in the heart is obtained by ultrasound equipment and nuclear magnetic resonance equipment, where the data represents the instantaneous blood flow velocity, and the Euler vortex structure in the heart is identified.

[0007] Then, the complete Euler vortex structure is represented by the center and boundary of the vortex. After identifying the Euler vortex at each stage, the vorticity within the boundary is extracted, and the intensity of the Euler vortex is represented by calculating the mean vorticity.

[0008] Finally, the evolution of the heart vortex is parameterized by calculating the Euler vortex strength at each period.

[0009] Compared with the prior art, the advantage of the present invention is that the method for identifying cardiac vortices based on spatial domain vortex deviation takes into account both local and global information of the flow field. Due to the locality and translation invariance of the convolution operation, the accuracy and efficiency of cardiac vortex identification are improved.

[0010] Further features and advantages of the present invention will become apparent from the following detailed description of exemplary embodiments of the present invention with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate embodiments of the invention and, together with the description, serve to explain the principles of the invention.

[0012] Figure 1 is a flow chart of a method for identifying cardiac vortices based on spatial domain vorticity deviation according to one embodiment of the present invention;

[0013] Figure 2 Demonstrated the measurement of blood flow data in the left ventricle and the vorticity calculation process based on VFM technology;

[0014] Figure 3 The Lagrangian vortex boundary and vortex center at time t0 (left) and time t1 (middle) are shown; the boundary of the Euler vortex (right);

[0015] Figure 4 It is a specific step to identify the Euler vortex in the left ventricle based on IVD and calculate its vortex strength;

[0016] Figure 5 Visualization of the segmentation results (green) of heart slices at each period compared with the manual segmentation results (red). DETAILED DESCRIPTION

[0017] Various exemplary embodiments of the present invention will now be described in detail with reference to the accompanying drawings. It should be noted that the relative arrangement of components and steps, numerical expressions and numerical values ​​set forth in these embodiments do not limit the scope of the present invention unless otherwise specifically stated.

[0018] The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the invention, its application, or uses.

[0019] Technologies, methods, and equipment known to ordinary technicians in the relevant art may not be discussed in detail, but where appropriate, the technologies, methods, and equipment should be considered part of the specification.

[0020] In all examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not limiting. Therefore, other examples of the exemplary embodiments may have different values.

[0021] It should be noted that like reference numerals and letters refer to similar items in the following figures, and therefore, once an item is defined in one figure, it need not be further discussed in subsequent figures.

[0022] Specifically, see Figure 1 As shown, the provided method for identifying cardiac vortices based on spatial domain vorticity deviation comprises the following steps:

[0023] Step S110, obtaining blood flow data.

[0024] This study included 45 healthy subjects and 45 patients with enlarged heart. All healthy subjects had normal blood pressure, normal electrocardiogram, and no history of cardiovascular disease. The study was approved by the local ethical review committee. All subjects underwent ultrasound examination, showing images of the heart 2-chamber, 3-chamber, 4-chamber and short-axis views. At the same time, multiple cardiac MRI slices were acquired using a nuclear magnetic resonance instrument, and the labeled images were manually segmented by medical experts. The performance of the cardiac chamber segmentation network developed based on U-Net was verified by the acquired dataset. During the study, the ultrasound equipment used was Prosound F75 ultrasound diagnostic instrument. During the color Doppler image acquisition process, a long-axis view, UST-52105 probe, a transducer frequency of 5MHz, a depth of 8cm, a focus of 5cm, and a frame rate of 29-57 were used. The ultrasound data images were captured in three consecutive heartbeats and stored on a built-in hard drive. Then, the blood flow visualization echocardiography technology, vector flow mapping (VFM) technology and analysis software (DAS-RS1, Hitachi Aloka Medical Ltd) were combined to draw the blood flow vector diagram in the left ventricle, and the complete electrocardiogram was recorded to provide a time indication for the flow, such as Figure 2 shown.

[0025] The blood flow state above the left ventricular mitral annulus is reconstructed from VFM data. VFM is a novel blood flow measurement technology that allows users to evaluate the blood flow velocity distribution within the cardiovascular system on the observation plane. This non-invasive velocity measurement technology relies on color Doppler acquisition and generates a blood flow velocity field on a two-dimensional image. VFM has no angle dependence or region of interest restrictions, making it superior to traditional Doppler techniques. VFM assumes two-dimensional flow and calculates the blood flow velocity by sequentially integrating the mass conservation equation and the heart wall velocity obtained by tissue tracking in the lateral direction. The accuracy of the blood flow velocity vector calculated by VFM was verified by comparing it with the velocity values ​​calculated by several reliable intracardiac blood flow velocity measurement methods.

[0026] Step S120, using the spatial domain vorticity deviation algorithm to identify the intra-core Euler vortex.

[0027] The algorithm idea is:

[0028] The flow trajectory of blood particles moving at velocity v within the heart is governed by the following differential equation:

[0029]

[0030] Define the flow mapping:

[0031]

[0032] Solve for the gradient of the blood flow map:

[0033]

[0034] It represents the change in the distance between two adjacent particles along the blood from position t0 to position t. It is not objective, and only considering the invariant cannot objectively reflect the rotational component of the motion. Through dynamic polar coordinate decomposition, the gradient is decomposed into the product of the rotation gradient and the strain gradient:

[0035]

[0036] Because it is a description of the vortex in the blood flow in the heart, the main reference is the dynamic rotation tensor, which satisfies dynamic consistency, that is, it satisfies the basic superposition property of solid rotation:

[0037]

[0038] Although the dynamic rotation tensor satisfies dynamic consistency, it is not objective. Therefore, it is necessary to determine the objective part of the blood rotation flow described and maintain its dynamic consistency. Using dynamic polar coordinates, it can be further decomposed into: relative rotation tensor and average rotation tensor:

[0039]

[0040] The relative rotation tensor satisfies dynamic consistency. The dynamic consistency of the relative rotation tensor means that the total angle swept by the tensor is dynamically consistent. This angle is expressed as the intrinsic rotation angle of the particle, denoted as. It is objective in both two-dimensional and three-dimensional blood flow fields, and the calculation expression is:

[0041]

[0042] Referring to the above formula, the Lagrangian-Averaged Vorticity Deviation (LAVD) is defined as twice the intrinsic rotation angle:

[0043]

[0044] Further deduction, in a very small time interval [t0, t+s] and s<<1, the Taylor expression of LAVD is:

[0045]

[0046] Therefore, the instantaneous vorticity deviation (IVD) is defined as the first-order coefficient of the LAVD Taylor expression:

[0047]

[0048] According to the above formula, the IVD field is objective and describes the rate of change of the LAVD field. At the same time, the instantaneous concept of the Euler vortex is described by introducing an infinitesimal time interval. The Euler vortex is composed of a tubular surface, and the fluid particles along the tubular surface have the same rotation rate. The details of the Euler vortex are defined below, such as Figure 3 As shown. At instantaneous time t:

[0049] (1) The Euler vortex in the heart cavity is defined as V(t), which is composed of a set of nested IVD(x,t) tubular horizontal planes, and the IVD value changes non-increasingly outward;

[0050] (2) The boundary B(t) of V(t) is a closed curve, which is the outermost tubular horizontal surface of IVD(x, t);

[0051] (3) The center C(t) of V(t) is the local maximum in the family of IVD(x,t) horizontal planes.

[0052] The Euler vortex in the heart cavity is expressed as:

[0053] E(t)={x0∈U(t):IVD(x,t)=C0(t)}

[0054] The blood particles have the same dynamic rotation rate on the tubular plane. Unlike the Lagrangian vortex, the single rotating Euler vortex is instantaneous and quantitative, and there is no clear evolution process, so the two vortex modes are expressed as derivative relations:

[0055]

[0056] Based on the objectivity of IVD, the above formula gives an objective definition of the center and boundary of the Euler vortex. Previously, a lot of work has studied how to define the Euler vortex. However, among the Euler vortex identification criteria proposed by Elbaz et al. and Haller et al., none of the criteria keep the relevant rotation and translation unchanged over a certain period of time. Therefore, the unstable flow in the cardiac cavity has no distinguishable reference system, which increases the difficulty of accurately defining the Euler vortex. In the process of IVD identification of Euler vortices in the cardiac cavity, the Euler vortex structure of the flow field with zero average vorticity is defined as a tubular level set without relying on a reference system. Therefore, the objective structure of the Lagrangian vortex derivative can be revealed based on the IVD field.

[0057] Step S130, verifying the performance of the cardiac cavity segmentation network.

[0058] In order to verify the performance of the cardiac cavity segmentation network designed in this chapter, the Jaccard index and Dice index are introduced. The Jaccard index is an important indicator for measuring the results of image semantic segmentation, which represents the proportion of the intersection of the predicted value and the gold standard in the overall set. The mathematical expression is as follows:

[0059]

[0060] Among them, TP is the true positive identified by the network, FN is the false negative, and FP is the false positive.

[0061] At the same time, as mentioned above, the Dice index measures the segmentation results by calculating the ratio of intersections. In order to test the trained model, several samples were randomly selected for verification. The effect of segmenting the diagnostic area can be better observed from the verification set, such as Figure 5 As shown in the segmentation results of the image in the figure, the segmentation results obtained by the network have a high degree of overlap with the manual segmentation results, which proves the effectiveness of the proposed method.

[0062] In summary, this patent proposes an algorithm for identifying Euler vortices in the heart based on the spatial vorticity deviation IVD algorithm, and parameterizes the identification results. At the same time, by measuring the vorticity difference of Euler vortices between healthy subjects and patients with heart enlargement, the effectiveness of the proposed method for diagnosing cardiovascular diseases is demonstrated.

[0063] The present invention may be a system, a method and / or a computer program product. The computer program product may include a computer-readable storage medium carrying computer-readable program instructions for causing a processor to implement various aspects of the present invention.

[0064] Computer readable storage medium can be a tangible device that can hold and store instructions used by an instruction execution device. Computer readable storage medium can be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination thereof. More specific examples (non-exhaustive list) of computer readable storage medium include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disk read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanical encoding device, for example, a punch card or a convex structure in a groove on which instructions are stored, and any suitable combination thereof. The computer readable storage medium used here is not interpreted as a transient signal itself, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagated by a waveguide or other transmission medium (for example, a light pulse by an optical fiber cable), or an electrical signal transmitted by a wire.

[0065] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, optical fiber transmissions, wireless transmissions, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in the computer-readable storage medium in each computing / processing device.

[0066] The computer program instructions for performing the operation of the present invention may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages, such as Smalltalk, C++, Python, etc., and conventional procedural programming languages, such as "C" language or similar programming languages. Computer-readable program instructions may be executed entirely on a user's computer, partially on a user's computer, as an independent software package, partially on a user's computer, partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., using an Internet service provider to connect via the Internet). In some embodiments, an electronic circuit, such as a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA), may be personalized by utilizing the state information of the computer-readable program instructions, and the electronic circuit may execute the computer-readable program instructions, thereby realizing various aspects of the present invention.

[0067] Various aspects of the present invention are described herein with reference to the flow charts and / or block diagrams of the methods, devices (systems) and computer program products according to embodiments of the present invention. It should be understood that each box of the flow chart and / or block diagram and the combination of each box in the flow chart and / or block diagram can be implemented by computer-readable program instructions.

[0068] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine, so that when these instructions are executed by the processor of the computer or other programmable data processing device, a device that implements the functions / actions specified in one or more boxes in the flowchart and / or block diagram is generated. These computer-readable program instructions can also be stored in a computer-readable storage medium, and these instructions cause the computer, programmable data processing device, and / or other equipment to work in a specific manner, so that the computer-readable medium storing the instructions includes a manufactured product, which includes instructions for implementing various aspects of the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0069] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operating steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0070] The flow charts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the systems, methods and computer program products according to multiple embodiments of the present invention. In this regard, each box in the flow chart or block diagram can represent a part of a module, a program segment or an instruction, and a part of the module, a program segment or an instruction contains one or more executable instructions for realizing the specified logical function. In some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented by a dedicated hardware-based system that performs the specified function or action, or can be implemented by a combination of dedicated hardware and computer instructions. It is well known to those skilled in the art that it is equivalent to implement it by hardware, implement it by software, and implement it by combining software and hardware.

[0071] Embodiments of the present invention have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or technical improvements in the marketplace, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein. The scope of the present invention is defined by the appended claims.

Claims

1. A method for identifying cardiac vortices based on spatial domain vorticity deviation, comprising the following steps: Firstly, the blood flow data in the heart is obtained by ultrasound equipment and nuclear magnetic resonance equipment, wherein the data represents the instantaneous blood flow velocity, and the Euler vortex structure in the heart is identified; Then, the complete Euler vortex structure is represented by the center and boundary of the vortex. After the Euler vortex of each stage is identified, the vorticity within the boundary is extracted, and the strength of the Euler vortex is represented by calculating the mean vorticity. Finally, the evolution of the heart vortex is parameterized by calculating the Euler vortex strength at each period.

2. The method according to claim 1, characterized in that The training dataset is constructed according to the following steps: Collect sample data multiple times, analyze blood flow velocity through blood flow vector imaging, obtain blood flow velocity data, and express it in a rectangular array form; For the blood flow velocity data, points outside the vortex boundary and points inside the vortex boundary are identified based on a comparison between the instantaneous vorticity deviation and a set threshold value to obtain a global label; Normalizing the blood flow velocity data to obtain a normalized blood flow velocity field; For the normalized blood flow velocity field, sampling is performed by locally patching around each point to obtain a local label, and the local label is used as a label of the sample.

3. The method according to claim 1, characterized in that The output layer is a softmax layer, where each neuron represents the probability that the input belongs to a category.

4. The method according to claim 1, characterized in that: The instantaneous vorticity deviation is used to describe the absolute value of the difference between the vorticity of a point and the spatial average vorticity of the global flow field, expressed as: IVD(x,t)=|ω(x,t)-ω avg (x,t)| Where ω represents the vorticity value, x is the position of the flow field, and ω avg (x, t) represents the spatially averaged vorticity of the global flow field.

5. A computer-readable storage medium having a computer program stored thereon, wherein: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 4 are implemented.

6. A computer device comprising a memory and a processor, wherein a computer program capable of being run on the processor is stored in the memory, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 4 are implemented.

Images