CN116051592A - Coronary artery dominant type judging method, system, device and storage medium - Google Patents

Abstract

Embodiments of the present disclosure provide a coronary artery dominant type judgment method, system, apparatus, and storage medium, the method including acquiring a medical image of a target object; determining a first segmentation result and a second segmentation result based on the medical image, wherein the first segmentation result is a coronary artery segmentation result and the second segmentation result is a heart segmentation result; extracting coronary artery branches related to dominant type judgment from the first segmentation result, wherein the coronary artery branches related to dominant type judgment comprise a right coronary artery and a left circumflex branch; determining a half-heart demarcation plane based on the second segmentation result; and determining the dominant type of the coronary artery of the target object through the dominant type judgment model based on the right coronary artery, the left circumflex circle and the half heart demarcation plane.

Description

Coronary artery dominant type judging method, system, device and storage medium

Technical Field

The present disclosure relates to the field of medical images, and in particular, to a coronary artery dominant type determination method, system, device, and storage medium.

Background

Judging the dominant type of heart coronary artery (abbreviated as coronary artery) from heart medical image is one of the widely used techniques in the medical field. The current dominant type judging method can be divided into two types according to whether heart segmentation information is combined or not: a method of not combining heart segmentation information and a method of combining heart segmentation information. Methods that do not incorporate cardiac segmentation information typically determine dominant types based solely on coronary segmentation results. For example, the dominant type is determined according to the spatial relationship between the central coordinates of the left and right coronary branches and the starting point thereof in the coronary artery segmentation result, but the method depends on the accuracy of determining the starting point position, and a small error may have a large influence on the result of the dominant type determination, and the starting point position is taken as a point, and cannot accurately represent the boundary position of the left and right half centers. For another example, the coronary artery segmentation result is converted into point cloud information and then is judged by using a neural network model, but the method is judged by only relying on the coronary artery topological structure, which is not in accordance with the basic principle of coronary artery dominant type judgment (namely, the judgment is carried out according to the distribution of left and right branches in a contralateral ventricle). The method combining heart segmentation information generally obtains the interface of the left and right half hearts based on the heart segmentation result, and uses the interface as one of the basis for judging the dominance. For example, the dominant type is judged according to the spatial distance between each point of the left and right coronary artery and the interface, or the dominant type is judged according to the number of intersection points with the interface, but none of these methods eliminates the coronary artery branches of which the part has no influence on the dominant type judgment. The coronary artery dominant type judgment method can not effectively combine heart segmentation information and coronary artery segmentation information, so that the obtained dominant type judgment result is inaccurate and incomplete.

Accordingly, it is desirable to provide a coronary artery dominant type judgment method, system, apparatus, and storage medium to improve the accuracy and comprehensiveness of coronary artery dominant type judgment.

Disclosure of Invention

One of the embodiments of the present disclosure provides a coronary artery dominant type determination method. The method comprises the following steps: acquiring a medical image of a target object; determining a first segmentation result and a second segmentation result based on the medical image, wherein the first segmentation result is a coronary artery segmentation result, and the second segmentation result is a heart segmentation result; extracting coronary artery branches related to dominant type judgment from the first segmentation result, wherein the coronary artery branches related to dominant type judgment comprise a right coronary artery and a left circumflex branch; determining a half-heart demarcation plane based on the second segmentation result; and determining the dominant type of the coronary artery of the target object through a dominant type judgment model based on the right coronary artery, the left circumflex circle and the half heart demarcation plane.

In some embodiments, left and right atria and ventricles may be inflated based on the second segmentation result, resulting in a first plane and a second plane, respectively; the half-heart demarcation plane is derived based on the first plane and the second plane.

In some embodiments, the half-heart demarcation plane may be obtained by fitting the first plane and the second plane by a least squares method.

In some embodiments, a coronary centerline may be extracted from the first segmentation result; acquiring coronary branch information using a coronary branch acquisition model based on the coronary centerline and the second segmentation result; and extracting the coronary artery branches related to dominant type judgment based on the coronary artery branch information.

In some embodiments, the training data of the dominant decision model may include: and judging results of the right coronary artery, the left circumflex, the half heart demarcation plane and the dominance of the plurality of historical users.

One embodiment of the present disclosure provides a dominant type judgment system for coronary arteries, including an image acquisition module, an image segmentation module, a coronary artery branch extraction module, a semi-heart interface determination module, and a dominant type determination module; the image acquisition module is used for acquiring a medical image of the target object; the image segmentation module is used for determining a first segmentation result and a second segmentation result based on the medical image, wherein the first segmentation result is a coronary artery segmentation result, and the second segmentation result is a heart segmentation result; the coronary artery branch extraction module is used for extracting coronary artery branches related to dominant type judgment from the first segmentation result, wherein the coronary artery branches related to dominant type judgment comprise a right coronary artery and a left circumflex artery; the half-heart interface determining module is used for determining a half-heart interface plane based on the second segmentation result; the dominant type determining module is used for determining the dominant type of the coronary artery of the target object through a dominant type judging model based on the right coronary artery, the left circumflex circle and the half heart demarcation plane.

In some embodiments, the semi-centered interface determination module may be configured to: expanding the left atrium and the right atrium and the ventricle based on the second segmentation result to respectively obtain a first plane and a second plane; the half-heart demarcation plane is derived based on the first plane and the second plane.

In some embodiments, the coronary branch extraction module may be to: extracting a coronary centerline from the first segmentation result; acquiring coronary branch information using a coronary branch acquisition model based on the coronary centerline and the second segmentation result; and extracting the coronary artery branches related to dominant type judgment based on the coronary artery branch information.

One of the embodiments of the present specification provides a coronary artery dominant type judgment device including a processor for executing the coronary artery dominant type judgment method.

One of the embodiments of the present specification provides a computer-readable storage medium storing computer instructions that when read by a computer in the storage medium, the computer performs the coronary artery dominant type judgment method.

In some embodiments of the present disclosure, a semi-heart interface is obtained by combining a heart segmentation result, a dominant type related branch is extracted by combining a coronary artery segmentation result and coronary artery branch information, and a neural network model is used to determine a dominant type of a coronary artery by combining the obtained information, so that the heart segmentation information and the coronary artery segmentation information are comprehensively combined, and the dominant type determination result of the coronary artery is more accurate and comprehensive; meanwhile, coronary branches which do not affect the dominant judgment are removed in the judging process, the data quantity to be processed is reduced, and the interference of useless data is avoided, so that the processing efficiency of the judging process is higher, and the result is more accurate.

Drawings

The present specification will be further elucidated by way of example embodiments, which will be described in detail by means of the accompanying drawings. The embodiments are not limiting, in which like numerals represent like structures, wherein:

fig. 1 is a schematic view of an application scenario of a dominant coronary judgment system according to some embodiments of the present disclosure;

FIG. 2 is a schematic diagram of a dominant coronary judgment system according to some embodiments of the present disclosure;

FIG. 3 is an exemplary flow chart of a coronary artery dominant decision method in accordance with some embodiments of the present disclosure;

FIG. 4 is a schematic diagram of a dominant coronary judgment method according to some embodiments of the present disclosure;

FIGS. 5A, 5B, 5C are two-dimensional cross-sectional schematic views of three-dimensional CT heart images at different view angles according to some embodiments of the present description;

FIGS. 6A and 6B are graphs of cardiac segmentation results for different perspectives according to some embodiments of the present disclosure;

FIGS. 7A and 7B are graphs of coronary artery segmentation results according to some embodiments of the present disclosure;

fig. 8 is a schematic diagram of coronary artery branching associated with dominant type judgment, according to some embodiments of the present disclosure.

Detailed Description

In order to more clearly illustrate the technical solutions of the embodiments of the present specification, the drawings that are required to be used in the description of the embodiments will be briefly described below. It is apparent that the drawings in the following description are only some examples or embodiments of the present specification, and it is possible for those of ordinary skill in the art to apply the present specification to other similar situations according to the drawings without inventive effort. Unless otherwise apparent from the context of the language or otherwise specified, like reference numerals in the figures refer to like structures or operations.

It will be appreciated that "system," "apparatus," "unit" and/or "module" as used herein is one method for distinguishing between different components, elements, parts, portions or assemblies at different levels. However, if other words can achieve the same purpose, the words can be replaced by other expressions.

As used in this specification and the claims, the terms "a," "an," "the," and/or "the" are not specific to a singular, but may include a plurality, unless the context clearly dictates otherwise. In general, the terms "comprises" and "comprising" merely indicate that the steps and elements are explicitly identified, and they do not constitute an exclusive list, as other steps or elements may be included in a method or apparatus.

A flowchart is used in this specification to describe the operations performed by the system according to embodiments of the present specification. It should be appreciated that the preceding or following operations are not necessarily performed in order precisely. Rather, the steps may be processed in reverse order or simultaneously. Also, other operations may be added to or removed from these processes.

Fig. 1 is a schematic view of an application scenario of a dominant coronary judgment system according to some embodiments of the present disclosure.

As shown in fig. 1, in some embodiments, the system 100 may include a medical imaging device 110, a processing device 120, a storage device 130, a terminal 140, a network 150.

The medical imaging device 110 refers to a device for reproducing a structure inside a human body as an image using different media in medicine. In some embodiments, the medical imaging device 110 may be any medical device that includes a detector for imaging or treating a specified body part of a patient with a radionuclide, such as computed tomography (Computed Tomography, CT), single Photon Emission Computed Tomography (SPECT), positron emission tomography (Positron Emission Tomography, PET), PET-CT, SPECT-CT, or the like. The medical imaging device 110 is provided above for illustrative purposes only and is not limiting in scope. In some embodiments, the medical imaging device 110 may obtain a medical image of a target object (e.g., a human body, an animal, a phantom, etc.) by scanning the target object. In some embodiments the medical imaging device 110 may receive instructions from a physician via the terminal 140 and perform associated operations, such as scanning imaging, etc., based on the instructions. In some embodiments, the medical imaging device 110 may exchange data and/or information with other components in the system 100 (e.g., the processing device 120, the storage device 130, the terminal 140) via the network 150. In some embodiments, the medical imaging device 110 may be directly connected to other components in the system 100. In some embodiments, one or more components in the system 100 (e.g., the processing device 120, the storage device 130) may be included within the medical imaging device 110.

The processing device 120 may process data and/or information obtained from other devices or system components and perform coronary artery dominance determination methods shown in some embodiments of the present description based on the data, information and/or processing results to perform one or more of the functions described in some embodiments of the present description. For example, the processing device 120 may determine segmentation results of the image based on the scanned image of the medical imaging device 110, e.g., coronary segmentation results and cardiac segmentation results based on the cardiac scanned image. For another example, the processing device 120 may determine the dominant type of coronary artery by the neural network model target object based on the coronary artery segmentation result and the heart segmentation result. In some embodiments, the processing device 120 may send the processed data, e.g., coronary artery segmentation results, heart segmentation results, coronary artery branches associated with dominant type determination, semi-heart demarcation planes, dominant type determination results, etc., to the storage device 130 for storage. In some embodiments, the processing device 120 may obtain pre-stored data and/or information from the storage device 130, for example, a dominant type determination model for determining a dominant type, a coronary branch acquisition model for acquiring a coronary branch, and the like, for performing the coronary artery dominant type determination method shown in some embodiments of the present specification, for example, determining a dominant type of a coronary artery, and the like.

In some embodiments, processing device 120 may include one or more sub-processing devices (e.g., single-core processing devices or multi-core processing devices). By way of example only, the processing device 120 may include a Central Processing Unit (CPU), an Application Specific Integrated Circuit (ASIC), an Application Specific Instruction Processor (ASIP), a Graphics Processor (GPU), a Physical Processor (PPU), a Digital Signal Processor (DSP), a Field Programmable Gate Array (FPGA), an editable logic circuit (PLD), a controller, a microcontroller unit, a Reduced Instruction Set Computer (RISC), a microprocessor, or the like, or any combination thereof.

Storage device 130 may store data or information generated by other devices. In some embodiments, the storage device 130 may store data and/or information acquired by the medical imaging device 110, such as scanned images of various portions of a target object (e.g., heart, brain, etc.), and the like. In some embodiments, the storage device 130 may store data and/or information processed by the processing device 120, such as coronary artery segmentation results, heart segmentation results, coronary artery branches associated with dominant type determination, semi-heart demarcation plane, dominant type determination results, and the like. Storage device 130 may include one or more storage components, each of which may be a separate device or may be part of another device. The storage device may be local or may be implemented by a cloud.

The terminal 140 may control the operation of the medical imaging device 110. The doctor may issue an operation instruction to the medical imaging device 110 through the terminal 140 to cause the medical imaging device 110 to perform a designated operation, such as scanning and imaging a designated body part of the patient. In some embodiments, the terminal 140 may cause the processing device 120 to perform the coronary artery dominant type judgment method as shown in some embodiments of the present specification by an instruction. In some embodiments, the terminal 140 may receive the coronary dominance determination of the patient from the processing device 120, whereby the physician may accurately determine the coronary dominance of the patient for effective and targeted examination and/or treatment of the patient. In some embodiments, terminal 140 may be one or any combination of mobile device 140-1, tablet computer 140-2, laptop computer 140-3, desktop computer, and other input and/or output enabled devices.

Network 150 may connect components of the system and/or connect the system with external resource components. Network 150 enables communication between the various components and with other components outside the system to facilitate the exchange of data and/or information. In some embodiments, one or more components in the system 100 (e.g., the medical imaging device 110, the processing device 120, the storage device 130, the terminal 140) may send data and/or information to other components over the network 150. In some embodiments, network 150 may be any one or more of a wired network or a wireless network.

It should be noted that the above description is provided for illustrative purposes only and is not intended to limit the scope of the present description. Many variations and modifications will be apparent to those of ordinary skill in the art, given the benefit of this disclosure. The features, structures, methods, and other features of the exemplary embodiments described herein may be combined in various ways to obtain additional and/or alternative exemplary embodiments. For example, the processing device 120 may be cloud computing platform based, such as public cloud, private cloud, community, hybrid cloud, and the like. However, such changes and modifications do not depart from the scope of the present specification.

Fig. 2 is a schematic diagram of a dominant coronary judgment system according to some embodiments of the present disclosure.

As shown in fig. 2, in some embodiments, the coronary dominance determination system 200 may include an image acquisition module 210, an image segmentation module 220, a coronary branch extraction module 230, a semi-centered interface determination module 240, and a dominance determination module 250. In some embodiments, the modules of the coronary dominance determination system 200 may be implemented by a processing device (e.g., the processing device 120).

In some embodiments, the image acquisition module 210 may be used to acquire medical images of the target object.

In some embodiments, the image segmentation module 220 may be configured to determine the first segmentation result and the second segmentation result based on the medical image. The first segmentation result is a coronary artery segmentation result, and the second segmentation result is a heart segmentation result.

In some embodiments, the coronary branch extraction module 230 may be configured to extract a coronary branch associated with a dominant decision from the first segmentation result. Wherein the coronary branches associated with the dominant type judgment include a right coronary artery and a left circumflex.

In some embodiments, the coronary branch extraction module 230 may extract a coronary centerline from the first segmentation result; based on the coronary centerline and the second segmentation result, obtaining coronary branch information using a coronary branch acquisition model; coronary artery branches associated with the dominant decision are extracted based on the coronary artery branch information.

In some embodiments, the half-heart interface determination module 240 may be configured to determine a half-heart interface plane based on the second segmentation result.

In some embodiments, the semi-centered interface determination module 240 may expand the left and right atria and ventricles to obtain the first plane and the second plane, respectively, based on the second segmentation result; a half-heart demarcation plane is obtained based on the first plane and the second plane.

In some embodiments, the half-center interface determination module 240 may fit the first plane and the second plane by a least squares method to obtain the half-center interface plane.

In some embodiments, the dominance determination module 250 may be configured to determine a dominance of the coronary artery of the target object by a dominance determination model based on the right coronary artery, the left circumflex, and the half-heart demarcation plane.

In some embodiments, the coronary dominance determination system 200 may also include a model training module (not shown). The model training module may be used to train a dominant decision model and a coronary branch acquisition model.

In some embodiments, the training data of the dominant decision model may include: right coronary artery, left circumflex, half heart demarcation plane, and dominant decision results of multiple historical users, etc.

Fig. 3 is an exemplary flow chart of a coronary artery dominant type judgment method shown in accordance with some embodiments of the present description.

As shown in fig. 3, the process 300 includes the following steps. In some embodiments, the process 300 may be performed by a processing device (e.g., the processing device 120).

The coronary arteries are arteries that supply blood to the heart, and are divided into left (left coronary artery, LCA) and right (right coronary artery, RCA). The coronary arteries include a plurality of branches that branch into a dendritic envelope around the heart. Wherein the Left coronary Artery branches into a Left circumflex (Left Circumflex Artery, LCX) and anterior descending (Left Anterior Descending, LAD) branch after its bifurcation, the portion before bifurcation being referred to as the Left Main (LM). The left coronary artery ensures the myocardial blood supply to the anterior and lateral walls of the heart. The right coronary artery originates from the right coronary valve of the aortic valve and has a main branch, the posterior ventricular branch (Ramus Interventricularis Posterior, RIVP). Under normal anatomy, blood flow is provided by the right coronary artery to the right ventricle, right atrium, left ventricle portion, back wall of the heart, sinus node, atrioventricular node.

The dominant type of coronary artery refers to which coronary artery (left/right) is responsible for more myocardial blood supply. Dominant types of coronary arteries can include three types: right dominant type, balanced type, left dominant type. If the left coronary artery provides blood supply to the back wall and the junction of the heart, i.e., the lower wall of the left ventricle, which is the left circumflex blood supply, it is referred to as left dominant; if the myocardium between the ventricular septum and the left ventricular septum surface is supplied by the right coronary artery, i.e., the coronary artery emanating from the right coronary sinus, extends to the apex of the heart at the right ventricular site, supplying the left ventricle, then it is referred to as right dominant; the rest of the cases are called equalization types. Coronary artery dominant type judgment result is one of important diagnostic basis of coronary artery disease and heart disease. In general, the dominant type of coronary arteries can be determined from a coronary angiography image (e.g., a cardiac CT image). Before the cardiac scan of the target object, a contrast agent may be injected into the target object by an vein, and a chest or a whole body of the target object may be scanned by a medical imaging device (for example, CT or the like), so as to obtain a coronary angiography image of the chest of the target object, where a cardiac structure and a coronary condition of the target object may be displayed.

In step 310, a medical image of a target object is acquired. In some embodiments, step 310 may be performed by image acquisition module 210.

The target object is an examination object for which a dominant type judgment of coronary arteries is required, for example, a patient suffering from heart disease or the like. In some embodiments, the target object may include a particular body organ and/or tissue of the patient, e.g., heart, coronary artery, etc. In some embodiments, the medical image of the target object may comprise a cardiac image of the patient, wherein the cardiac image further comprises an image of a coronary artery, e.g. the medical image of the target object may comprise a coronary angiography image or the like. In some embodiments, the medical image of the target object may comprise a three-dimensional image and/or a two-dimensional image, e.g. the coronary angiography image may comprise a three-dimensional image, which may comprise a multi-layer continuous two-dimensional coronary angiography tomographic image. In some embodiments, the medical image of the target object may comprise two-dimensional cross-sectional images of the heart at different perspectives. For example, the three-dimensional CT cardiac images shown in fig. 5A, 5B, 5C are two-dimensional cross-sectional views at different view angles, which correspond to the axial, sagittal, and coronal planes, respectively.

In some embodiments, the processing device may acquire a medical image of the target object by scanning the target object by a medical imaging device (e.g., medical imaging device 110). In some embodiments, the processing device may acquire the medical image of the target object by other means, such as by a storage device, by analog scanning of a digital model of the target object, etc.

At step 320, a first segmentation result and a second segmentation result are determined based on the medical image. The first segmentation result is a coronary artery segmentation result, and the second segmentation result is a heart segmentation result. In some embodiments, step 320 may be performed by image segmentation module 220.

In some embodiments, the processing device may perform image segmentation on the medical image of the target object to obtain image segmentation results, e.g., coronary segmentation results, cardiac segmentation results, etc., of different organs and/or tissues of the target object. In some embodiments, image segmentation may be performed in various ways. For example, by image segmentation algorithms, by machine learning models, etc.

In some embodiments, the processing device may perform image segmentation on the medical image of the target object, resulting in a first segmentation result and a second segmentation result. Wherein the first segmentation result comprises a coronary artery segmentation result and the second segmentation result comprises a heart segmentation result. In some embodiments, the segmentation results may include reconstructed images of the corresponding organ and/or tissue. For example, fig. 6A and 6B are diagrams illustrating cardiac segmentation results from different viewing angles according to some embodiments of the present disclosure, where 610 is the left atrial chamber, 620 is the right atrial chamber, 630 is the left ventricle, and 640 is the right ventricular chamber. For another example, fig. 7A and 7B are schematic diagrams of coronary artery segmentation results according to some embodiments of the present disclosure, where fig. 7A shows an initial coronary artery segmentation result, fig. 7B shows a result obtained after branching (segmentation) based on fig. 7A, 710 is left circumflex LCX, and 720 is right coronary artery RCA.

Step 330 extracts a coronary artery branch associated with the dominant type decision from the first segmentation result. Wherein the coronary branches associated with the dominant type judgment include a right coronary artery and a left circumflex. In some embodiments, step 330 may be performed by coronary branch extraction module 230.

In some embodiments, the processing device may extract a coronary artery branch associated with the dominant decision from the first segmentation result (i.e., the coronary artery segmentation result). Coronary artery branching associated with dominant type judgment refers to coronary artery branching information that can be used to judge dominant type of coronary arteries, including specific coronary artery branching distribution information. In some embodiments, the coronary branches associated with the dominant decision may include at least one branch of the left coronary artery and at least one branch of the right coronary artery. In some embodiments, the coronary branches associated with the dominant decision may include the right coronary artery and the left circumflex branch.

In some embodiments, the processing device may extract a coronary centerline from the first segmentation result. The coronary centerline is a curve characterizing the coronary topology. In some embodiments, the coronary centerline may be a curve along any portion of the coronary artery, e.g., a curve along the center of the coronary artery, a curve along the outer wall of the coronary artery, etc. In some embodiments, the processing device may perform image processing (e.g., refinement, smoothing, etc.) on the first segmentation result to extract the coronary centerline.

In some embodiments, the processing device may obtain the coronary branch information in a variety of ways based on the extracted coronary centerline and the second segmentation result (i.e., the heart segmentation result). The coronary branch information may include information related to the distribution of the branches of the coronary, e.g., an image of the coronary branch information. By way of example only, fig. 7B may represent distribution information of coronary branches, and the processing apparatus may perform branching (segmentation) processing based on the coronary segmentation result shown in fig. 7A, resulting in distribution information of each coronary branch shown in fig. 7B.

In some embodiments, the processing device may acquire the coronary branch information using a coronary branch acquisition model based on the extracted coronary centerline and the second segmentation result. Among other things, the coronary branch acquisition model may include various neural network models, such as convolutional neural networks (Convolutional Neural Network, CNN), recurrent neural networks (Recursive Neural Network, RNN), deep belief networks (Deep Belief Neural Networks, DBN), and the like.

In some embodiments, the processing device may input the coronary centerline and the second segmentation result into a coronary branch acquisition model, resulting in output coronary branch information. For example, the processing device may input the three-dimensional segmented images corresponding to fig. 6A, 6B, and 7A into the coronary branch acquisition model, resulting in the coronary branch information shown in fig. 7B.

In some embodiments, training data of the coronary branch acquisition model may include historical data (e.g., historical examination data) and/or simulation data (e.g., simulation scan data of a digital model based on the sample object) of the sample object (e.g., the patient), and so forth. In some embodiments, the training samples of the coronary branch acquisition model may include a sample coronary segmentation result image, a sample heart segmentation image, and a sample coronary branch information image, where the sample coronary segmentation result image may or may not include an extracted coronary centerline. The processing equipment can input the sample coronary artery segmentation result image and the sample heart segmentation image into an initial coronary artery branch acquisition model to obtain an output coronary artery branch information image; comparing the sample coronary branch information image with the output coronary branch information image as a training label; and carrying out iterative updating on the model based on the comparison result to obtain a trained coronary artery branch acquisition model.

In some embodiments of the present disclosure, coronary branch information is obtained by dividing the central line and the heart, so that the coronary branch information is more accurate, and further, the extracted coronary branch is more accurate; coronary artery segmentation results and heart segmentation results are processed through the neural network model, coronary artery branch information is obtained, the coronary artery segmentation and heart segmentation results are combined, the advantages of machine learning are utilized, the judgment of coronary artery branches is more accurate and efficient, meanwhile, historical data and/or simulation data of a patient can be effectively utilized, and the accuracy of the results output by the model is high.

In some embodiments, the processing device may obtain the coronary branch information by other means, for example, by algorithmic processing, manual processing, etc.

For the dominant type judgment, the whole information of the coronary branch is unnecessary, and the dominant type judgment may be made based on only part of the information of the coronary branch. In some embodiments, the processing device may extract coronary branches associated with the dominant decision from the obtained coronary branch information. Specifically, the processing device may determine a coronary artery branch related to the dominant type judgment, and then remove the other coronary artery branches other than the coronary artery branch from the image of the coronary artery branch information, leaving only the coronary artery branch. In some embodiments, dominant decision related coronary branches may be determined based on statistics or the like. For example, based on the statistics, most people are right dominant, then the left circumflex and right coronary arteries can be determined as coronary branches associated with dominant type judgment. By way of example only, fig. 8 is a schematic diagram of coronary artery branching associated with dominant type determination according to some embodiments of the present disclosure, and fig. 8 may be extracted from the coronary artery branching information shown in fig. 7B. Wherein 810 is the left circumflex left branch LCX and 820 is the right coronary artery RCA.

In some embodiments, the processing device may extract coronary branches relevant to the dominant decision from the coronary branch information in a variety of ways, e.g., by algorithms, by machine learning models, by manual processing, etc. In some embodiments, the processing device may extract coronary branches relevant to the dominant decision using a separate machine learning model or using a coronary branch acquisition model. For example, the output of the coronary branch acquisition model may include an image of the coronary branch associated with the dominant decision.

Step 340, determining a half-heart demarcation plane based on the second segmentation result. In some embodiments, step 340 may be performed by the semi-centered interface determination module 240.

The heart chamber is divided by the atrial and ventricular septum into left and right halves that are not interconnected, commonly referred to as the left and right half-hearts. The half-heart demarcation plane refers to the interface of the left and right half-hearts. In some embodiments, the half-heart demarcation plane may be comprised of an interface of the heart chamber and an interface of the atrium, and may include one or any combination of curved surfaces, planar surfaces, and the like.

In some embodiments, the processing device may expand the left and right atrium and ventricle in the second segmentation result to obtain the first plane and the second plane, respectively. Specifically, the processing apparatus may perform equal-proportion expansion processing on boundary profiles of the left and right atria and the left and right ventricles of the second division result until overlapping intersections of the left and right atria and the left and right ventricles occur, and then acquire intersection curved surfaces of the left and right atria and the left and right ventricles as the first plane and the second plane, respectively. Wherein the first plane comprises an interface of the left and right atria, the second plane comprises an interface of the left and right ventricles, and the first and second planes may comprise one or any combination of curved surfaces, planar surfaces, etc. In some embodiments, the processing device may combine the first plane and the second plane to obtain a half-heart demarcation plane. In some embodiments, the half-heart demarcation plane may be represented by an image. For example, as shown in fig. 6A, 6B, 650 may be the interface of left atrial blood chamber 610 and right atrial blood chamber 620, 660 may be the interface of left ventricle 630 and right ventricular blood chamber 640, and the half-heart demarcation plane may be comprised of 650 and 660.

In some embodiments, the processing device may use the spatial plane to fit pixels on the first plane and the second plane to obtain the half-center demarcation plane by a method such as least squares.

In some embodiments, the processing device may fit the first plane and the second plane by other means to obtain a half-heart decomposition plane, e.g., by machine learning model fitting, etc.

In some embodiments of the present disclosure, the semi-cardiac demarcation plane is obtained by fitting an atrial plane and a ventricular plane, so that the judgment of the score interface is more accurate, and the consistency of the dominant judgment result of the subsequent machine learning model and the judgment result of the clinician is improved.

In step 350, the dominant type of the coronary artery of the target object is determined by the dominant type judgment model based on the right coronary artery, the left circumflex and the half heart demarcation plane. In some embodiments, step 350 may be performed by the dominance determination module 250.

In some embodiments, the processing device may determine the dominant type of coronary artery of the target object by various means, such as by algorithms, by machine learning models, by manual processing decisions, etc., based on the coronary artery branches (e.g., right and left circumflex branches) and the semi-cardiac demarcation plane associated with the dominant type decisions.

In some embodiments, the processing device may determine the dominant type of the coronary artery of the target object by the dominant type judgment model based on the acquired coronary artery branches (e.g., right coronary artery and left circumflex branch) and the half-heart demarcation plane information. The dominant type judgment model may include various neural network models, for example, CNN, RNN, DBN and the like.

In some embodiments, the processing device may input an image including coronary branches (e.g., right and left circumflex branches) and a half-heart demarcation plane associated with the dominant type determination into the dominant type determination model, resulting in an output dominant type determination result. The dominant type determination result may include which dominant type the target object belongs to and/or which dominant type the target object does not belong to.

In some embodiments, the training data of the dominant decision model may include: coronary branches (e.g., right coronary artery and left circumflex), a half-heart demarcation plane, and dominant decision results, etc., associated with dominant decisions for a plurality of historical users as training samples. The sample dominant type judgment result can be used as a training label. The processing device may input the coronary artery branch and the half-heart boundary plane related to the dominant type judgment into the initial dominant type judgment model to obtain an output dominant type judgment result, compare the output dominant type judgment result with the sample dominant type judgment result, and iteratively update the model based on the comparison result until a trained initial dominant type judgment model is obtained. The termination condition of the iteration may include that a consistency ratio of an output result of the model and a sample dominant type judgment result is greater than or equal to a preset threshold.

In some embodiments, the training sample data of the dominant decision model may include simulation data based on a sample user, such as coronary artery branches, semi-heart demarcation planes, dominant decision results, and the like, which are obtained based on a digital model simulation of the sample user.

In some embodiments of the present disclosure, a neural network model is constructed by combining the historical user data with the coronary artery position information and the heart region position information, and the dominant type of the coronary artery is determined by the neural network model, so that a more comprehensive and accurate dominant type determination result can be obtained; and before the data is input into the model, redundant information is removed by only retaining coronary branches and the like which have influence on dominant judgment, so that the data processing amount is reduced, and meanwhile, the interference of redundant information is removed, thereby improving the efficiency of the judgment process and further improving the judgment accuracy.

It should be noted that the above description of the process 300 is for purposes of example and illustration only and is not intended to limit the scope of applicability of the present disclosure. Various modifications and changes to flow 300 will be apparent to those skilled in the art in light of the present description. However, such modifications and variations are still within the scope of the present description. For example, step 330 may be performed in parallel with step 340, or may be performed sequentially.

Fig. 4 is a schematic diagram of a dominant coronary judgment method according to some embodiments of the present disclosure.

In some embodiments, the processing device may determine the dominant type of coronary artery of the target object (e.g., patient) by performing the method as shown in fig. 4.

As shown in fig. 4, in some embodiments, the processing device may acquire a cardiac medical image 410 of the target object. In some embodiments, the cardiac medical image 410 may include a coronary angiography image or the like. For more details on how to acquire the medical image of the target object, reference may be made to the relevant description of step 310, which is not repeated here.

In some embodiments, the processing device may perform image segmentation on the cardiac medical image 410 to obtain a coronary artery segmentation result 420 and a cardiac segmentation result 430, wherein the coronary artery segmentation result 420 may be a first segmentation result and the cardiac segmentation result 430 may be a second segmentation result. In some embodiments, the image segmentation may include two times, one to obtain coronary segmentation results 420 and another to obtain cardiac segmentation results 430. In some embodiments, the processing device may obtain coronary artery segmentation results 420 and heart segmentation results 430 from only one image segmentation. For more on how to determine the first segmentation result and the second segmentation result based on the medical image, reference may be made to the relevant description of step 320, which is not repeated here.

In some embodiments, the processing device may extract a coronary centerline 440 from the coronary segmentation results 420; acquiring coronary branch information 450 from the coronary centerline 440 and the heart segmentation result 430 by a model (e.g., a coronary branch acquisition model); dominant correlated branches 460 correlated with dominant decisions are extracted from the coronary branch information 450, wherein the dominant correlated branches 460 may include partial branches of the coronary arteries (e.g., right and left circumflex). For more details on how to extract the coronary artery branches relevant to the dominant decision from the first segmentation result, reference may be made to the relevant description of step 330, which is not repeated here.

In some embodiments, the processing device may derive a semi-cardiac interface plane 470 from the cardiac segmentation result 430. For more details on how to determine the half-heart demarcation plane based on the second segmentation result, reference may be made to the relevant description of step 340, which is not repeated here.

In some embodiments, the processing device may determine a dominant type of coronary determination of the target object, i.e., a dominant type 480 of the coronary artery, from the dominant type-related branches 460 and the semi-centered interfacial plane 470 by a model (e.g., a dominant type determination model). The dominant type 480 of the coronary artery may include which dominant type and/or which dominant type the target object belongs to.

Possible benefits of embodiments of the present description include, but are not limited to: (1) The semi-heart interface is obtained by combining the heart segmentation result, the dominant type related branches are extracted by combining the coronary artery segmentation result and the coronary artery branch information, the coronary artery dominant type judgment is carried out by combining the obtained information and using the neural network model, and the heart segmentation information and the coronary artery segmentation information are comprehensively combined, so that the coronary artery dominant type judgment result is more accurate and comprehensive; (2) Meanwhile, coronary branches which do not affect the dominant judgment are removed in the judging process, the data quantity to be processed is reduced, and the interference of useless data is avoided, so that the processing efficiency of the judging process is higher, and the result is more accurate. It should be noted that, the advantages that may be generated by different embodiments may be different, and in different embodiments, the advantages that may be generated may be any one or a combination of several of the above, or any other possible advantages that may be obtained.

While the basic concepts have been described above, it will be apparent to those skilled in the art that the foregoing detailed disclosure is by way of example only and is not intended to be limiting. Although not explicitly described herein, various modifications, improvements, and adaptations to the present disclosure may occur to one skilled in the art. Such modifications, improvements, and modifications are intended to be suggested within this specification, and therefore, such modifications, improvements, and modifications are intended to be included within the spirit and scope of the exemplary embodiments of the present invention.

Meanwhile, the specification uses specific words to describe the embodiments of the specification. Reference to "one embodiment," "an embodiment," and/or "some embodiments" means that a particular feature, structure, or characteristic is associated with at least one embodiment of the present description. Thus, it should be emphasized and should be appreciated that two or more references to "an embodiment" or "one embodiment" or "an alternative embodiment" in various positions in this specification are not necessarily referring to the same embodiment. Furthermore, certain features, structures, or characteristics of one or more embodiments of the present description may be combined as suitable.

Furthermore, the order in which the elements and sequences are processed, the use of numerical letters, or other designations in the description are not intended to limit the order in which the processes and methods of the description are performed unless explicitly recited in the claims. While certain presently useful inventive embodiments have been discussed in the foregoing disclosure, by way of various examples, it is to be understood that such details are merely illustrative and that the appended claims are not limited to the disclosed embodiments, but, on the contrary, are intended to cover all modifications and equivalent arrangements included within the spirit and scope of the embodiments of the present disclosure. For example, while the system components described above may be implemented by hardware devices, they may also be implemented solely by software solutions, such as installing the described system on an existing server or mobile device.

Likewise, it should be noted that in order to simplify the presentation disclosed in this specification and thereby aid in understanding one or more inventive embodiments, various features are sometimes grouped together in a single embodiment, figure, or description thereof. This method of disclosure, however, is not intended to imply that more features than are presented in the claims are required for the present description. Indeed, less than all of the features of a single embodiment disclosed above.

In some embodiments, numbers describing the components, number of attributes are used, it being understood that such numbers being used in the description of embodiments are modified in some examples by the modifier "about," approximately, "or" substantially. Unless otherwise indicated, "about," "approximately," or "substantially" indicate that the number allows for a 20% variation. Accordingly, in some embodiments, numerical parameters set forth in the specification and claims are approximations that may vary depending upon the desired properties sought to be obtained by the individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and employ a method for preserving the general number of digits. Although the numerical ranges and parameters set forth herein are approximations that may be employed in some embodiments to confirm the breadth of the range, in particular embodiments, the setting of such numerical values is as precise as possible.

Each patent, patent application publication, and other material, such as articles, books, specifications, publications, documents, etc., referred to in this specification is incorporated herein by reference in its entirety. Except for application history documents that are inconsistent or conflicting with the content of this specification, documents that are currently or later attached to this specification in which the broadest scope of the claims to this specification is limited are also. It is noted that, if the description, definition, and/or use of a term in an attached material in this specification does not conform to or conflict with what is described in this specification, the description, definition, and/or use of the term in this specification controls.

Finally, it should be understood that the embodiments described in this specification are merely illustrative of the principles of the embodiments of this specification. Other variations are possible within the scope of this description. Thus, by way of example, and not limitation, alternative configurations of embodiments of the present specification may be considered as consistent with the teachings of the present specification. Accordingly, the embodiments of the present specification are not limited to only the embodiments explicitly described and depicted in the present specification.

Claims (10)

1. A coronary artery dominant type judging method comprises the following steps:

Acquiring a medical image of a target object;

determining a first segmentation result and a second segmentation result based on the medical image, wherein the first segmentation result is a coronary artery segmentation result, and the second segmentation result is a heart segmentation result;

extracting coronary artery branches related to dominant type judgment from the first segmentation result, wherein the coronary artery branches related to dominant type judgment comprise a right coronary artery and a left circumflex branch;

determining a half-heart demarcation plane based on the second segmentation result;

and determining the dominant type of the coronary artery of the target object through a dominant type judgment model based on the right coronary artery, the left circumflex circle and the half heart demarcation plane.

2. The method of claim 1, the determining a half-heart demarcation plane based on the second segmentation result comprising:

expanding the left atrium and the right atrium and the ventricle based on the second segmentation result to respectively obtain a first plane and a second plane;

the half-heart demarcation plane is derived based on the first plane and the second plane.

3. The method of claim 2, the deriving the half-heart demarcation plane based on the first plane and the second plane comprising:

Fitting the first plane and the second plane by a least square method to obtain the half-heart demarcation plane.

4. The method of claim 1, the extracting coronary artery branches associated with a dominant decision from the first segmentation result comprising:

extracting a coronary centerline from the first segmentation result;

acquiring coronary branch information using a coronary branch acquisition model based on the coronary centerline and the second segmentation result;

and extracting the coronary artery branches related to dominant type judgment based on the coronary artery branch information.

5. The method of claim 1, the training data of the dominant decision model comprising: and judging results of the right coronary artery, the left circumflex, the half heart demarcation plane and the dominance of the plurality of historical users.

6. A dominant coronary judgment system comprises an image acquisition module, an image segmentation module, a coronary artery branch extraction module, a semi-heart interface determination module and a dominant determination module;

the image acquisition module is used for acquiring a medical image of the target object;

the image segmentation module is used for determining a first segmentation result and a second segmentation result based on the medical image, wherein the first segmentation result is a coronary artery segmentation result, and the second segmentation result is a heart segmentation result;

The coronary artery branch extraction module is used for extracting coronary artery branches related to dominant type judgment from the first segmentation result, wherein the coronary artery branches related to dominant type judgment comprise a right coronary artery and a left circumflex artery;

the half-heart interface determining module is used for determining a half-heart interface plane based on the second segmentation result;

the dominant type determining module is used for determining the dominant type of the coronary artery of the target object through a dominant type judging model based on the right coronary artery, the left circumflex circle and the half heart demarcation plane.

7. The system of claim 6, the semi-centered interface determination module to:

expanding the left atrium and the right atrium and the ventricle based on the second segmentation result to respectively obtain a first plane and a second plane;

the half-heart demarcation plane is derived based on the first plane and the second plane.

8. The system of claim 6, the coronary branch extraction module to:

extracting a coronary centerline from the first segmentation result;

acquiring coronary branch information using a coronary branch acquisition model based on the coronary centerline and the second segmentation result;

and extracting the coronary artery branches related to dominant type judgment based on the coronary artery branch information.

9. A coronary artery dominant type judgment device comprising a processor for executing the method of any one of claims 1 to 5.

10. A computer readable storage medium storing computer instructions which, when read by a computer in the storage medium, perform the method of any one of claims 1 to 5.

Images