CN116228663B

CN116228663B - Myocardial hypertrophy measuring device, system and storage medium

Info

Publication number: CN116228663B
Application number: CN202211725479.6A
Authority: CN
Inventors: 王旭; 斯蒂芬妮·李; 李璟; 马骏; 郑凌霄; 兰宏志
Original assignee: Shenzhen Raysight Intelligent Medical Technology Co Ltd
Current assignee: Shenzhen Raysight Intelligent Medical Technology Co Ltd
Priority date: 2022-12-30
Filing date: 2022-12-30
Publication date: 2025-07-25
Anticipated expiration: 2042-12-30
Also published as: CN116228663A

Abstract

The present invention belongs to the field of image processing technology, and discloses a myocardial hypertrophy measurement device, system and storage medium. The device includes: an interface configured to receive a coronary CTA image of the heart; a processor configured to: obtain a myocardial segmentation binary map and a heart segmentation map based on the coronary CTA image; determine the left atrioventricular junction position centroid in the left atrioventricular junction position binary map and the right atrioventricular junction position centroid in the right atrioventricular junction position binary map based on the heart segmentation map; obtain a short axis plane, and intercept the myocardium based on the short axis plane to obtain a short axis myocardial annular segmentation map; determine the long axis plane based on the left atrioventricular junction position centroid, the right atrioventricular junction position centroid and the maximum distance point; intercept the short axis myocardial annular segmentation map based on the long axis plane to obtain a target connected domain; and use the maximum distance between any two points in the target connected domain as the middle myocardial thickness measurement value. The myocardial thickness can be measured quickly and accurately.

Description

Myocardial hypertrophy measuring device, system and storage medium

Technical Field

The present invention relates to the field of image processing technologies, and in particular, to a device, a system, and a storage medium for measuring myocardial hypertrophy.

Background

Cardiovascular disease has become one of the major diseases threatening human life safety, and doctors assist in diagnosing various vascular diseases through vascular imaging technology. In the clinic, in the medical image analysis of cardiovascular structures by doctors, quantitative results need to be obtained, so that corresponding treatment schemes are determined, and the automatic measurement and diagnosis can accelerate the diagnosis efficiency and reduce a great deal of repeated operations of doctors. However, for coronary CTA image data, the doctor needs to manually measure the myocardial thickness at the atrioventricular site to diagnose whether the patient is a cardiac hypertrophy patient. The process is complicated and laborious.

Disclosure of Invention

The invention mainly aims to provide a myocardial hypertrophy measuring device, a myocardial hypertrophy measuring system and a storage medium, and aims to solve the technical problem that in the prior art, a doctor needs to manually measure the myocardial thickness of a patient to diagnose whether the patient is a myocardial hypertrophy patient or not.

In order to achieve the above object, the present invention provides a myocardial hypertrophy measuring apparatus comprising:

An interface configured to receive a coronary CTA image of a heart;

a processor configured to:

Based on the coronary artery CTA image, respectively acquiring a myocardial segmentation binary image of the heart and a heart segmentation image of the heart;

Based on the heart segmentation map, determining a left atrioventricular junction position binary map and a right atrioventricular junction position binary map;

Determining a left atrioventricular junction centroid according to the left atrioventricular junction position binary map, and determining a right atrioventricular junction centroid according to the right atrioventricular junction position binary map;

Determining a maximum distance point from the myocardial to the centroid of the left atrioventricular junction position, and determining a center point between the centroid of the left atrioventricular junction position and the maximum distance point, wherein the maximum distance point is determined as a cardiac apex position;

acquiring a short axis plane, and intercepting cardiac muscle based on the short axis plane to obtain a short axis myocardial annular segmentation map, wherein the short axis plane is a plane which is perpendicular to the connecting line of the centroid of the boundary position of the left ventricle and the apex position and passes through the center point;

determining a long axis plane based on the left atrioventricular junction centroid, the right atrioventricular junction centroid, and the apex position;

based on the long axis plane, intercepting the short axis myocardial annular segmentation map to obtain a target connected domain;

And determining the positions of two endpoints in the target connected domain, determining the distance between the two endpoints according to the positions of the two endpoints, and taking the distance as a myocardial thickness measurement value at the middle.

Optionally, the cardiac segmentation map comprises a left ventricle, a right ventricle, a left atrium, and a right atrium, wherein,

The processor is further configured to:

respectively expanding the left ventricle and the left atrium, and determining a binary image of the boundary position of the left ventricle based on the intersection after the intersection of the expanded left ventricle and the expanded left atrium is not an empty set;

and respectively expanding the right ventricle and the right atrium, and determining a binary image of the boundary position of the right atrium based on the intersection after the intersection of the expanded right ventricle and the expanded right atrium is not an empty set.

Optionally, the processor is further configured to:

determining a right ventricle centroid according to the heart segmentation map;

based on the long axis plane, intercepting the short axis myocardial annular segmentation map to obtain a first communication domain and a second communication domain;

Determining a first distance of the right ventricular centroid to a midpoint of the first connected domain, and determining a second distance of the right ventricular centroid to a midpoint of the second connected domain;

And determining a smaller distance from the first distance and the second distance, and taking a connected domain corresponding to the smaller distance as a target connected domain.

Optionally, the processor is further configured to:

determining the number of pixels occupied by the maximum distance of the distance between any two points in the target connected domain based on the linear characteristics of the single pixels of the target connected domain;

and determining a myocardial thickness measurement value according to the occupied pixel number.

Optionally, the processor is further configured to:

inputting the coronary CTA image into a trained first depth convolution network to segment cardiac muscle, so as to obtain a cardiac muscle segmentation binary image of the heart;

And inputting the coronary artery CTA image into a trained second depth convolution network to divide the heart, so as to obtain a heart division map of the heart.

Optionally, the processor is further configured to:

Determining a diagnostic threshold for myocardial hypertrophy;

judging whether the measured value of the myocardial thickness at the middle part is larger than the diagnosis threshold value of myocardial hypertrophy;

and if the measured value of the myocardial thickness at the middle part is larger than the diagnosis threshold value of the myocardial hypertrophy, diagnosing that the patient corresponding to the heart is a patient with myocardial hypertrophy.

Optionally, the processor is further configured to:

Determining a first target point in a line segment O _{Left room}O_{Apex of heart} of the left atrioventricular junction position centroid and the maximum distance point, wherein the distance between the first target point and the left atrioventricular junction position centroid is between 0.2 and 0.3O _{Left room}O_{Apex of heart};

Acquiring a first short axis plane, and intercepting cardiac muscle based on the first short axis plane to obtain a first short axis myocardial annular segmentation map, wherein the first short axis plane is a plane perpendicular to the connecting line of the centroid of the boundary position of the left ventricle and the maximum distance point and passing through the first target point;

based on the long axis plane, intercepting the first short axis myocardial annular segmentation map to obtain a target connected domain;

And determining the positions of two endpoints in the target connected domain, determining the distance between the two endpoints according to the positions of the two endpoints, and taking the distance as a myocardial thickness measurement value at the bottom of the heart.

Optionally, the processor is further configured to:

Determining a second target point in a line segment O _{Left room}O_{Apex of heart} of the left atrioventricular junction position centroid and the maximum distance point, wherein the distance between the second target point and the left atrioventricular junction position centroid is between 0.7 and 0.8O _{Left room}O_{Apex of heart};

Acquiring a second short axis plane, and intercepting cardiac muscle based on the second short axis plane to obtain a second short axis myocardial annular segmentation map, wherein the second short axis plane is a plane perpendicular to the connecting line of the centroid of the boundary position of the left ventricle and the maximum distance point and passing through the second target point;

based on the long axis plane, intercepting the second short axis myocardial annular segmentation map to obtain a target connected domain;

Skeletonizing the target connected domain to obtain a skeletonized target connected domain;

and determining the positions of two endpoints based on the skeletonized target connected domain, determining the distance between the two endpoints according to the positions of the two endpoints, and taking the distance as a myocardial thickness measurement value at the apex of the heart.

In addition, in order to achieve the above object, the present invention also proposes a myocardial hypertrophy measuring system comprising a myocardial hypertrophy measuring apparatus as described above:

The myocardial hypertrophy diagnosis apparatus includes:

An interface configured to receive a coronary CTA image of a heart;

a processor configured to:

In addition, in order to achieve the above object, the present invention also proposes a storage medium having stored thereon a myocardial hypertrophy measurement program which, when executed by a processor, realizes the steps of:

determining a maximum distance point from the myocardial to the centroid of the boundary position of the left ventricle, and determining a center point between the centroid of the boundary position of the left ventricle and the maximum distance point;

Acquiring a short axis plane, and intercepting cardiac muscle based on the short axis plane to obtain a short axis myocardial annular segmentation map, wherein the short axis plane is a plane which is perpendicular to the connecting line of the centroid of the boundary position of the left ventricle and the maximum distance point and passes through the center point;

Determining a long axis plane based on the left atrioventricular junction centroid, the right atrioventricular junction centroid, and the maximum distance point;

and determining the maximum distance of the distance between any two points in the target communication domain as a myocardial thickness measurement value at the middle.

The invention provides a myocardial hypertrophy measuring device, a myocardial hypertrophy measuring system and a storage medium, wherein the myocardial hypertrophy diagnosing device comprises an interface, a processor, a left room junction position binary map and a right room junction position binary map, wherein the interface is configured to receive a coronary artery CTA image of a heart, the processor is configured to respectively acquire a myocardial segmentation binary map of the heart and a heart segmentation map of the heart based on the coronary artery CTA image, determine a left room junction position binary map and a right room junction position binary map based on the heart segmentation map, determine a left room junction position centroid according to the left room junction position binary map, determine a right room junction position centroid according to the right room junction position binary map, determine a maximum distance point from the heart muscle to the left room junction position centroid, determine a center point of the left room junction position centroid and the maximum distance point, wherein the maximum distance point is determined to be a heart apex position, acquire a short axis plane, intercept a short axis annular segmentation map based on the short axis plane, wherein the short axis plane is a short axis annular segmentation map which is perpendicular to the left room junction position and the heart, the long axis is obtained by intercepting the heart apex position, the long axis is determined based on the long axis and the center point in the annular intersection plane, the long axis is communicated with the object domain, and the center is determined

And determining the distance between the two endpoints according to the positions of the two endpoints, wherein 5 takes the distance as a myocardial thickness measurement value at the middle. By the above way, the method can quickly and accurately

The myocardial thickness was measured.

Drawings

FIG. 1 is a schematic diagram of a myocardial hypertrophy measurement system of a hardware running environment according to an embodiment of the present invention;

FIG. 2 is a flowchart of a processing method of a first embodiment of the myocardial hypertrophy measuring apparatus of the present invention;

FIG. 3 is a flowchart of a processing method of a first embodiment of the myocardial hypertrophy measuring apparatus of the present invention;

FIG. 4 shows a short-axis myocardial ring taken from the major-axis plane in the first embodiment of the myocardial hypertrophy measuring apparatus of the present invention

Schematic diagram of a shape segmentation map;

FIG. 5 is a flowchart of a processing method of a second embodiment of the myocardial hypertrophy measuring apparatus of the present invention;

fig. 6 is a flowchart of a processing method of a third embodiment of the myocardial hypertrophy measuring apparatus of the present invention.

The achievement of the objects, functional features and advantages of the present invention will be further described with reference to the accompanying drawings, in conjunction with the embodiments.

Detailed Description

It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.

Referring to fig. 1, fig. 1 is a schematic diagram of a myocardial hypertrophy measurement system 5 of a hardware running environment according to an embodiment of the present invention.

As shown in fig. 1, the myocardial hypertrophy measurement system may comprise a processor 1001, such as a central processing unit (Central Processing Unit, CPU), a communication bus 1002, a user interface 1003, a network interface 1004, a memory 1005. Wherein the communication bus 1002 is used to enable interfacing between these components

And (5) communication is connected. The user interface 1003 may include a Display, an input unit such as a Keyboard 0 (Keyboard), and the optional user interface 1003 may further include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a Wireless interface (e.g., a Wireless-Fidelity (Wi-Fi) interface). The Memory 1005 may be a high-speed random access Memory (Random Access Memory, RAM) Memory or a stable Non-Volatile Memory (NVM), such as a disk Memory. The memory 1005 may also optionally be a storage device separate from the processor 1001 described above.

It will be appreciated by those skilled in the art that the configuration shown in fig. 1 is not limiting of the myocardial hypertrophy measurement system and may include more or fewer components than shown, or certain components in combination, or a different arrangement of components.

As shown in fig. 1, an operating system, a network communication module, a user interface module, and a myocardial hypertrophy measurement program may be included in the memory 1005 as one storage medium.

In the myocardial hypertrophy measuring system shown in fig. 1, the network interface 1004 is mainly used for data communication with a network server, the user interface 1003 is mainly used for data interaction with a user, and the processor 1001 and the memory 1005 in the myocardial hypertrophy measuring system of the present invention can be arranged in the myocardial hypertrophy measuring system, and the myocardial hypertrophy measuring system calls the myocardial hypertrophy measuring program stored in the memory 1005 through the processor 1001.

Based on the above hardware structure, an embodiment of the myocardial hypertrophy measuring apparatus of the present invention is presented.

Referring to fig. 2, fig. 2 is a flowchart illustrating a processing method of a first embodiment of a cardiac hypertrophy measurement apparatus according to the present invention.

In this embodiment, the myocardial hypertrophy diagnosis apparatus includes:

an interface configured to:

Step S10, a coronary artery CTA image of the heart is received.

It should be noted that, the coronary CTA (Computed Tomography Angiography) image is obtained through CT blood vessel imaging, which is a very important part in CT clinical application, and conventional CT panning often has difficulty in displaying the coronary blood vessel due to the natural contrast difference between the coronary blood vessel and its background soft tissue. During CTA examination, contrast agent needs to be introduced to change the image contrast of the coronary blood vessel and the background tissue, so that the coronary blood vessel is highlighted. The coronary artery CTA image is a 3D image, has better three-dimensional information, and can intuitively and three-dimensionally present the three-dimensional spatial information of the coronary artery by carrying out three-dimensional reconstruction on the coronary artery CTA.

A processor configured to:

step S20, respectively acquiring a myocardial segmentation binary image of the heart and a heart segmentation image of the heart based on the coronary artery CTA image.

In an embodiment, the processor is further configured to:

It should be noted that, a large number of coronary CTA images may be input into the first deep convolutional network for training to obtain a trained first deep convolutional network, and a large number of coronary CTA images may be input into the second deep convolutional network for training to obtain a trained second deep convolutional network.

And step S30, determining a left compartment juncture position binary image and a right compartment juncture position binary image based on the heart segmentation image.

The atrioventricular junction refers to the junction between the atrium and the ventricle of the heart.

It should be noted that, the boundary position of the left atrium and the left ventricle refers to the boundary position of the left atrium and the left ventricle, and the boundary position of the right atrium and the right ventricle refers to the boundary position of the right atrium and the right ventricle.

In one embodiment, the cardiac segmentation map includes a left ventricle, a right ventricle, a left atrium, and a right atrium, wherein,

The processor is further configured to:

The expansion means expanding the boundary of the binarized object by an image processing operation method, and combining all background points in contact with the object into the object to expand the boundary of the object outwards.

In a specific implementation, as shown in fig. 3, the left graph in fig. 3 refers to a heart segmentation graph, and the right graph refers to a left atrioventricular junction position binary graph and a right atrioventricular junction position binary graph.

In a specific implementation, the expansion rate can be preset, then the left ventricle and the left atrium are respectively expanded according to the expansion rate, when the intersection of the expanded left ventricle and the expanded left atrium is an empty set, the expanded left ventricle and the expanded left atrium need to be continuously expanded, so that the intersection of the expanded left ventricle and the expanded left atrium is not the empty set, and then the binary image of the boundary position of the left ventricle is determined according to the intersection of the expanded left ventricle and the expanded left atrium.

In a specific implementation, the expansion rate may be preset, and then the right ventricle and the right atrium are respectively expanded according to the expansion rate, when the intersection of the expanded right ventricle and the expanded right atrium is an empty set, the expanded right ventricle and the expanded right atrium need to be continuously expanded, so that the intersection of the expanded right ventricle and the expanded right atrium is not the empty set, and then the binary map of the boundary position of the right atrium is determined according to the intersection of the expanded right ventricle and the expanded right atrium.

In this embodiment, the left atrium and the left ventricle in the heart segmentation image are simultaneously inflated to obtain the intersection of the inflated left ventricle and the inflated left atrium, and then the centroid of the boundary position of the left atrium is determined based on the intersection, so that the centroid of the boundary position of the left atrium can be rapidly and accurately determined.

And S40, determining a left atrioventricular junction position centroid according to the left atrioventricular junction position binary diagram, and determining a right atrioventricular junction position centroid according to the right atrioventricular junction position binary diagram.

And S50, determining a maximum distance point from the myocardial to the centroid of the boundary position of the left ventricle, and determining a center point between the centroid of the boundary position of the left ventricle and the maximum distance point, wherein the maximum distance point is determined to be the apex position.

The center point is spaced from the centroid of the left atrioventricular junction by 0.5O _{Left room}O_{Apex of heart}.

It will be appreciated that the apex position may also be obtained by other means, such as, for example, position detection.

And S60, acquiring a short axis plane, and intercepting cardiac muscle based on the short axis plane to obtain a short axis myocardial annular segmentation map, wherein the short axis plane is a plane which is perpendicular to the connecting line of the centroid of the left atrioventricular junction position and the apex position and passes through the center point.

It should be noted that, since the short axis plane is a plane perpendicular to the line connecting the first reference point and the second reference point and passing through the center point, the first reference point may be the centroid of the boundary position of the left ventricle, and the second reference point may be the apex position. Whichever of the short axis planes obtained as the first reference point and the second reference point is adopted is a criterion for setting the judgment of the myocardial thickness, and the selection of the reference point position is not unique.

It should be noted that the short axis plane may also be determined based on the left atrioventricular junction centroid and other reference points that the apex position can inspire, preferably as the left and right atrial centroids, etc.

And step S70, determining a long axis plane based on the left compartment boundary position centroid, the right compartment boundary position centroid and the maximum distance point.

And S80, based on the long-axis plane, intercepting the short-axis myocardial annular segmentation map to obtain a target connected domain.

The short-axis myocardial annular segmentation map is truncated based on the long-axis plane to obtain two connected domains, and the target connected domain can be determined from the two connected domains.

In a specific implementation, as shown in fig. 4, two connected domains are obtained by intercepting a short-axis myocardial annular segmentation map through a long-axis plane.

In an embodiment, the processor is further configured to:

determining a right ventricle centroid according to the heart segmentation map;

The target connected domain may be understood as a connected domain closest to the centroid of the right ventricle or the centroid of the right atrium.

And step S90, determining positions of two endpoints in the target connected domain, determining a distance between the two endpoints according to the positions of the two endpoints, and taking the distance as a myocardial thickness measurement value at the middle.

In an embodiment, the processor is further configured to:

In particular implementations, the myocardial thickness measurement may be determined from the product of the distance occupied by each pixel and the number of pixels.

In an embodiment, the processor is further configured to:

Determining a diagnostic threshold for myocardial hypertrophy;

In clinical diagnosis of myocardial hypertrophy, the myocardial hypertrophy is usually determined based on the myocardial thickness at the position near the inter-ventricular groove, and when the myocardial thickness is greater than 15mm, it is possible to diagnose myocardial hypertrophy, and preferably, the myocardial hypertrophy diagnosis threshold is set to 15mm.

The embodiment comprises the steps of receiving a coronary artery CTA image of a heart, respectively obtaining a myocardial segmentation binary image of the heart and a heart segmentation image of the heart based on the coronary artery CTA image, determining a left room junction position binary image and a right room junction position binary image based on the heart segmentation image, determining a left room junction position centroid according to the left room junction position binary image, determining a right room junction position centroid according to the right room junction position binary image, determining a maximum distance point from the myocardial to the left room junction position centroid, determining a center point of the left room junction position centroid and the maximum distance point, determining a short axis plane, intercepting cardiac muscle based on the short axis plane, obtaining a myocardial annular segmentation image, determining a short axis plane based on the short axis plane, wherein the short axis plane is a plane which is perpendicular to a connecting line of the left room position centroid and the apex position and passes through the center point, determining a long axis plane based on the left room junction position centroid, the right room junction position centroid and the long axis boundary position, determining a myocardial annular segmentation plane based on the two end points, and obtaining a measured value of the two end points, and connecting the two end points in a target domain. By the above manner, the myocardial thickness can be measured quickly and accurately.

Referring to fig. 5, fig. 5 is a flowchart illustrating a processing method of a second embodiment of a cardiac hypertrophy measurement apparatus according to the present invention.

Based on the first embodiment, the processing method of the present embodiment further includes:

step S110, determining a first target point in a line segment O _{Left room}O_{Apex of heart} between the centroid of the boundary position of the left ventricle and the maximum distance point, wherein the distance between the first target point and the centroid of the boundary position of the left ventricle is between 0.2 and 0.3O _{Left room}O_{Apex of heart}.

It should be noted that, the corresponding myocardial thickness at any point may be obtained according to the requirement of the doctor, specifically, the corresponding myocardial thickness may be obtained by adjusting the position of the first target point, and preferably, when the distance between the first target point and the centroid of the boundary position of the left ventricle is 0.25O _{Left room}O_{Apex of heart}, the myocardial thickness measurement at the fundus can be accurately determined.

Step S111, a first short axis plane is obtained, and a first short axis myocardial annular segmentation map is obtained by cutting the myocardium based on the first short axis plane, wherein the first short axis plane is a plane perpendicular to the connecting line of the centroid of the boundary position of the left ventricle and the maximum distance point and passing through the first target point.

And step S112, based on the long axis plane, intercepting the first short axis myocardial annular segmentation map to obtain a target connected domain.

The first short-axis myocardial annular segmentation map is truncated based on the long-axis plane to obtain two connected domains, and the target connected domain can be determined from the two connected domains.

And S113, determining positions of two endpoints in the target connected domain, determining a distance between the two endpoints according to the positions of the two endpoints, and taking the distance as a myocardial thickness measurement value at the bottom of the heart.

In a specific implementation, the myocardial thickness measurement value at the bottom of the heart can be determined by calculating the spatial distance between the coordinates of two end points of the target connected domain.

In an embodiment, the processor is further configured to:

and determining the myocardial thickness measurement value at the bottom of the heart according to the occupied pixel number.

In a particular implementation, the myocardial thickness measurements at the fundus can be determined from the product of the distance occupied by each pixel and the number of pixels.

The method comprises the steps of determining a first target point in a line segment O _{Left room}O_{Apex of heart} of a centroid of a boundary position of a left ventricle and a maximum distance point, wherein the distance between the first target point and the centroid of the boundary position of the left ventricle is 0.2-0.3O _{Left room}O_{Apex of heart}, obtaining a first short axis plane, intercepting cardiac muscle based on the first short axis plane to obtain a first short axis myocardial annular segmentation map, wherein the first short axis plane is a plane perpendicular to a line connecting the centroid of the boundary position of the left ventricle and the maximum distance point and passing through the first target point, intercepting the first short axis myocardial annular segmentation map based on the long axis plane to obtain a target communication domain, and determining the maximum distance of the distance between any two points in the target communication domain as a myocardial thickness measurement value at the bottom of a heart. By the method, the myocardial thickness measurement value at the bottom of the heart can be rapidly and accurately determined.

Referring to fig. 6, fig. 6 is a flowchart illustrating a processing method of a third embodiment of a cardiac hypertrophy measurement apparatus according to the present invention.

Step S120, determining a second target point in a line segment O _{Left room}O_{Apex of heart} between the centroid of the boundary position of the left ventricle and the maximum distance point, wherein the distance between the second target point and the centroid of the boundary position of the left ventricle is between 0.7 and 0.8O _{Left room}O_{Apex of heart}.

It should be noted that, the corresponding myocardial thickness at any point can be obtained according to the requirement of the doctor, specifically, the corresponding myocardial thickness can be obtained by adjusting the position of the second target point, preferably, when the distance between the first target point and the centroid of the boundary position of the left ventricle is 0.75O _{Left room}O_{Apex of heart}, the myocardial thickness measurement value at the apex can be accurately determined.

Step S121, a second short axis plane is obtained, and a second short axis myocardial annular segmentation map is obtained by cutting the myocardium based on the second short axis plane, wherein the second short axis plane is a plane perpendicular to the connecting line of the centroid of the boundary position of the left ventricle and the maximum distance point and passing through the second target point.

And step S122, based on the long axis plane, intercepting the second short axis myocardial annular segmentation map to obtain a target connected domain.

And step S123, skeletonizing the target connected domain to obtain a skeletonized target connected domain.

And S124, determining the positions of two endpoints based on the skeletonized target connected domain, determining the distance between the two endpoints according to the positions of the two endpoints, and taking the distance as a myocardial thickness measurement value at the apex of the heart.

In an embodiment, the processor is further configured to:

and determining the myocardial thickness measurement value at the apex of the heart according to the occupied pixel number.

In a specific implementation, the myocardial thickness measurement at the apex may be determined from the product of the distance occupied by each pixel and the number of pixels.

The embodiment comprises the steps of determining a second target point in a line segment O _{Left room}O_{Apex of heart} of the left atrioventricular junction position centroid and the maximum distance point, wherein the distance between the second target point and the left atrioventricular junction position centroid is between 0.7-0.8O _{Left room}O_{Apex of heart}, obtaining a second short axis plane, intercepting cardiac muscle based on the second short axis plane to obtain a second short axis myocardial annular segmentation map, wherein the second short axis plane is a plane perpendicular to a connecting line of the left atrioventricular junction position centroid and the maximum distance point and passing through the second target point, intercepting the second short axis myocardial annular segmentation map based on the long axis plane to obtain a target connected domain, skeletonizing the target connected domain to obtain a skeletonized target connected domain, determining the positions of two end points based on the skeletonized target connected domain, determining the distance between the two end points according to the positions of the two end points, and taking the distance as a myocardial thickness measurement value at the apex. By the method, the myocardial thickness measurement at the apex of the heart can be measured rapidly and accurately.

It should be noted that the above-described working procedure is merely illustrative, and does not limit the scope of the present invention, and in practical application, a person skilled in the art may select part or all of them according to actual needs to achieve the purpose of the embodiment, which is not limited herein.

Furthermore, it should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising one does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.

The foregoing embodiment numbers of the present invention are merely for the purpose of description, and do not represent the advantages or disadvantages of the embodiments.

From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (e.g. Read Only Memory)/RAM, magnetic disk, optical disk) and including several instructions for causing a terminal device (which may be a mobile phone, a computer, a server, or a network device, etc.) to perform the method according to the embodiments of the present invention.

The foregoing description is only of the preferred embodiments of the present invention, and is not intended to limit the scope of the invention, but rather is intended to cover any equivalents of the structures or equivalent processes disclosed herein or in the alternative, which may be employed directly or indirectly in other related arts.

Claims

1. A myocardial hypertrophy measuring device, characterized in that the myocardial hypertrophy diagnosing device comprises:

an interface configured to receive a coronary CTA image of the heart;

Processor, which is configured as:

Based on the coronary CTA image, respectively obtaining a myocardial segmentation binary image of the heart and a cardiac segmentation image of the heart;

Based on the cardiac segmentation map, determining a left atrioventricular junction position binary map and a right atrioventricular junction position binary map;

Determine the centroid of the left atrioventricular junction position according to the left atrioventricular junction position binary map, and determine the centroid of the right atrioventricular junction position according to the right atrioventricular junction position binary map;

Determine the maximum distance point from the myocardium to the mass center of the left atrioventricular junction, and determine the center point between the mass center of the left atrioventricular junction and the maximum distance point, wherein the maximum distance point is determined to be the apex position;

Acquire a short-axis plane, and cut the myocardium based on the short-axis plane to obtain a short-axis myocardial annular segmentation map, wherein the short-axis plane is a plane perpendicular to a line connecting the centroid of the left atrioventricular junction position and the apex position and passing through the center point;

Determine the long axis plane based on the left atrioventricular junction position centroid, the right atrioventricular junction position centroid and the apex position;

Based on the long-axis plane, the short-axis myocardial annular segmentation map is intercepted to obtain a target connected domain;

The positions of two endpoints in the target connected domain are determined, and the distance between the two endpoints is determined according to the positions of the two endpoints, and the distance is used as the measurement value of the myocardial thickness at the middle.

2. The device according to claim 1, wherein the cardiac segmentation map includes a left ventricle, a right ventricle, a left atrium and a right atrium; wherein,

The processor is further configured to:

Expanding the left ventricle and the left atrium respectively, after making the intersection of the expanded left ventricle and the expanded left atrium not an empty set, determining the left atrioventricular junction position binary map based on the intersection;

The right ventricle and the right atrium are expanded respectively, and after the intersection of the expanded right ventricle and the expanded right atrium is not an empty set, the binary map of the right atrioventricular junction position is determined based on the intersection.

3. The apparatus according to claim 2, wherein the processor is further configured to:

determining the right ventricular centroid according to the cardiac segmentation map;

Based on the long-axis plane, the short-axis myocardial annular segmentation map is intercepted to obtain a first connected domain and a second connected domain;

Determine a first distance from the center of mass of the right ventricle to a midpoint of the first connected domain, and determine a second distance from the center of mass of the right ventricle to a midpoint of the second connected domain;

A smaller distance between the first distance and the second distance is determined, and a connected domain corresponding to the smaller distance is used as a target connected domain.

4. The apparatus according to claim 1, wherein the processor is further configured to:

Based on the straight line characteristics of a single pixel of the target connected domain, determining the number of pixels occupied by the maximum distance between any two points in the target connected domain;

A myocardial thickness measurement is determined based on the number of occupied pixels.

5. The apparatus according to claim 1, wherein the processor is further configured to:

Inputting the coronary CTA image into a trained first deep convolutional network to segment the myocardium, thereby obtaining a myocardial segmentation binary image of the heart;

The coronary CTA image is input into a trained second deep convolutional network to segment the heart and obtain a heart segmentation map of the heart.

6. The apparatus according to claim 1, wherein the processor is further configured to:

Determine the diagnostic threshold for myocardial hypertrophy;

Determining whether the middle myocardial thickness measurement value is greater than the myocardial hypertrophy diagnosis threshold;

If it is determined that the measured value of the myocardial thickness at the middle is greater than the myocardial hypertrophy diagnosis threshold, the patient corresponding to the heart is diagnosed as a patient with myocardial hypertrophy.

7. The apparatus according to claim 1, wherein the processor is further configured to:

Determine a first target point in the line _segment O between the mass center of the left _{atrioventricular} junction and the maximum distance point, wherein the distance between the first target point and the mass center of the left atrioventricular junction is between 0.2-0.3O _{left atrioventricular} O _apex ;

Acquire a first short-axis plane, and intercept the myocardium based on the first short-axis plane to obtain a first short-axis myocardial annular segmentation map, wherein the first short-axis plane is a plane perpendicular to a line connecting the centroid of the left atrioventricular junction position and the maximum distance point and passing through the first target point;

Based on the long-axis plane, intercepting the first short-axis myocardial annular segmentation map to obtain a target connected domain;

The positions of two endpoints in the target connected domain are determined, and the distance between the two endpoints is determined according to the positions of the two endpoints, and the distance is used as the measurement value of the myocardial thickness at the heart bottom.

8. The apparatus according to claim 1, wherein the processor is further configured to:

Determine a second target point in the line _segment O between the mass center of the left _{atrioventricular} junction and the maximum distance point, wherein the distance between the second target point and the mass center of the left atrioventricular junction is between 0.7-0.8O _{left atrioventricular} O _apex ;

Acquire a second short-axis plane, and cut the myocardium based on the second short-axis plane to obtain a second short-axis myocardial annular segmentation map, wherein the second short-axis plane is a plane perpendicular to a line connecting the centroid of the left atrioventricular junction position and the maximum distance point and passing through the second target point;

Based on the long-axis plane, intercepting the second short-axis myocardial annular segmentation map to obtain a target connected domain;

Performing skeletonization processing on the target connected domain to obtain a skeletonized target connected domain;

The positions of two endpoints are determined based on the skeletonized target connected domain, the distance between the two endpoints is determined according to the positions of the two endpoints, and the distance is used as the measurement value of the myocardial thickness at the apex.

9. A myocardial hypertrophy measurement system, characterized in that the system comprises:

The measuring device according to any one of claims 1 to 8;

The myocardial hypertrophy diagnostic device comprises:

an interface configured to receive a coronary CTA image of the heart;

Processor, which is configured as:

10. A storage medium, characterized in that a myocardial hypertrophy measurement program is stored on the storage medium, and when the myocardial hypertrophy measurement program is executed by a processor, the following steps are implemented:

Based on the coronary CTA image, a myocardial segmentation binary image of the heart and a cardiac segmentation image of the heart are respectively obtained;