WO2022000726A1

WO2022000726A1 - Method and system for obtaining connected domains of left atrium and left ventricle on basis of ct image

Info

Publication number: WO2022000726A1
Application number: PCT/CN2020/109806
Authority: WO
Inventors: 冯亮; 王之元; 刘广志; 陈韵岱
Original assignee: 苏州润迈德医疗科技有限公司
Priority date: 2020-06-29
Filing date: 2020-08-18
Publication date: 2022-01-06
Also published as: CN111815586A; CN111815586B

Abstract

The present application provides a method and system for obtaining connected domains of the left atrium and the left ventricle on the basis of a CT image. The method comprises: removing the lungs, descending aorta, spine, and ribs from a CT image to obtain a new image; obtaining an aortic center line in the new image; obtaining an aortic image according to the extension direction of the aortic center line and the Bezier curve rule; and after the aortic image is removed from the new image, picking up pixel points, around the point of center of gravity the left ventricle, having the grayscale values Q greater than the grayscale threshold Q_descending of the descending aorta, to obtain a connected domain image of the left atrium and the left ventricle. The present application relates to a novel method for obtaining the left atrium and the left ventricle, and the method has advantages of being rapid and accurate in extraction and high in calculation speed.

Description

Method and system for obtaining the connected domain of left atrium and left ventricle based on CT image

technical field

The present invention relates to the technical field of coronary medicine, and in particular, to a method and system for acquiring the connected areas of the left atrium and the left ventricle based on CT images.

Background technique

Cardiovascular disease is the leading cause of death in the industrialized world. The major form of cardiovascular disease is caused by the chronic accumulation of fatty substances in the inner tissue layers of the arteries supplying the heart, brain, kidneys and lower extremities. Progressive coronary artery disease restricts blood flow to the heart. Due to the lack of accurate information provided by current non-invasive tests, many patients require invasive catheter procedures to evaluate coronary blood flow. Therefore, there is a need for a non-invasive method for quantifying blood flow in human coronary arteries to assess the functional significance of possible coronary artery disease. A reliable assessment of arterial volume will therefore be important for treatment planning addressing the patient's needs. Recent studies have demonstrated that hemodynamic properties, such as fractional flow reserve (FFR), are important indicators for determining optimal treatment for patients with arterial disease. Routine assessment of fractional flow reserve uses invasive catheterization to directly measure blood flow properties, such as pressure and flow rate. However, these invasive measurement techniques present risks to patients and can result in significant costs to the health care system.

Computed tomography arterial angiography is a computed tomography technique used to visualize arterial blood vessels. For this purpose, a beam of X-rays is passed from a radiation source through a region of interest in the patient's body to obtain projection images.

Because the CT data in the prior art cannot be obtained to obtain the left atrium, the left ventricle, or the method for obtaining the left atrium and the left ventricle is complicated, resulting in a large amount of computation, slow computation speed and inaccurate computation.

SUMMARY OF THE INVENTION

The present invention provides a method and system for picking up a point on the centerline of the aorta based on a CT image, so as to solve the problem that the CT data in the prior art cannot obtain the center of gravity of the heart and the spine or the method for obtaining the center of gravity of the heart and the spine is more complicated problem.

In order to achieve the above objects, in a first aspect, the present application provides a method for acquiring the connected domains of the left atrium and the left ventricle based on CT images, including:

Remove the lungs, descending aorta, spine and ribs from the CT image to obtain a new image;

obtaining the aortic centerline of the new image;

According to the extension direction of the aorta centerline, according to the Bezier curve rule, acquire the aorta image;

After removing the aorta image from the new image, select the pixels whose gray value Q around the center of gravity of the left ventricle is greater than the gray threshold Q of the _descending aorta, and obtain the connected domain between the left atrium and the left ventricle image.

Optionally, in the above-mentioned method for obtaining the connected domain of the left atrium and left ventricle based on CT images, the method for obtaining the aortic centerline of the new image includes:

Layer slices starting from the top layer of the new image to obtain a two-dimensional image group;

performing binarization processing on the two-dimensional image group to obtain a binarized image group;

_{N≤Nthreshold 1} is obtained from the slices of each layer in the binarized image group, R= _{Rthreshold 1} ±m, where N represents the number of pixels, then the detection within the slice of the kth layer is 1 circle, take the center of the circle as the center P _5k , and the radius of the circle corresponding to _{the center P 5k} _{is R k} ;

The center line of the aorta is obtained by smoothly connecting the circle centers P _{5k in sequence.}

Optionally, in the above-mentioned method for obtaining the connected domain of the left atrium and left ventricle based on CT images, the two-dimensional image group is subjected to binarization processing, and the method for obtaining the binarized image group includes:

Set the coronary tree grayscale threshold Q _{coronary 1} ; according to

binarizing slices of each layer of the new image from which the lungs, descending aorta, spine and ribs are removed to remove impurities in the new image from which the lungs, descending aorta, spine and ribs are removed point to obtain the binarized image group;

Among them, m is a positive integer, Q _m represents the grayscale value corresponding to the mth pixel point PO, and P(m) represents the pixel value corresponding to the mth pixel point PO.

Optionally, in the above-mentioned method for obtaining the connected domain of the left atrium and left ventricle based on CT images, N≤Nthreshold ₁ is obtained from the slices of each layer in the binarized image group, and R= _{Rthreshold 1} ± m, where N represents the number of pixels, then detect a circle in the slice of the kth layer, take the center of the circle as the center P _5k , and the radius of the circle corresponding to _{the center P 5k} _{is R k} Methods include:

establishing a search engine list for each layer of the slice in the binarized image group;

Search the circle of each layer slice, compare the number of pixels in the search engine list of each layer and the radius of the circle, and find the center point that meets the conditions;

If no matching center point can be found, search the center point of the next layer of slices.

Optionally, the above-mentioned method for obtaining the connected domain of the left atrium and the left ventricle based on CT images, the method for establishing a search engine list for each layer of the slice in the binarized image group includes:

The search engine list includes: a point list and a radius list, and the points with a pixel value of 1 extracted from the binarized image of each layer are correspondingly filled into the point list.

Optionally, the above-mentioned method for obtaining the connected domain of left atrium and left ventricle based on CT image, the circle of each layer slice is searched, and the number of pixels in the search engine list of each layer and the radius of the circle are compared, Methods to find the center point of the circle that meet the criteria include:

D) Set the threshold of the number of pixels in the point list of each layer of the slice to be N _{threshold 1} , and the radius threshold to be R _{threshold 1} , and perform step E for each layer of the slice in turn from the top layer to the process of step 1;

E) If N _{k ≤} N _{threshold 1} , R _k =R _{threshold 1} ±m, where N _k represents the number of pixels in the point list of the slice at the k th layer, then detect the k th layer For a circle in the slice, take the center of the circle as the center O _k , perform step I, and perform step H if the circle is not detected;

F) If N _{k ≤} N _{threshold 1} , R _k ≠R _{threshold 1} ±m, then detect 3 circles in the slice of the kth layer, if 3 circles are detected, go to step I, if 3 circles are not detected The circle then carries out the described step H;

G) If N _k > N _{threshold 1} , then re-determine the center of the circle, take the point with the closest distance between the center of the circle in the k-1 slice and the end point D in the point list as the center O _k , and proceed to step I, If no circle is detected, go to step H;

H) Detect _{the relationship between N k} and N _{threshold 1-1} , repeat steps E to G, if still no circle is detected, then detect _{the relationship between N and N threshold 1-2} , repeat steps E to Described step G; And so on, until the center of circle O _{k is} found;

1) take described circle center O _k as starting point, find 3 grayscale values 0 points along the positive direction of X axis, negative direction and Y axis positive direction respectively; Determine a circle according to 3 points and find center P _5k and radius R _k , to get the point on the centerline of the aorta.

Optionally, the above-mentioned method for obtaining the connected domain of the left atrium and the left ventricle based on the CT image further includes: filtering the center P _5k to generate a new point list, including:

J) Set another radius threshold of the pixels in the radius list of each layer of the slice to be R _threshold ₂ _{, if the radius R k of} the k-th slice of the slice <R _{threshold 2} , repeat the steps E to the process of the step I, until the center P _{5k of the} _{radius R k} ≥ R _{threshold 2} is found;

K) If the _{gray value of the center P 5k} on the new image from which the lungs, descending aorta, spine and ribs are removed is less than 0, repeat the process from step E to step I until the radius is found R ₁ ≥ R _{threshold 2} _{, and the center P 5k} of the circle whose gray value is greater than or equal to 0;

L) _{Add the circle center P 5k with} _{R 1} ≥ R _{threshold 2} and the gray value greater than or equal to 0 to the entry point list to generate a new radius list, and _{add the radius R k} into the radius list to obtain the eligible aortic centerline point on.

Optionally, the above-mentioned method for obtaining the connected domain of the left atrium and the left ventricle based on the CT image further includes: filtering the radius R _k to generate a new radius list, including:

_{M) Set another number threshold N threshold 2} of the pixel points in the point list of each layer of the slice, if N _k <N _{threshold 2} , compare the circle center P _5k with the end point in the point list distance L, if L>L _threshold , repeat steps E to N until the number of points in the point list N _{k ≥} _{N threshold 2} , or L ≤ L _threshold ;

N) If N _{k ≥} _{N threshold 2} , or N _k <N _{threshold 2} , L ≤ L _threshold , replace the radius value of the point far away from the center P _5k with the average radius value of the remaining points, as R _k , set The radius R _{k is} filled into the radius list, a new radius list is generated, and points on the centerline of the aorta that meet the conditions are obtained.

Optionally, the above-mentioned method for obtaining the connected domain of the left atrium and left ventricle based on CT images, according to the extension direction of the aortic centerline, according to the Bezier curve rule, the method for obtaining an aortic image includes:

Set the left ventricle gray threshold value Q _left , intercept the end point D in the point list in the YZ plane in the new image, obtain _{the pixel points with gray value Q > Q left} , and obtain a pixel point composed of all the pixel points. the center O ₂ of the circle, project the center O ₂ on the new image, and obtain the center of gravity point P _{6 of} the left ventricle;

Picking up the starting point in the list, a midpoint, gravity point P ₆ and the end point of the Bezier curve drawing;

Assuming that the center point P ₄ and the end point D of the connected domain are located on the Bezier curve, pick the curve segment of the Bezier curve between the end point D and the center of gravity point P ₆ , extending along the direction from the end point D to the P ₆ , the extension length is R _{threshold 1} , and the extension curve is obtained;

If the pixel point in the extension curve is located in the new image, and the gray value of the pixel point in the extension curve is _lower than Q>Q, the pixel point is extracted to obtain the aorta image.

In a second aspect, the present application provides a system for obtaining the connected domains of the left atrium and the left ventricle based on CT images, which is used for the above-mentioned method for obtaining the connected domains of the left atrium and the left ventricle based on CT images, including: sequentially connected images processor, aortic centerline extraction device, aortic image extraction device, left atrium, left ventricle extraction device;

the image processor for acquiring new images with the lungs, descending aorta, spine and ribs removed;

the aortic centerline extraction device for acquiring the aortic centerline of the new image;

The aortic image extraction device is configured to acquire an aortic image according to the extension direction of the aortic centerline and according to the Bezier curve rule;

The left atrium and left ventricle extraction device is configured to pick up the gray value Q around the center of gravity of the left ventricle after the aortic image is removed from the new image, which is greater than the descending aorta grayscale threshold Q- _drop . Pixel points to obtain the connected domain image of the left atrium and left ventricle.

In a third aspect, the present application provides a computer storage medium, and when the computer program is executed by a processor, the above-mentioned method for acquiring the connected domains of the left atrium and the left ventricle is implemented.

The beneficial effects brought by the solutions provided in the embodiments of the present application include at least:

The present application provides a method for obtaining the connected domain of the left atrium and the left ventricle based on CT images, which is a new method for obtaining and obtaining the left atrium and the left ventricle, and has the advantages of fast and accurate extraction and fast calculation speed.

Description of drawings

The accompanying drawings described herein are used to provide further understanding of the present invention and constitute a part of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the attached image:

Fig. 1 is the flow chart of the method for obtaining the connected domain of left atrium and left ventricle based on CT image of the present application;

Fig. 2 is the flow chart of S2000 of this application;

3 is a flowchart of S2300 of the application;

4 is a flowchart of S3000 of the application;

5 is a structural block diagram of a system for obtaining the connected domains of left atrium and left ventricle based on CT images of the present application;

FIG. 6 is a structural block diagram of the aortic centerline extraction device 200 of the present application;

Figure 7 is a structural block diagram of the center point pickup device 230 of the present application;

Reference numerals are explained below:

Image processor 100, aortic centerline extraction device 200, slice device 210, binarization device 220, center point pick-up device 230, search unit 231, comparison unit 232, center point pick-up unit 233, aortic image extraction device 300, Left atrium, left ventricle extraction device 400.

detailed description

In order to make the objectives, technical solutions and advantages of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the specific embodiments of the present invention and the corresponding drawings. Obviously, the described embodiments are only some, but not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

Various embodiments of the present invention will be disclosed in the drawings below, and for the sake of clarity, many practical details will be described together in the following description. It should be understood, however, that these practical details should not be used to limit the invention. That is, in some embodiments of the invention, these practical details are unnecessary. In addition, for the purpose of simplifying the drawings, some well-known structures and components will be shown in a simple schematic manner in the drawings.

The CT data in the prior art is not screened, resulting in a large amount of computation, slow computation speed and inaccurate computation.

Example 1:

In order to solve the above problems, the present application provides a method for obtaining the connected domains of the left atrium and the left ventricle based on CT images, as shown in FIG. 1 , including:

S1000, removing the lungs, descending aorta, spine and ribs from the CT image to obtain a new image, including: setting grayscale thresholds of pixels of the lungs, descending aorta, spine and ribs respectively, and obtaining a new image from the CT image The corresponding image is removed from the upper part; preferably, the lung gray threshold is equal to -150 to -50, the descending aorta threshold is equal to 180 to 220, the spine gray threshold is positive, and the rib threshold is 20 to 40; the lung gray threshold is equal to 20 to 40. Equal to -100, the descending aorta threshold is equal to 200, the spine gray threshold is positive, and the rib threshold is 30.

S2000, acquire the aortic centerline of a new image, as shown in Figure 2, including:

S2100, start layering slices from the top layer of the new image to obtain a two-dimensional image group;

S2200, performing binarization processing on the two-dimensional image group to obtain a binarized image group;

S2300, _{the threshold} is obtained N≤N _1, R = R ₁ ± m _threshold from the binarized image of each slice group, where, N represents the number of pixels, the detection of a circle in the first layer section k , taking the center of the circle as the center P _5k , the radius of the circle corresponding to the center P _5k _{is R k} , including: as shown in Figure 3, including:

S2310, establish a search engine list for each layer slice in the binarized image group, including:

The search engine list includes: a point list and a radius list, and the corresponding points with a pixel value of 1 extracted from the binarized image of each layer are filled into the point list.

S2320: Search the circles sliced at each layer, compare the number of pixels in the search engine list of each layer and the radius of the circle, and find the center point that meets the conditions, including:

D) setting the number threshold of the pixel points in the point list of each layer of slices is N _{threshold 1} , and the radius threshold is R _{threshold 1} , and sequentially from the top layer, the process of step E to step 1 is carried out to each layer slice;

E) If N _{k ≤} N _{threshold 1} , R _k =R _{threshold 1} ±m, where N _k represents the number of pixels in the point list of the k-th slice, then detect a circle in the k-th slice , take the center of the circle as the center O _k , go to step I, if no circle is detected, go to step H; preferably, R _{threshold 1} =15mm

F) If N _{k ≤} N _{threshold 1} , R _k ≠R _{threshold 1} ±m, then detect 3 circles in the slice of the kth layer, if 3 circles are detected, go to step I, if no 3 circles are detected, then Go to step H; preferably, N _threshold ₁ =4

G) If N _k > N _{threshold 1} , then re-determine the center of the circle, take the closest point between the center of the circle in the k-1 slice and the end point D in the point list as the center O _k , go to step I, if not detected If it is a circle, go to step H;

H) Detect _{the relationship between N k} and N _{threshold 1-1} , repeat step E to step G, if still no circle is detected, then detect _{the relationship between N and N threshold 1-2} , repeat step E to step G; and so on, until the center O _{k is} found;

1) take the circle center O _k as the starting point, find 3 points whose gray value is 0 along the positive direction, the negative direction and the positive direction of the Y axis respectively along the positive direction of the X axis; determine a circle according to the 3 points to find the center P _5k and the radius R _k , Get the point on the centerline of the aorta.

S2330, if the center point that meets the conditions cannot be found, search for the center point of the slice of the next layer;

In an embodiment of the present application, the method further includes: filtering the circle center P _5k to generate a new point list, including:

J) Set another radius threshold of the pixels in the radius list of each slice to be R _{threshold 2} , if the radius of the k-th slice of slice R _k <R _{threshold 2} , repeat the process from step E to step I until Find the center P _{5k of} radius R _k ≥ R _{threshold 2} ; preferably, R _{threshold 2} =3mm;

K) If _{the gray value of the center P 5k} on the new image with the lungs, descending aorta, spine and ribs removed is less than 0, repeat the process from step E to step I until the radius R ₁ ≥ R _{threshold 2 is found} , and _{The center of the circle P 5k} whose gray value is greater than or equal to 0;

In an embodiment of the present application, the method further includes: filtering the radius R _k to generate a new radius list, including:

_{M) Set another number threshold N threshold 2} of the pixel points in the point list of each slice, if N _k <N _{threshold 2} , compare the distance L between the center P _5k and the end point in the point list, if L > L _threshold , then repeat steps E to N until the number of points in the point list N _{k ≥} _{N threshold 2} , or L≤L _threshold ; preferably, L _threshold =8mm. Preferably, _{Nthreshold 2} =3.

N) If N _{k ≥} _{N threshold 2} , or N _k <N _{threshold 2} , L ≤ L _threshold , replace the radius value of the point away from the center P _5k with the average radius value of the remaining points, as R _k , replace the radius R _{k is} filled in the radius list, a new radius list is generated, and the points on the centerline of the aorta that meet the conditions are obtained.

S2340, the center line of the aorta is obtained by smoothly connecting the _{circle centers P 5k in sequence.}

S3000, according to the extension direction of the aorta center line, according to the Bezier curve rule, to obtain the aorta image, as shown in Figure 4, including:

S3100, setting _{the left} ventricle gray threshold Q, intercepting the end of the list of points in the point D YZ plane of the new image acquired gradation value Q> Q pixel to _{the left,} all the pixels are obtained from the _{The center O 2} of the circle formed by the points is projected, and the center O _{2 is} projected onto the new image to obtain the center of gravity point P _{6 of} the left ventricle;

S3200, the starting point of the pickup point list, the midpoint, the center of gravity point P ₆ and the end point of the Bezier curve drawing;

S3300, assuming that the center point P ₄ and the end point D of the connected domain are located on the Bezier curve, pick up the Bezier curve between the end point D and the center of gravity point P ₆ . The curve segment extends along the direction from the end point D to the P ₆ , the extension length is R _{threshold 1} , and the curve of the extension segment is obtained;

S3400 , if the pixels in the extension curve are located in the new image, and the grayscale values of the pixels in the extension curve Q>Q _drop , extract the pixels to obtain the aorta image. Preferably, Q _drop =180-220, and Q _drop =200 has the best effect.

S4000, after removing the aorta image from the new image, pick up the pixel points whose gray value Q around the center of gravity of the left ventricle is greater than the gray threshold Q _drop of the descending aorta to obtain a connected domain image of the left atrium and the left ventricle .

The present application provides a method for picking up points on the central line of the aorta based on CT images, which is a new method for acquiring points on the central line of the aorta, which has the advantages of fast and accurate extraction and fast calculation speed.

Example 2:

As shown in FIG. 5 , the present application provides a system for obtaining the connected domains of the left atrium and the left ventricle based on CT images, which is used for the above-mentioned method for obtaining the connected domains of the left atrium and the left ventricle based on CT images, including: including: The image processor 100, the aortic centerline extraction device 200, the aortic image extraction device 300, and the left atrium and left ventricle extraction device 400 are connected in sequence; the image processor 100 is used to acquire and remove the lungs, descending aorta, spine and ribs the new image of the aortic centerline; the aortic centerline extraction device 200 is used to obtain the aortic centerline of the new image; the aortic image extraction device 300 is used to obtain the aortic centerline according to the extension direction of the aortic centerline and according to the Bezier curve rule, Acquiring an image of the aorta; the left atrium and left ventricle extraction device 400 is configured to remove the aortic image from the new image, and pick up the gray value Q around the center of gravity of the left ventricle that is greater than the descending aorta gray threshold The pixels of the Q _drop , the connected domain images of the left atrium and left ventricle are obtained.

As shown in FIG. 6 , in an embodiment of the present application, the aortic centerline extraction device 200 includes: a slicing device 210 , a binarization device 220 and a center point picking device 230 connected in sequence; The top layer of the image starts to be sliced in layers to obtain a two-dimensional image group; the binarization device 220 is used for binarizing the two-dimensional image group to obtain a binarized image group; the center point pickup device 230 is used for binarization. _{N≤N threshold 1} is obtained on each slice in the image group, R=R _{threshold 1} ±m, where N represents the number of pixels, then detect a circle in the k-th slice, and use the center of the circle is the center P _5k , and the radius of the circle corresponding to the _{center P 5k} _{is R k} .

As shown in FIG. 7 , in an embodiment of the present application, the center point picking device 230 includes: a search unit 231 , a comparison unit 232 and a center point picking unit 233 connected in sequence; the search unit 231 is connected to the binarization device 220 , using To establish a search engine list for each layer slice in the binarized image group, search the circle of each layer slice; the comparison unit 232 is used to compare the number of pixels and the radius of the circle in the search engine list of each layer; The point picking unit 233 is used to find the center point that meets the conditions from the slices of each layer, and if the center point that meets the conditions cannot be found, it searches for the center point of the slice of the next layer.

The present application provides a computer storage medium, and when the computer program is executed by a processor, the above-mentioned method for acquiring the connected domains of the left atrium and the left ventricle based on a CT image is implemented.

As will be appreciated by one skilled in the art, various aspects of the present invention may be embodied as a system, method or computer program product. Accordingly, various aspects of the present invention may be embodied in the form of an entirely hardware implementation, an entirely software implementation (including firmware, resident software, microcode, etc.), or a combination of hardware and software aspects, It may be collectively referred to herein as a "circuit," "module," or "system." Furthermore, in some embodiments, various aspects of the present invention may also be implemented in the form of a computer program product on one or more computer-readable media having computer-readable program code embodied thereon. Implementation of the method and/or system of embodiments of the present invention may involve performing or completing selected tasks manually, automatically, or a combination thereof.

For example, hardware for performing selected tasks according to embodiments of the invention may be implemented as a chip or a circuit. As software, selected tasks according to embodiments of the invention may be implemented as a plurality of software instructions executed by a computer using any suitable operating system. In an exemplary embodiment of the invention, one or more tasks according to exemplary embodiments of a method and/or system as herein are performed by a data processor, such as a computing platform for executing a plurality of instructions. Optionally, the data processor includes volatile storage for storing instructions and/or data and/or non-volatile storage for storing instructions and/or data, such as a magnetic hard disk and/or a Move media. Optionally, a network connection is also provided. A display and/or user input device, such as a keyboard or mouse, is optionally also provided.

Any combination of one or more computer readable may be utilized. The computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus or device, or a combination of any of the above. More specific examples (non-exhaustive list) of computer-readable storage media would include the following:

Electrical connection with one or more wires, portable computer disk, hard disk, random access memory (RAM), read only memory (ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disk Read only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

A computer-readable signal medium may include a propagated data signal in baseband or as part of a carrier wave, with computer-readable program code embodied thereon. Such propagated data signals may take a variety of forms including, but not limited to, electromagnetic signals, optical signals, or any suitable combination of the foregoing. A computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device .

Program code embodied on a computer-readable medium may be transmitted using any suitable medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

For example, computer program code for performing operations for various aspects of the invention may be written in any combination of one or more programming languages, including object-oriented programming languages such as Java, Smalltalk, C++, and conventional procedural programming languages, such as The "C" programming language or similar programming language. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer, or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network - including a local area network (LAN) or a wide area network (WAN) - or may be connected to an external computer (eg using an Internet service provider via Internet connection).

It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to the processor of a general purpose computer, special purpose computer or other programmable data processing apparatus to produce a machine that causes the computer program instructions when executed by the processor of the computer or other programmable data processing apparatus , resulting in means for implementing the functions/acts specified in one or more blocks of the flowchart and/or block diagrams.

These computer program instructions can also be stored on a computer-readable medium, the instructions cause a computer, other programmable data processing apparatus, or other device to operate in a particular manner, whereby the instructions stored on the computer-readable medium produce a An article of manufacture of instructions implementing the functions/acts specified in one or more blocks of the flowcharts and/or block diagrams.

Computer program instructions can also be loaded on a computer (eg, a coronary artery analysis system) or other programmable data processing device to cause a series of operational steps to be performed on the computer, other programmable data processing device or other device to produce a computer-implemented process , such that instructions executing on a computer, other programmable apparatus, or other device provide a process for implementing the functions/acts specified in the flowchart and/or one or more block diagram blocks.

The above specific examples of the present invention further describe the purpose, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above are only specific embodiments of the present invention, and are not intended to limit the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

A method for obtaining the connected domain of left atrium and left ventricle based on CT image, which is characterized in that, comprising:

Remove the lungs, descending aorta, spine and ribs from the CT image to obtain a new image;

obtaining the aortic centerline of the new image;

According to the extension direction of the aorta centerline, according to the Bezier curve rule, acquire the aorta image;

After removing the aorta image from the new image, select the pixels whose gray value Q around the center of gravity of the left ventricle is greater than the gray threshold Q of the descending aorta, and obtain the connected domain between the left atrium and the left ventricle image.
The method for obtaining the connected domain of the left atrium and the left ventricle based on a CT image according to claim 1, wherein the method for obtaining the aortic centerline of the new image comprises:

Layer slices starting from the top layer of the new image to obtain a two-dimensional image group;

performing binarization processing on the two-dimensional image group to obtain a binarized image group;

N≤Nthreshold 1 is obtained from the slices of each layer in the binarized image group, R= Rthreshold 1 ±m, where N represents the number of pixels, then the detection within the slice of the kth layer is 1 circle, take the center of the circle as the center P 5k , and the radius of the circle corresponding to the center P 5k is R k ;

The center line of the aorta is obtained by smoothly connecting the circle centers P 5k in sequence.
The method for obtaining the connected domain of the left atrium and the left ventricle based on a CT image according to claim 2, wherein the method for performing a binarization process on the two-dimensional image group to obtain a binarized image group comprises:

Set the coronary tree grayscale threshold Q coronary 1 ; according to
binarizing slices of each layer of the new image from which the lungs, descending aorta, spine and ribs are removed to remove impurities in the new image from which the lungs, descending aorta, spine and ribs are removed point to obtain the binarized image group;

Among them, m is a positive integer, Q m represents the grayscale value corresponding to the mth pixel point PO, and P(m) represents the pixel value corresponding to the mth pixel point PO.
The method for obtaining the connected domain of the left atrium and the left ventricle based on CT images according to claim 2, wherein the obtaining N≤Nthreshold 1 from each slice in the binarized image group , R=R threshold 1 ±m, where N represents the number of pixel points, then detect a circle in the slice of the kth layer, take the center of the circle as the center P 5k , the center P 5k corresponds to Methods for a circle of radius R k include:

establishing a search engine list for each layer of the slice in the binarized image group;

Search the circle of each layer slice, compare the number of pixels in the search engine list of each layer and the radius of the circle, and find the center point that meets the conditions;

If no matching center point can be found, search the center point of the next layer of slices.
The method for obtaining the connected domains of the left atrium and the left ventricle based on CT images according to claim 4, wherein the method for establishing a search engine list for each slice of the binarized image group comprises the following steps: :

The search engine list includes: a point list and a radius list, and the points with a pixel value of 1 extracted from the binarized image of each layer are correspondingly filled into the point list.
The method for obtaining the connected domain of the left atrium and the left ventricle based on CT images according to claim 5, wherein the search for the circle of each slice of slices compares the number of pixels in the search engine list of each layer and the radius of the circle, the methods to find the center point of the circle that meet the conditions include:

D) Set the threshold of the number of pixels in the point list of each layer of the slice to be N threshold 1 , and the radius threshold to be R threshold 1 , and perform step E for each layer of the slice in turn from the top layer to the process of step 1;

E) If N k ≤ N threshold 1 , R k =R threshold 1 ±m, where N k represents the number of pixels in the point list of the slice at the k th layer, then detect the k th layer For a circle in the slice, take the center of the circle as the center O k , perform step I, and perform step H if the circle is not detected;

F) If N k ≤ N threshold 1 , R k ≠R threshold 1 ±m, then detect 3 circles in the slice of the kth layer, if 3 circles are detected, go to step I, if 3 circles are not detected The circle then carries out the described step H;

G) If N k > N threshold 1 , then re-determine the center of the circle, take the point with the closest distance between the center of the circle in the k-1 slice and the end point D in the point list as the center O k , and proceed to step I, If no circle is detected, go to step H;

H) Detect the relationship between N k and N threshold 1-1 , repeat steps E to G, if still no circle is detected, then detect the relationship between N and N threshold 1-2 , repeat steps E to Described step G; And so on, until the center of circle O k is found;

1) take described circle center O k as starting point, find 3 grayscale values 0 points along the positive direction of X axis, negative direction and Y axis positive direction respectively; Determine a circle according to 3 points and find center P 5k and radius R k , to get the point on the centerline of the aorta.
The method for obtaining the connected domain of the left atrium and the left ventricle based on the CT image according to claim 6, further comprising: filtering the center P 5k to generate a new point list, comprising:

J) Set another radius threshold of the pixels in the radius list of each layer of the slice to be R threshold 2 , if the radius R k of the k-th slice of the slice <R threshold 2 , repeat the steps E to the process of the step I, until the center P 5k of the radius R k ≥ R threshold 2 is found;

K) If the gray value of the center P 5k on the new image from which the lungs, descending aorta, spine and ribs are removed is less than 0, repeat the process from step E to step I until the radius is found R 1 ≥ R threshold 2 , and the center P 5k of the circle whose gray value is greater than or equal to 0;

L) Add the circle center P 5k with R 1 ≥ R threshold 2 and the gray value greater than or equal to 0 to the entry point list to generate a new radius list, and add the radius R k into the radius list to obtain the eligible aortic centerline point on.
The method for obtaining the connected domain of the left atrium and the left ventricle based on the CT image according to claim 7, further comprising: filtering the radius R k to generate a new radius list, comprising:

M) Set another number threshold N threshold 2 of the pixel points in the point list of each layer of the slice, if N k <N threshold 2 , compare the circle center P 5k with the end point in the point list distance L, if L>L threshold , repeat steps E to N until the number of points in the point list N k ≥ N threshold 2 , or L ≤ L threshold ;

N) If N k ≥ N threshold 2 , or N k <N threshold 2 , L ≤ L threshold , replace the radius value of the point far away from the center P 5k with the average radius value of the remaining points, as R k , set The radius R k is filled into the radius list, a new radius list is generated, and points on the centerline of the aorta that meet the conditions are obtained.
The method for acquiring the connected domain of the left atrium and the left ventricle based on CT images according to claim 8, wherein the method for acquiring the aortic image is based on the extension direction of the aortic centerline and the Bezier curve rule include:

Set the left ventricle gray threshold value Q left , intercept the end point D in the point list in the YZ plane in the new image, obtain the pixel points with gray value Q > Q left , and obtain a pixel point composed of all the pixel points. the center O 2 of the circle, project the center O 2 on the new image, and obtain the center of gravity point P 6 of the left ventricle;

Picking up the starting point in the list, a midpoint, gravity point P 6 and the end point of the Bezier curve drawing;

Assuming that the center point P 4 and the end point D of the connected domain are located on the Bezier curve, pick the curve segment of the Bezier curve between the end point D and the center of gravity point P 6 , extending along the direction from the end point D to the P 6 , the extension length is R threshold 1 , and the extension curve is obtained;

If the pixel point in the extension curve is located in the new image, and the gray value of the pixel point in the extension curve is lower than Q>Q, the pixel point is extracted to obtain the aorta image.
A system for obtaining the connected domain of the left atrium and the left ventricle based on a CT image, which is used in the method for obtaining the connected domain of the left atrium and the left ventricle based on the CT image according to any one of claims 1 to 9, characterized in that it comprises: : image processor, aortic centerline extraction device, aortic image extraction device, left atrium and left ventricle extraction device connected in sequence;

the image processor for acquiring new images with the lungs, descending aorta, spine and ribs removed;

the aortic centerline extraction device for acquiring the aortic centerline of the new image;

The aortic image extraction device is configured to acquire an aortic image according to the extension direction of the aortic centerline and according to the Bezier curve rule;

The left atrium and left ventricle extraction device is configured to pick up the gray value Q around the center of gravity of the left ventricle after the aortic image is removed from the new image, which is greater than the descending aorta grayscale threshold Q- drop . Pixel points to obtain the connected domain image of the left atrium and left ventricle.
A computer storage medium, characterized in that, when the computer program is executed by the processor, the method for obtaining the connected domain of the left atrium and the left ventricle based on a CT image according to any one of claims 1 to 9 is implemented.