1. A pulmonary artery and vein segmentation method of a CT image is characterized by comprising the following steps:

s10, preprocessing a chest CT image acquired in advance to obtain a lung region range in the chest CT image;

s20, performing multi-plane reconstruction based on the chest CT image, and obtaining a pulmonary vessel image by segmentation through a threshold segmentation method in the reconstruction process; wherein, the threshold value adopted in the threshold value segmentation method is a CT value interval determined based on a two-dimensional segmentation result of the lung region obtained by reconstruction;

s30, selecting a pixel point from the right ventricle pulmonary artery region of the pulmonary vessel image as a first seed point, selecting a first sub-region from the CT value region as a first threshold value region, carrying out image segmentation by a region growing method to obtain a pulmonary artery initial image, and carrying out morphological processing on the pulmonary artery initial image to obtain a pulmonary artery image and a vein image to be segmented which does not contain an artery;

s40, selecting a pixel point from a pulmonary vein region as a second seed point, selecting a second sub-region from the CT value region as a second threshold value region, and performing image segmentation on the to-be-segmented vein image by a region growing method to obtain a pulmonary vein image; any numerical value in the second subinterval is greater than the numerical value in the first subinterval;

s50, carrying out image segmentation on the pulmonary artery image and the pulmonary vein image based on the lung region range to obtain a pulmonary artery image and a pulmonary vein image.

2. The method according to claim 1, wherein step S10 includes:

s11, carrying out binarization processing on the chest CT image based on the CT value to obtain a binarization image of the lung;

s12, selecting the largest connected domain of the binary image to fill the cavity, and obtaining a human tissue region image;

s13, carrying out binarization processing on the human tissue region image, and selecting a region smaller than a first preset threshold value for region growth to obtain a lung region image;

and S14, determining the lung region range based on the lung region image.

3. The method according to claim 2, wherein in step S11, when the binarization processing is performed on the chest CT image, a region larger than a second preset threshold is selected with-400 HU as the second preset threshold.

4. The method according to claim 2, wherein the method for determining the first preset threshold value comprises:

establishing a multi-plane reconstructed image generation model, wherein the multi-plane reconstructed image generation model generates a corresponding multi-plane reconstructed image by taking a currently input CT image as an input image and taking a currently set CT value as a threshold, and the multi-plane reconstructed image comprises three display angles of a transverse position, a vector position and a coronal position;

and inputting the multi-plane reconstructed image generation model by taking the human tissue region image as an input image and taking a first CT value set determined in advance as a candidate threshold value, and determining the first preset threshold value based on a two-dimensional segmentation result of a lung region obtained by reconstructing the multi-plane reconstructed image generation model.

5. The method according to claim 1, wherein in S20, the segmenting by threshold segmentation in the reconstruction process to obtain the pulmonary vessel image comprises:

the chest CT image is used as an input image, the multi-plane reconstructed image generation model is input based on a second CT value set which is determined in advance and used as a candidate threshold, and a CT value interval is determined as a threshold interval based on a two-dimensional segmentation result of the pulmonary blood vessel which is obtained by the multi-plane reconstructed image generation model through reconstruction;

and segmenting pixels of which the CT values fall into the threshold interval from the chest CT image to obtain the pulmonary blood vessel image.

6. The method according to claim 1, wherein performing morphological processing on the pulmonary artery initial image to obtain a pulmonary artery image and a vein image to be segmented which does not contain an artery comprises:

sequentially performing expansion and corrosion treatment on the pulmonary artery initial image to obtain a pulmonary artery image, wherein a corroded area is marked as a background area in the corrosion process;

and based on the background region, segmenting the pulmonary artery image from the pulmonary blood vessel image to obtain the vein image to be segmented.

7. The method according to claim 1, further comprising, before step S10:

a10, obtaining a chest CT image, wherein the chest CT image comprises adjacent multilayer tomographic images.

8. A pulmonary artery and vein segmentation device of a CT image is characterized by comprising:

the preprocessing module is used for preprocessing a chest CT image acquired in advance to obtain a lung region range in the chest CT image;

the pulmonary blood vessel image segmentation module is used for carrying out multi-plane reconstruction based on the chest CT image and obtaining a pulmonary blood vessel image by segmentation of a threshold segmentation method in the reconstruction process; wherein, the threshold value adopted in the threshold value segmentation method is a CT value interval determined based on a two-dimensional segmentation result of the lung region obtained by reconstruction;

the pulmonary artery image segmentation module is used for selecting a pixel point from the right ventricle pulmonary artery region of the pulmonary vessel image as a first seed point, selecting a first sub-region from the CT value region as a first threshold value region, carrying out image segmentation by a region growing method to obtain a pulmonary artery initial image, and carrying out morphological processing on the pulmonary artery initial image to obtain a pulmonary artery image and a vein image to be segmented which does not contain an artery;

the pulmonary vein image segmentation module is used for selecting a pixel point from a pulmonary vein region as a second seed point, selecting a second sub-region from the CT value region as a second threshold value region, and performing image segmentation on the to-be-segmented vein image by a region growing method to obtain the pulmonary vein image; any numerical value in the second subinterval is greater than the numerical value in the first subinterval;

and the pulmonary artery and vein image segmentation module is used for carrying out image segmentation on the pulmonary artery image and the pulmonary vein image based on the lung region range to obtain a pulmonary artery image and a pulmonary vein image.

9. A computer-readable storage medium, characterized in that a computer program is stored on the computer-readable storage medium, which computer program, when being executed by a processor, carries out the steps of the method for pulmonary arteriovenous segmentation of a CT image according to any one of the preceding claims 1 to 7.

10. An electronic device, comprising: memory, processor and computer program stored on the memory and executable on the processor, the computer program, when being executed by the processor, implementing the steps of the method for pulmonary arteriovenous segmentation of CT images as set forth in any one of the preceding claims 1 to 7.

Background

The pulmonary blood vessel is a set of independent blood circulation system, and the main function is to transport blood to the lung or carry blood away from the lung, so as to complete the exchange of qi and blood in the lung. The segmentation of the pulmonary artery and the pulmonary vein has great significance for detecting lung diseases, the segmentation of the pulmonary artery and the pulmonary vein in the CT image is very difficult, the dosage and the scanning time of the angiography agent have great influence on the angiography result, the pulmonary blood vessel circulates fast, the angiography results obtained by different doctors and equipment by scanning have great difference on the gray value, when the existing automatic segmentation method is used for performing the arteriovenous segmentation, effective segmentation can be performed on partial data, the segmentation accuracy on most data is low, and the clinical application requirements are difficult to meet.

The above-described deficiencies are desired to be overcome by those skilled in the art.

Disclosure of Invention

Technical problem to be solved

In view of the above-mentioned shortcomings and drawbacks of the prior art, the present application provides a method, an apparatus, a medium, and a device for pulmonary artery and vein segmentation of CT images.

(II) technical scheme

In order to achieve the purpose, the technical scheme is as follows:

in a first aspect, the present application provides a method for pulmonary artery and vein segmentation of a CT image, the method comprising:

s10, preprocessing a chest CT image acquired in advance to obtain a lung region range in the chest CT image;

s20, performing multi-plane reconstruction based on the chest CT image, and obtaining a pulmonary vessel image by segmentation through a threshold segmentation method in the reconstruction process; wherein, the threshold value adopted in the threshold value segmentation method is a CT value interval determined based on a two-dimensional segmentation result of the lung region obtained by reconstruction;

s30, selecting a pixel point from the right ventricle pulmonary artery region of the pulmonary vessel image as a first seed point, selecting a first sub-region from the CT value region as a first threshold value region, carrying out image segmentation by a region growing method to obtain a pulmonary artery initial image, and carrying out morphological processing on the pulmonary artery initial image to obtain a pulmonary artery image and a vein image to be segmented which does not contain an artery;

s40, selecting a pixel point from a pulmonary vein region as a second seed point, selecting a second sub-region from the CT value region as a second threshold value region, and performing image segmentation on the to-be-segmented vein image by a region growing method to obtain a pulmonary vein image; any numerical value in the second subinterval is greater than the numerical value in the first subinterval;

s50, carrying out image segmentation on the pulmonary artery image and the pulmonary vein image based on the lung region range to obtain a pulmonary artery image and a pulmonary vein image.

Optionally, step S10 includes:

s11, carrying out binarization processing on the chest CT image based on the CT value to obtain a binarization image of the lung;

s12, selecting the largest connected domain of the binary image to fill the cavity, and obtaining a human tissue region image;

s13, carrying out binarization processing on the human tissue region image, and selecting a region smaller than a first preset threshold value for region growth to obtain a lung region image;

and S14, determining the lung region range based on the lung region image.

Optionally, in step S11, when the binarization processing is performed on the chest CT image, the region larger than the second preset threshold is selected by taking-400 HU as the second preset threshold.

Optionally, the method for determining the first preset threshold includes:

establishing a multi-plane reconstructed image generation model, wherein the multi-plane reconstructed image generation model generates a corresponding multi-plane reconstructed image by taking a currently input CT image as an input image and taking a currently set CT value as a threshold, and the multi-plane reconstructed image comprises three display angles of a transverse position, a vector position and a coronal position;

and inputting the multi-plane reconstructed image generation model by taking the human tissue region image as an input image and taking a first CT value set determined in advance as a candidate threshold value, and determining the first preset threshold value based on a two-dimensional segmentation result of a lung region obtained by reconstructing the multi-plane reconstructed image generation model.

Optionally, in S20, segmenting the pulmonary blood vessel image by a threshold segmentation method in the reconstruction process, including:

the chest CT image is used as an input image, the multi-plane reconstructed image generation model is input based on a second CT value set which is determined in advance and used as a candidate threshold, and a CT value interval is determined as a threshold interval based on a two-dimensional segmentation result of the pulmonary blood vessel which is obtained by the multi-plane reconstructed image generation model through reconstruction;

and segmenting pixels of which the CT values fall into the threshold interval from the chest CT image to obtain the pulmonary blood vessel image.

Optionally, performing morphological processing on the pulmonary artery initial image to obtain a pulmonary artery image and a vein image to be segmented, which does not include an artery, includes:

sequentially performing expansion and corrosion treatment on the pulmonary artery initial image to obtain a pulmonary artery image, wherein a corroded area is marked as a background area in the corrosion process;

and based on the background region, segmenting the pulmonary artery image from the pulmonary blood vessel image to obtain the vein image to be segmented.

Optionally, before step S10, the method further includes:

a10, obtaining a chest CT image, wherein the chest CT image comprises adjacent multilayer tomographic images.

In a second aspect, the present application provides a pulmonary artery and vein segmentation apparatus for a CT image, including:

the preprocessing module is used for preprocessing a chest CT image acquired in advance to obtain a lung region range in the chest CT image;

the pulmonary blood vessel image segmentation module is used for carrying out multi-plane reconstruction based on the chest CT image and obtaining a pulmonary blood vessel image by segmentation of a threshold segmentation method in the reconstruction process; wherein, the threshold value adopted in the threshold value segmentation method is a CT value interval determined based on a two-dimensional segmentation result of the lung region obtained by reconstruction;

the pulmonary artery image segmentation module is used for selecting a pixel point from the right ventricle pulmonary artery region of the pulmonary vessel image as a first seed point, selecting a first sub-region from the CT value region as a first threshold value region, carrying out image segmentation by a region growing method to obtain a pulmonary artery initial image, and carrying out morphological processing on the pulmonary artery initial image to obtain a pulmonary artery image and a vein image to be segmented which does not contain an artery;

the pulmonary vein image segmentation module is used for selecting a pixel point from a pulmonary vein region as a second seed point, selecting a second sub-region from the CT value region as a second threshold value region, and performing image segmentation on the to-be-segmented vein image by a region growing method to obtain the pulmonary vein image; any numerical value in the second subinterval is greater than the numerical value in the first subinterval;

and the pulmonary artery and vein image segmentation module is used for carrying out image segmentation on the pulmonary artery image and the pulmonary vein image based on the lung region range to obtain a pulmonary artery image and a pulmonary vein image.

In a third aspect, the present application provides a computer-readable storage medium having stored thereon a computer program which, when being executed by a processor, implements the steps of the method for pulmonary artery and vein segmentation of a CT image according to any one of the first aspect above.

In a fourth aspect, the present application provides an electronic device comprising: a memory, a processor and a computer program stored on the memory and executable on the processor, the computer program, when executed by the processor, implementing the steps of the method for pulmonary arteriovenous segmentation of CT images as defined in any one of the above first aspects.

(III) advantageous effects

The beneficial effect of this application is: the application provides a pulmonary artery and vein segmentation method, a pulmonary artery and vein segmentation device, a pulmonary artery and vein segmentation medium and pulmonary artery and vein segmentation equipment of a CT image. The method comprises the steps of firstly segmenting the lung region where the pulmonary blood vessels are located through a preset threshold, then determining the threshold through a two-dimensional segmentation result by utilizing the gray level difference of the artery and the vein to realize the accurate segmentation of the artery and the vein, segmenting all the pulmonary blood vessels for the first time, segmenting the artery for the second time, segmenting the vein for the third time, and finally segmenting to obtain a pulmonary artery tree and a pulmonary vein tree. The image obtained by segmentation has high accuracy and can meet the requirements of clinical application.

Drawings

The application is described with the aid of the following figures:

fig. 1 is a schematic flow chart of a pulmonary artery and vein segmentation method of a CT image according to an embodiment of the present disclosure;

FIG. 2 is an exemplary illustration of a lung tomogram in one embodiment of the present application;

FIG. 3 is an exemplary illustration of a binarized image of a lung according to an embodiment of the present application;

FIG. 4 is an exemplary illustration of an image of a lung region in one embodiment of the present application;

FIG. 5 is an exemplary image of a pulmonary vessel obtained by segmentation in an embodiment of the present application;

FIG. 6 is an exemplary illustration of an image of a pulmonary artery obtained by segmentation in an embodiment of the present application;

FIG. 7 is an exemplary graph of a pulmonary vein image obtained by segmentation in an embodiment of the present application;

FIG. 8 is an exemplary image of a pulmonary artery and vein segmented in accordance with an embodiment of the present application;

fig. 9 is a schematic structural diagram of a pulmonary artery and vein segmentation apparatus for CT images according to another embodiment of the present application.

Fig. 10 is a schematic structural diagram of an electronic device according to another embodiment of the present application.

Detailed Description

For the purpose of better explaining the present invention and to facilitate understanding, the present invention will be described in detail by way of specific embodiments with reference to the accompanying drawings. It is to be understood that the following specific examples are illustrative of the invention only and are not to be construed as limiting the invention. In addition, it should be noted that, in the case of no conflict, the embodiments and features in the embodiments in the present application may be combined with each other; for convenience of description, only portions related to the invention are shown in the drawings.

In CT, a certain thickness of the human body is scanned by X-ray beams, the X-rays transmitted through the layer are received by a detector, converted into visible light, converted into electrical signals by photoelectric conversion, converted into digital signals by an analog/digital converter (analog/digital converter), and input into a computer for processing. The image formation is performed as if the selected slice is divided into cuboids of the same volume, called voxels (voxels). Different tissues have relatively large density differences in CT imaging, generally, the air density is relatively low, the fat is second, the blood vessels are higher, and the bone or calcified tissue density is highest.

The pulmonary arteries and veins belong to the functional blood vessels of the lungs, circulating between the heart and the lungs. The pulmonary artery is sent out from the right ventricle to enter the lung along with the bronchus, repeatedly branches along with the bronchus, finally forms a capillary network to wrap around the alveolus, then gradually gathers into the pulmonary vein, and flows back to the left atrium to complete the exchange of carbon dioxide and oxygen in the alveolus and blood.

Aiming at the problem of low accuracy of arteriovenous segmentation, the application provides a pulmonary artery and vein segmentation method of a CT image, and the invention is described in detail by embodiments below.

Example one

Fig. 1 is a schematic flow chart of a pulmonary artery and vein segmentation method of a CT image in an embodiment of the present application, as shown in fig. 1, the method includes:

s10, preprocessing the chest CT image acquired in advance to obtain the lung region range in the chest CT image;

s20, performing multi-plane reconstruction based on the chest CT image, and obtaining a pulmonary vessel image by segmentation through a threshold segmentation method in the reconstruction process; wherein, the threshold value adopted in the threshold value segmentation method is a CT value interval determined based on a two-dimensional segmentation result of the lung region obtained by reconstruction;

s30, selecting a pixel point from the right ventricle pulmonary artery region of the pulmonary vessel image as a first seed point, selecting a first sub-region from a CT value region as a first threshold value region, and performing image segmentation by a region growing method to obtain a pulmonary artery image and a vein image to be segmented, wherein the vein image does not contain an artery;

s40, selecting a pixel point from the pulmonary vein region as a second seed point, selecting a second sub-region from the CT value region as a second threshold value region, performing image segmentation on the to-be-segmented vein image by a region growing method to obtain a pulmonary artery initial image, and performing morphological processing on the pulmonary artery initial image to obtain the pulmonary vein image; any value in the second sub-interval is greater than the value in the first sub-interval;

and S50, carrying out image segmentation on the pulmonary artery image and the pulmonary vein image based on the lung region range to obtain a pulmonary artery image and a pulmonary vein image.

The pulmonary artery tree and pulmonary vein tree images obtained by the pulmonary artery and vein segmentation method of the CT image can effectively solve the problem of gray level difference caused by the influence of the dosage of the contrast agent, the segmentation result is high in accuracy, and the clinical application requirements can be met. The following will specifically explain each step in the present embodiment.

It should be noted that an execution main body of the method in this embodiment may be a computing service device with network communication, data processing, and program running functions, such as a mobile phone, a tablet computer, a personal computer, a cloud, or a remote server, and the specific form of the computing service device is not limited in this application embodiment.

In this embodiment, before step S10, the method further includes:

and A10, acquiring a chest CT image, wherein the chest CT image comprises adjacent multilayer tomographic images.

The CT image is a medical image obtained by an electron computer tomography, and generally includes a multi-slice image. In this embodiment, the brain CT image is a sequence of scan images obtained by scanning the chest of the subject with a CT device, and each sequence may include 200 and 300 CT images. Fig. 2 is an exemplary lung tomographic image in an embodiment of the present application, and in this step, the acquired tomographic image may be the tomographic image shown in fig. 2.

After the CT device scans, the obtained breast CT image can be uploaded to a Picture Archiving and Communication System (PACS), and then the computer device can acquire a corresponding brain CT image from the PACS system.

Alternatively, the computer device may acquire the breast CT images uploaded by the CT device from the PACS system in real time, or may acquire all the breast CT images uploaded by the CT device during the time period from the PACS system at regular time intervals.

And S10, preprocessing the chest CT image acquired in advance to obtain the lung region range in the chest CT image.

In order to segment the pulmonary blood vessels, the image needs to be preprocessed to extract the region where the pulmonary blood vessels are located. The pulmonary vein is connected with the great vein of the lung and the left atrium, and the pulmonary artery is divided into a left pulmonary artery and a right pulmonary artery at the 5 th thoracic vertebra height from the right ventricular pulmonary artery cone to the lower part of the aortic arch. In order to segment the pulmonary vessels, the heart region and the lung region need to be segmented. The following specifically describes steps S11-S14 included in step S10.

And S11, carrying out binarization processing on the chest CT image based on the CT value to obtain a binarization image of the lung.

CT is characterized by the ability to distinguish slight differences in tissue density in humans, using criteria that depend on the linear absorption coefficient (μ value) of various tissues to X-rays. For ease of calculation and discussion, the linear attenuation coefficient is divided into 2000 units, called CT values, in Hounsfield Units (HU), with water as the 0 value and the CT value for the uppermost bone as 1000 HU; the CT value for the lowest air is-1000 HU and the CT value for fat is between-90 HU and 70 HU.

In this embodiment, the chest CT image is binarized to remove air and bed plates outside the tissue, 400HU may be selected as the second preset threshold value for binarization, and the region larger than the second preset threshold value is selected to obtain the binarized image of the lung. And acquiring a layer of data of the lung region wrapped by the middle layer for the data of the chest and the abdomen.

Referring to fig. 3, fig. 3 is a diagram illustrating an exemplary lung binary image according to an embodiment of the present application, in which a white area is the lung binary image.

For the segmentation of the lung, the present embodiment adopts a semi-automatic left and right lung segmentation method, that is, the threshold needs to be selected by the operator, and the seed points of the left and right lungs are automatically selected.

And S12, selecting the largest connected domain of the binary image to fill the cavity, and obtaining the human tissue region image.

The binarized image includes the lung region and air, so the air needs to be removed. And selecting a maximum communication area, filling the cavity, wherein the filled area does not contain air.

And S13, carrying out binarization processing on the human tissue region image, and carrying out region growth on the region smaller than a first preset threshold value to obtain a lung region image.

The method includes the steps of conducting binarization processing on a human tissue region image, selecting a region smaller than a first preset threshold value to obtain two large regions, namely a left lung and a right lung, respectively, selecting a seed point in the two regions to conduct three-dimensional region growing to obtain segmentation results of all lung regions, wherein the segmentation results are shown in fig. 4, and fig. 4 is an exemplary diagram of a lung region image in one embodiment of the application.

In this embodiment, the determination method of the threshold in steps S11 and S13 may be:

establishing a multi-plane reconstructed image generation model, wherein the multi-plane reconstructed image generation model generates a corresponding multi-plane reconstructed image by taking a currently input CT image as an input image and taking a currently set CT value as a threshold, and the multi-plane reconstructed image comprises three display angles of a transverse position, a vector position and a coronal position;

the chest CT image or the human tissue region image is used as an input image, a multi-plane reconstruction image generation model is input based on a predetermined CT value set as a candidate threshold value, and the threshold value is determined based on the multi-plane reconstruction image generation model reconstruction result.

Preferably, the multi-planar reconstructed image generated by selecting different thresholds can be observed in real time through an interactive interface.

For example, a selection tool of a threshold range is provided on the interface design UI, and the regions of the selected threshold are respectively identified by green regions in the three MPR windows of the transection position, the sagittal position and the coronal position.

Performing region growth on a region smaller than a first preset threshold, specifically comprising:

s01, selecting appointed pixel points of the lung region on an appointed image layer to obtain initial seed points;

s02, selecting a pixel point from 26 neighborhood pixel points of the initially marked seed point;

s03, judging whether the selected pixel point is marked as a mark point, if so, returning to the step S02, otherwise, executing the step S04;

s04, judging whether the gray value of the selected pixel meets the preset requirement, if so, marking the pixel as a mark point, adding a mark point set, and executing the step S06, otherwise, executing the step S05;

s05, stopping marking the pixel point, and executing the step S06;

s06, judging whether all the neighborhood pixels are judged completely or not, if yes, executing a step S08, and if not, returning to the step S02;

s08, judging whether the mark point set is empty, if not, taking one mark point from the mark point set as an initial marked seed point, returning to the step S02, and removing the point from the mark point set, otherwise, executing the step S09;

and S09, acquiring a marked pixel point set, wherein the pixel point set is a lung region image.

The step of selecting the appointed pixel point of the lung region on the appointed image layer to obtain the initial seed point comprises the following steps:

and calculating the center position of the point set, if the position is the lung region, using the position as a seed point, if not, adding 1 in the x direction and the y direction of the image respectively until the point is the lung region, and selecting the point as the seed point.

S20, performing multi-plane reconstruction based on the chest CT image, and obtaining a pulmonary vessel image by segmentation through a threshold segmentation method in the reconstruction process; wherein, the threshold value adopted in the threshold value segmentation method is a CT value interval determined based on a two-dimensional segmentation result of the lung region obtained by reconstruction;

in this embodiment, after the pulmonary vessel region is segmented, the threshold is adjusted to realize the segmentation of the pulmonary vessel by specifying the two-dimensional segmentation result in the CT value range on the MPR plane, as shown in fig. 5.

In this embodiment, one seed point may be selected in the two-dimensional blood vessel region, and the threshold selection tool in step S10 is used to perform threshold selection, so that the range of the threshold should include all blood vessels in the lung, and the two-dimensional image can be observed synchronously.

Fig. 5 is an exemplary image of a segmented pulmonary blood vessel according to an embodiment of the present application, in which the segmented thoracic blood vessel includes left and right pulmonary arteries, left and right pulmonary veins, a great vein between the lung and the left atrium, and a right ventricular pulmonary artery.

Preferably, an adjusting device may be designed in a User Interface (UI), and a User may manually adjust the threshold, so as to display different CT value ranges on the MPR plane, thereby providing an accurate threshold range for the three-time segmentation.

By adopting the simple user interaction mode of the user interface and the visual threshold range interaction interface, more intuitive and more accurate segmentation threshold selection is provided for the user, and more accurate arteriovenous segmentation is realized.

S30, selecting a pixel point from the right ventricle pulmonary artery region of the pulmonary vessel image as a first seed point, selecting a first sub-region from the CT value region as a first threshold value region, and performing image segmentation by a region growing method to obtain a pulmonary artery image and a vein image to be segmented, wherein the vein image does not contain an artery.

After all the pulmonary vessels are obtained, the corresponding segmentation threshold range is recorded and used for final arteriovenous segmentation. Since the CT value of the pulmonary artery is higher than that of the pulmonary vein, the artery and vein are separated by the difference of the CT values of the artery and vein. First, a suitable CT value range is selected for segmentation of the pulmonary artery region, and the threshold value range is displayed on the MPR plane in real time during adjustment of the threshold value by the threshold value selection tool in step S10, so that the reasonability of the threshold value can be determined. After a proper position is selected, a seed point is selected in a heart area connected with the pulmonary artery, and a pulmonary artery segmentation result is obtained after the pulmonary artery segmentation is executed.

In this embodiment, the morphological processing on the pulmonary artery initial image to obtain a pulmonary artery image and a vein image to be segmented that does not include an artery includes:

sequentially expanding and corroding the pulmonary artery initial image to obtain a pulmonary artery image, wherein a corroded area is marked as a background area in the corrosion process;

and based on the background area, segmenting a pulmonary artery image from the pulmonary vessel image to obtain a vein image to be segmented.

Because the CT value range of the peripheral boundary region of the pulmonary artery is close to the CT value range of the pulmonary vein, before the pulmonary vein is segmented, the segmentation result of the pulmonary artery is firstly expanded for a plurality of times until the periphery of the current artery does not contain a vein region, then corrosion is carried out, the number of times of corrosion execution is consistent with the number of times of expansion, and the pulmonary artery before expansion is obtained and is a final pulmonary artery image; in the erosion process, the eroded region, i.e., the peripheral region of the pulmonary artery, is marked as a background region (non-blood vessel region), and when the pulmonary vein segmentation is performed, the region is not marked as a pulmonary vein because it is already marked as a background although the threshold value is close to the pulmonary vein region. Fig. 6 is an exemplary image of a pulmonary artery obtained by segmentation according to an embodiment of the present application, and as shown in fig. 6, the pulmonary artery obtained by segmentation includes an external pulmonary region such as a heart and an aorta in addition to an arterial blood vessel inside a lung.

S40, selecting a pixel point from the pulmonary vein region as a second seed point, selecting a second sub-region from the CT value region as a second threshold value region, and performing image segmentation on the to-be-segmented vein image by a region growing method to obtain the pulmonary vein image; any value in the second sub-interval is greater than the value in the first sub-interval.

After the pulmonary artery segmentation is completed, the pulmonary artery region removed from the pulmonary vessel region is marked as a region to be subjected to pulmonary vein segmentation, the region also stores a pulmonary artery distal region which is not completely segmented, the threshold range of the pulmonary artery distal region is similar to the CT value range of the pulmonary vein, although the expansion corrosion can remove the peripheral region of the pulmonary artery, the distal region of the pulmonary artery cannot be removed. According to observation and analysis, the distal regions of the pulmonary arteries are relatively close to the pulmonary veins in CT value characteristics, but the regions are separated from the pulmonary veins, so that the threshold range is reset to be the threshold range for storing pulmonary blood vessels, a seed point is selected in the vein region for vein segmentation, and a region growing algorithm is executed to obtain the connected pulmonary vein region. Fig. 7 is an exemplary image of a pulmonary vein obtained by segmentation according to an embodiment of the present application, and as shown in fig. 7, the pulmonary vein obtained by segmentation includes an area outside the lung, such as a heart and an aorta, in addition to a blood vessel inside the lung, and these areas need to be removed.

And S50, carrying out image segmentation on the pulmonary artery image and the pulmonary vein image based on the lung region range to obtain a pulmonary artery image and a pulmonary vein image.

And (3) the arteriovenous in the pulmonary artery image and the pulmonary vein image comprise blood vessels in a heart region, and the segmentation result outside the lung is removed by combining the segmentation result of the lung, so that the segmentation result of the pulmonary artery tree and the pulmonary vein tree is obtained. Fig. 8 is an exemplary image of pulmonary artery and vein obtained by segmentation according to an embodiment of the present application, and as shown in fig. 8, white blood vessels are left and right pulmonary artery trees and gray blood vessels are left and right pulmonary vein trees.

In this embodiment, the lung region is segmented based on a region growing algorithm by setting a threshold range for segmenting the lung region; then setting a threshold value for segmenting blood vessels, and segmenting a pulmonary blood vessel region based on a region growing algorithm; then setting a threshold value for segmenting the artery, and segmenting the pulmonary artery based on a region growing algorithm; then setting a threshold value for segmenting the pulmonary veins, and carrying out region growing in the blood vessel region to segment the pulmonary veins; finally, blood vessels outside the lung are removed based on the lung segmentation result, and the segmented image is high in accuracy and effectively meets the clinical application requirement.

Example two

Corresponding to the above-mentioned pulmonary artery and vein segmentation method of the CT image, fig. 9 is a schematic structural diagram of a pulmonary artery and vein segmentation device of a CT image in another embodiment of the present application, and referring to fig. 9, a pulmonary artery and vein segmentation device 900 of a CT image includes: a preprocessing module 910, a pulmonary vessel image segmentation module 920, a pulmonary artery image segmentation module 930, a pulmonary vein image segmentation module 940, and a pulmonary artery and vein image segmentation module 950.

The preprocessing module 910 is configured to preprocess a chest CT image acquired in advance to obtain a lung region range in the chest CT image;

a pulmonary blood vessel image segmentation module 920, configured to perform multi-plane reconstruction based on the chest CT image, and obtain a pulmonary blood vessel image by segmentation in the reconstruction process through a threshold segmentation method; wherein, the threshold value adopted in the threshold value segmentation method is a CT value interval determined based on a two-dimensional segmentation result of the lung region obtained by reconstruction;

the pulmonary artery image segmentation module 930 is configured to select a pixel point from a right ventricular pulmonary artery region as a first seed point, select a first sub-region from a CT value region as a first threshold region, perform image segmentation by a region growing method to obtain a pulmonary artery initial image, and perform morphological processing on the pulmonary artery initial image to obtain a pulmonary artery image and a vein image to be segmented, which does not include an artery, of the pulmonary vessel image;

the pulmonary vein image segmentation module 940 is configured to select a pixel point from a pulmonary vein region as a second seed point, select a second sub-region from a CT value region as a second threshold region, and perform image segmentation on the to-be-segmented vein image by a region growing method to obtain a pulmonary vein image; any value in the second sub-interval is greater than the value in the first sub-interval;

and a pulmonary artery and vein image segmentation module 950, configured to perform image segmentation on the pulmonary artery image and the pulmonary vein image based on the lung region range to obtain a pulmonary artery image and a pulmonary vein image.

Since each functional module of the device for segmenting pulmonary arteriovenous of a CT image in the exemplary embodiment of the present disclosure corresponds to the steps of the above-mentioned exemplary embodiment of the method for segmenting pulmonary arteriovenous of a CT image shown in fig. 1, please refer to the above-mentioned embodiment of the method for segmenting pulmonary arteriovenous of a CT image in the embodiments of the present disclosure for details that are not disclosed in the embodiments of the device of the present disclosure.

In summary, the technical effects of the pulmonary artery and vein segmentation apparatus using the CT image provided by the embodiment of the present disclosure refer to the technical effects of the above method, and are not described herein again.

EXAMPLE III

A third aspect of the present application provides an electronic device by another embodiment, including: a memory, a processor and a computer program stored on the memory and executable on the processor, the computer program, when executed by the processor, implementing the steps of the method for pulmonary artery and vein segmentation of CT images as described in any of the above embodiments.

Fig. 10 is a schematic structural diagram of an electronic device according to another embodiment of the present application.

The electronic device shown in fig. 10 may include: at least one processor 101, at least one memory 102, at least one network interface 104, and other user interfaces 103. The various components in the electronic device are coupled together by a bus system 105. It is understood that the bus system 105 is used to enable communications among the components. The bus system 105 includes a power bus, a control bus, and a status signal bus in addition to a data bus. For clarity of illustration, however, the various buses are labeled as bus system 105 in fig. 10.

The user interface 103 may include, among other things, a display, a keyboard, or a pointing device (e.g., a mouse, trackball, or touch pad, among others.

It will be appreciated that the memory 102 in this embodiment may be either volatile memory or nonvolatile memory, or may include both volatile and nonvolatile memory. The non-volatile memory may be a Read-only memory (ROM), a programmable Read-only memory (PROM), an erasable programmable Read-only memory (erasabprom, EPROM), an electrically erasable programmable Read-only memory (EEPROM), or a flash memory. The volatile memory may be a Random Access Memory (RAM) which functions as an external cache. By way of example, but not limitation, many forms of RAM are available, such as static random access memory (staticiram, SRAM), dynamic random access memory (dynamic RAM, DRAM), synchronous dynamic random access memory (syncronous DRAM, SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM ), Enhanced Synchronous DRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), and direct memory bus RAM (DRRAM). The memory 62 described herein is intended to comprise, without being limited to, these and any other suitable types of memory.

In some embodiments, memory 102 stores elements, executable units or data structures, or a subset thereof, or an expanded set thereof as follows: an operating system 1021 and application programs 1022.

The operating system 1021 includes various system programs, such as a framework layer, a core library layer, a driver layer, and the like, and is used for implementing various basic services and processing hardware-based tasks. The application 622 includes various applications for implementing various application services. Programs that implement methods in accordance with embodiments of the invention can be included in application 1022.

In the embodiment of the present invention, the processor 101 is configured to execute the method steps provided in the first aspect by calling a program or an instruction stored in the memory 102, specifically, a program or an instruction stored in the application 1022, for example, including the following steps:

s10, preprocessing the chest CT image acquired in advance to obtain the lung region range in the chest CT image;

s20, performing multi-plane reconstruction based on the chest CT image, and obtaining a pulmonary vessel image by segmentation through a threshold segmentation method in the reconstruction process; wherein, the threshold value adopted in the threshold value segmentation method is a CT value interval determined based on a two-dimensional segmentation result of the lung region obtained by reconstruction;

s30, selecting a pixel point from the right ventricle pulmonary artery region of the pulmonary vessel image as a first seed point, selecting a first sub-region from a CT value region as a first threshold value region, carrying out image segmentation by a region growing method to obtain a pulmonary artery initial image, and carrying out morphological processing on the pulmonary artery initial image to obtain a pulmonary artery image and a vein image to be segmented which does not contain an artery;

s40, selecting a pixel point from the pulmonary vein region as a second seed point, selecting a second sub-region from the CT value region as a second threshold value region, and performing image segmentation on the to-be-segmented vein image by a region growing method to obtain the pulmonary vein image; any numerical value in the second sub-interval is larger than the numerical value in the first sub-interval;

and S50, carrying out image segmentation on the pulmonary artery image and the pulmonary vein image based on the lung region range to obtain a pulmonary artery image and a pulmonary vein image.

The method disclosed by the above embodiment of the present invention can be applied to the processor 101, or implemented by the processor 101. The processor 101 may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuits of hardware or instructions in the form of software in the processor 101. The processor 101 may be a general-purpose processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic device, or discrete hardware component. The various methods, steps and logic blocks disclosed in the embodiments of the present invention may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in connection with the embodiments of the present invention may be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software elements in the decoding processor. The software elements may be located in ram, flash, rom, prom, or eprom, registers, among other storage media that are well known in the art. The storage medium is located in the memory 102, and the processor 101 reads the information in the memory 102 and completes the steps of the method in combination with the hardware thereof.

In addition, in combination with the pulmonary artery and vein segmentation method of the CT image in the above embodiments, an embodiment of the present invention may provide a computer-readable storage medium, on which a computer program is stored, where the computer program is executed by a processor to implement the pulmonary artery and vein segmentation method of the CT image as in any one of the above embodiments.

It is to be understood that the embodiments described herein may be implemented in hardware, software, firmware, middleware, microcode, or any combination thereof. For a hardware implementation, the processing units may be implemented within one or more Application Specific Integrated Circuits (ASICs), Digital Signal Processors (DSPs), Digital Signal Processing Devices (DSPDs), Programmable Logic Devices (PLDs), Field Programmable Gate Arrays (FPGAs), general purpose processors, controllers, micro-controllers, microprocessors, other electronic units designed to perform the functions described herein, or a combination thereof.

For a software implementation, the techniques described herein may be implemented by means of units performing the functions described herein. The software codes may be stored in a memory and executed by a processor. The memory may be implemented within the processor or external to the processor.

In the above embodiments disclosed in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The apparatus and method embodiments described above are illustrative only, as the flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of methods, apparatus, and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

It should be noted that in the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. Furthermore, it should be noted that in the description of the present specification, the description of the term "one embodiment", "some embodiments", "examples", "specific examples" or "some examples", etc., means that a specific feature, structure, material or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, the claims should be construed to include preferred embodiments and all changes and modifications that fall within the scope of the invention.

It will be apparent to those skilled in the art that various modifications and variations can be made in the present invention without departing from the spirit or scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention should also include such modifications and variations.