CN113658172A

CN113658172A - Image processing method and device, computer readable storage medium and electronic device

Info

Publication number: CN113658172A
Application number: CN202111007006.8A
Authority: CN
Inventors: 刘泽庆; 尹思源; 王少康; 陈宽
Original assignee: Infervision Medical Technology Co Ltd
Current assignee: Infervision Medical Technology Co Ltd
Priority date: 2021-08-30
Filing date: 2021-08-30
Publication date: 2021-11-16
Anticipated expiration: 2041-08-30
Also published as: CN113658172B

Abstract

The application provides an image processing method and device, a computer readable storage medium and electronic equipment, and relates to the technical field of medical image processing. The image processing method comprises the following steps: determining a candidate calcified area corresponding to the flat-scan CT image sequence based on the flat-scan CT image sequence corresponding to the target coronary artery; the method has the advantages that the first coronary artery calcification data corresponding to the coronary artery segmentation image is determined based on the coronary artery segmentation image corresponding to the candidate calcification region and the target coronary artery, the purpose of automatically segmenting the coronary artery calcification region from the flat scan CT image is favorably realized, the image processing speed is high, the calculation resources are small, extra hardware resources are not required to be occupied, the clinical diagnosis efficiency is greatly improved, and an important risk assessment basis is provided for predicting the development of the coronary heart disease. Meanwhile, the radiation of coronary artery CTA examination to the patient is avoided, and the patient seeing cost is reduced.

Description

Image processing method and device, computer readable storage medium and electronic device

Technical Field

The present application relates to the field of medical image processing technologies, and in particular, to an image processing method and apparatus, a computer-readable storage medium, and an electronic device.

Background

Coronary heart disease is the short term for coronary heart disease, and is the most common heart disease. Medical research shows that coronary artery calcification is closely related to coronary heart disease. Therefore, the detection and quantification of Coronary Artery Calcification (CAC) can provide an important basis for risk assessment for predicting the development of Coronary heart disease.

However, in the existing technique for segmenting the coronary calcified region, since the flat-scan CT image sequence cannot show the trend of the blood vessel, the coronary calcified region needs to be manually marked in the flat-scan CT image sequence clinically, which is inefficient and has large error. Therefore, there is a need to solve the problem of how to accurately obtain calcified regions on coronary branches based on chest flat scan CT.

Disclosure of Invention

The present application is proposed to solve the above-mentioned technical problems. The embodiment of the application provides an image processing method and device, a computer readable storage medium and electronic equipment.

According to an aspect of the present application, an embodiment of the present application provides an image processing method, including: determining a candidate calcified area corresponding to the flat-scan CT image sequence based on the flat-scan CT image sequence corresponding to the target coronary artery; and determining first coronary artery calcification data corresponding to the coronary artery segmentation image based on the coronary artery segmentation image of the candidate calcification region corresponding to the target coronary artery.

With reference to the first aspect, in certain implementations of the first aspect, determining, based on a coronary artery segmentation image in which the candidate calcification region corresponds to the target coronary artery, first coronary artery calcification data corresponding to the coronary artery segmentation image includes: determining a coronary artery region corresponding to the coronary artery segmentation image; first coronary calcification data is determined based on the candidate calcification regions and the coronary regions.

With reference to the first aspect, in certain implementations of the first aspect, determining first coronary calcification data based on the candidate calcification region and the coronary region includes: determining a first seed point corresponding to the coronary artery region based on the coronary artery region; determining first growth range information corresponding to the first seed point based on the candidate calcified region; first coronary calcification data is determined based on the first seed point and the first growth range information.

With reference to the first aspect, in certain implementations of the first aspect, determining a candidate calcified region corresponding to a flat-scan CT image sequence based on the flat-scan CT image sequence corresponding to the target coronary artery includes: determining a heart region corresponding to the flat-scan CT image sequence; determining a first threshold region based on the heart region and a first preset threshold; determining a second threshold region based on the heart region and a second preset threshold; determining a candidate calcification region based on a first threshold region and a second threshold region, wherein the first preset threshold is greater than the second preset threshold.

With reference to the first aspect, in certain implementations of the first aspect, determining a candidate calcification region based on the first threshold region and the second threshold region includes: determining a second seed point corresponding to the first threshold area based on the first threshold area; determining second growth area information corresponding to the second seed point based on the second threshold area; and determining candidate calcified areas based on the second seed points and the second growth area information.

With reference to the first aspect, in certain implementations of the first aspect, after determining first coronary calcification data corresponding to a coronary segmentation image based on a coronary segmentation image in which the candidate calcification region corresponds to the target coronary, the method further includes: and determining coronary artery calcification focus data corresponding to the flat-scan CT image sequence based on the first coronary artery calcification data and the flat-scan CT image sequence.

With reference to the first aspect, in certain implementations of the first aspect, after determining first coronary calcification data corresponding to a coronary segmentation image based on a coronary segmentation image in which the candidate calcification region corresponds to the target coronary, the method further includes: and performing post-processing operation on the first coronary artery calcification data to obtain second coronary artery calcification data corresponding to the first coronary artery calcification data, wherein the post-processing operation is used for deleting false positive information and/or noise information in the first coronary artery calcification data.

In a second aspect, an embodiment of the present application provides an image processing apparatus, including: a first determination module configured to determine a candidate calcified region corresponding to a flat-scan CT image sequence based on the flat-scan CT image sequence corresponding to the target coronary artery; and the second determination module is configured to determine first coronary artery calcification data corresponding to the coronary artery segmentation image based on the coronary artery segmentation image of the candidate calcification region corresponding to the target coronary artery.

In a third aspect, an embodiment of the present application provides a computer-readable storage medium, where a computer program is stored, and the computer program is configured to execute the method mentioned in the first aspect.

In a fourth aspect, an embodiment of the present application provides an electronic device, including: a processor; a memory for storing processor-executable instructions; the processor is adapted to perform the method of the first aspect.

According to the image processing method provided by the embodiment of the application, the candidate calcified area corresponding to the flat-scan CT image sequence is determined based on the flat-scan CT image sequence corresponding to the target coronary artery; based on the candidate calcified area and the coronary artery segmentation image corresponding to the target coronary artery, the first coronary artery calcification data corresponding to the coronary artery segmentation image can be accurately determined, the aim of automatically segmenting the final coronary artery calcification area from the flat-scan CT image is favorably achieved, the image processing speed is high, the calculation resources are small, extra hardware resources are not occupied, the efficiency of clinical diagnosis is greatly improved, and an important risk assessment basis is provided for predicting the development of the coronary heart disease. Meanwhile, the radiation of coronary artery CTA examination to the patient is avoided, and the patient seeing cost is reduced.

Drawings

The above and other objects, features and advantages of the present application will become more apparent by describing in more detail embodiments of the present application with reference to the attached drawings. The accompanying drawings are included to provide a further understanding of the embodiments of the application and are incorporated in and constitute a part of this specification, illustrate embodiments of the application and together with the description serve to explain the principles of the application. In the drawings, like reference numbers generally represent like parts or steps.

Fig. 1 is a schematic view of a scenario applicable to the embodiment of the present application.

Fig. 2 is a schematic view of another scenario applicable to the embodiment of the present application.

Fig. 3 is a schematic flowchart illustrating an image processing method according to an embodiment of the present application.

Fig. 4 shows a coronary artery segmentation image according to an embodiment of the present application.

Fig. 5 is a schematic flowchart of an image processing method according to another embodiment of the present application.

Fig. 6 is a schematic flowchart of an image processing method according to another embodiment of the present application.

Fig. 7 is a coronary calcification segmentation mask image provided in accordance with an embodiment of the present application.

Fig. 8 is a schematic flowchart of an image processing method according to another embodiment of the present application.

Fig. 9 illustrates an image of a heart region provided by an embodiment of the present application.

Fig. 10 is a schematic flowchart of an image processing method according to another embodiment of the present application.

Fig. 11 is a schematic flowchart of an image processing method according to another embodiment of the present application.

Fig. 12 is a schematic flowchart of an image processing method according to yet another embodiment of the present application.

Fig. 13 is a schematic structural diagram of an image processing apparatus according to an embodiment of the present application.

Fig. 14 is a schematic flowchart of an image processing method according to yet another embodiment of the present application.

Fig. 15 is a schematic structural diagram of a second determining module according to an embodiment of the present application.

Fig. 16 is a schematic structural diagram of a first determining unit according to an embodiment of the present application.

Fig. 17 is a schematic structural diagram of a first determining module according to an embodiment of the present application.

Fig. 18 is a schematic structural diagram of a second determining unit according to an embodiment of the present application.

Fig. 19 is a schematic structural diagram of an image processing apparatus according to another embodiment of the present application.

Fig. 20 is a schematic structural diagram of an image processing apparatus according to still another embodiment of the present application.

Fig. 21 is a schematic structural diagram of an electronic device according to an embodiment of the present application.

Detailed Description

The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

Summary of the application

The image segmentation technology is an important research direction in the technical field of image processing and the technical field of computer vision, and is an important link for image semantic understanding. In particular, image segmentation techniques refer to techniques that divide a region of an image to be segmented into several regions having the same or similar properties. The image segmentation technology is an auxiliary technology of subsequent image processing, analysis and other technologies, and the application scenarios of the image segmentation technology are very wide. Particularly in the application scene of medical images (such as a focus positioning scene), the quality of the image segmentation technology can directly influence the focus positioning accuracy, and further directly influence the subsequent auxiliary diagnosis effect.

The coronary artery (coronary artery for short) is the artery supplying blood to the heart, starts from the aortic root in the aortic sinus, divides into two branches, left and right, and runs on the surface of the heart.

At present, the prevalence rate and mortality rate of coronary heart disease are still in a continuously rising state, and medical research shows that coronary artery (namely coronary artery) calcification is related to the incidence of coronary heart disease. Calcification is a ubiquitous pathological manifestation in vascular diseases, mainly manifested by increased stiffness and reduced compliance of vascular walls, and is one of the important factors for high morbidity and mortality of cardiovascular and cerebrovascular diseases.

Therefore, the detection and quantification of Coronary Artery Calcification (CAC) can provide an important basis for risk assessment for predicting the development of Coronary heart disease.

Computed Tomography (CT) mainly uses precisely collimated X-ray beams, gamma rays, ultrasonic waves, and the like, and performs cross-section scanning one by one around a certain part of a human body together with a detector with extremely high sensitivity.

The CT examination includes a flat scan CT examination and an enhanced CT examination, and the common CT examination directly performed on the instrument without injecting a contrast medium is the flat scan CT examination. The principle of diagnosing diseases by flat scan CT examination is as follows: the attenuation value of the measuring radiation after passing through different tissues of a human body is different due to different refractive indexes of different tissues, the professional term of the attenuation value of the reaction radiation is density, and the CT value is a measuring Unit for measuring the density of a certain local tissue or organ of the human body and is generally called Hounsfield Unit (Hu). The same texture should be of the same density and different textures should be of different densities.

In the prior art, since the CT image cannot display the trend of the blood vessel, the calcified area on the coronary artery branch cannot be accurately obtained. The coronary calcification treatment mostly depends on manual treatment and labeling, and a doctor is usually required to manually select a coronary calcification region in a CT image clinically. In addition, conventional cardiac calcium scoring scans are often incorporated into coronary CT angiography (CTA) examinations, where a complete coronary CTA examination is several times more expensive than a thoracic CT and the patient is exposed to a much higher dose of radiation. In addition, coronary CTA has certain risks, needs an electrocardiograph gating device and strictly cooperates with respiration of patients, and the coronary CTA examination can not be performed in every level of hospitals. While flat-scan CT is relatively low cost and has a wider coverage, the efficiency of clinical diagnosis will be greatly improved if coronary calcification scores can be based on thoracic flat-scan CT images.

In addition, there are some problems in calculating the calcification score based on the chest flat scan CT, and especially, the chest CT data reconstructed by using the lung window has very large noise and is difficult to be directly and effectively used for calculating the coronary artery score, so a coronary artery calcification segmentation technology based on the chest flat scan CT is urgently needed.

In order to solve the technical problem, the application provides an image processing method, which is used for processing a flat-scan CT image sequence corresponding to a target coronary artery and determining a candidate calcified area corresponding to the flat-scan CT image sequence; the purpose of determining the first coronary artery calcification data corresponding to the coronary artery segmentation image based on the coronary artery segmentation image of the candidate calcification region corresponding to the target coronary artery is achieved. Through a series of image processing operations, the coronary artery calcification region can be accurately segmented from the coronary artery branch, the speed is high, the calculation resource is small, extra hardware resources are not occupied, and the efficiency of clinical diagnosis is greatly improved. Meanwhile, the radiation of coronary artery CTA examination to the patient is avoided, and the patient seeing cost is reduced.

Exemplary application scenarios

Fig. 1 is a schematic view of a scenario applicable to the embodiment of the present application. As shown in fig. 1, a scenario to which the embodiment of the present application is applied includes a server 1 and an image capturing device 2, where there is a communication connection relationship between the server 1 and the image capturing device 2.

Specifically, the image acquisition device 2 is configured to acquire a flat-scan CT image sequence, and the image acquisition device 2 may be a CT scanner, and the CT scanner is configured to perform X-ray scanning on a human chest to obtain a CT image of the human chest.

The server 1 may be one server, or a server group composed of a plurality of servers, or may be one virtualization platform or one cloud computing service center, and the present disclosure does not specifically limit the type of the server 1. The server 1 is configured to determine a candidate calcification region corresponding to the flat-scan CT image sequence based on the flat-scan CT image sequence acquired by the image acquisition device 2, and then determine first coronary artery calcification data corresponding to the coronary artery segmentation image based on a coronary artery segmentation image in which the candidate calcification region corresponds to the target coronary artery. That is, the scene implements an image processing method. Since the scene shown in fig. 1 implements the image processing method by using the server 1, the scene not only can improve the adaptability of the scene, but also can effectively reduce the calculation amount of the image acquisition device 2.

It should be noted that the present disclosure is also applicable to another scenario. Fig. 2 is a schematic view of another scenario applicable to the embodiment of the present application. Specifically, the scene includes an image processing device 3, wherein the image processing device 3 includes an image acquisition module 31 and a calculation module 32, and a communication connection relationship exists between the image acquisition module 31 and the calculation module 32.

Specifically, the image acquisition module 31 in the image processing apparatus 3 is configured to acquire a flat scan CT image sequence, and the calculation module 32 in the image processing apparatus 3 is configured to determine a candidate calcification region corresponding to the flat scan CT image sequence based on the flat scan CT image sequence acquired by the image acquisition apparatus 2, and then determine first coronary calcification data corresponding to the coronary segmentation image based on the coronary segmentation image in which the candidate calcification region corresponds to the target coronary. That is, the scene implements an image processing method. Since the scene shown in fig. 2 implements an image processing method using the image processing apparatus 3, data transmission operations with a server or other related devices are not required, and thus the scene can ensure real-time performance of the image processing method.

Exemplary image processing method

Fig. 3 is a schematic flowchart illustrating an image processing method according to an embodiment of the present application. As shown in fig. 3, the image processing method includes the following steps.

Step 101: and determining candidate calcified regions corresponding to the flat-scan CT image sequence based on the flat-scan CT image sequence corresponding to the target coronary artery.

Specifically, the flat-scan CT image sequence may be an image obtained by performing a flat-scan CT examination on a human breast, or may be a flat-scan CT image based on cardiac segmentation. The flat scan CT image sequence includes a cardiac region. The candidate calcified regions are used to characterize data on the heart region that satisfies the location and contour of the calcific definition.

Step 102, determining first coronary artery calcification data corresponding to the coronary artery segmentation image based on the coronary artery segmentation image of the candidate calcification region and the target coronary artery.

Illustratively, the coronary segmentation image may be a coronary quadric-dominant mask image based on a pre-model segmentation. For example, the coronary artery image may be input into a coronary artery segmentation module (i.e., a trained neural network model) to obtain a coronary artery segmentation image.

Specifically, the mask image corresponding to the candidate calcified region has the same size, the same pixel spatial size, and the same pixel directivity as the coronary artery segmentation image.

For example, the mask image of the candidate calcified region may be a binary image consisting of 0 and 1 values, where the 0 value region is the background region and the 1 value region is the calcified region. Whether the pixel points in the image belong to the calcified area or the background area irrelevant to the calcified area is distinguished by setting a 0 value and a 1 value.

The mask image of the candidate calcified region may be considered as an attribute value image in which pixels are alternatively set to a valid value or an invalid value. The valid value can be set to 255, and each bit in the binary value 11111111 is logically and-operated with the corresponding bit of the other value, so that the corresponding bit of the other value can keep the original value; an invalid value may be set to 0, and each bit of the binary value 00000000 logically andes with a corresponding bit of the other value, which may cause the corresponding bit of the other value to be 0 indicating invalid. Accordingly, the mask image corresponds to pixels in the calcified regions being valid values and pixels in other non-calcified regions being invalid values.

Illustratively, the first coronary calcification data includes a coronary calcification mask image. For example, the coronary calcification mask image may be a multi-label image, with 0-value regions as the background and 1-4-value regions for each coronary segment.

The embodiment of the present application does not limit the specific form of the coronary artery segmentation image, and may be an original medical image, a preprocessed medical image, or a partial image series in the original medical image, that is, a part of the original medical image. In addition, the acquisition object corresponding to the coronary artery segmentation image can be a human body or an animal body.

The image processing method provided by the embodiment of the application determines a candidate calcified area corresponding to a flat-scan CT image sequence based on the flat-scan CT image sequence corresponding to a target coronary artery; the purpose of determining the first coronary artery calcification data corresponding to the coronary artery segmentation image based on the coronary artery segmentation image of the candidate calcification region corresponding to the target coronary artery is achieved. Through a series of image processing operations, the coronary artery calcification region can be accurately segmented, the speed is high, the computing resource is small, no additional hardware resource is occupied, and the efficiency of clinical diagnosis is greatly improved. Meanwhile, the radiation of coronary artery CTA examination to the patient is avoided, and the patient seeing cost is reduced.

Fig. 4 shows a coronary artery segmentation image according to an embodiment of the present application. As shown in fig. 4, for the coronary artery segmentation image, in order to be able to sufficiently match with the coronary artery in the flat scan CT image sequence and reduce the matching error, it is usually subjected to a preprocessing operation.

Illustratively, the preprocessing operations include graphical dilation operations, where the dilation kernel size may be 3 x 3. By carrying out graphical expansion operation on the coronary artery segmentation image, the target coronary artery in the coronary artery segmentation image can be lengthened or thickened, and the matching effect of the subsequent coronary artery segmentation image and the flat-scan CT image sequence is further improved.

It should be understood that the preprocessing operation may also be an open operation or a closed operation. The present application is not particularly limited to this, as long as the function of lengthening or thickening the target coronary artery can be achieved.

Fig. 5 is a schematic flowchart of an image processing method according to another embodiment of the present application. As shown in fig. 5, the first coronary calcification data corresponding to the coronary segmentation image is determined based on the coronary segmentation image of the candidate calcification region corresponding to the target coronary (step 102), which includes the following steps.

Step 1020, determining a coronary artery region corresponding to the coronary artery segmentation image.

Specifically, the coronary artery segmentation image comprises a background region and a coronary artery region, the coronary artery segmentation image is cut through the minimum external frame by acquiring the minimum external frame of the coronary artery segmentation image, so that the coronary artery region is extracted, the background region is filtered, a better segmentation effect can be realized, and an important role is played in the subsequent extraction of a final calcified lesion region.

Step 1022, determining first coronary calcification data based on the candidate calcification regions and the coronary regions.

Illustratively, the first coronary calcification data referred to in step 1022 includes coronary calcification regions.

Specifically, after determining the candidate calcification area, in order to locate the calcification focus in the coronary artery, the candidate calcification area needs to be matched and marked with the coronary artery area in the coronary artery segmentation image, and the calcification area covered by the coronary artery is found, so that the coronary artery calcification area can be obtained.

According to the image processing method provided by the embodiment of the application, the coronary artery region corresponding to the coronary artery segmentation image is determined, and then the purpose of determining the first coronary artery calcification data is achieved according to the candidate calcification region and the coronary artery region. The coronary artery region is determined in a minimum external frame cutting mode, the range of image processing can be reduced, and unnecessary noise in the image is filtered. The matching is carried out based on the coronary artery region and the candidate calcification region, so that the determined first coronary artery calcification data is more accurate, and the situation of low robustness caused by unnecessary noise is further reduced.

Fig. 6 is a schematic flowchart of an image processing method according to another embodiment of the present application. As shown in fig. 6, first coronary calcification data is determined based on the candidate calcification regions and the coronary regions (step 1022), which includes the following steps.

And step 2121, determining a first seed point corresponding to the coronary artery region based on the coronary artery region.

Specifically, the coronary artery branches from the trunk structure one level by one level, and the complicated multi-level branches are made, and based on the characteristics of the multi-level branch structure of the coronary artery, the coronary artery region can be used as the selection range of the first seed point.

Step 2221, based on the candidate calcified regions, determine first growth range information corresponding to the first seed point.

Illustratively, the candidate calcified region serves as a growth region of the first seed point for limiting the growth of the first seed point within the candidate calcified region.

Step 2321, first coronary calcification data is determined based on the first seed point and the first growth range information.

Illustratively, the first coronary calcification data includes coronary calcification regions.

Illustratively, the first coronary calcification data is determined using a region growing algorithm based on the candidate calcification regions and the coronary regions.

Specifically, a coronary artery region in a coronary artery segmentation image is used as a first seed point (namely a starting point), a candidate calcified region is used as a growth range of the first seed point, the first seed point is expanded in the candidate calcified region for a certain number of times, namely a growth process, and if the candidate calcified region is not provided with the first seed point, no change occurs, so that all coronary artery calcified regions overlapping with the coronary artery region, namely first coronary artery calcified data, are obtained.

According to the image processing method provided by the embodiment of the application, the purpose of determining the first coronary artery calcification data based on the first seed point and the first growth range information is achieved by determining the first seed point corresponding to the coronary artery region based on the coronary artery region and determining the first growth range information corresponding to the first seed point based on the candidate calcification region. Compared with the prior art, the image intersection matching is directly carried out to obtain the calcification area on the coronary artery, the error generated in the matching process can be further reduced, the calcification focus in the coronary artery can be accurately positioned, and a precondition basic condition is provided for obtaining effective coronary artery calcification focus data subsequently.

Fig. 7 is a coronary calcification segmentation mask image provided in accordance with an embodiment of the present application. As shown in fig. 7, the white region in the coronary calcification segmentation mask image is the target coronary artery, and the black region is the background region. The coronary calcified area 1 is a calcified area on the target coronary artery.

Compared with the prior art that the candidate calcified area is directly intersected with the coronary artery area for matching, the image processing method provided by the embodiment of the application has the advantages that based on the candidate calcified area and the coronary artery area, the area growth algorithm is utilized, the coronary artery area is used as a seed point, the area growth is carried out in the growth range limited by the candidate calcified area, the calcified area on the coronary artery can be rapidly positioned, and meanwhile, the accuracy of first coronary artery calcification data can be guaranteed.

According to the definition of calcified plaque in medicine, the coronary calcification score is more than 1mm²Or the sum of the area of the calcified region of 1 pixel multiplied by its maximum density weighting factor. Wherein the value of the weighting coefficient is related to the density of the calcified plaque. When the density is less than 130Hu, the weighting coefficient is 0; when the density value is 130-199 Hu, the weighting coefficient is 1; when the density value is 200-299 Hu, the weighting coefficient is 2; when the density is 300-399 Hu, the weighting coefficient is 3; when the density value is larger than 400, the weighting coefficient is 4. That is, pixels or regions in the image that appear at the position of coronary vessels at a density of 130Hu or more, that is, Hu values of 130 and more in a flat-scan CT image sequence will be determined as calcified regions. Therefore, it is necessary to perform Hu threshold segmentation on the cut flat-scan CT image, and after the Hu threshold segmentation, all regions satisfying the definition of calcified plaque in the CT image can be identified, but these regions are not all coronary calcified plaque. Some of these regions that are too small of noise can be eliminated by limiting the size of the connected component. However, in experiments, it is found that some images cannot completely and effectively segment calcified regions at the value of 130Hu, and a large amount of noise higher than 130Hu occurs, so that in an embodiment of the present application, a threshold segmentation is performed twice to determine candidate calcified regions corresponding to a flat-scan CT image sequence.

Fig. 8 is a schematic flowchart of an image processing method according to another embodiment of the present application. As shown in fig. 8, determining a candidate calcified region corresponding to a flat-scan CT image sequence based on the flat-scan CT image sequence corresponding to the target coronary artery (step 101) includes the following steps.

Step 1001, a heart region corresponding to the flat scan CT image sequence is determined.

Specifically, the flat-scan CT image sequence includes a background region and a heart region, and the flat-scan CT image sequence is cut based on a minimum bounding box by obtaining the minimum bounding box of the flat-scan CT image sequence, so as to determine the heart region corresponding to the flat-scan CT image sequence, and filter out other irrelevant background regions, such as a rib region. Fig. 9 illustrates an image of a heart region provided by an embodiment of the present application. As shown in fig. 9, the flat-scan CT image sequence is cut through the minimum bounding box, so as to determine the heart region 2 corresponding to the flat-scan CT image sequence.

Based on the heart region and a first preset threshold, a first threshold region is determined, step 1002.

Step 1003, determining a second threshold region based on the heart region and a second preset threshold.

Step 1004, determining a candidate calcified region based on a first threshold region and a second threshold region, wherein the first preset threshold is greater than the second preset threshold.

Illustratively, the second preset threshold may be 130 Hu. The first preset threshold may be 250 Hu. Specifically, the calcified regions cannot be completely and effectively segmented by the heart region after being segmented by the first preset threshold, namely, a large number of noise points higher than 130Hu exist in the first threshold region. And segmenting the heart area by a second preset threshold to obtain a second threshold area, wherein the second threshold area is a smaller calcified area. It is necessary to merge the first threshold region and the second threshold region to determine the candidate calcification region.

It should be understood that the first preset threshold and the second preset threshold are not specifically limited in the present application, as long as the first preset threshold is greater than the second preset threshold.

The image processing method provided by the embodiment of the application can determine the heart region corresponding to the flat-scan CT image sequence in a minimum bounding box segmentation mode, plays an important role in subsequently extracting the final calcification focus region, effectively reduces the image range needing to be processed, and can remove unnecessary noise. In addition, a first threshold region is determined by segmenting the cardiac region and a first preset threshold. And segmenting the heart area by the second preset threshold value to determine a second threshold value area. By performing two segmentations and combining the results of the two segmentations, unnecessary noise can be filtered out, and effective candidate calcified regions can be determined.

Fig. 10 is a schematic flowchart of an image processing method according to another embodiment of the present application. As shown in fig. 10, based on the first threshold region and the second threshold region, a candidate calcified region is determined (step 1004), including the following steps.

Step 1014, determining a second seed point corresponding to the first threshold region based on the first threshold region.

And 1024, determining second growth area information corresponding to the second seed point based on the second threshold area.

Step 1034, determining candidate calcified regions based on the second seed points and the second growth region information.

Exemplarily, the first preset threshold is greater than the second preset threshold, a first threshold region corresponding to the first preset threshold is used as the second seed point, a second threshold region corresponding to the second preset threshold is used as the growth range of the second seed point, and the second seed point is expanded in the second growth region for a certain number of times, that is, in the growth process, so as to finally determine the candidate calcified region.

In the image processing method provided by the embodiment of the application, the region divided by the high threshold is used as the seed point by using the region growing algorithm, and the region divided by the low threshold is subjected to filling growth in the region divided by the low threshold, and if the seed point does not exist in a certain low threshold divided region, that is, the region divided by the high threshold does not exist, the low threshold divided region is deleted. By means of two threshold value segmentation and combination of results of the two threshold value segmentation, a better calcification segmentation effect can be achieved, and therefore candidate calcification areas which meet the definition of calcified plaques in a flat-scan CT image sequence are determined.

Fig. 11 is a schematic flowchart of an image processing method according to another embodiment of the present application. As shown in fig. 11, after determining first coronary calcification data corresponding to a coronary segmentation image based on a coronary segmentation image in which a candidate calcification region corresponds to a target coronary (step 102), the method further includes the following steps.

And 103, determining coronary artery calcification focus data corresponding to the flat-scan CT image sequence based on the first coronary artery calcification data and the flat-scan CT image sequence.

Specifically, the first coronary calcification data includes a coronary calcification mask image. The coronary calcification lesion data includes a coronary calcification segmentation image. The coronary calcification mask image is different from the flat-scan CT image sequence in size, and the parameters of other various images are the same. The size of the coronary artery calcification mask image is only required to be reconstructed to the size of the original flat-scan CT image, the reconstructed mask image can be obtained, then, post-processing operation is carried out on each connected domain in the reconstructed mask image, noise data are filtered, and the segmentation effect is improved. Specifically, for each connected domain, a minimum bounding box of each connected domain is obtained and compared with a minimum bounding box corresponding to a previously obtained coronary artery region, and if a certain boundary of the two minimum bounding boxes is overlapped, the connected domain is determined to be not a calcified region on the coronary artery and is removed, wherein the boundary indicates that the connected domain is cut by the minimum bounding box corresponding to the coronary artery region. Therefore, an effective and complete coronary artery calcification segmentation image can be obtained.

The image processing method provided by the embodiment of the application realizes the purpose of determining the coronary artery calcification disease data corresponding to the flat-scan CT image sequence by a mode based on the first coronary artery calcification data and the flat-scan CT image sequence, can further evaluate the degree of coronary artery calcification lesions by the coronary artery calcification disease data, and provides an important risk evaluation basis for predicting the development of the coronary heart disease.

In an embodiment, after the coronary artery calcification segmentation image is obtained, information such as an area and a volume of a calcified region may be further determined based on the coronary artery calcification segmentation image, and a calcification score corresponding to the coronary artery calcification segmentation image is determined according to a calcification score calculation formula.

For example, the assignment is performed according to the CT value corresponding to the calcified region of the lesion, the assignment of 130-299 Hu is 1, the assignment of 200-299 Hu is 2, the assignment of 300-399 Hu is 3, the assignment of 400Hu and above is 4, the assigned CT value and the calcified area (in mm) are²Calculation) and finally adding the scores of all coronary arteries in all sections of the flat-scan CT image sequence to obtain the total calcification score. In general, the higher the total calcification score, the higher the risk of developing cardiovascular disease.

It will be appreciated that other calcium score calculation means are included, such as directly multiplying the area of the calcification by the thickness of the layer to produce a volume score to reflect the total volume of the calcification. This is not a particular limitation of the present application.

According to the image processing method provided by the embodiment of the application, the coronary calcification mask image corresponding to the first coronary calcification data and the flat-scan CT image sequence are reconstructed to determine the coronary calcification lesion data corresponding to the flat-scan CT image sequence, so that the purpose of automatically acquiring an accurate coronary calcification region and a calcification score thereof from the flat-scan CT image sequence is realized, the overall calcification degree of the coronary is quantified, the condition of a patient is conveniently further evaluated, and the efficiency of clinical diagnosis is improved.

Fig. 12 is a schematic flowchart of an image processing method according to yet another embodiment of the present application. As shown in fig. 12, after determining first coronary calcification data corresponding to a coronary segmentation image based on a coronary segmentation image in which a candidate calcification region corresponds to a target coronary (step 102), the method further includes the following steps.

And 104, performing post-processing operation on the first coronary artery calcification data to obtain second coronary artery calcification data corresponding to the first coronary artery calcification data, wherein the post-processing operation is used for deleting false positive information and/or noise information in the first coronary artery calcification data.

Specifically, since the coronary artery segmentation image is subjected to a graphical dilation operation before matching, so that the size and the shape of the coronary artery are changed, the coronary artery is easily communicated with other positions in the process of matching with the flat-scan CT image sequence, and therefore the matching result needs to be further denoised.

Specifically, after the first coronary artery calcification data is subjected to the first post-processing operation, false positive information and/or noise information in the first coronary artery calcification data is filtered, and the obtained second coronary artery calcification data is effective information.

According to the image processing method provided by the embodiment of the application, the first coronary artery calcification data is subjected to post-processing operation, and the false positive information and/or the noise information in the first coronary artery calcification data are/is deleted, so that a more accurate segmentation result is obtained, the segmentation precision is effectively improved, and the robustness is enhanced.

Fig. 13 is a schematic flowchart of an image processing method according to yet another embodiment of the present application. As shown in fig. 13, the image processing method mainly uses the coronary artery 4 main branch mask image corresponding to the heart to match with the flat scan CT image sequence, and then obtains the final coronary calcification focus through a post-processing algorithm.

Firstly, a coronary artery 4 main branch mask image is obtained through preposed model segmentation, and the coronary artery 4 main branch mask image is preprocessed through graphical expansion operation, so that the coronary artery area in the coronary artery 4 main branch mask image can be lengthened or thickened, the coronary artery 4 main branch mask image is convenient to match with the coronary artery in a flat-scan CT image sequence, and errors are reduced.

Secondly, the preprocessed coronary artery 4 main branch mask image is cut through the minimum external frame to obtain the coronary artery area in the coronary artery 4 main branch mask image, the image range needing to be processed is narrowed, accurate positioning of the coronary artery area is facilitated, unnecessary noise can be removed, and the effects of reducing resource expenditure and accelerating a post-processing algorithm are achieved to a certain extent.

And after the flat-scan CT image sequence is acquired, cutting the flat-scan CT image sequence through the minimum external frame to obtain a heart region corresponding to the flat-scan CT image sequence. And acquiring a calcification mask image by adopting a mode of twice threshold segmentation based on the heart region image. Specifically, the flat-scan CT image sequence after the minimum bounding box is cut is subjected to binarization segmentation according to 250Hu, and a first threshold region is determined. And performing binarization segmentation on the flat-scan CT image sequence subjected to minimum bounding box cutting according to 130Hu, and determining a second threshold region. The first threshold region obtained by high threshold segmentation is mostly a small calcified region, and a region growing algorithm is required to be used to allow the region segmented by high threshold (i.e. the first threshold region) to be used as a seed point, and to allow the seed point to be subjected to filling growth in the region segmented by low threshold (i.e. the second threshold region), so as to determine the calcified mask image. If there is no seed point in a low-threshold segmentation area, i.e. there is no high-threshold segmentation area, then the low-threshold segmentation area is deleted. The aim of determining the calcification mask image is achieved by two-time segmentation and combining the results of the two-time segmentation, and better calcification segmentation effect is obtained.

After obtaining the calcification mask image, in order to locate the calcification focus in the coronary artery, the calcification mask image needs to be matched with the cut main coronary artery 4 mask image, and the calcification area covered by the coronary artery is marked, so as to obtain the coronary artery calcification mask image. The matching method is realized based on a region growing algorithm. Firstly, the main coronary artery 4 mask image cut by the minimum external frame is used as a seed point, and the seed point is subjected to region growth in the divided calcification mask image, so that the coronary artery calcification mask image intersected with the main coronary artery 4 mask image is obtained. Since the coronary artery 4 main branch mask image is subjected to the graphical expansion operation in advance, so that the size and the shape of the coronary artery are changed, the coronary artery is easily communicated with other positions in the matching process, noise exists in the matching result, and the result needs to be further denoised by combining the post-processing operation.

And finally, reconstructing the coronary artery calcification mask image obtained by matching on the size of the original flat-scan CT image sequence, so as to obtain the coronary artery calcification mask image segmented by the flat-scan CT image sequence. Processing each connected domain existing in the coronary artery calcification mask image, acquiring the minimum external frame of each connected domain, comparing the minimum external frame with the minimum external frame of the main branch mask image of the previously cut coronary artery 4, judging whether the two minimum external frames have overlapped boundaries or not, and removing the minimum external frames if the boundary is overlapped. So far, the operations of denoising and/or false positive removing of the coronary calcification mask image are completed, and the effective and complete final coronary calcification focus is obtained.

According to the image processing method provided by the embodiment of the application, the coronary 4 main branch mask image corresponding to the heart is matched with the flat-scan CT image sequence, and then the final coronary calcification focus is obtained through a post-processing algorithm, so that the purpose of automatically obtaining an accurate coronary calcification region from the flat-scan CT image sequence is achieved, the calculation speed is high, extra hardware resources are not occupied, and the efficiency of clinical diagnosis is greatly improved. Meanwhile, the radiation of coronary artery CTA examination to the patient is avoided, and the patient seeing cost is reduced.

Exemplary devices

The method embodiment of the present application is described in detail above with reference to fig. 1 to 13, and the apparatus embodiment of the present application is described in detail below with reference to fig. 14 to 21. It is to be understood that the description of the method embodiments corresponds to the description of the apparatus embodiments, and therefore reference may be made to the preceding method embodiments for parts not described in detail.

Fig. 14 is a schematic structural diagram of an image processing apparatus according to an embodiment of the present application. As shown in fig. 14, the image processing apparatus 100 includes a first determination module 1100 and a second determination module 1110.

The first determination module 1100 is configured to determine a candidate calcified region corresponding to a flat-scan CT image sequence based on the flat-scan CT image sequence corresponding to the target coronary artery. The second determination module 1110 is configured to determine first coronary calcification data corresponding to the coronary segmentation image based on the coronary segmentation image in which the candidate calcification region corresponds to the target coronary.

Fig. 15 is a schematic structural diagram of a second determining module according to an embodiment of the present application. As shown in fig. 15, the second determination module 1110 includes a coronary region determination unit 1111 and a first determination unit 1112.

The coronary-artery region determination unit 1111 is configured to determine a coronary-artery region corresponding to the coronary-artery segmentation image. The first determination unit 1112 is configured to determine first coronary calcification data based on the candidate calcification regions and the coronary regions.

Fig. 16 is a schematic structural diagram of a first determining unit according to an embodiment of the present application. As shown in fig. 16, the first determination unit 1112 includes a first seed point determination subunit 1122, a first growth range information determination subunit 1132, and a first determination subunit 1142.

The first seed point determining subunit 1122 is configured to determine, based on the coronary artery region, a first seed point corresponding to the coronary artery region. The first growth range information determining subunit 1132 is configured to determine, based on the candidate calcified regions, first growth range information corresponding to the first seed point. The first determining subunit 1142 is configured to determine first coronary calcification data based on the first seed point and the first growth range information.

Fig. 17 is a schematic structural diagram of a first determining module according to an embodiment of the present application. As shown in fig. 17, the first determination module 1100 includes: a heart region determining unit 1101, a first threshold region determining unit 1102, a second threshold region determining unit 1103, and a second determining unit 1104.

The cardiac region determination unit 1101 is configured to determine a cardiac region to which the flat scan CT image sequence corresponds. The first threshold region determining unit 1102 is configured to determine a first threshold region based on the heart region and a first preset threshold. The second threshold region determining unit 1103 is configured to determine the second threshold region based on the cardiac region and a second preset threshold. The second determination unit 1104 is configured to determine a candidate calcified region based on a first threshold region and a second threshold region, wherein the first preset threshold is greater than the second preset threshold.

Fig. 18 is a schematic structural diagram of a second determining unit according to an embodiment of the present application. As shown in fig. 18, the second determining unit 1104 includes a second determining sub-unit 1114, a third determining sub-unit 1124, and a fourth determining sub-unit 1134.

The second determining subunit 1114 is configured to determine, based on the first threshold region, a second seed point corresponding to the first threshold region. The third determining subunit 1124 is configured to determine, based on the second threshold region, second growth region information corresponding to the second seed point. The fourth determining subunit 1134 is configured to determine a candidate calcified region based on the second seed point and the second growth region information.

Fig. 19 is a schematic structural diagram of an image processing apparatus according to another embodiment of the present application. As shown in fig. 19, the image processing apparatus 100 further includes a coronary calcification lesion data determining module 1210.

The coronary calcification lesion data determining module 1210 is configured to determine coronary calcification lesion data corresponding to the flat-scan CT image sequence based on the first coronary calcification data and the flat-scan CT image sequence.

Fig. 20 is a schematic structural diagram of an image processing apparatus according to still another embodiment of the present application. As shown in fig. 20, the image processing apparatus 100 further includes a post-processing operation module 1310.

The post-processing operation module 1310 is configured to perform a post-processing operation on the first coronary artery calcification data to obtain second coronary artery calcification data corresponding to the first coronary artery calcification data, where the post-processing operation is used to delete false positive information and/or noise information in the first coronary artery calcification data.

Exemplary electronic device

Next, an electronic apparatus according to an embodiment of the present application is described with reference to fig. 21. Fig. 21 is a schematic structural diagram of an electronic device according to an embodiment of the present application. As shown in fig. 21, the electronic device 200 includes one or more processors 201 and memory 202.

The processor 201 may be a Central Processing Unit (CPU) or other form of processing unit having data processing capabilities and/or instruction execution capabilities, and may control other components in the electronic device 200 to perform desired functions.

Memory 202 may include one or more computer program products that may include various forms of computer-readable storage media, such as volatile memory and/or non-volatile memory. The volatile memory may include, for example, Random Access Memory (RAM), cache memory (cache), and/or the like. The non-volatile memory may include, for example, Read Only Memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium and executed by the processor 201 to implement the image processing methods of the various embodiments of the present application described above and/or other desired functions.

In one example, the electronic device 200 may further include: an input device 203 and an output device 204, which are interconnected by a bus system and/or other form of connection mechanism (not shown).

For example, the input device 203 may be the above-mentioned apparatus for performing a flat-scan CT image sequence detection.

The output device 204 may output various information, such as the first coronary calcification data corresponding to the coronary segmentation image, and the like, to the outside, and the output device 204 may include, for example, a display, a printer, and a communication network and a remote output device connected thereto.

Of course, for the sake of simplicity, only some of the components related to the present application in the electronic apparatus 200 are shown in fig. 21, and components such as a bus, an input/output interface, and the like are omitted. In addition, electronic device 200 may include any other suitable components depending on the particular application.

Exemplary computer program product and computer-readable storage Medium

In addition to the above-described methods and apparatus, embodiments of the present application may also be a computer program product comprising computer program instructions that, when executed by a processor, cause the processor to perform the steps in the image processing method according to various embodiments of the present application described in the "example line image processing method" section of this specification, above.

The computer program product may write program code for carrying out operations for embodiments of the present application in any combination of one or more programming languages, including an object oriented programming language such as Java, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device, or entirely on the remote computing device or server.

Furthermore, embodiments of the present application may also be a computer-readable storage medium having stored thereon computer program instructions that, when executed by a processor, cause the processor to perform the steps in the image processing method according to various embodiments of the present application described in the "image processing method" section above in this specification.

The computer-readable storage medium may take any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may include, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable disk, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

The foregoing describes the general principles of the present application in conjunction with specific embodiments, however, it is noted that the advantages, effects, etc. mentioned in the present application are merely examples and are not limiting, and they should not be considered essential to the various embodiments of the present application.

The foregoing description has been presented for purposes of illustration and description. Furthermore, the description is not intended to limit embodiments of the application to the form disclosed herein. While a number of example aspects and embodiments have been discussed above, those of skill in the art will recognize certain variations, modifications, alterations, additions and sub-combinations thereof.

Claims

1. An image processing method, comprising:

determining a candidate calcified area corresponding to a flat-scan CT image sequence based on the flat-scan CT image sequence corresponding to the target coronary artery;

determining first coronary artery calcification data corresponding to the coronary artery segmentation image based on the coronary artery segmentation image of the candidate calcification region corresponding to the target coronary artery.

2. The image processing method according to claim 1, wherein the determining first coronary calcification data corresponding to the coronary segmentation image based on the coronary segmentation image in which the candidate calcification region corresponds to the target coronary comprises:

determining a coronary artery region corresponding to the coronary artery segmentation image;

determining the first coronary calcification data based on the candidate calcification regions and the coronary regions.

3. The image processing method of claim 2, wherein the determining the first coronary calcification data based on the candidate calcification region and the coronary region comprises:

determining a first seed point corresponding to the coronary artery region based on the coronary artery region;

determining first growth range information corresponding to the first seed point based on the candidate calcified region;

determining the first coronary calcification data based on the first seed point and the first growth range information.

4. The image processing method according to any one of claims 1 to 3, wherein the determining the candidate calcified region corresponding to the flat-scan CT image sequence based on the flat-scan CT image sequence corresponding to the target coronary artery comprises:

determining a heart region corresponding to the flat scanning CT image sequence;

determining a first threshold region based on the heart region and a first preset threshold;

determining a second threshold region based on the heart region and a second preset threshold;

determining the candidate calcified region based on the first threshold region and the second threshold region, wherein the first preset threshold is greater than the second preset threshold.

5. The image processing method of claim 4, wherein the determining the candidate calcification region based on the first threshold region and the second threshold region comprises:

determining a second seed point corresponding to the first threshold area based on the first threshold area;

determining second growth area information corresponding to the second seed point based on the second threshold area;

determining the candidate calcified region based on the second seed point and the second growth region information.

6. The image processing method according to any one of claims 1 to 3, further comprising, after the determining first coronary calcification data corresponding to the coronary segmentation image based on the coronary segmentation image in which the candidate calcification region corresponds to the target coronary, the step of:

determining coronary calcification lesion data corresponding to the flat-scan CT image sequence based on the first coronary calcification data and the flat-scan CT image sequence.

7. The image processing method according to any one of claims 1 to 3, further comprising, after the determining first coronary calcification data corresponding to the coronary segmentation image based on the coronary segmentation image in which the candidate calcification region corresponds to the target coronary, the step of:

and performing post-processing operation on the first coronary artery calcification data to obtain second coronary artery calcification data corresponding to the first coronary artery calcification data, wherein the post-processing operation is used for deleting false positive information and/or noise information in the first coronary artery calcification data.

8. An image processing apparatus characterized by comprising:

the first determination module is configured to determine a candidate calcified region corresponding to a flat-scan CT image sequence based on the flat-scan CT image sequence corresponding to a target coronary artery;

a second determination module configured to determine first coronary calcification data corresponding to the coronary segmentation image based on a coronary segmentation image of the candidate calcification region corresponding to the target coronary.

9. A computer-readable storage medium storing a computer program for executing the image processing method according to any one of claims 1 to 7.

10. An electronic device, comprising:

a processor;

a memory for storing the processor-executable instructions;

the processor configured to perform the image processing method according to any one of claims 1 to 7.