Calcified bar lesion area identification system for coronary angiography

Abstract

The invention relates to the field of medical image recognition, in particular to a coronary angiography calcified bar lesion area recognition system, which comprises a coronary angiography image acquisition module for acquiring a pre-contrast agent key frame image and a post-contrast agent key frame image; the coronary angiography image first analysis module is used for analyzing gray level distribution and gray level change conditions of pixel points in the pre-contrast agent key frame image and the post-contrast agent key frame image to obtain a suspected calcification point set; the coronary angiography image second analysis module is used for obtaining an angiography coefficient in combination with distance distribution from elements to edges in the suspected calcification point set; obtaining the relative displacement of each pixel point through the difference characteristics of the gray distribution between the pixel points of the adjacent contrast agent key frame images, and screening to obtain a suspected calcification distance; and the calcified section lesion area image recognition module obtains a heartbeat fluctuation coefficient and recognizes a calcified lesion area in coronary angiography. The purpose of the invention is to enhance the recognizability of tiny calcified lesion areas.

Description

Technical Field

[0001] The present application relates to the field of medical image recognition, and in particular to a system for identifying calcified nodular lesion areas in coronary angiography. Background Art

[0002] Cardiovascular disease is one of the leading causes of death worldwide, especially coronary artery disease, which is particularly important. The coronary arteries provide the myocardium with essential oxygen and nutrients. When these blood vessels are narrowed or blocked due to factors such as atherosclerosis, it may lead to serious complications such as angina pectoris and myocardial infarction. Coronary artery calcification is a key factor in arteriosclerosis, further aggravating the stiffness and narrowing of blood vessels. Among the various coronary artery examination techniques, coronary angiography is widely regarded as the "gold standard" for diagnosing coronary atherosclerotic heart disease because it can intuitively display coronary artery lesions, greatly reducing the risk of misdiagnosis and missed diagnosis, and has a high diagnostic accuracy.

[0003] Although coronary angiography has been quite mature in clinical applications, the existing technology still has some shortcomings in identifying calcified lesions. At present, the annotation of lesion areas in coronary angiography images still mainly relies on manual annotation by doctors. Although there are some automated tools for auxiliary diagnosis, these tools have better effects on lesions with clearer features such as thrombus, but the annotation and recognition effect of lesions with relatively low feature clarity such as calcification is not ideal; at the same time, the existing automated tools for auxiliary diagnosis often process and identify single-frame images, resulting in poor recognition effect. If only single-frame images are analyzed, the calcification of some smaller areas in the coronary artery may even be ignored. Summary of the invention

[0004] In view of the above, it is necessary to provide a calcified nodule lesion area recognition system for coronary angiography to solve the above problems.

[0005] An embodiment of the present application provides a system for identifying calcified nodular lesion areas in coronary angiography, the system comprising: The coronary angiography image acquisition module is used to obtain dynamic images of coronary angiography. In a cardiac cycle before contrast agent injection, all frames of coronary angiography images obtained are classified as pre-contrast agent key frame images; in a cardiac cycle after contrast agent injection, all frames of coronary angiography images obtained are classified as post-contrast agent key frame images; The first analysis module of the coronary angiography image is used to analyze the gray value distribution of the pixels in the pre-contrast agent key frame image to obtain the high-density shadow set and the suspected blood vessel set of the pre-contrast agent key frame image; the pre-contrast agent key frame image and the post-contrast agent key frame image with the same index in the cardiac cycle are formed into a pair, and the gray value changes of the pixels at the same position of each pair of images are analyzed, and the suspected calcification point set of the post-contrast agent key frame image is obtained in combination with the high-density shadow set; edge detection is performed on each post-contrast agent key frame image, and the contrast coefficient is obtained according to the distance distribution of the elements in the suspected calcification point set of the post-contrast agent key frame image to the edge in the image and the edge pixel distribution, combined with the suspected blood vessel set of the pre-contrast agent key frame image; The second analysis module of the coronary angiography image is used to compare the difference characteristics of the grayscale distribution between all adjacent post-contrast agent key frame image pixels in sequence, calculate the matching index between the pixels, obtain the matching point set of each pixel in the initial post-contrast agent key frame image of the cardiac cycle, analyze the matching index between adjacent elements in the matching point set, combine the position distribution of the elements in the matching point set, obtain the relative displacement of each pixel, and screen out the suspected calcification distance; The calcified segment lesion area image recognition module is used to analyze the distribution characteristics of suspected calcification distances and the quantitative characteristics of suspected calcification distances to obtain the cardiac fluctuation coefficient, and combine the angiography coefficient to identify the calcified lesion area in coronary angiography.

[0006] The step of obtaining the high-density shadow set and the suspected blood vessel set of the pre-contrast agent key frame image specifically includes: In each pre-contrast agent key frame image, a set consisting of coordinates of all pixels whose grayscale values ​​are greater than the upper quartile of the grayscale values ​​of all pixels in the corresponding image is obtained, which is recorded as a high-density shadow set; Get a set consisting of all pixel coordinates whose grayscale values ​​are less than the lower quartile of all pixel grayscale values ​​in the corresponding image, which is recorded as a high-density shadow set.

[0007] The specific process of obtaining the suspected calcification point set of the post-contrast agent key frame image is as follows: In each pair of images, the grayscale value change of the pixel at the same position is calculated, and the set of pixel coordinates whose grayscale value change is less than the lower quartile of all grayscale value changes in the corresponding image is recorded as the grayscale slight change point set; The intersection of the grayscale slight change point set of each pair of images and the high-density shadow set of the pre-contrast agent key frame image in each pair of images is used as the suspected calcification point set of the post-contrast agent key frame image in each pair of images.

[0008] The contrast coefficient is obtained as follows: For each post-contrast agent key frame image, a suspected calcification point distance distribution set of the post-contrast agent key frame image is obtained according to the distance distribution of the elements in the suspected calcification point set to the edge in the image; Calculate the intersection-and-union ratio of the suspected blood vessel set in each pre-contrast agent key frame image and the set consisting of all edge pixel points in the post-contrast agent key frame image with the same index; Obtaining the discreteness of the distance distribution set of the suspected calcification points of each post-contrast key frame image; The negative correlation mapping results of the discreteness of all pre-contrast agent key frame images are fused with the intersection and union ratios of all post-contrast agent key frame images to obtain a contrast coefficient.

[0009] The process of obtaining the suspected calcification point distance distribution set of the post-contrast agent key frame image is as follows: In each post-contrast agent key frame image, the minimum distance between each element in the suspected calcification point set and the edge line in the image is calculated, and the set consisting of the minimum distances is used as the suspected calcification point distance distribution set of each post-contrast agent key frame image.

[0010] The calculation of the matching index between the pixels is specifically as follows: For each post-contrast agent key frame image, the grayscale value of the pixel points in the neighborhood of each element in the suspected calcification point set is obtained to form a grayscale value sequence of each element; For a pixel point in each post-contrast agent key frame image and a pixel point in the next adjacent post-contrast key frame image, the Euclidean distance between the coordinates of the two pixel points and the similarity measure between the gray value sequences corresponding to the two pixel points are obtained; the negative correlation mapping of the Euclidean distance is fused with the similarity measure to obtain a matching index between the two pixel points.

[0011] The matching point set of each pixel in the initial post-contrast agent key frame image of the cardiac cycle is obtained as follows: For a pixel point corresponding to any element in the set of suspected calcification points of each post-contrast agent key frame image, a pixel point corresponding to the element with the largest matching index among the suspected calcification points of the next post-contrast agent key frame image is used as a matching point of the pixel point corresponding to any element; For each pixel point in the initial contrast agent key frame image of the cardiac cycle, all matching points of each pixel point are combined into a matching point set of each pixel point according to the transitive feature; The transitive feature is: for pixel point a, if pixel point b is the matching point of pixel point a, and pixel point c is the matching point of pixel point b, then both pixel points b and c are the matching points of pixel point a.

[0012] The relative displacement of each pixel is obtained as follows: ;in, is the relative displacement of each pixel, The matching point set of each pixel belongs to 1. The matching index between two pixels of the post-contrast key frame image, It is The distance weight of the matching index; among them, , is the number of elements in the matching point set, is the index of the matching index.

[0013] The suspected calcification distance is obtained as follows: The relative displacement of all pixels in the initial post-contrast agent key frame image of the cardiac cycle is used as input, and a threshold segmentation algorithm is used to obtain a segmentation threshold. The relative displacement less than the segmentation threshold is used as the suspected calcification distance.

[0014] The obtained cardiac fluctuation coefficient is combined with the angiography coefficient to identify the calcified lesion area in coronary angiography. The specific process is as follows: Calculate the proportion of the number of suspected calcification distances in all relative displacement numbers; divide it by the mean of all suspected calcification distances, and then divide it by the variance of all suspected calcification distances; obtain the cardiac fluctuation coefficient; A preset number of samples of coronary angiography dynamic images are obtained, and the contrast coefficients and cardiac fluctuation coefficients of all samples are subjected to advance segmentation to obtain a contrast coefficient threshold and a cardiac fluctuation coefficient threshold; If the contrast coefficient of the coronary angiography dynamic image is greater than the contrast coefficient threshold and the cardiac fluctuation coefficient is greater than the cardiac fluctuation coefficient threshold, it is determined that there is a calcified lesion area in the coronary angiography dynamic image, and the lesion area is all pixel points corresponding to the suspected calcification distance.

[0015] This application has at least the following beneficial effects: The embodiment of the present application obtains a set of suspected calcification points by analyzing the changes in the coronary artery images before and after the contrast agent injection, and screens the pixel points based on the distribution characteristics of the calcification points, thereby providing an important basis for subsequent calcification point judgment and lesion assessment; according to the edge detection results in the post-contrast agent key frame image, the distance characteristics between the suspected calcification points and the edges are analyzed, and the contrast coefficient is obtained in combination with the suspected blood vessel set of the pre-contrast agent key frame image, and the change in the grayscale of the pixel points in the coronary artery image before and after the contrast agent injection is evaluated, so as to preliminarily measure whether there is calcification and the degree of calcification, and enhance the recognition ability of calcification features; then, according to the time series difference caused by the change of the coronary artery blood vessels with the heartbeat after the injection of the contrast agent, the difference characteristics of the grayscale distribution between all adjacent post-contrast agent key frame image pixels are compared, and the matching index between the pixels is calculated. , and obtain the matching point set for each pixel point in the initial post-contrast agent key frame image of the cardiac cycle. Its beneficial effect is to analyze the similarity between the pixels in adjacent post-contrast agent key frame images, so as to facilitate the subsequent characterization of the displacement of each pixel point over time; analyze the matching index between adjacent elements in the matching point set, and combine the position distribution of the elements in the matching point set to obtain the relative displacement of each pixel point, and screen out the suspected calcification distance. Its beneficial effect is to identify the displacement of the suspected calcification point over time, and can identify the calcification area, and can also accurately calculate its position and range; finally, based on the distribution of the suspected calcification distance, calculate the cardiac fluctuation coefficient, and combine the angiography coefficient to identify the calcified lesion area in coronary angiography, thereby enhancing the recognition ability of the calcified lesion characteristics in the coronary artery, and at the same time helping to enhance the comparative recognition of the micro-calcified lesion area. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A block diagram of a system for identifying calcified nodular lesion areas in coronary angiography provided in this application; Figure 2 A specific flow chart for identifying calcified lesion areas in coronary angiography provided in this application. DETAILED DESCRIPTION

[0017] In the description of the embodiments of the present application, words such as "exemplary", "or", "for example" and the like are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary", "or", "for example" and the like is intended to present related concepts in a concrete manner.

[0018] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art in the present application. The terms used in the specification of the present application are only for the purpose of describing specific embodiments and are not intended to limit the present application.

[0019] It should also be noted that the terms "first" and "second" in this application and its drawings are used to distinguish similar objects, rather than to describe a specific order or sequence. The method disclosed in the embodiments of the present application or the method shown in the flow chart includes one or more steps for implementing the method. Without departing from the scope of protection of this application, the execution order of multiple steps can be interchanged with each other, and some steps can also be deleted.

[0020] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.

[0021] The specific scheme of the system for identifying calcified nodular lesion areas in coronary angiography provided by the present application is described in detail below with reference to the accompanying drawings.

[0022] See also Figure 1 , which shows a block diagram of a calcified nodule lesion area identification system for coronary angiography provided by an embodiment of the present application. The system includes: a coronary angiography image acquisition module, a first coronary angiography image analysis module, a second coronary angiography image analysis module, and a calcified nodule lesion area image recognition module.

[0023] The present application embodiment first proposes a system for identifying calcified nodular lesion areas in coronary angiography, which is applied to the field of medical image recognition. The system includes: Coronary angiography image acquisition module: obtains dynamic coronary angiography images, and classifies all frames of coronary angiography images obtained within a cardiac cycle before the injection of contrast agent as pre-contrast agent key frame images; within a cardiac cycle after the injection of contrast agent, classifies all frames of coronary angiography images obtained as post-contrast agent key frame images.

[0024] This application adopts the posteroanterior head position Position, insert a catheter through radial artery puncture, inject iodide contrast agent in the catheter, observe the imaging of blood vessels under X-ray, and obtain the original data of coronary angiography, which is a Dicom file with continuous angiography frames. Then in the Dicom file, all frame images within a cardiac cycle before the injection of contrast agent are used as pre-contrast agent key frames, and all frame images within a cardiac cycle after the injection of contrast agent are used as post-contrast agent key frames, and the key frame sequences before and after the injection of contrast agent are respectively composed of pre-contrast agent image sequence and post-contrast agent image sequence in chronological order. Among them, the cardiac cycle refers to the time interval from the start of one heart beat to the start of the next heart beat. Each key frame image is enhanced, and a multi-scale Retinex enhancement algorithm is used in this embodiment. In other embodiments, the image enhancement methods that can be used include image enhancement based on Laplace operator, image enhancement based on logarithmic transformation, image enhancement based on gamma transformation, etc., which are not limited in this application.

[0025] The first analysis module of coronary angiography images: analyze the grayscale value distribution of pixels in the pre-contrast agent key frame image to obtain the high-density shadow set and suspected blood vessel set of the pre-contrast agent key frame image; form a pair of pre-contrast agent key frame images and post-contrast agent key frame images with the same index in the cardiac cycle, analyze the grayscale changes of pixels at the same position in each pair of images, and obtain the suspected calcification point set of the post-contrast agent key frame image in combination with the high-density shadow set; perform edge detection on each post-contrast agent key frame image, and obtain the angiography coefficient based on the distance distribution of the elements in the suspected calcification point set of the post-contrast agent key frame image to the edge of the image and the edge pixel distribution, combined with the suspected blood vessel set of the pre-contrast agent key frame image.

[0026] Coronary artery calcification refers to a phenomenon in which calcium salts are abnormally deposited on the blood vessel wall in the coronary artery. As calcium deposition becomes more and more serious, the scope of atherosclerotic lesions will become wider and wider. Therefore, timely identification of the calcification area and degree in the coronary artery is crucial for coronary examination. Coronary angiography is widely used in clinical practice. Currently, most lesion annotation and identification in coronary angiography still rely mainly on manual operation by doctors. However, since the characteristics of calcified lesions are often not significant enough, there is a high risk of missed diagnosis. Although there are automated tools to assist diagnosis and enhance the sensitivity of recognition, this tool often pays too much attention to the information in a single frame image and ignores the changes in the coronary angiography process, so that the accuracy still needs to be improved. In particular, for some small areas of calcified lesions, it is more difficult to detect them relying only on a single frame image.

[0027] The characteristics of the calcified areas in the coronary arteries are closely related to the degree of calcification. Before contrast agent injection, mild calcification appears as a faint and blurred high-density image when the heart is beating, but no calcified image can be observed when the heart is at rest, and the coronary vessel contour is almost invisible; in the case of moderate calcification, a relatively clear and easily recognizable high-density image can be observed when the heart is beating, and some coronary vessel contours are visible; severe calcification is manifested as obvious high-density images both when the heart is beating and at rest, and the coronary vessel contours are clearer. In X-ray images, the calcified area has a stronger ability to absorb X-rays than the surrounding soft tissue due to the high atomic number of calcium, so the high-density area usually appears as a brighter area than the surrounding tissue, that is, a bright white area with a larger grayscale value. At the same time, because calcium salts are deposited on the blood vessel wall, these areas are often distributed along the blood vessels. Normal vascular soft tissue presents a gray or black image with a lower grayscale value.

[0028] After the contrast agent is injected, since the contrast agent is a high-density substance, it can significantly enhance the X-ray absorption of blood vessels and other soft tissues, making the grayscale changes of these structures on the image relatively obvious; and in areas where calcifications exist, since calcification itself is a high-density substance, it already has a high X-ray absorption rate in the absence of contrast agent, so even after the contrast agent is injected, the brightness of the calcified area increases relatively little.

[0029] In the pre-contrast agent image sequence, Take an image as an example, get the gray value of each pixel in the image, and The set of pixels whose grayscale values ​​are greater than the upper quartile in the first image is recorded as the high-density shadow set. The suspected blood vessel set is a set of pixels whose grayscale values ​​are less than the lower quartile in each image. In this way, the high-density shadow set and the suspected blood vessel set of each image in the pre-contrast agent image sequence are obtained respectively.

[0030] Then, images with the same index in the pre-contrast agent image sequence and the post-contrast agent image sequence are formed into a pair. In each pair of images, the absolute value of the difference between the grayscale values ​​of pixels at the same position in the two images is used as the grayscale value change, and all grayscale value changes are obtained. All pixel points whose grayscale value changes are less than the lower quartile of all grayscale value changes of the corresponding images constitute a grayscale slight change point set; the grayscale slight change point set of all image pairs is obtained; and then, for each image in the post-contrast agent image sequence after the injection of contrast agent, the Canny edge detection algorithm is used to output corresponding edge detection images respectively. Canny edge detection is a well-known technology and will not be described in detail.

[0031] The intersection of the high-density shadow set of an image in the pre-contrast agent image sequence and the grayscale slight change point set of the same index image pair is taken as the suspected calcification point set of the post-contrast agent key frame image at the same index, and the minimum distance between each pixel point in the suspected calcification point set of each post-contrast agent key frame image and the edge line in the same post-contrast agent key frame image is calculated. All the minimum distances in a post-contrast agent key frame image constitute the suspected calcification point distance distribution set of the post-contrast agent key frame image.

[0032] According to the distribution of suspected calcification points in the suspected blood vessel set of each pre-contrast agent key frame image and the post-contrast agent key frame image with the same index, the contrast coefficient is obtained, which is used to evaluate the change in the grayscale of the pixels in the coronary artery image before and after the contrast agent injection, so as to preliminarily measure the presence and degree of calcification: calculate the intersection and union ratio of the suspected blood vessel set of each pre-contrast agent key frame image and the set composed of all edge pixels in the post-contrast agent key frame image with the same index; obtain the discreteness of the suspected calcification point distance distribution set of each post-contrast agent key frame image; fuse the negative correlation mapping results of the discreteness of all pre-contrast agent key frame images with the intersection and union ratio of all post-contrast agent key frame images to obtain the contrast coefficient.

[0033] In this embodiment, the intersection-to-union ratio is specifically the ratio of the number of elements in the intersection of two sets to the number of elements in the union of the two sets; the discreteness of the suspected calcification point distance set of the post-contrast agent key frame image is calculated using the variance, and the formula form of the contrast coefficient is: ;in, represents the intersection-over-union ratio of the i-th pre-contrast agent key frame image; represents the discreteness of the i-th post-contrast agent key frame image; N represents the total number of pre-contrast agent key frame images, and also represents the total number of post-contrast agent key frame images; A represents the contrast coefficient.

[0034] It should be understood that when calcification exists, the calcification is distributed along the blood vessels, that is, the distance between the calcified pixels and the edge of the blood vessels is relatively small. At the same time, the severity of calcification is proportional to the degree of visibility of the blood vessels before contrast imaging. That is, the more severe the calcification, the clearer the blood vessels appear before contrast imaging, so the intersection before and after contrast imaging is relatively large, so the contrast coefficient at this time is On the contrary, when there is no calcification or the degree of calcification is low, the contrast coefficient Also smaller.

[0035] The second analysis module of coronary angiography images: by comparing the difference characteristics of the grayscale distribution between all adjacent post-contrast key frame image pixels in turn, the matching index between the pixels is calculated to obtain the matching point set for each pixel in the initial post-contrast key frame image of the cardiac cycle, and the matching index between adjacent elements in the matching point set is analyzed. Combined with the position distribution of the elements in the matching point set, the relative displacement of each pixel is obtained, and the suspected calcification distance is screened.

[0036] Under normal circumstances, as the heart beats, blood vessels will be pushed by blood flow to dilate and contract. After contrast agent is injected, normal blood vessels will change their vascular cavity as the heart contracts and dilates, and the contrast agent gradually fills the blood vessels, or dynamic vascular stenosis occurs. Therefore, in different image frames, the position and shape of the blood vessel wall will be significantly displaced and changed. When calcification occurs, since the calcium component is hard and difficult to change, the calcified area appears as a relatively stable high-density area in different frames of images; at the same time, calcification is usually accompanied by the pathological process of atherosclerosis. Calcium deposition in the blood vessel wall will cause the blood vessel wall to harden and its elasticity will decrease significantly, making it impossible for the calcified area to effectively dilate and contract. Therefore, the dilation and contraction amplitude of the blood vessels in the calcified area becomes smaller, which is manifested as a smaller displacement of the calcified area in different frames of images.

[0037] In the post-contrast image sequence, Taking the post-contrast key frame image as an example, the grayscale value of each pixel in the suspected calcification point set of the image is obtained in the eight neighborhoods, and the grayscale value sequence of the pixel is constructed from left to right and from top to bottom. The sequence obtained by this construction method can measure the distribution of grayscale values ​​in the neighborhood around each pixel.

[0038] By comparing the difference characteristics of the grayscale distribution between the pixels of two adjacent post-contrast agent key frame images, the matching index of the pixels between the two adjacent post-contrast agent key frame images is obtained, and its formula form is: ; It is 1. Pixel points in the key frame image of the contrast agent after the frame and pixels The matching index between the pixels Belong to Key frame image after contrast agent, pixel point Belong to A post-contrast key frame image, is the Euclidean distance between the coordinates of pixel a and pixel b, is the similarity measure between the gray value sequences of the two pixels. In this embodiment, cosine similarity is used. In other embodiments, similarity measures that can be used include Pearson correlation coefficient, Spearman correlation coefficient, etc., which are not limited in this application. It indicates a parameter that is preset to be greater than zero. In this embodiment, the value is 0.01, which is used to avoid the denominator being 0.

[0039] It can be understood that since the pixel displacement in the calcified area is small and relatively stable in the high-density area, the position and gray value distribution of the pixels at the same calcified position in different frame images are relatively close, so the matching index The larger the value, the more likely it is that the two pixels are the same calcification position in different frames. Each pixel in the suspected calcification point set of the post-contrast key frame image is converted into The matching point is the one with the largest matching index in the set of suspected calcification points in the post-contrast agent key frame image.

[0040] According to the above method, the matching points of each pixel in the suspected calcification point set of all post-contrast key frame images are obtained. The matching points have transitivity. According to the transitivity feature, all the matching points of a pixel constitute the matching point set of the pixel. Transitivity means that, assuming that for the first The pixel points in the set of suspected calcification points in the image The matching point is The pixel points in the set of suspected calcification points of an image ,and The matching point is The pixel points in the set of suspected calcification points of an image ,but Too After obtaining the matching point set of each pixel in the suspected calcification point set of the first image of the post-contrast image sequence, the relative displacement of each pixel is calculated, and the formula is as follows: ;in, is the relative displacement of each pixel, The matching point set of each pixel belongs to 1. The matching index between two pixels of the post-contrast key frame image, It is The distance weight of the matching index. , is the number of elements in the matching point set.

[0041] It can be understood that as the interval frame number from the first image of the post-contrast agent image sequence increases, the difference between coronary vascular contraction and relaxation becomes more and more obvious, and the distance displacement of the calcified area becomes relatively larger. According to the characteristics of the vascular calcified area, its displacement change should be smaller. Therefore, the more the interval frame number, the more helpful it is to distinguish whether it is calcified or not. Therefore, the corresponding weight The larger the relative displacement is, the better it can reflect the displacement characteristics of the calcified area.

[0042] The relative displacement of each pixel in the suspected calcification point set of the first post-contrast key frame image is calculated respectively, and then all relative displacements are used as input, and the segmentation threshold is obtained by using Otsu threshold segmentation, and the relative displacement less than the segmentation threshold is used as the suspected calcification distance. Otsu threshold segmentation is a well-known technology and will not be described in detail.

[0043] Since the pixel displacement in the calcified area is relatively small and the grayscale distribution around the calcified point is relatively stable, obtaining the suspected calcification distance in the above manner helps to measure the displacement and grayscale distribution of the suspected calcified point in different frame images, thereby helping to improve the accuracy of subsequent calcification measurement.

[0044] Calcification segment lesion area image recognition module: Analyze the distribution characteristics of suspected calcification distances and the quantitative characteristics of suspected calcification distances to obtain the cardiac fluctuation coefficient, and combine it with the angiography coefficient to identify the calcification lesion area in coronary angiography.

[0045] The distribution characteristics of the suspected calcification distances and the quantitative characteristics of the suspected calcification distances were analyzed to obtain the cardiac fluctuation coefficient, which is used to measure the changes in the diastolic and systolic displacement of the blood vessels with changes in the cardiac rhythm: , is the cardiac fluctuation coefficient, is the mean of all suspected calcification distances, is the variance of all suspected calcification distances, It is the ratio of the number of suspected calcification distances to the number of all relative displacements. It can be understood that when there is a calcified lesion, the calcified area is relatively stable and the displacement is small, so the suspected calcification distance is relatively small. At the same time, the calcified area is relatively stable, and the greater the proportion of this calcification feature, the more serious the calcified lesion, and thus the heart rate fluctuation coefficient On the contrary, when there is no calcification or the calcification is relatively mild, the cardiac fluctuation coefficient The smaller.

[0046] Get coronary angiography dynamic image samples, and obtain each frame image before and after the angiography of each sample. Each needs to include normal coronary angiography, slightly calcified coronary angiography, moderately calcified coronary angiography, and severely calcified coronary angiography. The value is 200, where each type of sample accounts for ; The implementer can adjust it according to the actual situation. Then calculate the contrast coefficient and cardiac fluctuation coefficient of each sample, and then take all the contrast coefficients and cardiac fluctuation coefficients as input, and use Otsu threshold segmentation to obtain the contrast coefficient threshold and cardiac fluctuation coefficient threshold respectively. In the subsequent calcification judgment, when the calculated contrast coefficient and cardiac fluctuation coefficient are greater than the contrast coefficient threshold and cardiac fluctuation coefficient threshold respectively, it is judged that there are calcified lesions in the coronary angiography under this position, and the area that needs to be focused on is the pixel point corresponding to the suspected calcification distance.

[0047] In this way, the ability to identify coronary calcification is enhanced based on the image changes before and after contrast agent injection and the time series changes after contrast agent injection. At the same time, this time series comparison method can achieve accurate identification based on the image changes before and after, even if the area of ​​calcified lesions is small, thereby enhancing the ability to identify calcified nodular lesions in coronary angiography images.

[0048] Among them, the specific flow chart for identifying calcified lesion areas in coronary angiography is as follows: Figure 2 shown.

[0049] In summary, the embodiment of the present application obtains a set of suspected calcification points by analyzing the changes in the coronary artery images before and after the contrast agent injection, and screens the pixel points based on the distribution characteristics of the calcification points, thereby providing an important basis for the subsequent calcification point judgment and lesion assessment; according to the edge detection results in the post-contrast agent key frame image, the distance characteristics between the suspected calcification points and the edges are analyzed, and the contrast coefficient is obtained by combining the suspected blood vessel set of the pre-contrast agent key frame image, and the change in the grayscale of the pixel points in the coronary artery image before and after the contrast agent injection is evaluated, so as to preliminarily measure whether there is calcification and the degree of calcification, and enhance the recognition ability of calcification features; and then, according to the time series differences caused by the changes in the coronary artery blood vessels with the heartbeat after the injection of the contrast agent, the difference characteristics of the grayscale distribution between all adjacent post-contrast agent key frame image pixels are compared, and the matching between the pixels is calculated. The index is used to obtain the matching point set for each pixel in the initial post-contrast agent key frame image of the cardiac cycle. The beneficial effect is that the similarity between the pixels in adjacent post-contrast agent key frame images is analyzed to facilitate the subsequent characterization of the displacement of each pixel over time; the matching index between adjacent elements in the matching point set is analyzed, and the relative displacement of each pixel is obtained in combination with the position distribution of the elements in the matching point set, and the suspected calcification distance is screened. The beneficial effect is that the displacement of the suspected calcification point over time can be identified, and the calcification area can be identified, and its position and range can be accurately calculated; finally, based on the distribution of the suspected calcification distance, the cardiac fluctuation coefficient is calculated, and combined with the angiography coefficient, the calcified lesion area in coronary angiography is identified, which enhances the recognition ability of the calcified lesion characteristics in the coronary artery, and at the same time helps to enhance the comparative recognition of the micro-calcified lesion area.

[0050] The flowchart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to the embodiment of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of the code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. In some alternative implementations, the function marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two continuous boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which can depend on the functions involved. In the description corresponding to the flowchart and the block diagram in the accompanying drawings, the operations or steps corresponding to different boxes can also occur in a different order from the order disclosed in the description, and sometimes there is no specific order between different operations or steps. For example, two continuous operations or steps can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which can depend on the functions involved. Each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented by a dedicated hardware-based system that performs the specified functions or actions, or may be implemented by a combination of dedicated hardware and computer instructions.

[0051] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A system for identifying calcified nodular lesion areas in coronary angiography, characterized in that: The system includes: The coronary angiography image acquisition module is used to obtain dynamic images of coronary angiography. In a cardiac cycle before contrast agent injection, all frames of coronary angiography images obtained are classified as pre-contrast agent key frame images; in a cardiac cycle after contrast agent injection, all frames of coronary angiography images obtained are classified as post-contrast agent key frame images; The first analysis module of the coronary angiography image is used to analyze the gray value distribution of the pixels in the pre-contrast agent key frame image to obtain the high-density shadow set and the suspected blood vessel set of the pre-contrast agent key frame image; the pre-contrast agent key frame image and the post-contrast agent key frame image with the same index in the cardiac cycle are formed into a pair, and the gray value changes of the pixels at the same position of each pair of images are analyzed, and the suspected calcification point set of the post-contrast agent key frame image is obtained in combination with the high-density shadow set; edge detection is performed on each post-contrast agent key frame image, and the contrast coefficient is obtained according to the distance distribution of the elements in the suspected calcification point set of the post-contrast agent key frame image to the edge in the image and the edge pixel distribution, combined with the suspected blood vessel set of the pre-contrast agent key frame image; The second analysis module of the coronary angiography image is used to compare the difference characteristics of the grayscale distribution between all adjacent post-contrast agent key frame image pixels in sequence, calculate the matching index between the pixels, obtain the matching point set of each pixel in the initial post-contrast agent key frame image of the cardiac cycle, analyze the matching index between adjacent elements in the matching point set, combine the position distribution of the elements in the matching point set, obtain the relative displacement of each pixel, and screen out the suspected calcification distance; The calcified segment lesion area image recognition module is used to analyze the distribution characteristics of suspected calcification distances and the quantitative characteristics of suspected calcification distances to obtain the cardiac fluctuation coefficient, and combine the angiography coefficient to identify the calcified lesion area in coronary angiography.

2. A system for identifying calcified nodular lesion areas in coronary angiography according to claim 1, characterized in that: The steps of obtaining the high-density shadow set and the suspected blood vessel set of the pre-contrast agent key frame image specifically include: In each pre-contrast agent key frame image, a set consisting of coordinates of all pixels whose grayscale values ​​are greater than the upper quartile of the grayscale values ​​of all pixels in the corresponding image is obtained, which is recorded as a high-density shadow set; Get a set consisting of all pixel coordinates whose grayscale values ​​are less than the lower quartile of all pixel grayscale values ​​in the corresponding image, which is recorded as a high-density shadow set.

3. The system for identifying calcified nodular lesion areas in coronary angiography according to claim 1, characterized in that: The specific process of obtaining the suspected calcification point set of the post-contrast agent key frame image is as follows: In each pair of images, the grayscale value change of the pixel at the same position is calculated, and the set of pixel coordinates whose grayscale value change is less than the lower quartile of all grayscale value changes in the corresponding image is recorded as the grayscale slight change point set; The intersection of the grayscale slight change point set of each pair of images and the high-density shadow set of the pre-contrast agent key frame image in each pair of images is used as the suspected calcification point set of the post-contrast agent key frame image in each pair of images.

4. The system for identifying calcified nodular lesion areas in coronary angiography according to claim 1, characterized in that: The contrast coefficient is obtained as follows: For each post-contrast agent key frame image, a suspected calcification point distance distribution set of the post-contrast agent key frame image is obtained according to the distance distribution of the elements in the suspected calcification point set to the edge in the image; Calculate the intersection-and-union ratio of the suspected blood vessel set in each pre-contrast agent key frame image and the set consisting of all edge pixel points in the post-contrast agent key frame image with the same index; Obtaining the discreteness of the distance distribution set of the suspected calcification points of each post-contrast key frame image; The negative correlation mapping results of the discreteness of all pre-contrast agent key frame images are fused with the intersection and union ratios of all post-contrast agent key frame images to obtain a contrast coefficient.

5. A system for identifying calcified nodular lesion areas in coronary angiography according to claim 4, characterized in that: The process of obtaining the suspected calcification point distance distribution set of the post-contrast agent key frame image is as follows: In each post-contrast agent key frame image, the minimum distance between each element in the suspected calcification point set and the edge line in the image is calculated, and the set consisting of the minimum distances is used as the suspected calcification point distance distribution set of each post-contrast agent key frame image.

6. The system for identifying calcified nodular lesion areas in coronary angiography according to claim 1, characterized in that: The calculation of the matching index between the pixels is specifically as follows: For each post-contrast agent key frame image, the grayscale value of the pixel points in the neighborhood of each element in the suspected calcification point set is obtained to form a grayscale value sequence of each element; For a pixel point in each post-contrast agent key frame image and a pixel point in the next adjacent post-contrast key frame image, the Euclidean distance between the coordinates of the two pixel points and the similarity measure between the gray value sequences corresponding to the two pixel points are obtained; the negative correlation mapping of the Euclidean distance is fused with the similarity measure to obtain a matching index between the two pixel points.

7. The system for identifying calcified nodular lesion areas in coronary angiography according to claim 1, characterized in that: The matching point set of each pixel in the initial post-contrast agent key frame image of the cardiac cycle is obtained as follows: For a pixel point corresponding to any element in the set of suspected calcification points of each post-contrast agent key frame image, a pixel point corresponding to the element with the largest matching index among the suspected calcification points of the next post-contrast agent key frame image is used as a matching point of the pixel point corresponding to any element; For each pixel point in the initial contrast agent key frame image of the cardiac cycle, all matching points of each pixel point are combined into a matching point set of each pixel point according to the transitive feature; The transitive feature is: for pixel point a, if pixel point b is the matching point of pixel point a, and pixel point c is the matching point of pixel point b, then both pixel points b and c are the matching points of pixel point a.

8. The system for identifying calcified nodular lesion areas in coronary angiography according to claim 1, characterized in that: The relative displacement of each pixel is obtained as follows: ;in, is the relative displacement of each pixel, The matching point set of each pixel belongs to 1. The matching index between two pixels of the post-contrast key frame image is the matching index between the two pixels of the post-contrast key frame image. It is The distance weight of the matching index; among them, , is the number of elements in the matching point set, is the index of the matching index.

9. The system for identifying calcified nodular lesion areas in coronary angiography according to claim 1, characterized in that: The suspected calcification distance is obtained as follows: The relative displacement of all pixels in the initial post-contrast agent key frame image of the cardiac cycle is used as input, and a threshold segmentation algorithm is used to obtain a segmentation threshold. The relative displacement less than the segmentation threshold is used as the suspected calcification distance.

10. The system for identifying calcified nodular lesion areas in coronary angiography according to claim 1, characterized in that: The obtained cardiac fluctuation coefficient is combined with the angiography coefficient to identify the calcified lesion area in coronary angiography. The specific process is as follows: Calculate the proportion of the number of suspected calcification distances in all relative displacement numbers; divide it by the mean of all suspected calcification distances, and then divide it by the variance of all suspected calcification distances; obtain the cardiac fluctuation coefficient; A preset number of samples of coronary angiography dynamic images are obtained, and the contrast coefficients and cardiac fluctuation coefficients of all samples are subjected to advance segmentation to obtain a contrast coefficient threshold and a cardiac fluctuation coefficient threshold; If the contrast coefficient of the coronary angiography dynamic image is greater than the contrast coefficient threshold and the cardiac fluctuation coefficient is greater than the cardiac fluctuation coefficient threshold, it is determined that there is a calcified lesion area in the coronary angiography dynamic image, and the lesion area is all pixel points corresponding to the suspected calcification distance.

Images