Intelligent assessment method and system for coronary artery stenosis based on chest radiography

Abstract

The invention discloses an intelligent assessment method and system for coronary stenosis based on chest radiography, and relates to the technical field of health risk assessment, and the method comprises the steps: obtaining chest radiography image data of a target patient; based on the time sequence fluctuation of the calcification focus area in the chest radiograph image data, calculating to obtain a calcification activity index, determining a cardiac pulsation key point in the chest radiograph image data, and based on the displacement change of the cardiac pulsation key point between each image frame, calculating to obtain a collateral circulation compensation index of the calcification focus area; based on the collateral circulation compensation index and the calcification activity index, calculating a dynamic risk factor corresponding to the coronary artery stenosis; and inputting the dynamic risk factor into a preset neural network model for iterative training, and performing prediction processing on the chest radiograph image data based on the trained preset neural network model to obtain a coronary artery stenosis risk assessment result. The technical effect of reducing the clinical misjudgment risk of coronary artery stenosis is achieved.

Description

Technical Field

[0001] This application relates to the field of health risk assessment technology, and in particular to a method and system for intelligent assessment of coronary artery stenosis based on chest X-ray. Background Technology

[0002] Coronary artery stenosis is a significant problem in cardiovascular disease. It usually manifests as narrowing or blockage of the lumen of the coronary arteries, leading to insufficient blood supply to the myocardium and subsequently causing serious consequences such as angina pectoris and myocardial infarction.

[0003] Existing intelligent assessment methods for coronary artery stenosis are mostly based on extracting image features from single-frame static chest radiographs. However, chest radiographs are limited by the two-dimensional projection principle and soft tissue resolution, and cannot directly visualize the fine anatomical structure of the coronary arteries. This results in a serious disconnect between pathological anatomical information and imaging features, increasing the risk of clinical misdiagnosis. Summary of the Invention

[0004] The main purpose of this application is to provide a method and system for intelligent assessment of coronary artery stenosis based on chest X-rays, aiming to solve the technical problem in related technologies where the assessment of coronary artery stenosis based on the extraction of image features from a single static chest X-ray results in a serious disconnect between pathological anatomical information and image features, which increases the risk of clinical misjudgment.

[0005] To achieve the above objectives, embodiments of this application provide a method for intelligent assessment of coronary artery stenosis based on chest X-ray, comprising: Retrieve chest X-ray image data of the target patient from a pre-set database; Based on the temporal fluctuations of calcification areas in chest X-ray images, a calcification activity index is calculated, which is used to characterize the activity of coronary artery stenosis progression. Key points of cardiac pulsation in chest X-ray images were identified, and the collateral circulation compensation index of the calcified lesion area was calculated based on the displacement changes of the key points of cardiac pulsation between each image frame. Based on the collateral circulation compensation index and the calcification activity index, the dynamic risk factors corresponding to coronary artery stenosis were calculated. Dynamic risk factors are input into a preset neural network model for iterative training, and the chest X-ray image data is then used to make predictions based on the trained preset neural network model to obtain the risk assessment results of coronary artery stenosis.

[0006] In one possible implementation of this application, a calcification activity index is calculated based on the temporal fluctuations of calcification areas in chest X-ray image data, including: Image segmentation processing is performed on chest X-ray image data to obtain the calcification mask in each image frame; Calculate the average gray value of each calcification region in the calcification mask; Based on the average gray value, the fluctuation intensity coefficient of each calcification zone in the time series is calculated. The fluctuation intensity coefficient is used to characterize the time series fluctuation of the density corresponding to the calcification zone. The boundary pixels of the calcification foci mask are detected by an edge detection algorithm to obtain a binary image of the edge contour. Based on the binary image of the edge contour, the edge roughness index of each calcification zone is calculated. The calcification activity index is calculated based on the fluctuation intensity coefficient and the edge roughness index.

[0007] In one possible implementation of this application, the edge roughness index of each calcification region is calculated based on the edge contour binary map, including: Based on the binary image of the edge contour, the contour perimeter and equivalent circle area of ​​the boundary pixels of the calcification foci region are determined. Based on the equivalent circle area and the contour perimeter, the edge roughness index of each calcification zone is calculated. The edge roughness index is used to reflect the roughness of the edge of the calcification zone.

[0008] In one possible embodiment of this application, the calcification activity index is calculated based on the fluctuation intensity coefficient and the edge roughness index, including: A roughness data sequence is constructed based on the edge roughness index of each image frame. Determine the roughness fluctuation intensity between the maximum and minimum sequence values ​​in the roughness data sequence; The calcification activity index is calculated based on the fluctuation intensity coefficient, the roughness fluctuation intensity, and the average edge roughness index of each image frame.

[0009] In one possible implementation of this application, the collateral circulation compensation index of the calcification region is calculated based on the displacement changes of key cardiac pulsation points between each image frame, including: Based on the Euclidean distance between key points of cardiac pulsation in each image frame, the displacement time sequence of each key point of cardiac pulsation is determined. Based on the displacement time sequence, the instantaneous phase time delay coefficient of each key point of heartbeat is calculated; By matching the calcification areas with key points of cardiac pulsation, a set of multiple key point calcifications is obtained. The first Pearson correlation coefficient is calculated between the sequence corresponding to the instantaneous phase time delay coefficient and the roughness data sequence corresponding to the set of key point calcifications. The first Pearson correlation coefficient is used as the collateral circulation compensation index of the calcification region.

[0010] In one possible implementation of this application, the displacement temporal sequence of each cardiac pulsation key point is determined based on the Euclidean distance between each image frame, including: For any cardiac pulsation key point, calculate the first Euclidean distance between adjacent image frames and use the absolute value of the first Euclidean distance as the inter-frame displacement of each cardiac pulsation key point. The cardiac pulsation key points include the apex of the heart, the left atrial appendage, and the ventricular diaphragmatic surface. Based on inter-frame displacement, the displacement time sequence of each key point of heartbeat is determined.

[0011] In one possible implementation of this application, the instantaneous phase time delay coefficient of each key point of cardiac pulsation is calculated based on the displacement time sequence, including: Linear fitting was performed on the displacement time sequence to obtain the displacement fitting curve for each key point of heartbeat. Determine the instantaneous phase information of the displacement fitting curve corresponding to each key point of heart pulsation; For any key point of heart pulsation, calculate the instantaneous phase difference between the current key point of heart pulsation and other different key points of heart pulsation, and use the average of the absolute values ​​of each instantaneous phase difference as the instantaneous phase time delay coefficient.

[0012] In one possible implementation of this application, the calcification area is matched with key points of cardiac pulsation to obtain a set of multiple key point calcifications, including: Obtain the coordinates of the centroid of the calcification in the mask, and calculate the second Euclidean distance from the centroid of the mask to each key point of cardiac pulsation. Each calcification region is assigned to the region corresponding to the cardiac pulsation key point with the minimum second Euclidean distance, generating multiple key point calcification sets.

[0013] In one possible implementation of this application, dynamic risk factors corresponding to coronary artery stenosis are calculated based on the collateral circulation compensation index and the calcification activity index, including: The second Pearson correlation coefficient was calculated between the corresponding sequence of the calcification activity index and the inverse corresponding sequence of the collateral circulation compensation index, and the second Pearson correlation coefficient was used as the corrected weight. Based on the calcification activity index, collateral circulation compensation index, and adjusted weights, the dynamic risk factors corresponding to coronary artery stenosis were calculated.

[0014] To achieve the above objectives, a coronary artery stenosis intelligent assessment system based on chest X-ray is also provided. The system includes a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, it implements the steps of the above-described intelligent assessment method for coronary artery stenosis based on chest X-ray.

[0015] This application provides a method and system for intelligent assessment of coronary artery stenosis based on chest X-rays. Compared to related technologies that rely on extracting image features from single-frame static chest X-rays for coronary artery stenosis assessment, leading to a severe disconnect between pathological anatomical information and image features and increasing the risk of clinical misdiagnosis, this application obtains chest X-ray image data of the target patient from a pre-set database. First, based on the temporal fluctuations of calcification areas in the chest X-ray image data, a calcification activity index is calculated. This index characterizes the activity of coronary artery stenosis progression. Then, key cardiac pulsation points in the chest X-ray image data are identified. Finally, the displacement changes of these key cardiac pulsation points between each image frame are used to calculate... The collateral circulation compensation index of the calcified area is obtained. Then, based on the collateral circulation compensation index and the calcification activity index, the dynamic risk factor corresponding to coronary artery stenosis is calculated. Through the dynamic risk factor, the synergistic effect of calcification activity and collateral circulation compensation ability on the stenosis risk is quantified, thereby establishing a precise mapping relationship between multi-dimensional dynamic pathological features and the degree of stenosis. The preset neural network model is trained by the dynamic risk factor, and then the trained preset neural network model is used to predict and process chest X-ray image data to output the coronary artery stenosis risk assessment result. The coronary artery stenosis risk assessment result is then used to assist doctors in making judgments, thereby reducing the risk of clinical misjudgment. Attached Figure Description

[0016] Figure 1 This is a flowchart illustrating the first embodiment of the intelligent assessment method for coronary artery stenosis based on chest X-ray of this application; Figure 2 This is a flowchart illustrating the second embodiment of the intelligent assessment method for coronary artery stenosis based on chest X-ray in this application; Figure 3 This is a schematic diagram of the device structure of the hardware operating environment involved in the embodiments of this application. Detailed Implementation

[0017] It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit this application.

[0018] This application provides a method for intelligent assessment of coronary artery stenosis based on chest X-ray. In the first embodiment of this method, referring to... Figure 1 The methods include: Step S10: Obtain chest X-ray image data of the target patient from a preset database; Step S20: Based on the temporal fluctuations of calcification areas in chest X-ray images, the calcification activity index is calculated. The calcification activity index is used to characterize the activity of coronary artery stenosis progression. Step S30: Determine the key points of cardiac pulsation in the chest X-ray image data, and calculate the collateral circulation compensation index of the calcification area based on the displacement changes of the key points of cardiac pulsation between each image frame. Step S40: Based on the collateral circulation compensation index and the calcification activity index, calculate the dynamic risk factors corresponding to coronary artery stenosis. Step S50: Input the dynamic risk factor into the preset neural network model for iterative training, and perform predictive processing on the chest X-ray image data based on the preset neural network model after training to obtain the coronary artery stenosis risk assessment result.

[0019] This embodiment aims to: train a preset neural network model using dynamic risk factors, and then use the trained preset neural network model to predict and process chest X-ray image data, outputting accurate coronary artery stenosis risk assessment results, thereby reducing the risk of clinical misjudgment.

[0020] The specific steps are as follows: Step S10: Obtain chest X-ray image data of the target patient from the preset database.

[0021] As an example, the intelligent assessment method for coronary artery stenosis based on chest X-ray can be applied to an intelligent assessment device for coronary artery stenosis based on chest X-ray, which belongs to the category of intelligent assessment equipment for coronary artery stenosis based on chest X-ray.

[0022] As an example, the intelligent assessment method for coronary artery stenosis based on chest X-ray can also be applied to an intelligent assessment system for coronary artery stenosis based on chest X-ray. This system includes a data acquisition platform and an intelligent assessment unit. The data acquisition platform is used to acquire chest X-ray image data of the target patient, while the intelligent assessment unit is used to perform risk assessment based on the chest X-ray image data, thereby outputting the risk assessment results.

[0023] As an example, chest X-ray image data can be obtained by extracting it from a preset database. Images of patients have been acquired within a historical time period. The process of acquiring images can be as follows: using the standard shooting position (posteroanterior and left lateral views) of a digital X-ray imaging device, with the patient standing upright and in contact with the detector plane. The imaging equipment is set with tube voltage of 100–150 kVp, tube current of 2–10 mAs (adjusted according to the patient's body size), and focal distance of 180 cm. Continuous imaging is performed during the patient's breath-holding phase at the end of deep inspiration (to ensure full expansion of the lung field and reduce cardiac motion blur) to acquire a short temporal image sequence within the same respiratory cycle (at the end of deep inspiration and breath-holding state). The acquired chest X-rays are then preprocessed, including grayscale normalization, noise suppression, and spatial coordinate calibration (using deformable registration technology to align the cardiac region), to ensure that the input data meets the analysis requirements.

[0024] Step S20: Based on the temporal fluctuations of calcification areas in chest X-ray images, the calcification activity index is calculated. The calcification activity index is used to characterize the activity of coronary artery stenosis progression.

[0025] As an example, chest X-ray images are limited by their resolution and cannot accurately display the anatomical structure of the coronary arteries. However, calcification of atherosclerotic plaques around the coronary arteries is a marker of stenosis progression. Therefore, the essence of intelligent assessment of coronary artery stenosis based on chest X-rays is to quantify the mapping relationship between calcified plaques on chest X-rays and the actual pathological mapping of coronary artery stenosis.

[0026] As an example, the temporal fluctuation of the calcification area can be the change caused by the change of the calcification area over time. The degree of progression of coronary artery stenosis can be determined by the degree of change of gray value of the coronary calcification area in chest X-ray image data, that is, the calcification activity index is calculated.

[0027] The step S20, which involves intelligent assessment of coronary artery stenosis based on chest X-ray, also includes steps S21 to S26, including: Step S21: Perform image segmentation processing on the chest X-ray image data to obtain the calcification mask in each image frame.

[0028] As an example, chest X-ray image data is not a single frame of image data, but a sequence of chest X-ray images including multiple image frames over a period of time, such as a chest X-ray sequence. The acquisition time period can be 5 seconds, 10 seconds, etc., and there is no specific limitation. The total number of frames is set to T, and each image frame is a static chest X-ray taken within the same respiratory cycle.

[0029] As an example, calcifications in the stenotic segment of the coronary artery are typically composed of calcium deposits, exhibiting a higher X-ray absorption density than the surrounding tissue. Therefore, in chest X-rays, calcified plaques in the stenotic segment of the coronary artery appear as high-brightness areas. An adaptive threshold segmentation algorithm (Otsu's method) is used for each frame of the chest X-ray to automatically calculate the optimal grayscale threshold, extract all high-brightness areas within the cardiac silhouette that meet the threshold condition, and mark them as calcification areas. Finally, a binary calcification mask for each image frame is output. The binary calcification mask can be obtained by performing frame-by-frame binary segmentation of cardiac image sequences (such as CT and ultrasound) to obtain a single-channel binary image (0=non-calcified, 1=calcified) containing only the "calcification" area in each frame.

[0030] Step S22: Calculate the average gray value of each calcification area in the calcification mask.

[0031] As an example, for each frame of chest X-ray image data, the spatial coordinates of all calcified lesion regions are located to ensure spatial consistency of the same calcified lesion region across different time series (achieved through coordinate registration). For each calcified lesion region, its average gray value in each frame of the chest X-ray image sequence is calculated. (This can be obtained by statistically analyzing the average grayscale value of all pixels within the calcification mask area).

[0032] Step S23: Based on the average gray value, calculate the fluctuation intensity coefficient of each calcification zone in the time series. The fluctuation intensity coefficient is used to characterize the time series fluctuation of the density corresponding to the calcification zone.

[0033] As an example, the fluctuation intensity coefficient of each calcification region over time is calculated. The method can be: Where T represents the number of image frames. and The fluctuation intensity coefficient represents the average gray value of the (t+1)th adjacent image frame and the average gray value of the tth image frame in the chest radiograph sequence. The value of reflects the degree of change in gray value of coronary calcifications in a short time-series chest radiograph, that is, the temporal fluctuation of the density corresponding to the calcification area. The larger the value, the faster the calcium salt deposition rate in the stenotic segment of the coronary artery and the acute progression of coronary stenosis.

[0034] Step S24: Detect the boundary pixels of the calcification mask using an edge detection algorithm to obtain a binary image of the edge contour.

[0035] As an example, the fluctuation intensity coefficient can only reflect the temporal fluctuation of calcification density, but cannot distinguish its spatial pattern of calcium salt deposition, such as uniform deposition and non-uniform dendritic deposition. In order to capture the morphological active features of calcification, it is necessary to analyze its edge evolution law. Therefore, the Sobel edge detection algorithm (existing technology) is performed on the calcification mask in each image frame of the chest radiograph sequence to detect the boundary pixels of each calcification region and generate a binary map of edge contours.

[0036] Step S25: Based on the binary edge contour map, calculate the edge roughness index of each calcification zone.

[0037] As an example, during the progression of stenosis in a local segment of the coronary artery, calcium salts are rapidly deposited, and the edges of the calcifications appear "spiky" with irregular contours. In contrast, during the chronic phase of stenosis, the calcification structure is mature, with smooth edges and a near-geometric circular contour (calcium salt deposition tends to be uniform, and the calcification morphology tends to be stable due to changes in the mechanical properties of the vessel wall). Based on this, the edge roughness index of each calcification region is calculated by statistically analyzing the perimeter of the boundary pixels in the binary edge contour image and the area of ​​the calcification.

[0038] As an example, the edge roughness index is used to reflect the roughness of the edge of the calcification zone. The larger the value, the rougher and more irregular the edge of the calcification zone, indicating that the area is in an active calcification stage and the calcium salt deposition is not yet fully mature.

[0039] Step S25, which calculates the edge roughness index of each calcification region based on the binary edge contour map, includes: Based on the binary image of the edge contour, the perimeter of the boundary pixels of the calcification foci region and the area of ​​the equivalent circle are determined.

[0040] Based on the equivalent circle area and the contour perimeter, the edge roughness index of each calcification zone is calculated. The edge roughness index is used to reflect the roughness of the edge of the calcification zone.

[0041] As an example, for each calcification region, the total length of the 8-neighborhood connections of the boundary pixels is calculated using the chain code method. The minimum circumference of the calcification lesion is considered as the perimeter of the outline, and the area of ​​the smallest circumscribed circle of the calcification lesion is considered as the equivalent circle area.

[0042] As an example, the edge roughness index R can be calculated as follows: Where A represents the area of ​​the equivalent circle and P represents the perimeter of the outline.

[0043] Step S26: Calculate the calcification activity index based on the fluctuation intensity coefficient and the edge roughness index.

[0044] As an example, the calcification activity index is calculated by combining the fluctuation intensity coefficient and the edge roughness index to reflect the calcium salt deposition process in the calcification foci area. Calcium salt deposition accelerates the hardening process of blood vessels, thereby aggravating the stenosis of blood vessels and laying the foundation for the subsequent generation of dynamic risk factors.

[0045] Step S26, which calculates the calcification activity index based on the fluctuation intensity coefficient and the edge roughness index, includes: A roughness data sequence is constructed based on the edge roughness index of each image frame.

[0046] Determine the roughness fluctuation intensity between the maximum and minimum sequence values ​​in the roughness data sequence.

[0047] As an example, a roughness data sequence is constructed based on the edge roughness index of each image frame, where the roughness fluctuation intensity is... The calculation method can be: Indicates the maximum sequence value. This represents the minimum sequence value, and the subscript t indicates the time corresponding to the video frame. The larger the value, the more it indicates that the edge of the calcification is constantly changing, corresponding to the phenomenon of continuous changes in the edge of calcification in the acute phase of coronary artery stenosis.

[0048] The calcification activity index is calculated based on the fluctuation intensity coefficient, the roughness fluctuation intensity, and the average edge roughness index of each image frame.

[0049] As an example, the calcification activity index The calculation method can be: in, Indicates the fluctuation intensity coefficient. Indicates the intensity of roughness fluctuation. The average value of the edge roughness index is used to characterize the edge roughness of the target calcification in the current cycle. This value is used as a weight. When the average roughness of the calcification is high in the (respiratory) cycle, it indicates that the calcification itself is in an active state. At this time, the pathological significance of edge fluctuation is greater (acute coronary artery stenosis is significant).

[0050] Specifically, higher The value indicates that the blood vessel wall in the corresponding calcified area is undergoing rapid calcium salt deposition, which accelerates the hardening process of the blood vessels and further aggravates the narrowing of the blood vessels.

[0051] Step S30: Determine the key points of cardiac pulsation in the chest X-ray image data, and calculate the collateral circulation compensation index of the calcified lesion area based on the displacement changes of the key points of cardiac pulsation between each image frame.

[0052] As an example, the selection of key points of cardiac pulsation is used to analyze the dynamic characteristics of cardiac pulsation in chest X-rays to capture the myocardial compensatory response induced by coronary artery stenosis. Coronary artery stenosis usually triggers a myocardial compensatory response. Therefore, the myocardial compensatory response can be determined by detecting changes in key points of cardiac pulsation.

[0053] Specifically, the myocardial compensatory response induced by coronary artery stenosis is essentially myocardial hypoxia caused by regional blood flow restriction. The heart maintains blood circulation by increasing the frequency and force of its beats, thereby generating a stronger motion or pulsation response near the stenotic segment. Furthermore, by determining the displacement changes of each cardiac pulsation point between each image frame, its pulsation response can be judged, thereby calculating the collateral circulation compensation index of the calcified lesion area. The collateral circulation compensation index is used to represent the correlation between the displacement changes of key cardiac pulsation points and the edge roughness of the calcified lesion area. Based on this correlation, it can be determined whether the coronary artery stenosis area corresponding to the calcified lesion has good collateral circulation compensation function.

[0054] Step S40: Based on the collateral circulation compensation index and the calcification activity index, the dynamic risk factors corresponding to coronary artery stenosis are calculated.

[0055] Step S40, which calculates the dynamic risk factors corresponding to coronary artery stenosis based on the collateral circulation compensation index and the calcification activity index, includes: The second Pearson correlation coefficient was calculated between the corresponding sequence of the calcification activity index and the inverse corresponding sequence of the collateral circulation compensation index, and the second Pearson correlation coefficient was used as the corrected weight.

[0056] As an example, the second Pearson correlation coefficient is the Pearson correlation coefficient between the sequence corresponding to the calcification activity index and the sequence corresponding to the inverse of the collateral circulation compensation index. It is used to represent the correlation between the two sequences. The inverse of the collateral circulation compensation index indicates the degree of loss of collateral circulation compensation function. The calcification activity index characterizes the activity of coronary artery stenosis progression, while the collateral circulation compensation index represents the collateral circulation compensation function in the coronary artery stenosis area corresponding to the calcification lesion. When the calcification activity index is larger, it indicates that the collateral circulation compensation function is worse. That is, there is a negative correlation between the calcification activity index and the collateral circulation compensation index. Then, there is a positive correlation between the sequence corresponding to the calcification activity index and the sequence corresponding to the inverse of the collateral circulation compensation index. When the second Pearson correlation coefficient is larger, the positive correlation between the two sequences is stronger.

[0057] As an example, Indicates the collateral circulation compensation index, Defined as the degree of collateral circulation compensation deficiency, the second Pearson correlation coefficient is used as a correction weight. The larger the value, the stronger the positive correlation between the calcification activity of calcification foci and the degree of regional collateral circulation compensation deficiency. That is, the calcification activity of calcification foci will significantly aggravate the degree of regional collateral circulation compensation deficiency, and calcification activity is the main factor causing the aggravation of the degree of regional collateral circulation compensation deficiency.

[0058] Based on the calcification activity index, collateral circulation compensation index, and adjusted weights, the dynamic risk factors corresponding to coronary artery stenosis were calculated.

[0059] As an example, dynamic risk factors The calculation method can be: In the formula, This represents a dynamic risk factor for stenosis of the coronary artery segment corresponding to the current chest X-ray calcification area. Indicates the calcification activity index, Indicates the collateral circulation compensation index. Indicates the degree of deficiency in collateral circulation compensation. The second Pearson correlation coefficient indicates that a larger DRF value suggests higher calcification activity in the calcification foci and weaker compensatory capacity of the regional collateral circulation. This implies that there may be more severe stenosis in the coronary artery segment, which has a greater impact on blood flow, and the risk of coronary artery stenosis in this region is higher.

[0060] Step S50: Input the dynamic risk factor into the preset neural network model for iterative training, and perform predictive processing on the chest X-ray image data based on the preset neural network model after training to obtain the coronary artery stenosis risk assessment result.

[0061] As an example, dynamic risk factors The key spatiotemporal dynamic features are input into a pre-trained neural network model (such as a gradient boosting decision tree, a temporal convolutional network, or a graph neural network). Through offline training, the model learns the complex relationship between dynamic risk factors and the degree of coronary artery stenosis. The model also incorporates the patient's basic physiological parameters (such as immune markers and clinical history) as auxiliary features to enhance the model's predictive ability. After iterative training, the pre-trained neural network model is obtained.

[0062] As an example, a pre-trained neural network model is used to predict and process chest X-ray data and relevant physiological parameters of the target patient to obtain coronary artery stenosis risk assessment results. The model provides the predicted probability or specific assessment level of coronary artery stenosis for the patient, providing decision support for clinicians, helping to determine the patient's coronary artery health status and guiding subsequent treatment plans.

[0063] This application provides an intelligent assessment method for coronary artery stenosis based on chest X-rays. Compared with related technologies that rely on extracting image features from single-frame static chest X-rays for coronary artery stenosis assessment, leading to a severe disconnect between pathological anatomical information and image features and increasing the risk of clinical misdiagnosis, this application obtains chest X-ray image data of the target patient from a pre-set database. First, based on the temporal fluctuations of calcification areas in the chest X-ray image data, a calcification activity index is calculated. The calcification activity index is used to characterize the activity of coronary artery stenosis progression. Then, key points of cardiac pulsation in the chest X-ray image data are identified. Finally, the displacement changes of these key points between each image frame are used to calculate... The collateral circulation compensation index of the calcified area is obtained. Then, based on the collateral circulation compensation index and the calcification activity index, the dynamic risk factor corresponding to coronary artery stenosis is calculated. Through the dynamic risk factor, the synergistic effect of calcification activity and collateral circulation compensation ability on the stenosis risk is quantified, thereby establishing a precise mapping relationship between multi-dimensional dynamic pathological features and stenosis degree. The preset neural network model is trained by the dynamic risk factor, and then the trained preset neural network model is used to predict and process chest X-ray image data to output the coronary artery stenosis risk assessment result. The coronary artery stenosis risk assessment result is then used to assist doctors in judgment, thereby reducing the risk of clinical misjudgment.

[0064] Furthermore, referring to Figure 2 Based on the first embodiment of this application, another embodiment of this application is provided. In this embodiment, step S30, which calculates the collateral circulation compensation index of the calcification region based on the displacement change of the cardiac pulsation key point between each image frame, includes: Step S31: Based on the Euclidean distance between the cardiac pulsation key points in each image frame, determine the displacement time sequence of each cardiac pulsation key point.

[0065] As an example, the cardiac pulsation keypoints will undergo different displacement changes between different image frames. The displacement change is represented by calculating the Euclidean distance between the cardiac pulsation keypoints in different image frames. Then, the displacement value of each cardiac pulsation keypoint is determined, and a displacement time sequence is constructed based on each displacement value.

[0066] Step S31 further includes: For any cardiac pulsation key point, calculate the first Euclidean distance between adjacent image frames and use the absolute value of the first Euclidean distance as the inter-frame displacement of each cardiac pulsation key point. The cardiac pulsation key points include the apex of the heart, the left atrial appendage, and the ventricular diaphragmatic surface.

[0067] Based on inter-frame displacement, the displacement time sequence of each key point of heartbeat is determined.

[0068] As an example, in each image frame of a short-sequence chest radiograph, the following key points of cardiac pulsation are automatically located using an anatomical topology constraint algorithm. These key points include the apex, left atrial appendage, and ventricular-diaphragmatic surface. The apex can be the intersection of the projection of the most distal segment of the left ventricle and the diaphragm, the left atrial appendage can be the turning point between the pulmonary artery segment and the left ventricular segment, and the ventricular-diaphragmatic surface can be the highest point where the right ventricle meets the diaphragm.

[0069] As an example, the first Euclidean distance represents the Euclidean distance between any heartbeat keypoint and adjacent image frames. The inter-frame displacement of each heartbeat keypoint is tracked by the pyramid optical flow method, and the spatial coordinate Euclidean distance of the displacement between adjacent image frames is calculated, which is the first Euclidean distance. The absolute value of the first Euclidean distance is used as the inter-frame displacement of each heartbeat keypoint.

[0070] As an example, after obtaining the inter-frame displacements of keypoints for each type of heartbeat, a temporal sequence of displacements for each keypoint is constructed: ( (This refers to the total number of image frames corresponding to the chest X-ray image data).

[0071] Step S32: Based on the displacement time sequence, calculate the instantaneous phase time delay coefficient of each key point of heartbeat.

[0072] As an example, the instantaneous phase time delay coefficient is used to characterize the degree of pathological asynchrony during the pulsation of cardiac structures. The larger the value, the more the cardiac structure corresponding to the key point of the heart pulsation loses synchronization with other parts. The reduced blood flow in the corresponding coronary artery stenosis area leads to compensatory myocardial contraction in that area, which in turn affects its coordination with other cardiac regions. The instantaneous phase time delay coefficient is calculated by calculating the instantaneous phase change of each sequence value in the displacement time sequence.

[0073] Step S32, which calculates the instantaneous phase time delay coefficient for each key point of cardiac pulsation based on the displacement time sequence, includes: Linear fitting was performed on the displacement time sequence to obtain the displacement fitting curve for each key point of heartbeat.

[0074] Determine the instantaneous phase information of the displacement fitting curve corresponding to each key point of heartbeat.

[0075] As an example, the displacement time sequence corresponding to each key point of heartbeat is mapped onto a two-dimensional coordinate system, and the displacement fitting curve of the displacement time sequence of each key point of heartbeat is obtained by linear fitting (polynomial fitting method): , where the subscript r indicates the key point of heartbeat.

[0076] As an example, displacement fitting curves are generated for all key points of the heartbeat. The Fast Fourier Transform (FFT) is performed to convert the data into frequency domain data, thereby obtaining the instantaneous phase information of the fitted curve corresponding to each key point of the heartbeat. (The phase information is converted using the trigonometric function cos to facilitate subsequent data calculation).

[0077] For any key point of heart pulsation, calculate the instantaneous phase difference between the current key point of heart pulsation and other different key points of heart pulsation, and use the average of the absolute values ​​of each instantaneous phase difference as the instantaneous phase time delay coefficient.

[0078] As an example, for any cardiac pulsation key point, the instantaneous phase difference between the current cardiac pulsation key point and other different cardiac pulsation key points is calculated. ,in, This represents the instantaneous phase information at key points of the current heartbeat. This represents the instantaneous phase information at other key points of the heartbeat, determining the absolute value of the instantaneous phase difference. Since there are multiple key points in the heartbeat, the instantaneous phase difference of each instantaneous point is integrated and its average value is calculated to obtain the instantaneous phase time delay coefficient of the current key point in the heartbeat.

[0079] Step S33: Match the calcification area with the key points of heart pulsation to obtain a set of multiple key point calcifications.

[0080] As an example, when calculating the correlation between calcification regions and cardiac pulsation keypoints, all calcification regions in each image frame need to be grouped according to spatial affiliation. The calcification regions are then matched with cardiac pulsation keypoints to obtain the set of calcifications assigned to each cardiac pulsation keypoint, i.e., the keypoint calcification set. Within this set, calcification regions and their corresponding cardiac pulsation keypoints are assigned to the same spatial affiliation. The keypoint calcification set is represented as follows: ,in Represents the key points of heartbeat. This represents the calcified foci region corresponding to the key points of heart pulsation.

[0081] Step S33, which involves matching calcification areas with key points of cardiac pulsation to obtain a set of multiple key-point calcifications, includes: Obtain the coordinates of the centroid of the calcification in the mask, and calculate the second Euclidean distance from the centroid of the mask to each key point of cardiac pulsation.

[0082] As an example, the mask centroid coordinates can be the geometric centroid of all valid pixels in the mask (usually regions with values ​​of 1 or 255), and the second Euclidean distance represents the Euclidean distance from the mask centroid coordinates to each heartbeat keypoint.

[0083] Each calcification region is assigned to the region corresponding to the cardiac pulsation key point with the minimum second Euclidean distance, generating multiple key point calcification sets.

[0084] Step S34: Calculate the first Pearson correlation coefficient between the sequence corresponding to the instantaneous phase time delay coefficient and the roughness data sequence corresponding to the set of key point calcification foci, and use the first Pearson correlation coefficient as the collateral circulation compensation index of the calcification foci region.

[0085] As an example, the roughness data sequence is represented as ,in Number the calcified areas in the image. R represents the image frame number in the sequence, and R represents the edge roughness index.

[0086] As an example, determine the sequence of instantaneous phase time delay coefficients U between each cardiac pulsation key point and other cardiac pulsation key points ( Data sequence: ), and the temporal sequence of the edge roughness of coronary artery calcifications within the allocation region where the key point of cardiac pulsation is located ( ).

[0087] As an example, calculate a data sequence With data sequence The first Pearson correlation coefficient between them, which ranges from -1 to 1, is defined as the collateral circulation compensation index of the corresponding coronary artery calcification mask region. ).

[0088] Specifically, when When the value is greater than 0, the closer it is to 1, the stronger the positive correlation between the B sequence (instantaneous phase time delay coefficient) and the C sequence (calcification edge roughness). In this case, the asynchronous beating in certain areas of the heart is positively correlated with the edge roughness of the coronary calcification in those areas, meaning that coronary artery stenosis leads to reduced local blood flow, and the myocardium compensates for the insufficient blood flow by increasing its beating. At this time, the stenotic segment of the coronary artery corresponding to the calcification may have good collateral circulation compensation function, thereby reducing the risk of coronary artery stenosis.

[0089] when When the value of is (0,1), the two are negatively correlated, which means that the local blood flow reduction caused by coronary artery stenosis is insufficient, and the compensatory pulsation of the myocardium is insufficient, which cannot effectively compensate for the loss of blood flow. At this time, the stenotic segment of the coronary artery corresponding to the calcification lacks effective collateral circulation compensation function, and the risk caused by coronary artery stenosis will be further aggravated.

[0090] In this embodiment, the collateral circulation compensation index is calculated based on the instantaneous phase time delay coefficient between each key point of cardiac pulsation and the edge roughness time sequence. This is used to determine whether the coronary artery stenosis segment corresponding to the calcification area has effective collateral circulation compensation function, thereby accurately determining the degree of risk caused by coronary artery stenosis.

[0091] Specifically, this application also provides a coronary artery stenosis intelligent assessment system based on chest X-ray. The system includes a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, it implements the steps of the coronary artery stenosis intelligent assessment method based on chest X-ray as described in the above embodiments.

[0092] Reference Figure 3 , Figure 3 This is a schematic diagram of the device structure of the hardware operating environment involved in the embodiments of this application.

[0093] like Figure 3 As shown, the intelligent assessment device for coronary artery stenosis based on chest X-ray may include: a processor 1001, a memory 1005, and a communication bus 1002. The communication bus 1002 is used to realize the connection and communication between the processor 1001 and the memory 1005.

[0094] Optionally, the intelligent assessment device for coronary artery stenosis based on chest X-ray may also include a user interface, a network interface, a camera, RF (Radio Frequency) circuitry, sensors, a WiFi module, etc. The user interface may include a display screen and an input submodule such as a keyboard; optional user interfaces may also include standard wired or wireless interfaces. The network interface may include standard wired or wireless interfaces (such as a Wi-Fi interface).

[0095] Those skilled in the art will understand that Figure 3 The structure of the intelligent assessment device for coronary artery stenosis based on chest X-ray shown does not constitute a limitation on the intelligent assessment device for coronary artery stenosis based on chest X-ray. It may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0096] like Figure 3As shown, the memory 1005, serving as a storage medium, may include an operating system, a network communication module, and a chest X-ray-based intelligent assessment program for coronary artery stenosis. The operating system is a program that manages and controls the hardware and software resources of the chest X-ray-based intelligent assessment device for coronary artery stenosis, supporting the operation of the chest X-ray-based intelligent assessment program for coronary artery stenosis and other software and / or programs. The network communication module is used to enable communication between the various components within the memory 1005, as well as communication with other hardware and software in the chest X-ray-based intelligent assessment system for coronary artery stenosis.

[0097] exist Figure 3 In the illustrated intelligent assessment device for coronary artery stenosis based on chest X-ray, the processor 1001 is used to execute the intelligent assessment program for coronary artery stenosis based on chest X-ray stored in the memory 1005, and to implement the steps of the intelligent assessment method for coronary artery stenosis based on chest X-ray as described above.

[0098] The specific implementation of the intelligent assessment device for coronary artery stenosis based on chest X-ray in this application is basically the same as the embodiments of the intelligent assessment method for coronary artery stenosis based on chest X-ray described above, and will not be repeated here.

[0099] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.

[0100] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0101] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0102] The above are merely preferred embodiments of this application and do not limit the scope of this application. Any equivalent structural or procedural transformations made based on the description and drawings of this application, or direct or indirect applications in other related technical fields, are similarly included within the scope of protection of this application.

[0103] It should be noted that the order of the above embodiments of the present invention is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0104] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

Claims

1. A method for intelligent assessment of coronary artery stenosis based on chest X-ray, characterized in that, The method includes: Retrieve chest X-ray image data of the target patient from a pre-set database; Based on the temporal fluctuations of calcification areas in the chest X-ray image data, a calcification activity index is calculated, which is used to characterize the activity of coronary artery stenosis progression. The key points of cardiac pulsation in the chest X-ray image data are identified, and the collateral circulation compensation index of the calcified lesion area is calculated based on the displacement changes of the key points of cardiac pulsation between each image frame. Based on the collateral circulation compensation index and the calcification activity index, the dynamic risk factor corresponding to coronary artery stenosis is calculated. The dynamic risk factors are input into a preset neural network model for iterative training, and the chest X-ray image data is then used for prediction based on the trained preset neural network model to obtain the coronary artery stenosis risk assessment result.

2. The intelligent assessment method for coronary artery stenosis based on chest X-ray as described in claim 1, characterized in that, The calculation of the calcification activity index based on the temporal fluctuations of the calcification areas in the chest X-ray image data includes: The chest X-ray image data is processed by image segmentation to obtain the calcification mask in each image frame; Calculate the average gray value of each calcification zone in the calcification zone mask; Based on the average gray value, the fluctuation intensity coefficient of each calcification zone in the time series is calculated, and the fluctuation intensity coefficient is used to characterize the time series fluctuation of the density corresponding to the calcification zone. The boundary pixels of the calcification mask are detected by an edge detection algorithm to obtain a binary image of the edge contour. Based on the binary image of the edge contour, the edge roughness index of each calcification zone is calculated; The calcification activity index is calculated based on the fluctuation intensity coefficient and the edge roughness index.

3. The intelligent assessment method for coronary artery stenosis based on chest X-ray as described in claim 2, characterized in that, The calculation of the edge roughness index of each calcification region based on the edge contour binary map includes: Based on the edge contour binary map, the contour perimeter and equivalent circle area of ​​the boundary pixels of the calcification foci region are determined. Based on the equivalent circle area and the contour perimeter, the edge roughness index of each calcification zone is calculated. The edge roughness index is used to reflect the roughness of the edge of the calcification zone.

4. The intelligent assessment method for coronary artery stenosis based on chest X-ray as described in claim 2, characterized in that, The calculation of the calcification activity index based on the fluctuation intensity coefficient and the edge roughness index includes: Based on the edge roughness index of each image frame, a roughness data sequence is constructed; Determine the roughness fluctuation intensity between the maximum and minimum sequence values ​​in the roughness data sequence; The calcification activity index is calculated based on the fluctuation intensity coefficient, the roughness fluctuation intensity, and the average value of the edge roughness index of each image frame.

5. The intelligent assessment method for coronary artery stenosis based on chest X-ray as described in claim 2, characterized in that, The collateral circulation compensation index for the calcified lesion region is calculated based on the displacement changes of the key cardiac pulsation points between each image frame, including: Based on the Euclidean distance between the key points of heart pulsation in each image frame, the displacement time sequence of each key point of heart pulsation is determined; Based on the displacement time sequence, the instantaneous phase time delay coefficient of each key point of heartbeat is calculated; By matching the calcification area with the key points of cardiac pulsation, a set of multiple key point calcifications is obtained. Calculate the first Pearson correlation coefficient between the sequence corresponding to the instantaneous phase time delay coefficient and the roughness data sequence corresponding to the set of key point calcifications, and use the first Pearson correlation coefficient as the collateral circulation compensation index of the calcification region.

6. The intelligent assessment method for coronary artery stenosis based on chest X-ray as described in claim 5, characterized in that, The determination of the displacement temporal sequence of each cardiac pulsation key point based on the Euclidean distance between each image frame includes: For any key point of heart pulsation, calculate the first Euclidean distance between adjacent image frames of the key point displacement, and take the absolute value of the first Euclidean distance as the inter-frame displacement of each key point of heart pulsation. The key points of heart pulsation include the apex of the heart, the left atrial appendage, and the ventricular diaphragmatic surface. Based on the inter-frame displacement, the displacement time sequence of each key point of heartbeat is determined.

7. The intelligent assessment method for coronary artery stenosis based on chest X-ray as described in claim 5, characterized in that, The instantaneous phase time delay coefficient for each key point of cardiac pulsation, calculated based on the displacement time sequence, includes: The displacement time sequence is linearly fitted to obtain the displacement fitting curve for each of the key points of heart pulsation. Determine the instantaneous phase information of the displacement fitting curve corresponding to each key point of heart pulsation; For any key point of heart pulsation, calculate the instantaneous phase difference between the current key point of heart pulsation and other different key points of heart pulsation, and use the average of the absolute values ​​of the instantaneous phase differences as the instantaneous phase time delay coefficient.

8. The intelligent assessment method for coronary artery stenosis based on chest X-ray as described in claim 5, characterized in that, The process of matching the calcified lesion region with the key points of cardiac pulsation yields a set of multiple key point calcified lesions, including: Obtain the centroid coordinates of the calcification mask, and calculate the second Euclidean distance from the centroid coordinates of the mask to each of the key points of cardiac pulsation; Each calcification region is assigned to the region corresponding to the cardiac pulsation key point with the minimum second Euclidean distance, generating multiple key point calcification sets.

9. The intelligent assessment method for coronary artery stenosis based on chest X-ray as described in claim 1, characterized in that, The dynamic risk factors corresponding to coronary artery stenosis are calculated based on the collateral circulation compensation index and the calcification activity index, including: Calculate the second Pearson correlation coefficient between the sequence corresponding to the calcification activity index and the inverse sequence corresponding to the collateral circulation compensation index, and use the second Pearson correlation coefficient as the correction weight; Based on the calcification activity index, the collateral circulation compensation index, and the corrected weight, the dynamic risk factor corresponding to coronary artery stenosis is calculated.

10. A smart assessment system for coronary artery stenosis based on chest X-ray, characterized in that, The system includes a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that the processor executes the computer program to implement the steps of the method as described in any one of claims 1 to 9.

Images