Cardiac phase acquisition method and device, storage medium, and computer equipment

Abstract

The present application discloses a cardiac phase acquisition method and apparatus, storage medium, and computer equipment. The method comprises: acquiring cardiac images to be segmented corresponding to a plurality of candidate phases; performing image segmentation on the cardiac images to be segmented corresponding to each candidate phase to obtain a coronary artery region image corresponding to each candidate phase; determining coronary artery motion change data between candidate phases based on the coronary artery region image, and acquiring a target cardiac phase based on the coronary artery motion change data. The present application can automatically acquire the optimal target cardiac phase based on the coronary artery motion change, so that a clear, low-artifact coronary artery image can be obtained by reconstructing an image of the target cardiac phase. This not only reduces the physician's workload and reliance on the physician's experience, but also improves the efficiency and accuracy of image reconstruction.

Description

Technical Field

[0001] The present application relates to the field of image reconstruction technology, and in particular to a method and device for acquiring cardiac phases, a storage medium, and a computer device. Background Art

[0002] As we all know, cardiovascular and cerebrovascular diseases are a common and fatal disease in my country. This is especially true with the aging population, rising living standards, and unbalanced diets, which can easily lead to problems like high cholesterol, high blood pressure, and high blood sugar. Coronary heart disease is one of these common conditions. With the continuous advancement of CT technology, the rotation speed of CT gantry and the number of detector rows have continued to increase, allowing CT to handle more scanning tasks. Coronary angiography (CTA) has become a key diagnostic tool for excluding coronary heart disease. Its non-invasive nature, low cost, and the absence of hospitalization make it easily accepted by patients.

[0003] However, when performing actual imaging for clinical diagnosis, doctors typically select a few target phases based on experience, which can sometimes produce suboptimal images. If images are reconstructed for the entire scanning phase range, and doctors then manually identify high-quality, low-artifact coronary angiography images of the optimal phase from all reconstructed images, not only does image reconstruction take a long time, resulting in low CT utilization efficiency, but it also consumes a significant amount of the doctor's time and energy. Automatically acquiring the optimal cardiac phase will effectively reduce image reconstruction time, improve the efficiency of acquiring optimal cardiac phase images, enhance cardiac imaging quality, and reduce doctors' workload. Summary of the Invention

[0004] In view of this, the present application provides a method and apparatus for acquiring cardiac phases, a storage medium, and a computer device.

[0005] According to one aspect of the present application, a method for acquiring cardiac phases is provided, comprising:

[0006] Acquire a plurality of heart images to be segmented corresponding to candidate periods;

[0007] performing image segmentation on the to-be-segmented heart image corresponding to each candidate period to obtain a coronary artery region image corresponding to each candidate period;

[0008] According to the coronary artery regional image, coronary artery motion change data between candidate phases is determined, and based on the coronary artery motion change data, a target cardiac phase is acquired.

[0009] Optionally, acquiring the heart images to be segmented corresponding to the multiple phases specifically includes:

[0010] Acquiring cardiac scan data, wherein a scan phase range of the cardiac scan data is determined based on a preset reconstruction phase range;

[0011] The heart scan data corresponding to the preset reconstruction phase range is reconstructed according to the preset phase interval to determine the heart images to be segmented corresponding to a plurality of candidate phases.

[0012] Optionally, determining the coronary artery motion change data between candidate phases based on the coronary artery regional image specifically includes:

[0013] Acquire a coronary artery region image i and a coronary artery region image i+1 corresponding to any two consecutive candidate phases, wherein the coronary artery region image i represents the coronary artery region image corresponding to candidate phase i, and the coronary artery region image i+1 represents the coronary artery region image corresponding to candidate phase i+1, and i is less than the number of candidate phases;

[0014] taking the intersection of the coronary artery regional image i and the coronary artery regional image i+1 as a comparison template i, and determining coronary artery contour data i based on the coronary artery regional image i and the comparison template i, and determining coronary artery contour data i+1 based on the coronary artery regional image i+1 and the comparison template i;

[0015] The coronary artery motion change data corresponding to the candidate phase i to the candidate phase i+1 is determined based on the coronary artery contour data i+1 and the coronary artery contour data i.

[0016] Optionally, acquiring a target cardiac phase based on the coronary artery motion change data specifically includes:

[0017] Drawing a coronary artery change curve corresponding to the preset reconstruction phase range based on the coronary artery motion change data;

[0018] The phase corresponding to the minimum value in the coronary artery change curve is obtained as the target cardiac phase.

[0019] Optionally, obtaining the phase corresponding to the minimum value in the coronary artery change curve as the target cardiac phase specifically includes:

[0020] Using a preset cardiac contraction period as a first starting search point, searching for a first minimum extreme point within a first search phase range corresponding to the preset cardiac contraction period, and obtaining a phase corresponding to the first minimum extreme point as a first target cardiac phase, wherein the target cardiac phase includes the first target cardiac phase; and / or,

[0021] The preset cardiac diastole is used as the second starting search point, and a second minimum extreme point is searched within a second search phase range corresponding to the preset cardiac diastole, and the phase corresponding to the second minimum extreme point is obtained as the second target cardiac phase, wherein the target cardiac phase includes the second target cardiac phase.

[0022] Optionally, performing image segmentation on the heart image to be segmented corresponding to each candidate period to obtain a coronary artery region image corresponding to each candidate period specifically includes:

[0023] Performing image segmentation on the multi-layer heart images to be segmented corresponding to each candidate period to obtain multi-layer coronary artery region images corresponding to each candidate period;

[0024] Smoothing is performed on the segmented edges of the multi-layer coronary artery region image corresponding to each candidate period to determine the coronary artery region image corresponding to each candidate period.

[0025] Optionally, after obtaining the coronary artery region image corresponding to each candidate period, the method further includes:

[0026] Determining the heart centroid corresponding to each coronary artery regional image according to the coronary artery regional image corresponding to each candidate period;

[0027] acquiring at least one target coronary artery region image in each of the coronary artery region images based on a positional relationship between the heart centroid and at least one target coronary artery;

[0028] Accordingly, determining the coronary artery motion change data between candidate phases based on the coronary artery regional image specifically includes:

[0029] The coronary artery motion change data between each candidate phase is determined based on the target coronary artery region image.

[0030] According to another aspect of the present application, a cardiac phase acquisition device is provided, comprising:

[0031] An image acquisition module, configured to acquire heart images to be segmented corresponding to a plurality of candidate periods;

[0032] a coronary artery segmentation module, configured to perform image segmentation on the heart image to be segmented corresponding to each candidate period, to obtain a coronary artery region image corresponding to each candidate period;

[0033] The phase acquisition module is used to determine the coronary artery motion change data between each candidate phase according to the coronary artery regional image, and acquire the target cardiac phase based on the coronary artery motion change data.

[0034] Optionally, the image acquisition module is specifically configured to:

[0035] Acquiring cardiac scan data, wherein a scan phase range of the cardiac scan data is determined based on a preset reconstruction phase range;

[0036] The heart scan data corresponding to the preset reconstruction phase range is reconstructed according to the preset phase interval to determine the heart images to be segmented corresponding to a plurality of candidate phases.

[0037] Optionally, the phase acquisition module is specifically configured to:

[0038] Acquire a coronary artery region image i and a coronary artery region image i+1 corresponding to any two consecutive candidate phases, wherein the coronary artery region image i represents the coronary artery region image corresponding to candidate phase i, and the coronary artery region image i+1 represents the coronary artery region image corresponding to candidate phase i+1, and i is less than the number of candidate phases;

[0039] taking the intersection of the coronary artery regional image i and the coronary artery regional image i+1 as a comparison template i, and determining coronary artery contour data i based on the coronary artery regional image i and the comparison template i, and determining coronary artery contour data i+1 based on the coronary artery regional image i+1 and the comparison template i;

[0040] The coronary artery motion change data corresponding to the candidate phase i to the candidate phase i+1 is determined based on the coronary artery contour data i+1 and the coronary artery contour data i.

[0041] Optionally, the phase acquisition module is specifically configured to:

[0042] Drawing a coronary artery change curve corresponding to the preset reconstruction phase range based on the coronary artery motion change data;

[0043] The phase corresponding to the minimum value in the coronary artery change curve is obtained as the target cardiac phase.

[0044] Optionally, the phase acquisition module is further configured to:

[0045] Using a preset cardiac contraction period as a first starting search point, searching for a first minimum extreme point within a first search phase range corresponding to the preset cardiac contraction period, and obtaining a phase corresponding to the first minimum extreme point as a first target cardiac phase, wherein the target cardiac phase includes the first target cardiac phase; and / or,

[0046] The preset cardiac diastole is used as the second starting search point, and a second minimum extreme point is searched within a second search phase range corresponding to the preset cardiac diastole, and the phase corresponding to the second minimum extreme point is obtained as the second target cardiac phase, wherein the target cardiac phase includes the second target cardiac phase.

[0047] Optionally, the coronary artery segmentation module is specifically configured to:

[0048] Performing image segmentation on the multi-layer heart images to be segmented corresponding to each candidate period to obtain multi-layer coronary artery region images corresponding to each candidate period;

[0049] Smoothing is performed on the segmented edges of the multi-layer coronary artery region image corresponding to each candidate period to determine the coronary artery region image corresponding to each candidate period.

[0050] Optionally, the coronary artery segmentation module is further configured to:

[0051] After obtaining the coronary artery regional image corresponding to each candidate period, determining the heart centroid corresponding to each coronary artery regional image based on the coronary artery regional image corresponding to each candidate period; and acquiring at least one target coronary artery regional image in each coronary artery regional image based on a positional relationship between the heart centroid and at least one target coronary artery;

[0052] Correspondingly, the phase acquisition module is further configured to determine the coronary artery motion change data between the candidate phases based on the target coronary artery region image.

[0053] According to another aspect of the present application, a storage medium is provided, on which a computer program is stored. When the program is executed by a processor, the above-mentioned method for acquiring cardiac phases is implemented.

[0054] According to another aspect of the present application, a computer device is provided, comprising a storage medium, a processor, and a computer program stored on the storage medium and executable on the processor, wherein the processor implements the above-mentioned cardiac phase acquisition method when executing the program.

[0055] By means of the above-mentioned technical solution, the present application provides a cardiac phase acquisition method and apparatus, storage medium, and computer equipment, which reconstructs scan data, obtains cardiac images to be segmented corresponding to multiple candidate phases, and segments the coronary artery region images in the images. Furthermore, based on the coronary artery region images, the motion data of the coronary arteries between the candidate phases are statistically calculated, thereby selecting the optimal target cardiac phase based on the change data. Compared to the prior art method in which doctors rely on experience or manually select images reconstructed from all phases, the embodiments of the present application can automatically obtain the optimal target cardiac phase based on the motion changes of the coronary arteries, so that a clear, low-artifact coronary artery image can be obtained by reconstructing the image of the target cardiac phase. This not only reduces the doctor's workload and reliance on the doctor's experience, but also improves the efficiency and accuracy of image reconstruction.

[0056] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0058] Figure 1 A schematic diagram showing a flow chart of a cardiac phase acquisition method provided in an embodiment of the present application is shown;

[0059] Figure 2 A schematic diagram of a process for segmenting a coronary artery region provided in an embodiment of the present application is shown;

[0060] Figure 3 A schematic flow chart of another cardiac phase acquisition method provided in an embodiment of the present application is shown;

[0061] Figure 4 A schematic diagram of a coronary artery change curve provided in an embodiment of the present application is shown;

[0062] Figure 5 A schematic structural diagram of a cardiac phase acquisition device provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0063] The present application will be described in detail below with reference to the accompanying drawings and in combination with embodiments. It should be noted that, unless there is a conflict, the embodiments and features in the embodiments of the present application can be combined with each other.

[0064] In this embodiment, a method for obtaining cardiac phase is provided, such as Figure 1 As shown, the method includes:

[0065] Step 101, obtaining a plurality of heart images to be segmented corresponding to candidate periods;

[0066] In the embodiment of the present application, the cardiac image to be segmented can be obtained by reconstructing CT scan data. In specific application scenarios, a prospective ECG gating mode can be used to scan any phase, such as a full-phase mode scan, where a full-phase scan covers the entire cardiac cycle in one scan. Alternatively, a retrospective ECG gating spiral acquisition mode can be used to scan any phase.

[0067] The candidate phases can be any number of all scan phases. For example, when acquiring a cardiac image to be segmented based on full-phase scan data, the full phase ranges from 0% to 100%. A uniform selection of 20 phases can be used for image reconstruction to obtain the cardiac image to be segmented. The relative phase of the cardiac scan refers to the time range of the reconstructed cardiac image on the ECG signal, as a percentage of the range between two adjacent R-peaks in the ECG signal. 0% corresponds to the position of the first R-peak, and 100% corresponds to the position of the second R-peak. The full phase range covers 0%-100%.

[0068] Optionally, step 101 may specifically include: acquiring cardiac scanning data, wherein a scanning phase range of the cardiac scanning data is determined based on a preset reconstruction phase range; reconstructing the cardiac scanning data corresponding to the preset reconstruction phase range according to a preset phase interval, and determining the cardiac images to be segmented corresponding to multiple candidate phases.

[0069] In this embodiment, the cardiac scan data can be data obtained by performing a CT scan in any mode. Since image reconstruction requires the use of scan data within a certain range before and after the image reconstruction phase, in actual application scenarios, the cardiac scan phase range can be determined based on the preset reconstruction phase range. For example, if the preset reconstruction phase range is 5% to 95%, then the cardiac scan phase range can be 0 to 100%. Then, according to the pre-set preset phase interval, multiple candidate phases are determined within the preset reconstruction phase range, and the corresponding cardiac image to be segmented for each candidate phase is reconstructed to reduce the workload of image reconstruction and improve efficiency. For example, the preset phase interval can be selected as 5%, and the candidate phases can include 5%, 10%, 15%...

[0070] In addition, to improve image reconstruction efficiency, since the range of CT scanning may be large, the field of view of image reconstruction can be adjusted. Only the image within a certain range around the heart needs to be reconstructed, thereby improving image reconstruction efficiency.

[0071] Step 102, performing image segmentation on the to-be-segmented heart image corresponding to each candidate period to obtain a coronary artery region image corresponding to each candidate period;

[0072] Since cardiac image reconstruction mainly focuses on whether the coronary arteries of the heart have lesions, plaques, stenosis and blockage, and the movement states of the atria and ventricles are different during the contraction and relaxation of the heart, the size change of the entire heart contour alone may not necessarily represent the actual movement state of the coronary arteries, resulting in inaccurate optimal phase acquisition and motion artifacts in the reconstructed image of the coronary arteries, which affects the doctor's evaluation and diagnosis. Therefore, in the embodiment of the present application, after determining the cardiac image to be segmented corresponding to each candidate phase, each image can be segmented separately to segment out the coronary artery region image, so that the coronary artery region image can be used to analyze the optimal cardiac phase later, which helps to improve the accuracy of determining the optimal cardiac phase and the accuracy of image reconstruction. In actual application scenarios, the segmentation of the coronary artery region can be achieved through a coronary artery segmentation model, or it can be achieved through coronary artery feature recognition, which is not limited here.

[0073] Step 103 : determining coronary artery motion change data between candidate phases according to the coronary artery regional image, and acquiring a target cardiac phase based on the coronary artery motion change data.

[0074] Finally, based on the segmented coronary artery region image, the change data of the coronary artery between each candidate phase is determined. The phase with the smoothest coronary artery motion state is found through this change data, and the phase with the smoothest motion state is used as the final target cardiac phase. The cardiac image of the target cardiac phase is then reconstructed to obtain a high-quality, low-artifact cardiac reconstructed image.

[0075] In the embodiment of the present application, optionally, step 103 may further include:

[0076] Step 104 : performing image reconstruction based on the cardiac scan data and the target cardiac phase to determine a cardiac reconstructed image corresponding to the target cardiac phase.

[0077] In addition, in the embodiment of the present application, optionally, between step 103 and step 104, the following may be further included: outputting the target cardiac phase, and executing step 104 in response to an image reconstruction instruction. The image reconstruction instruction may be a confirmation instruction for the target cardiac phase, or an instruction for modifying data of the target cardiac phase.

[0078] By applying the technical solution of this embodiment, scan data is reconstructed to obtain cardiac images to be segmented corresponding to multiple candidate phases, and images of the coronary artery region in the image are segmented. Furthermore, based on the coronary artery region images, statistical data on the motion of the coronary arteries between each candidate phase is calculated, thereby selecting the optimal target cardiac phase based on the variation data. Compared to the prior art method in which a physician manually selects images reconstructed from all phases, this embodiment of the present application can automatically obtain the optimal target cardiac phase based on the variation in coronary artery motion. This allows for a clear, low-artifact coronary artery image to be obtained by reconstructing an image of the target cardiac phase. This not only reduces the physician's workload and reliance on the physician's experience, but also improves the efficiency and accuracy of image reconstruction.

[0079] In the embodiment of the present application, optionally, in step 103, “determining the coronary artery motion change data between candidate phases based on the coronary artery regional image” may specifically include:

[0080] Step 103-1, obtaining a coronary artery regional image i and a coronary artery regional image i+1 corresponding to any two consecutive candidate phases, wherein the coronary artery regional image i represents the coronary artery regional image corresponding to candidate phase i, and the coronary artery regional image i+1 represents the coronary artery regional image corresponding to candidate phase i+1;

[0081] Step 103-2: Take the intersection of the coronary artery regional image i and the coronary artery regional image i+1 as a comparison template i, and determine coronary artery contour data i based on the coronary artery regional image i and the comparison template i, and determine coronary artery contour data i+1 based on the coronary artery regional image i+1 and the comparison template i; and determine the coronary artery motion change data corresponding to the candidate phase i to the candidate phase i+1 based on the coronary artery contour data i+1 and the coronary artery contour data i.

[0082] In this embodiment, the changes in the coronary arteries between candidate phase i and candidate phase i+1 can be determined in the following manner: first, obtaining a coronary artery region image i and a coronary artery region image i+1 corresponding to candidate phase i; then, taking the intersection of the coronary artery region image i and the coronary artery region image i+1, using the intersection as a comparison template i; performing coronary artery recognition on the region of the coronary artery region image i that overlaps with the comparison template i, and obtaining corresponding coronary artery contour data i; similarly, performing coronary artery recognition on the region of the coronary artery region image i+1 that overlaps with the comparison template i, and obtaining corresponding coronary artery contour data i+1; finally, performing a difference between the coronary artery contour data i+1 and the coronary artery contour data i, and using the difference as the change data of the coronary arteries from candidate phase i to candidate phase i+1. Specifically, the coronary artery motion change data can be used as the coronary artery motion change corresponding to phase [i+(i+1)] / 2 to facilitate subsequent screening of the optimal cardiac phase. For example, the phase with the smallest motion change can be selected as the optimal cardiac phase.

[0083] In the embodiment of the present application, optionally, in step 103, “obtaining a target cardiac phase based on the coronary artery motion change data” may specifically include:

[0084] Step 103-3, drawing a coronary artery change curve corresponding to the preset reconstruction phase range based on the coronary artery motion change data;

[0085] Step 103 - 4 , obtaining the phase corresponding to the minimum value in the coronary artery change curve as the target cardiac phase.

[0086] In the above embodiment, to analyze motion changes across all phases within a preset reconstruction phase range, the coronary artery motion change data corresponding to multiple candidate phases can be used to fit a coronary artery change curve corresponding to the preset reconstruction phase range. Specifically, the coronary artery motion change data can be interpolated to obtain coronary artery change values corresponding to more phase points, thereby improving the smoothness of the curve and eliminating the influence of interference factors on the curve. Furthermore, the minimum value corresponding to the coronary artery change curve is determined, and the phase corresponding to the minimum value is used as the optimal target cardiac phase. Subsequently, image reconstruction can be performed according to the target cardiac phase to obtain high-quality, low-artifact coronary artery images.

[0087] In the embodiment of the present application, in order to further improve the reliability of the optimal phase, optionally, step 103-4 may specifically include:

[0088] S1, using a preset cardiac contraction period as a first starting search point, searching for a first minimum extreme point within a first search phase range corresponding to the preset cardiac contraction period, and obtaining a phase corresponding to the first minimum extreme point as a first target cardiac phase, wherein the target cardiac phase includes the first target cardiac phase; and / or,

[0089] S2, taking the preset cardiac diastole as the second starting search point, searching for the second minimum extreme point within the second search phase range corresponding to the preset cardiac diastole, and obtaining the phase corresponding to the second minimum extreme point as the second target cardiac phase, wherein the target cardiac phase includes the second target cardiac phase.

[0090] In this embodiment, based on the heartbeat pattern, it is known that the optimal cardiac phase is generally the systolic period or the diastolic period. The approximate range of the systolic period and the diastolic period is fixed. Generally speaking, the systolic period is about 40% and the diastolic period is about 75%. Therefore, the systolic period and the diastolic period can be used as the starting search points to search for the target cardiac phase. Figure 4 In the schematic diagram of the coronary artery variation curve shown, the horizontal axis represents the phase, and the vertical axis represents the amount of coronary artery motion change, both measured in Hounsfield units (HU). A preset systolic period fSystoleLocate (e.g., 40%) and a preset diastolic period fDiastoleLocate (e.g., 75%), estimated based on empirical values, are used as the first starting search point, and the preset diastolic period fDiastoleLocate is used as the second starting search point. A first minimum point is found near the first search starting point (e.g., 30% to 50%), and a second minimum point is found near the second search starting point (e.g., 60% to 90%). The first and second minimum points are then used as the phases where the coronary artery motion is most gentle, i.e., the optimal systolic period OptimalSystole and the optimal diastolic period OptimalDiastole, i.e., the first and second target cardiac phases. This method can prevent the target cardiac phase from deviating from the reasonable range due to factors such as interference, thereby improving the reliability of the optimal phase.

[0091] In the embodiment of the present application, optionally, step 102 may specifically include:

[0092] Step 102-1, performing image segmentation on the multi-layer heart image to be segmented corresponding to each candidate period to obtain a multi-layer coronary artery region image corresponding to each candidate period;

[0093] Step 102 - 2 , smoothing the segmented edges of the multi-layer coronary artery region image corresponding to each candidate period to determine the coronary artery region image corresponding to each candidate period.

[0094] In this embodiment, the coronary artery region image can be obtained by a pre-trained model, such as Figure 2 As shown, a model is trained using a sample set to obtain a target region shape model, and a classifier is constructed using the model. The classifier is used to classify the coronary artery region in the input image. Specifically, after the image is input into the classifier, the classifier can classify whether each pixel in the image belongs to a coronary artery and generate a segmentation template (i.e., a coronary artery region). In actual application scenarios, when scanning the heart, a layered scan is generally performed. The reconstructed image corresponding to each candidate phase includes multiple layers of heart images to be segmented. Then, the coronary artery is segmented for each layer of the heart images to be segmented, and the edge feature points of each layer of coronary arteries obtained by segmentation are smoothed to make the edge feature points of the coronary artery regions in adjacent layers coherent and smooth. Thus, a three-dimensional coronary artery region image can be constructed based on the multiple layers of coronary artery region images corresponding to each candidate phase, and then the coronary artery motion change data can be calculated and the target heart phase phase can be acquired.

[0095] Furthermore, the present application also provides another method for obtaining cardiac phases, such as Figure 3 As shown, the method includes:

[0096] Step 201, obtaining a plurality of heart images to be segmented corresponding to candidate periods;

[0097] Step 202 , performing image segmentation on the heart image to be segmented corresponding to each candidate period to obtain a coronary artery region image corresponding to each candidate period;

[0098] Step 203, determining the heart centroid corresponding to each coronary artery regional image based on the coronary artery regional image corresponding to each candidate period;

[0099] Step 204: acquiring at least one target coronary artery region image in each of the coronary artery region images based on a positional relationship between the heart centroid and at least one target coronary artery, wherein the target coronary artery includes but is not limited to at least one of the right coronary artery, the left circumflex artery, and the left anterior descending artery;

[0100] Step 205 : determining coronary artery motion change data between candidate phases according to the target coronary artery region image, and acquiring a target cardiac phase based on the coronary artery motion change data.

[0101] In this embodiment, the coronary arteries primarily include the right coronary artery, the left anterior descending artery, and the left anterior descending artery. Since the motion variations of different coronary arteries may differ, in practical applications, the target cardiac phase can be found based on the overall motion variations of the coronary arteries, or based on the motion variations of one or more coronary arteries. After obtaining coronary artery regional images corresponding to multiple candidate phases, the cardiac centroid position can be determined first. The target coronary artery can then be identified based on actual needs. Furthermore, regional images of different target coronary arteries can be obtained based on the relationship between the cardiac centroid position and the position of the various target coronary arteries. The right coronary artery is generally located to the right of the cardiac centroid, the left anterior descending artery is located to the upper left of the cardiac centroid, and the left circumflex artery is located to the lower left of the cardiac centroid. Furthermore, during the target cardiac phase search, if there is only one target coronary artery, the target cardiac phase can be determined directly based on the motion variations of that one target coronary artery. If there are multiple target coronary arteries, multiple target cardiac phases can be determined based on the motion variations of each target coronary artery, and one of the multiple target cardiac phases can be selected as the final optimal phase. For example, the target coronary artery includes the left circumflex artery and the left anterior descending artery. By searching for the minimum point near the preset cardiac contraction period, it is determined that the target cardiac phase includes phase A corresponding to the left circumflex artery and phase B corresponding to the left anterior descending artery, and the phase closest to the preset cardiac contraction period is selected as the final optimal phase. Among them, the method for determining the motion change of the target coronary artery is similar to the method for determining the coronary artery motion change data mentioned above, and will not be repeated here. By searching for the optimal phase in this way, it is possible to avoid calculating the motion change of multiple coronary arteries as a whole, which causes the motion changes of multiple coronary arteries to cancel each other out, resulting in inaccurate description of the motion change, and further improves the accuracy of obtaining the target cardiac phase.

[0102] Further, as Figure 1 The specific implementation of the method, the embodiment of the present application provides a device for obtaining cardiac phase, such as Figure 5 As shown, the device includes:

[0103] An image acquisition module, configured to acquire heart images to be segmented corresponding to a plurality of candidate periods;

[0104] a coronary artery segmentation module, configured to perform image segmentation on the heart image to be segmented corresponding to each candidate period, to obtain a coronary artery region image corresponding to each candidate period;

[0105] The phase acquisition module is used to determine the coronary artery motion change data between each candidate phase according to the coronary artery regional image, and acquire the target cardiac phase based on the coronary artery motion change data.

[0106] Optionally, the image acquisition module is specifically configured to:

[0107] Acquiring cardiac scan data, wherein a scan phase range of the cardiac scan data is determined based on a preset reconstruction phase range;

[0108] The heart scan data corresponding to the preset reconstruction phase range is reconstructed according to the preset phase interval to determine the heart images to be segmented corresponding to a plurality of candidate phases.

[0109] Optionally, the phase acquisition module is specifically configured to:

[0110] Acquire a coronary artery region image i and a coronary artery region image i+1 corresponding to any two consecutive candidate phases, wherein the coronary artery region image i represents the coronary artery region image corresponding to candidate phase i, and the coronary artery region image i+1 represents the coronary artery region image corresponding to candidate phase i+1, and i is less than the number of candidate phases;

[0111] The intersection of the coronary artery region image i and the coronary artery region image i+1 is taken as the comparison image i+1, and the coronary artery motion change data corresponding to the candidate phase i to the candidate phase i+1 is determined.

[0112] Optionally, the phase acquisition module is specifically configured to:

[0113] Drawing a coronary artery change curve corresponding to the preset reconstruction phase range based on the coronary artery motion change data;

[0114] The phase corresponding to the minimum value in the coronary artery change curve is obtained as the target cardiac phase.

[0115] Optionally, the phase acquisition module is further configured to:

[0116] Using a preset cardiac contraction period as a first starting search point, searching for a first minimum extreme point within a first search phase range corresponding to the preset cardiac contraction period, and obtaining a phase corresponding to the first minimum extreme point as a first target cardiac phase, wherein the target cardiac phase includes the first target cardiac phase; and / or,

[0117] The preset cardiac diastole is used as the second starting search point, and a second minimum extreme point is searched within a second search phase range corresponding to the preset cardiac diastole, and the phase corresponding to the second minimum extreme point is obtained as the second target cardiac phase, wherein the target cardiac phase includes the second target cardiac phase.

[0118] Optionally, the coronary artery segmentation module is specifically configured to:

[0119] Performing image segmentation on the multi-layer heart images to be segmented corresponding to each candidate period to obtain multi-layer coronary artery region images corresponding to each candidate period;

[0120] Smoothing is performed on the segmented edges of the multi-layer coronary artery region image corresponding to each candidate period to determine the coronary artery region image corresponding to each candidate period.

[0121] Optionally, the coronary artery segmentation module is further configured to:

[0122] After obtaining the coronary artery regional image corresponding to each candidate period, determining the heart centroid corresponding to each coronary artery regional image based on the coronary artery regional image corresponding to each candidate period; and acquiring at least one target coronary artery regional image in each coronary artery regional image based on a positional relationship between the heart centroid and at least one target coronary artery;

[0123] Correspondingly, the phase acquisition module is further configured to determine the coronary artery motion change data between the candidate phases based on the target coronary artery region image.

[0124] It should be noted that for other corresponding descriptions of the functional units involved in the cardiac phase acquisition device provided in the embodiment of the present application, reference can be made to Figures 1 to 3 The corresponding description in the method will not be repeated here.

[0125] Based on the above Figures 1 to 3 The method shown in FIG. 1 is a method for performing the above-mentioned operation. Accordingly, the embodiment of the present application further provides a storage medium on which a computer program is stored. When the computer program is executed by a processor, the above-mentioned operation is performed. Figures 1 to 3 The method for obtaining the cardiac phase is shown.

[0126] Based on this understanding, the technical solution of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, USB flash drive, mobile hard disk, etc.), including a number of instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute the methods described in each implementation scenario of the present application.

[0127] Based on the above Figures 1 to 3 The method shown, and Figure 5 In order to achieve the above-mentioned purpose, the embodiment of the present application further provides a computer device, which can be a personal computer, a server, a network device, etc. The computer device includes a storage medium and a processor; the storage medium is used to store a computer program; the processor is used to execute the computer program to achieve the above-mentioned Figures 1 to 3 The method for obtaining the cardiac phase is shown.

[0128] Optionally, the computer device may further include a user interface, a network interface, a camera, a radio frequency (RF) circuit, a sensor, an audio circuit, a Wi-Fi module, etc. The user interface may include a display, an input unit such as a keyboard, etc., and the optional user interface may also include a USB interface, a card reader interface, etc. The network interface may optionally include a standard wired interface, a wireless interface (such as a Bluetooth interface, a Wi-Fi interface), etc.

[0129] Those skilled in the art will understand that the computer device structure provided in this embodiment does not constitute a limitation on the computer device, and may include more or fewer components, or a combination of certain components, or different component arrangements.

[0130] The storage medium may also include an operating system and a network communication module. An operating system is a program that manages and stores the hardware and software resources of a computer device, supporting the execution of information processing programs and other software and / or programs. The network communication module facilitates communication between components within the storage medium, as well as with other hardware and software within the physical device.

[0131] Through the description of the above embodiments, those skilled in the art can clearly understand that the present application can be implemented by means of software plus a necessary general hardware platform, or by means of hardware to reconstruct the scan data, obtain the cardiac images to be segmented corresponding to multiple candidate phases, and segment the coronary artery region images in the images, and further calculate the motion data of the coronary arteries between the candidate phases based on the coronary artery region images, so as to select the optimal target cardiac phase based on the change data. Compared with the prior art method in which doctors rely on experience or manually select images reconstructed from all phases, the embodiments of the present application can automatically obtain the optimal target cardiac phase based on the motion changes of the coronary arteries, so that a clear, low-artifact coronary artery image can be obtained by reconstructing the image of the target cardiac phase, which not only reduces the workload of doctors and the reliance on the doctor's experience, but also improves the efficiency and accuracy of image reconstruction.

[0132] Those skilled in the art will understand that the accompanying drawings are only schematic diagrams of a preferred implementation scenario, and the modules or processes in the accompanying drawings are not necessarily required to implement the present application. Those skilled in the art will understand that the modules in the devices in the implementation scenario can be distributed in the devices of the implementation scenario according to the implementation scenario description, or can be changed accordingly and located in one or more devices different from the implementation scenario. The modules of the above-mentioned implementation scenario can be combined into one module, or can be further split into multiple sub-modules.

[0133] The serial numbers of the above application are for descriptive purposes only and do not represent the advantages or disadvantages of the implementation scenarios. The above disclosure only discloses several specific implementation scenarios of the present application, but the present application is not limited thereto. Any changes that can be conceived by those skilled in the art should fall within the scope of protection of the present application.

Claims

1. A method for acquiring cardiac phases, characterized in that: include: Acquire a plurality of heart images to be segmented corresponding to candidate periods; performing image segmentation on the to-be-segmented heart image corresponding to each candidate period to obtain a coronary artery region image corresponding to each candidate period, the method further comprising: determining, based on the coronary artery region image corresponding to each candidate period, a heart centroid corresponding to each coronary artery region image; and obtaining, based on a positional relationship between the heart centroid and at least one target coronary artery, at least one target coronary artery region image in each of the coronary artery region images, each target coronary artery region image corresponding to a target coronary artery; Based on the coronary artery regional image, the coronary artery motion change data between each candidate phase is determined. Coronary artery motion change data between each candidate phase is determined accordingly based on the target coronary artery regional image, and a target cardiac phase is acquired based on the coronary artery motion change data. If the target coronary artery includes one type, the target cardiac phase is determined based on the coronary artery motion change data of one target coronary artery. If the target coronary artery includes multiple types, multiple target cardiac phases are first determined based on the coronary artery motion change data of each target coronary artery, and one target cardiac phase is selected from the multiple target cardiac phases as the final optimal phase.

2. The method according to claim 1, characterized in that The step of obtaining the heart images to be segmented corresponding to the plurality of phases specifically includes: Acquiring cardiac scan data, wherein a scan phase range of the cardiac scan data is determined based on a preset reconstruction phase range; The heart scan data corresponding to the preset reconstruction phase range is reconstructed according to the preset phase interval to determine the heart images to be segmented corresponding to a plurality of candidate phases.

3. The method according to claim 1, characterized in that Determining the coronary artery motion change data between candidate phases based on the coronary artery regional image specifically includes: Acquire a coronary artery regional image i and a coronary artery regional image i+1 corresponding to any two consecutive candidate phases, wherein the coronary artery regional image i represents the coronary artery regional image corresponding to candidate phase i, and the coronary artery regional image i+1 represents the coronary artery regional image corresponding to candidate phase i+1; taking the intersection of the coronary artery regional image i and the coronary artery regional image i+1 as a comparison template i, and determining coronary artery contour data i based on the coronary artery regional image i and the comparison template i, and determining coronary artery contour data i+1 based on the coronary artery regional image i+1 and the comparison template i; The coronary artery motion change data corresponding to the candidate phase i to the candidate phase i+1 is determined based on the coronary artery contour data i+1 and the coronary artery contour data i.

4. The method according to claim 2, characterized in that The step of acquiring a target cardiac phase based on the coronary artery motion change data specifically includes: Drawing a coronary artery change curve corresponding to the preset reconstruction phase range based on the coronary artery motion change data; The phase corresponding to the minimum value in the coronary artery change curve is obtained as the target cardiac phase.

5. The method according to claim 4, characterized in that The acquiring the phase corresponding to the minimum value in the coronary artery change curve as the target cardiac phase specifically includes: Using a preset cardiac contraction period as a first starting search point, searching for a first minimum extreme point within a first search phase range corresponding to the preset cardiac contraction period, and obtaining a phase corresponding to the first minimum extreme point as a first target cardiac phase, wherein the target cardiac phase includes the first target cardiac phase; and / or, The preset cardiac diastole is used as the second starting search point, and a second minimum extreme point is searched within a second search phase range corresponding to the preset cardiac diastole, and the phase corresponding to the second minimum extreme point is obtained as the second target cardiac phase, wherein the target cardiac phase includes the second target cardiac phase.

6. The method according to claim 1, characterized in that The performing image segmentation on the heart image to be segmented corresponding to each candidate period to obtain the coronary artery region image corresponding to each candidate period specifically includes: Performing image segmentation on the multi-layer heart images to be segmented corresponding to each candidate period to obtain multi-layer coronary artery region images corresponding to each candidate period; Smoothing is performed on the segmented edges of the multi-layer coronary artery region image corresponding to each candidate period to determine the coronary artery region image corresponding to each candidate period.

7. A cardiac phase acquisition device, used to perform the method according to any one of claims 1 to 6, characterized in that: include: An image acquisition module, configured to acquire heart images to be segmented corresponding to a plurality of candidate periods; a coronary artery segmentation module configured to perform image segmentation on the to-be-segmented cardiac image corresponding to each candidate period to obtain a coronary artery regional image corresponding to each candidate period, the method further comprising: determining, based on the coronary artery regional image corresponding to each candidate period, a heart centroid corresponding to each coronary artery regional image; and obtaining, based on a positional relationship between the heart centroid and at least one target coronary artery, at least one target coronary artery regional image in each of the coronary artery regional images, each target coronary artery regional image corresponding to a target coronary artery; A phase acquisition module is used to determine the coronary artery motion change data between each candidate phase based on the coronary artery regional image, and correspondingly, to determine the coronary artery motion change data between each candidate phase based on the target coronary artery regional image, and to acquire the target cardiac phase based on the coronary artery motion change data; wherein, if the target coronary artery includes one type, the target cardiac phase is determined based on the motion change of one target coronary artery; if the target coronary artery includes multiple types, multiple target cardiac phases are first determined based on the motion change of each target coronary artery, and one of the multiple target cardiac phases is selected as the final optimal phase.

8. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

9. A computer device comprising a storage medium, a processor, and a computer program stored on the storage medium and executable on the processor, wherein: When the processor executes the computer program, the method according to any one of claims 1 to 6 is implemented.

Images