Heart scanning control method and device, equipment, storage medium and program product

Abstract

The invention relates to a heart scanning control method and device, equipment, a storage medium and a program product, and the method comprises the steps: obtaining a heart monitoring image, positioning a candidate region where a target blood vessel is located from the heart monitoring image based on a pre-trained target positioning model, and determining a target region for CT value monitoring according to the candidate region, the target area is located in the blood vessel cavity of the target blood vessel, and when it is monitored that the CT value of the target area reaches a set threshold value, scanning equipment is triggered to conduct heart enhancement scanning. Therefore, the problems of inaccurate position and low efficiency caused by manual determination of the target area for CT value monitoring are avoided, the positioning of the target area for CT value monitoring is more accurate, and the scanning efficiency can be effectively improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of medical image processing, and in particular, to a heart scan control method and device, an electronic device, a computer readable storage medium, and a computer program product. BACKGROUND

[0002] With the continuous development of medical imaging technology, computed tomography (CT) has become an important means for diagnosing heart diseases. In heart CT enhanced scanning, in order to obtain high-quality vascular images, scanning needs to be performed at the best time when the contrast agent reaches the target blood vessel.

[0003] In the traditional technology, the widely used contrast agent tracking technology (Bolus Tracking) in the clinic is to place a region of interest (ROI) on a monitoring image, to monitor the CT value change of the region in real time, so as to trigger the enhanced scanning of the scanning device when the CT value reaches the best time.

[0004] However, in the traditional technology, the placement of the ROI highly depends on manual operation, and the operator needs to have rich experience and anatomical knowledge. For new operators or operators who do not often operate heart scans, it is difficult to accurately select the ROI, which can easily lead to inaccurate monitoring. SUMMARY

[0005] The present application provides a heart scan control method, device, electronic device, computer readable storage medium, and computer program product to at least solve the problem of difficult accurate selection of the ROI in the related art. The technical solutions of the present application are as follows: According to a first aspect of an embodiment of the present application, a heart scan control method is provided, and the method comprises: obtaining a heart monitoring image, the heart monitoring image being obtained by monitoring scanning a heart region; locating a candidate region where a target blood vessel is located from the heart monitoring image based on a pre-trained target positioning model; determining a target region for CT value monitoring according to the candidate region, the target region being located inside a blood vessel cavity of the target blood vessel; triggering a heart enhanced scan of a scanning device in a case where a CT value of the target region reaches a set threshold.

[0006] In one of the embodiments, the method further comprises: determining a center of the candidate region; generating a candidate target region according to the center and a shape and size of a preset standard region; and determining the candidate target region as the target region for CT value monitoring in a case where the candidate target region satisfies a region condition.

[0007] In one of the embodiments, the method further comprises: in a case where the candidate target region does not satisfy the region condition, reducing the candidate target region; and determining the target region for CT value monitoring based on the reduced candidate target region.

[0008] In one of the embodiments, the candidate region comprises a plurality of candidate regions; and the method of determining the center of the candidate region comprises: obtaining areas of the plurality of candidate regions; determining a candidate region with an area greater than or equal to a first area threshold and less than or equal to a second area threshold as a final candidate region, the first area threshold being less than the second area threshold; and determining the center from the final candidate region.

[0009] In one of the embodiments, the candidate region comprises a plurality of candidate regions; and the method of determining the center of the candidate region comprises: obtaining circularities of the plurality of candidate regions; determining a candidate region with a circularity greater than a circularity threshold as a final candidate region; and determining the center from the final candidate region.

[0010] In one of the embodiments, the center of the candidate region comprises any one of a center point or a geometric center of the candidate region.

[0011] In one of the embodiments, the method further comprises: in a case where the candidate target region satisfies the region condition, obtaining an image feature of the candidate target region; determining the candidate target region as the target region for CT value monitoring in a case where the image feature satisfies a set condition; and determining a predefined region as the target region for CT value monitoring in a case where the image feature does not satisfy the set condition.

[0012] In one of the embodiments, the image feature comprises an image standard deviation; and the method further comprises: determining that the image feature of the candidate target region satisfies the set condition in a case where the image standard deviation of the candidate target region is greater than or equal to a first standard deviation threshold and less than or equal to a second standard deviation threshold; and determining that the image feature of the candidate target region does not satisfy the set condition in a case where the image standard deviation of the candidate target region is less than the first standard deviation threshold or in a case where the image standard deviation of the candidate target region is greater than the second standard deviation threshold.

[0013] In one embodiment, the image features include image texture features; the method further includes: if the image texture features of the candidate target region are determined to be normal, determining that the image features of the candidate target region meet a set condition; if the image texture features of the candidate target region are determined to be abnormal, determining that the image features of the candidate target region do not meet the set condition.

[0014] In one embodiment, the method further includes: determining positive feedback samples based on identifying the candidate target region as the target region for CT value monitoring; determining negative feedback samples based on identifying a predefined region as the target region for CT value monitoring; and optimizing the target localization model based on the positive feedback samples and the negative feedback samples.

[0015] In one embodiment, triggering the scanning device to perform a cardiac enhancement scan when the CT value of the target area is detected to reach a set threshold includes: sending a scan trigger command to the scanning device when the CT value of the target area is detected to reach the set threshold, the scan trigger command being used to instruct the scanning device to perform a cardiac enhancement scan.

[0016] In one embodiment, the scan trigger command carries a scan delay duration, which is used to instruct the scanning device to perform a cardiac enhancement scan based on the scan delay duration after receiving the scan trigger command.

[0017] In one embodiment, sending a scan trigger command to the scanning device includes: sending a scan trigger command to the scanning device when a preset scan delay duration is reached.

[0018] In one embodiment, the target localization model is trained by: acquiring a sample CT image in which a first location of the target blood vessel is marked; inputting the sample CT image into a deep learning recognition model to obtain a second location of the target blood vessel output by the deep learning recognition model; determining the difference between the second location and the first location; and training the deep learning recognition model based on the difference to obtain the target localization model.

[0019] In one embodiment, the sample CT images include CT images of different body types and different pathological conditions; the deep learning recognition model is implemented using a convolutional neural network.

[0020] According to a second aspect of the embodiments of this application, a cardiac scanning control device is provided, comprising: The image acquisition module is configured to acquire cardiac monitoring images, which are obtained by monitoring and scanning the cardiac region. The region localization module is configured to execute a pre-trained target localization model to locate the candidate region where the target blood vessel is located from the cardiac monitoring image; The region determination module is configured to determine a target region for CT value monitoring based on the candidate regions, wherein the target region is located inside the lumen of the target blood vessel; The scan trigger module is configured to trigger the scanning device to perform a cardiac enhancement scan when the CT value of the target area is detected to reach a set threshold.

[0021] In one embodiment, the region determination module is further configured to perform: determining the center of the candidate region; generating a candidate target region based on the center and the shape and size of a preset standard region; and determining the candidate target region as the target region for CT value monitoring if the candidate target region meets the region conditions.

[0022] In one embodiment, the region determination module is further configured to perform: narrowing down the candidate target region if it is determined that the candidate target region does not meet the region conditions; and determining the target region for CT value monitoring based on the narrowed candidate target region.

[0023] In one embodiment, the candidate regions include a plurality of regions; the region determination module is further configured to perform: obtaining the area of ​​the plurality of candidate regions; determining the candidate regions whose area is greater than or equal to a first area threshold and less than or equal to a second area threshold as final candidate regions, wherein the first area threshold is less than the second area threshold; and determining a center from the final candidate regions.

[0024] In one embodiment, the candidate regions include a plurality of regions; the region determination module is further configured to perform: obtaining the circularity of the plurality of candidate regions; determining the candidate regions with a circularity greater than a circularity threshold as final candidate regions; and determining a center from the final candidate regions.

[0025] In one embodiment, the region determination module is further configured to perform: if the candidate target region satisfies the region conditions, acquire the image features of the candidate target region; if the image features satisfy the set conditions, determine the candidate target region as the target region for CT value monitoring; if the image features do not satisfy the set conditions, determine the predefined region as the target region for CT value monitoring.

[0026] In one embodiment, the scan trigger module is further configured to: when the CT value of the target area is detected to reach a set threshold, send a scan trigger command to the scanning device, the scan trigger command being used to instruct the scanning device to perform a cardiac enhancement scan.

[0027] According to a third aspect of the embodiments of this application, a cardiac scanning system is provided, including the cardiac scanning control device and scanning device described in the second aspect above, wherein the scanning device performs cardiac enhancement scanning based on the triggering of the cardiac scanning control device.

[0028] According to a fourth aspect of the present application, an electronic device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the method described in the first aspect above.

[0029] According to a fifth aspect of the present application, a computer-readable storage medium is provided, on which a computer program is stored, wherein the computer program, when executed by a processor, implements the steps of the method described in the first aspect above.

[0030] According to a sixth aspect of the embodiments of this application, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps of the method described in the first aspect above.

[0031] The technical solution provided by the embodiments of this application brings at least the following beneficial effects: by acquiring cardiac monitoring images and locating candidate regions of target blood vessels from the cardiac monitoring images based on pre-trained target localization models, the target region for CT value monitoring is determined according to the candidate regions. The target region is located inside the lumen of the target blood vessel. When the CT value of the target region reaches a set threshold, the scanning device is triggered to perform a cardiac enhancement scan. This avoids the problems of inaccurate positioning and low efficiency caused by manually determining the target region for CT value monitoring, making the localization of the target region for CT value monitoring more accurate and effectively improving scanning efficiency.

[0032] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Attached Figure Description

[0033] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application, and do not constitute an undue limitation of this application.

[0034] Figure 1 This is an application environment diagram illustrating a cardiac scan control method according to an exemplary embodiment.

[0035] Figure 2 This is a flowchart illustrating a cardiac scan control method according to an exemplary embodiment.

[0036] Figure 3 This is a flowchart illustrating the steps of determining a target region according to an exemplary embodiment.

[0037] Figure 4 This is a flowchart illustrating the steps for validating a candidate target region according to an exemplary embodiment.

[0038] Figure 5 This is a block diagram illustrating a cardiac scanning control device according to an exemplary embodiment.

[0039] Figure 6 This is a block diagram illustrating an electronic device according to an exemplary embodiment. Detailed Implementation

[0040] To enable those skilled in the art to better understand the technical solutions of this application, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings.

[0041] It should be noted that the terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0042] It should also be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for display, data used for analysis, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0043] Because traditional ROI (Region of Interest) location relies heavily on manual operation, it requires operators with extensive experience and anatomical knowledge. For new operators or those inexperienced in cardiac scanning, accurately selecting ROIs can be difficult, easily leading to inaccurate monitoring. Furthermore, in busy radiology environments, this repetitive manual ROI selection consumes a significant amount of time, reducing efficiency. Additionally, differences in operator habits and experience levels result in inconsistencies in ROI location and size, affecting the standardization of scan trigger point selection and ultimately causing fluctuations in image quality, which is detrimental to the consistency and accuracy of clinical diagnosis.

[0044] Secondly, if the ROI is improperly located, such as on calcified plaques, the vessel wall, or adjacent structures (e.g., the pulmonary artery), the monitored CT value changes will not accurately reflect the contrast agent concentration within the aortic lumen, potentially leading to inappropriate scan triggering timing (e.g., triggering too early before the contrast agent reaches its peak or triggering too late after the peak). Both premature and delayed triggering will affect image quality, reduce diagnostic value, and in severe cases, may even require a second scan, thereby increasing radiation dose and contrast agent usage.

[0045] Based on this, this application provides a cardiac scan control method that can be applied to, for example... Figure 1 In the application environment shown, terminal 110 communicates with scanning device 120 via a network. Terminal 110 can be, but is not limited to, various personal computers, laptops, smartphones, tablets, IoT devices, and portable wearable devices. Scanning device 120 can be an image acquisition device for acquiring medical images, such as a CT scanner.

[0046] Terminal 110 acquires cardiac monitoring images obtained by scanning device 120 performing low-dose dynamic monitoring scans on the target object's cardiac region, and locates candidate regions containing the target blood vessels from the cardiac monitoring images based on a pre-trained target localization model. Based on the candidate regions, it determines the target region for CT value monitoring, wherein the target region is located inside the lumen of the target blood vessel. When the CT value of the target region reaches a set threshold, it triggers scanning device 120 to perform a cardiac enhancement scan. This avoids the problems of inaccurate positioning and low efficiency caused by manually determining the target region.

[0047] In one embodiment, such as Figure 2 As shown, a cardiac scan control method is provided. This embodiment illustrates the application of this method to a terminal. In this embodiment, the method may include the following steps: In step S210, a cardiac monitoring image is acquired.

[0048] The cardiac monitoring image is obtained by monitoring and scanning the cardiac region. This can be a CT scan or an MRI (Magnetic Resonance Imaging) image, allowing for enhanced scanning by tracking the arrival time of the contrast agent. Specifically, after the contrast agent is injected into the target subject, a preliminary scan of the cardiac region can be performed using scanning equipment (such as a CT scanner or MRI scanner) to obtain a cardiac monitoring image containing the heart and surrounding blood vessels. The terminal can then acquire the cardiac monitoring image from the scanning equipment for subsequent target vessel localization and contrast agent monitoring.

[0049] In step S220, the candidate region where the target blood vessel is located is located from the cardiac monitoring image based on the pre-trained target localization model.

[0050] The target localization model can be trained using deep learning methods. During training, sample CT images are first acquired, in which the first location of the target vessel is already labeled. Target vessels include, but are not limited to, the ascending aorta, aortic arch, and descending aorta. Specifically, these sample CT images can include CT images of different body types and different pathological conditions (such as aneurysms, calcifications, etc.) to ensure the model's generalization ability. Then, the sample CT images are input into the deep learning recognition model to obtain the second location of the target vessel, output by the deep learning recognition model. The deep learning recognition model can be implemented using a convolutional neural network to improve the model's ability to extract image features. The difference between the second and first locations is then determined, and the deep learning recognition model is trained based on this difference, ultimately obtaining the trained target localization model. The target localization model trained in this way can adapt to various anatomical variations and pathological conditions of different users, thus exhibiting stronger stability.

[0051] Candidate regions are areas where target blood vessels are located from cardiac monitoring images based on pre-trained target localization models. For example, they may include at least one of the regions where the ascending aorta, the aortic arch, and the descending aorta are located.

[0052] In one scenario, the candidate region can be a precise pixel-level segmentation mask of the region where the target blood vessel is located, or it can be the bounding box of the region where the target blood vessel is located. This embodiment does not limit this.

[0053] In this embodiment, the terminal may be loaded with a target localization model trained as described above. After obtaining the cardiac monitoring image through the above steps, the terminal can also locate the candidate region where the target blood vessel is located from the cardiac monitoring image based on the target localization model.

[0054] In step S230, the target area for CT value monitoring is determined based on the candidate areas.

[0055] CT value, or CT value, is an indicator used in computed tomography (CT) images to quantify the degree of X-ray absorption by tissue, reflecting tissue density. It is measured in Hounsfield Units (HU) and is also known as contrast agent concentration. The target region is the final area determined based on candidate regions for CT value (i.e., contrast agent concentration) monitoring. The target region is located inside the lumen of the target blood vessel, thus avoiding contact with the vessel wall and improving the accuracy of subsequent contrast agent monitoring.

[0056] Specifically, the terminal can determine the target area for CT value monitoring based on the candidate area, and perform CT value monitoring based on subsequent steps to trigger the scanning device to perform cardiac enhancement scanning.

[0057] In step S240, when the CT value of the target area is detected to reach a set threshold, the scanning device is triggered to perform a cardiac enhancement scan.

[0058] The threshold setting can be a pre-defined optimal concentration of contrast agent used for cardiac enhancement scanning. For example, the threshold setting can be any value between 100 HU and 150 HU, and can be set according to the actual scenario.

[0059] In this embodiment, the terminal can monitor the CT value of the target area determined in the above steps in real time, and trigger the scanning device to perform cardiac enhancement scanning when the CT value of the target area reaches a set threshold in order to obtain scanning data.

[0060] In the aforementioned cardiac scanning control method, the terminal acquires cardiac monitoring images and, based on a pre-trained target localization model, locates candidate regions containing target blood vessels from these images. Based on these candidate regions, the target region for CT value monitoring is determined. This target region is located inside the lumen of the target blood vessel. When the CT value of the target region reaches a set threshold, the scanning device is triggered to perform a cardiac enhancement scan. This avoids the inaccuracies and inefficiencies caused by manually determining the target region for CT value monitoring, resulting in more precise localization of the target region and significantly improved scanning efficiency.

[0061] In one exemplary embodiment, such as Figure 3 As shown, in step S230, the target area for CT value monitoring is determined based on the candidate area, which can be achieved through the following steps: In step S310, the center of the candidate region is determined.

[0062] The center of the candidate region can be either the center point or the geometric center of the candidate region. Specifically, the candidate regions obtained by the target localization model can be one or more. When there is only one candidate region, the center of the candidate region can be determined directly, and the target region can be further determined based on subsequent steps.

[0063] In one scenario, when there are multiple candidate regions, the areas of these regions can be acquired, and a final candidate region can be determined based on the area of ​​each candidate region. Specifically, candidate regions with an area greater than or equal to a first area threshold and less than or equal to a second area threshold can be identified as final candidate regions, and a center can be determined from these final candidate regions. The first area threshold is less than the second area threshold. The first and second area thresholds can be pre-set minimum and maximum areas for filtering the final candidate regions. For example, the first area threshold could be 50 mm², and the second area threshold could be 500 mm², thus excluding candidate regions with an area less than 50 mm² or an area greater than 500 mm². This improves the quality of subsequent target regions by excluding abnormal regions with excessively small or large areas.

[0064] In one scenario, when there are multiple candidate regions, the roundness of each candidate region can be obtained, and the final candidate region can be determined based on the roundness of each candidate region. Specifically, candidate regions with a roundness greater than a roundness threshold can be determined as the final candidate regions, and the center can be determined from the final candidate regions. The roundness threshold can be a pre-set condition for filtering the final candidate regions. For example, the roundness threshold could be 0.7, meaning that candidate regions with a roundness less than or equal to 0.7 are excluded, while circular or elliptical candidate regions with a roundness greater than 0.7 are preferentially selected as the final candidate regions to improve the quality of subsequent target regions.

[0065] In one scenario, when there are multiple candidate regions, abnormal regions that are too small or too large can be excluded based on their area. If multiple candidate regions remain after excluding abnormal regions, then regions with a roundness greater than a roundness threshold can be prioritized as final candidate regions based on their roundness. If multiple final candidate regions are still selected based on roundness, a unique final candidate region can be determined based on the priority of the target blood vessel corresponding to each final candidate region. For example, if the priority of the target blood vessels from high to low is: ascending aorta, aortic arch, descending aorta, then the region containing the ascending aorta can be prioritized as the unique final candidate region from among the multiple final candidate regions. This improves the quality of subsequent target regions.

[0066] In one scenario, the following steps can also be performed based on multiple final candidate regions to generate multiple candidate target regions and determine the target region for CT value monitoring from the multiple candidate target regions.

[0067] In step S320, candidate target regions are generated based on the shape and size of the center and the preset standard region.

[0068] The preset standard area can be a pre-defined area with a standard shape (such as a circle or square) and a standard size (such as a diameter or side length of 10mm-20mm). The candidate target area can be an area initially generated based on the center of the aforementioned candidate area or final candidate area, as well as the shape and size of the preset standard area. For example, if the standard shape of the preset standard area is a circle and the standard size is a diameter of 10mm, a circular area with a diameter of 10mm can be generated based on the center of the aforementioned candidate area or final candidate area as the center of the target area. This circular area is the candidate target area.

[0069] In step S330, it is determined whether the candidate target region meets the region conditions.

[0070] The regional conditions include the location conditions corresponding to the region. For example, if it is determined that the candidate target region is located inside the lumen of the target blood vessel, and the shortest distance between the boundary of the candidate target region and the wall of the target blood vessel is greater than or equal to a distance threshold, then the candidate target region can be determined to meet the regional conditions. If the regional conditions are met, step S340 is executed.

[0071] If the candidate target region is not located inside the lumen of the target blood vessel, or if the candidate target region is located inside the lumen of the target blood vessel but the shortest distance between the boundary of the candidate target region and the wall of the target blood vessel is less than a distance threshold, then the candidate target region is determined not to meet the region condition. If the region condition is not met, then step S350 is executed.

[0072] In step S340, if the candidate target area meets the regional conditions, the candidate target area is determined as the target area for CT value monitoring.

[0073] Specifically, if the terminal determines that the candidate target area meets the regional conditions, it can then identify the candidate target area as the target area for CT value monitoring.

[0074] In step S350, if it is determined that the candidate target region does not meet the region conditions, the candidate target region is narrowed down.

[0075] Specifically, if the terminal determines that the candidate target area does not meet the area conditions, it can narrow down the candidate target area and return to step S330 to determine whether the narrowed candidate target area meets the area conditions. Only if the narrowed candidate target area meets the area conditions can it be determined as the target area for CT value monitoring.

[0076] In this embodiment, by determining the center of the candidate region, a candidate target region is generated based on the center and the shape and size of a preset standard region. It is then determined whether the candidate target region meets the region conditions, and the candidate target region that meets the region conditions is determined as the target region for CT value monitoring. If the candidate target region does not meet the region conditions, the candidate target region is dynamically reduced. This ensures that the final target region for CT value monitoring is completely located inside the blood vessel lumen, avoiding contact with the blood vessel, and ensuring that the target region maintains a sufficient safe distance from the blood vessel wall, preventing the monitoring results from being affected by the blood vessel wall.

[0077] In one exemplary embodiment, such as Figure 4 As shown, in step S340, if the candidate target region is determined to meet the region conditions, the above method may further include the following steps: In step S410, image features of the candidate target region are obtained.

[0078] The image features may include at least one of image standard deviation and image texture features. Specifically, if the terminal determines that the candidate target region meets the regional conditions based on the above steps, it can further acquire the image features of the candidate target region.

[0079] In step S420, it is determined whether the image features meet the set conditions.

[0080] In one scenario, taking image features including image standard deviation as an example, if the image standard deviation of a candidate target region is greater than or equal to a first standard deviation threshold and less than or equal to a second standard deviation threshold, then the image features of the candidate target region can be determined to meet the set conditions. If the image standard deviation of a candidate target region is less than the first standard deviation threshold, or if the image standard deviation of a candidate target region is greater than the second standard deviation threshold, then the image features of the candidate target region can be determined to not meet the set conditions. Here, the first standard deviation threshold is less than the second standard deviation threshold. The first and second standard deviation thresholds can be pre-set image feature conditions used to verify the validity of candidate target regions. For example, the first standard deviation threshold could be 15 HU, and the second standard deviation threshold could be 50 HU. If the image standard deviation of a candidate target region is too low, it indicates that the candidate target region may be located on homogeneous tissue rather than a blood flow area, which is detrimental to the accurate monitoring of the contrast agent.

[0081] In one scenario, taking image features including image texture features as an example, if the image texture features of the candidate target region are determined to be normal, then the image features of the candidate target region can be determined to meet the set conditions. If the image texture features of the candidate target region are determined to be abnormal, then the image features of the candidate target region can be determined to not meet the set conditions. Abnormal image texture features include, but are not limited to, chaotic image textures or the presence of multiple different tissues; it can also be a case where the local CT value in the image of the candidate target region is too high. If the local CT value in the image is greater than a certain set value (e.g., 130 HU), it indicates that the corresponding area of ​​the image may contain calcified plaques, which is detrimental to the accurate monitoring of the contrast agent.

[0082] Therefore, this embodiment achieves accurate monitoring of the contrast agent by eliminating candidate target regions that do not meet the set conditions and only selecting candidate target regions that meet the set conditions as the basis for determining subsequent target regions.

[0083] In step S430, if the image features meet the set conditions, the candidate target region is determined as the target region for CT value monitoring.

[0084] Specifically, when the terminal determines that the image features meet the set conditions, it identifies the candidate target area as the target area for CT value monitoring, so as to achieve accurate monitoring of the contrast agent.

[0085] In step S440, if it is determined that the image features do not meet the set conditions, the predefined area is determined as the target area for CT value monitoring.

[0086] The predefined region can be a region that is relatively located based on anatomical landmarks. Its position can be 10-20 mm below the tracheal bifurcation on the axial image.

[0087] Specifically, if the terminal determines that the image features do not meet the set conditions, it can identify a predefined area as the target area for CT value monitoring in order to achieve accurate monitoring of the contrast agent.

[0088] In this embodiment, the validity of the candidate target region is verified by the image features of the candidate target region, so that the location of the finally determined target region is more accurate, effectively avoiding scan failure caused by the target region being located on the blood vessel wall, calcified plaque or adjacent blood vessel, and greatly improving the success rate of the examination.

[0089] In an exemplary embodiment, the method may further include: determining positive feedback samples based on identifying candidate target regions as target regions for CT value monitoring; determining negative feedback samples based on identifying predefined regions as target regions for CT value monitoring; and optimizing the target localization model based on the positive and negative feedback samples. This adaptive optimization mechanism enables the target localization model to continuously learn and self-optimize, thereby improving the accuracy and reliability of the target localization model.

[0090] In an exemplary embodiment, in step S240, when the CT value of the target area is detected to reach a set threshold, the scanning device is triggered to perform a cardiac enhancement scan. Specifically, this may include sending a scan trigger command to the scanning device when the CT value of the target area is detected to reach the set threshold. The scan trigger command is used to instruct the scanning device to perform a cardiac enhancement scan.

[0091] In one scenario, the scan trigger command can include a scan delay duration. This delay duration instructs the scanning device to perform a cardiac enhancement scan after receiving the scan trigger command, based on the delay duration. This allows for precise control over the timing of the enhancement scan, ensuring that the scan occurs when the contrast agent reaches the optimal imaging position.

[0092] In one scenario, when the terminal detects that the CT value of the target area has reached a set threshold, it can send a scan trigger command to the scanning device only after a preset scan delay has elapsed. This allows for precise control over the timing of the contrast-enhanced scan, ensuring that the scan is performed when the contrast agent reaches the optimal imaging position.

[0093] The above methods enable precise control of contrast-enhanced cardiac scans, improving image quality, reducing unnecessary radiation exposure, and decreasing contrast agent usage, providing users with a safer and more effective examination experience. Furthermore, they eliminate manual operation steps, significantly shorten preparation time, reduce operational differences between different operators and equipment, improve the efficiency of the radiology department's workflow, and alleviate the workload of operators.

[0094] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages in other steps. It is understood that the steps in different embodiments can be freely combined as needed, and all non-contradictory solutions formed by such combinations are within the scope of protection of this application.

[0095] Based on the same inventive concept, this application also provides a cardiac scan control device for implementing the cardiac scan control method described above. The solution provided by this device is similar to the implementation described in the above method; therefore, the specific limitations in one or more cardiac scan control device embodiments provided below can be found in the limitations of the cardiac scan control method described above, and will not be repeated here.

[0096] In one exemplary embodiment, such as Figure 5 As shown, a cardiac scanning control device is provided, comprising: an image acquisition module 502, a region positioning module 504, a region determination module 506, and a scan triggering module 508, wherein: The image acquisition module 502 is configured to acquire a cardiac monitoring image, which is obtained by monitoring and scanning the cardiac region. The region localization module 504 is configured to execute a pre-trained target localization model to locate the candidate region where the target blood vessel is located from the cardiac monitoring image; The region determination module 506 is configured to determine a target region for CT value monitoring based on the candidate regions, wherein the target region is located inside the lumen of the target blood vessel; The scan trigger module 508 is configured to trigger the scanning device to perform a cardiac enhancement scan when the CT value of the target area is detected to reach a set threshold.

[0097] In an exemplary embodiment, the region determination module is further configured to perform: determining the center of the candidate region; generating a candidate target region based on the center and the shape and size of a preset standard region; and determining the candidate target region as the target region for CT value monitoring if the candidate target region meets the region conditions.

[0098] In an exemplary embodiment, the region determination module is further configured to perform: narrowing down the candidate target region if it is determined that the candidate target region does not meet the region conditions; and determining the target region for CT value monitoring based on the narrowed candidate target region.

[0099] In an exemplary embodiment, the candidate regions include a plurality of regions; the region determination module is further configured to perform: obtaining the area of ​​the plurality of candidate regions; determining the candidate regions whose area is greater than or equal to a first area threshold and less than or equal to a second area threshold as final candidate regions, wherein the first area threshold is less than the second area threshold; and determining a center from the final candidate regions.

[0100] In an exemplary embodiment, the candidate regions include a plurality of regions; the region determination module is further configured to perform: obtaining the circularity of the plurality of candidate regions; determining the candidate regions whose circularity is greater than a circularity threshold as final candidate regions; and determining a center from the final candidate regions.

[0101] In one exemplary embodiment, the center of the candidate region includes either the center point of the candidate region or the geometric center.

[0102] In an exemplary embodiment, the region determination module is further configured to perform: if it is determined that the candidate target region meets the region conditions, acquiring the image features of the candidate target region; if it is determined that the image features meet the set conditions, determining the candidate target region as the target region for CT value monitoring; if it is determined that the image features do not meet the set conditions, determining a predefined region as the target region for CT value monitoring.

[0103] In an exemplary embodiment, the image features include image standard deviation; the region determination module is further configured to: determine that the image features of the candidate target region satisfy a set condition if the image standard deviation of the candidate target region is greater than or equal to a first standard deviation threshold and less than or equal to a second standard deviation threshold; and determine that the image features of the candidate target region do not satisfy the set condition if the image standard deviation of the candidate target region is less than the first standard deviation threshold, or if the image standard deviation of the candidate target region is greater than the second standard deviation threshold.

[0104] In an exemplary embodiment, the image features include image texture features; the region determination module is further configured to: if the image texture features of the candidate target region are determined to be normal, determine that the image features of the candidate target region meet the set conditions; if the image texture features of the candidate target region are determined to be abnormal, determine that the image features of the candidate target region do not meet the set conditions.

[0105] In an exemplary embodiment, the apparatus further includes a model optimization module configured to perform: determining positive feedback samples based on identifying the candidate target region as a target region for CT value monitoring; determining negative feedback samples based on identifying a predefined region as a target region for CT value monitoring; and optimizing the target localization model based on the positive feedback samples and the negative feedback samples.

[0106] In an exemplary embodiment, the scan triggering module is further configured to: send a scan triggering command to the scanning device when the CT value of the target area is detected to reach a set threshold, the scan triggering command being used to instruct the scanning device to perform a cardiac enhancement scan.

[0107] In one exemplary embodiment, the scan trigger command carries a scan delay duration, which is used to instruct the scanning device to perform a cardiac enhancement scan based on the scan delay duration after receiving the scan trigger command.

[0108] In an exemplary embodiment, the scan triggering module is further configured to: when the CT value of the target area is detected to reach a set threshold, send a scan trigger command to the scanning device when a preset scan delay time is reached.

[0109] In an exemplary embodiment, the apparatus further includes a model training module configured to perform: acquiring a sample CT image in which a first location of a target blood vessel is marked; inputting the sample CT image into a deep learning recognition model to obtain a second location of the target blood vessel output by the deep learning recognition model; determining the difference between the second location and the first location; and training the deep learning recognition model based on the difference to obtain the target localization model.

[0110] In one exemplary embodiment, the sample CT images include CT images of different body types and different pathological conditions; the deep learning recognition model is implemented using a convolutional neural network.

[0111] Each module in the aforementioned cardiac scanning control device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of a computer device in hardware form or independent of it, or stored in the memory of a computer device in software form, so that the processor can call and execute the corresponding operations of each module.

[0112] Based on the same inventive concept, embodiments of this application also provide a cardiac scanning system for implementing the cardiac scanning control method described above. It includes, for example: Figure 5 The illustrated cardiac scan control device and scanning equipment perform enhanced cardiac scans based on triggers from the cardiac scan control device. The solution provided by this system is similar to the solution described in the above method; for details, please refer to the limitations of the cardiac scan control method above, which will not be repeated here.

[0113] In one exemplary embodiment, an electronic device is provided, the internal structure of which can be shown as follows: Figure 6 As shown, this electronic device includes a processor, memory, input / output interface, communication interface, display unit, and input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interface. The processor provides computing and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The input / output interface is used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, Near Field Communication (NFC), or other technologies. When the computer program is executed by the processor, it implements a cardiac scan control method. The display unit is used to form a visually visible image and can be a display screen, projection device, or virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the electronic device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the electronic device, or external keyboards, touchpads, or mice, etc.

[0114] Those skilled in the art will understand that Figure 6The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the electronic device to which the present application is applied. The specific electronic device may include more or fewer components than shown in the figure, or combine certain components, or have different component arrangements.

[0115] In one exemplary embodiment, an electronic device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0116] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps in the above method embodiments.

[0117] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0118] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0119] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0120] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0121] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A cardiac scanning control method, characterized in that, The method includes: Acquire cardiac monitoring images, which are obtained by monitoring and scanning the cardiac region; Based on a pre-trained target localization model, candidate regions containing target blood vessels are located from the cardiac monitoring images; Based on the candidate regions, a target region for CT value monitoring is determined, wherein the target region is located inside the lumen of the target blood vessel; If the CT value of the target area reaches a set threshold, the scanning device is triggered to perform a cardiac enhancement scan.

2. The method according to claim 1, characterized in that, The step of determining the target area for CT value monitoring based on the candidate areas includes: Determine the center of the candidate region; Based on the center and the shape and size of the preset standard area, candidate target areas are generated; If the candidate target region is determined to meet the regional conditions, the candidate target region is determined as the target region for CT value monitoring.

3. The method according to claim 2, characterized in that, The method further includes: If it is determined that the candidate target region does not meet the region conditions, the candidate target region is narrowed down; The target area for CT value monitoring is determined based on the narrowed candidate target area.

4. The method according to claim 2, characterized in that, The candidate regions include multiple regions; determining the center of the candidate regions includes: Obtain the area of ​​multiple candidate regions; The candidate regions whose areas are greater than or equal to a first area threshold and less than or equal to a second area threshold are determined as the final candidate regions, wherein the first area threshold is less than the second area threshold. The center is determined from the final candidate region.

5. The method according to claim 2, characterized in that, The candidate regions include multiple regions; determining the center of the candidate regions includes: Obtain the circularity of multiple candidate regions; Candidate regions with a circularity greater than a circularity threshold are identified as final candidate regions. The center is determined from the final candidate region.

6. The method according to claim 2, characterized in that, The center of the candidate region includes either the center point of the candidate region or the geometric center.

7. The method according to claim 2, characterized in that, When the candidate target region is determined to meet the regional conditions, the method further includes: Obtain the image features of the candidate target region; If the image features meet the set conditions, the candidate target region is determined as the target region for CT value monitoring. If the image features do not meet the set conditions, the predefined region will be determined as the target region for CT value monitoring.

8. The method according to claim 7, characterized in that, The image features include the image standard deviation; the method further includes: If the image standard deviation of the candidate target region is greater than or equal to a first standard deviation threshold and less than or equal to a second standard deviation threshold, the image features of the candidate target region are determined to meet the set conditions. If the standard deviation of the image of the candidate target region is less than the first standard deviation threshold, or if the standard deviation of the image of the candidate target region is greater than the second standard deviation threshold, the image features of the candidate target region are determined not to meet the set conditions.

9. The method according to claim 7, characterized in that, The image features include image texture features; the method further includes: If the image texture features of the candidate target region are determined to be normal, then the image features of the candidate target region are determined to meet the set conditions. If the image texture features of the candidate target region are determined to be abnormal, the image features of the candidate target region are determined not to meet the set conditions.

10. The method according to claim 7, characterized in that, The method further includes: Based on identifying the candidate target region as the target region for CT value monitoring, positive feedback samples are determined. Based on defining a predefined region as the target region for CT value monitoring, negative feedback samples are determined. The target localization model is optimized based on the positive feedback samples and the negative feedback samples.

11. The method according to any one of claims 1 to 10, characterized in that, The step of triggering a cardiac enhancement scan when the CT value of the target area reaches a set threshold includes: When the CT value of the target area is detected to reach a set threshold, a scan trigger command is sent to the scanning device, which instructs the scanning device to perform a cardiac enhancement scan.

12. The method according to claim 11, characterized in that, The scan trigger command carries a scan delay duration, which is used to instruct the scanning device to perform a cardiac enhancement scan based on the scan delay duration after receiving the scan trigger command.

13. The method according to claim 11, characterized in that, Sending a scan trigger command to the scanning device includes: When the preset scan delay time is reached, a scan trigger command is sent to the scanning device.

14. The method according to any one of claims 1 to 10, characterized in that, The target localization model is trained using the following method: Acquire a sample CT image, in which the first location of the target blood vessel is marked; The sample CT image is input into a deep learning recognition model to obtain the second location of the target blood vessel output by the deep learning recognition model. The difference between the second position and the first position is determined, and the deep learning recognition model is trained based on the difference to obtain the target localization model.

15. The method according to claim 13, characterized in that, The sample CT images include CT images of different body types and different pathological conditions; the deep learning recognition model is implemented using a convolutional neural network.

16. A cardiac scanning control device, characterized in that, include: The image acquisition module is configured to acquire cardiac monitoring images, which are obtained by monitoring and scanning the cardiac region. The region localization module is configured to execute a pre-trained target localization model to locate the candidate region where the target blood vessel is located from the cardiac monitoring image; The region determination module is configured to determine a target region for CT value monitoring based on the candidate regions, wherein the target region is located inside the lumen of the target blood vessel; The scan trigger module is configured to trigger the scanning device to perform a cardiac enhancement scan when the CT value of the target area is detected to reach a set threshold.

17. The apparatus according to claim 16, characterized in that, The region determination module is also configured to perform: Determine the center of the candidate region; Based on the center and the shape and size of the preset standard area, candidate target areas are generated; If the candidate target region is determined to meet the regional conditions, the candidate target region is determined as the target region for CT value monitoring.

18. The apparatus according to claim 17, characterized in that, The region determination module is also configured to perform: If it is determined that the candidate target region does not meet the region conditions, the candidate target region is narrowed down; The target area for CT value monitoring is determined based on the narrowed candidate target area.

19. The apparatus according to claim 17, characterized in that, The candidate regions include multiple regions; the region determination module is also configured to perform: Obtain the area of ​​multiple candidate regions; The candidate regions whose areas are greater than or equal to a first area threshold and less than or equal to a second area threshold are determined as the final candidate regions, wherein the first area threshold is less than the second area threshold. The center is determined from the final candidate region.

20. The apparatus according to claim 17, characterized in that, The candidate regions include multiple regions; the region determination module is also configured to perform: Obtain the circularity of multiple candidate regions; Candidate regions with a circularity greater than a circularity threshold are identified as final candidate regions. The center is determined from the final candidate region.

21. The apparatus according to claim 17, characterized in that, The region determination module is also configured to perform: If the candidate target region is determined to meet the regional conditions, the image features of the candidate target region are obtained; If the image features meet the set conditions, the candidate target region is determined as the target region for CT value monitoring. If the image features do not meet the set conditions, the predefined region will be determined as the target region for CT value monitoring.

22. The apparatus according to any one of claims 16 to 21, characterized in that, The scan trigger module is also configured to execute: When the CT value of the target area is detected to reach a set threshold, a scan trigger command is sent to the scanning device, which instructs the scanning device to perform a cardiac enhancement scan.

23. A cardiac scanning system, characterized in that, The invention includes a cardiac scan control device and a scanning device as described in any one of claims 16 to 22, wherein the scanning device performs a cardiac enhancement scan based on a triggering action of the cardiac scan control device.

24. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 15.

25. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 15.

26. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 15.

Images