Image scanning triggering method, system, electronic device and medium

Abstract

The present invention discloses a triggering method, system, electronic device and medium for image scanning, wherein the triggering method for image scanning comprises setting a monitoring layer scan to obtain a monitoring layer image; determining a region of interest in the monitoring layer image, wherein the region of interest includes a target part; identifying the target part in the region of interest, so as to update the region corresponding to the identified target part as the region of interest; generating a CT control parameter based on a CT value in the region of interest, wherein the CT control parameter is used to control CT sampling exposure, and can accurately determine the region of interest corresponding to the target part, and further determine the optimal scanning time, thereby realizing accurate determination of the trigger scanning time point with the best scanning effect on the region of interest.

Description

Technical Field

[0001] The present invention relates to the technical field of computer tomography, and in particular to a triggering method, system, electronic equipment and medium for image scanning. Background Art

[0002] Computed tomography (CT) uses computers to reconstruct images from X-ray tomography data of an object. It boasts advantages such as fast imaging, high density resolution of reconstructed images, and ease of reconstructing three-dimensional images from various cross-sections. It is currently widely used in medical imaging and other fields. One such technique is CTA (CT Angiography).

[0003] During a CTA scan, contrast agent is rapidly injected into the patient's veins. Based on each patient's blood circulation status, a CT scan of the target vessel is performed at the moment when the contrast agent concentration in the target vessel is optimal. During the three-dimensional reconstruction, unnecessary structures such as skin, muscle, and bone are removed, and only the three-dimensional vascular and visceral structures are displayed. Currently, there are four commonly used CTA triggering methods: (1) manual triggering; (2) timed triggering; (3) bolus tracking (or detection layer detection triggering); and (4) test bolus tracking.

[0004] Timed triggering is based on experience-based time settings, requiring technicians to have extensive experience to set the time. For areas with very fast blood flow, it is difficult to capture the peak time. The bolus tracking method detects the peak time of the contrast agent by detecting the CT value of the upstream blood vessels. However, the blood vessels in the detection layer are very thin, making it difficult to accurately determine the location of the contrast agent concentration. In addition, slight movement of the patient may make it impossible to accurately observe the changes in the contrast agent concentration, resulting in inaccurate peak time. Small-dose bolus injections require first injecting a small dose of contrast agent, detecting the entire contrast agent flow, and then setting the time. This often requires two injections of contrast agent and multiple scans of the detection layer. The radiation dose is high, and there is a period of time between the two scans. The overall examination time is long and the operation is cumbersome, making it unsuitable for emergency applications. Therefore, the CTA triggering methods in the existing technology all have the problem of not being able to accurately determine the peak time, which in turn leads to the inability to determine the optimal scanning time and the inability to obtain clear scan images. Summary of the Invention

[0005] The technical problem to be solved by the present invention is to overcome the above-mentioned defects in the prior art and to provide a triggering method, system, electronic device and medium for image scanning.

[0006] The present invention solves the above technical problems through the following technical solutions:

[0007] The present invention provides a method for triggering image scanning, the method comprising:

[0008] Set up monitoring layer scanning to obtain monitoring layer images;

[0009] Determining a region of interest in the monitoring layer image, wherein the region of interest includes a target site;

[0010] Identifying the target part in the region of interest, and updating the area corresponding to the identified target part as the region of interest;

[0011] A CT control parameter is generated according to the CT value in the region of interest, and the CT control parameter is used to control the CT sampling exposure.

[0012] Preferably, the region of interest includes a first region of interest, and the target site includes a first target site;

[0013] The identifying the target part in the region of interest to update the region corresponding to the identified target part as the region of interest includes:

[0014] determining a center point of the first region of interest;

[0015] Extracting similar pixels from the center point to the surrounding area to identify the boundary of the first target part;

[0016] The area corresponding to the boundary of the first target part is updated as the first region of interest.

[0017] Generating CT control parameters according to the CT value within the region of interest includes:

[0018] If the CT value in the first region of interest reaches the preset threshold, the image scan is triggered.

[0019] Preferably, the region of interest further includes a second region of interest, the target site further includes a second target site, and the contrast agent peak time of the second target site is similar to the contrast agent peak time of the first target site;

[0020] After updating the area corresponding to the boundary of the first target as the first region of interest, the method further includes:

[0021] identifying a second target part in the monitoring layer image based on the first target part to determine a second region of interest corresponding to the second target part;

[0022] Generating CT control parameters according to the CT value within the region of interest includes:

[0023] If the CT value in the second region of interest reaches the preset threshold, the image scan is triggered.

[0024] Preferably, the identifying a second target part in the monitoring layer image based on the first target part to determine a second region of interest corresponding to the second target part includes:

[0025] identifying the second target part in the image based on a preset similar target recognition model and the first target part;

[0026] An area corresponding to the boundary of the second object is determined as the second region of interest.

[0027] Preferably, the training step of the preset similar target recognition model includes:

[0028] Obtain historical scan images of different parts;

[0029] Marking target locations with similar peak time or similar flow velocity in the historical scan images to obtain a data set;

[0030] The data set is input into the target recognition model to obtain the preset similar target recognition model.

[0031] Preferably, the method for setting the preset threshold includes:

[0032] Determine a first threshold corresponding to the target part based on a preset threshold recommendation model, and set the first threshold as the preset threshold;

[0033] or,

[0034] A second threshold is obtained, and the second threshold is set as the preset threshold.

[0035] Preferably, the triggering method further includes:

[0036] Obtaining a CT value corresponding to the first region of interest or the second region of interest;

[0037] Adjusting the exposure interval of the monitoring layer scan according to the CT value;

[0038] and / or,

[0039] The first target includes a blood vessel or an organ, and the second target includes a blood vessel or an organ.

[0040] The present invention also provides a trigger system for image scanning, the trigger system comprising:

[0041] An image acquisition module is used to set a monitoring layer scan to acquire a monitoring layer image;

[0042] A region of interest determination module, configured to determine a region of interest in the monitoring layer image, wherein the region of interest includes a target site;

[0043] a region of interest updating module, configured to identify the target part in the region of interest, and update the region corresponding to the identified target part as the region of interest;

[0044] The image scanning trigger module is used to generate CT control parameters according to the CT values in the region of interest, and the CT control parameters are used to control CT sampling exposure.

[0045] Preferably, the region of interest includes a first region of interest, and the target site includes a first target site;

[0046] The region of interest updating module is further configured to determine a center point of the first region of interest;

[0047] Extracting similar pixels from the center point to the surrounding area to identify the boundary of the first target part;

[0048] The area corresponding to the boundary of the first target part is updated as the first region of interest.

[0049] The image scanning trigger module is further configured to generate the CT control parameter if the CT value within the first region of interest reaches a preset threshold.

[0050] Preferably, the region of interest further includes a second region of interest, the target site further includes a second target site, and the contrast agent peak time of the second target site is similar to the contrast agent peak time of the first target site;

[0051] The region of interest updating module is further configured to identify a second target portion in the monitoring layer image based on the first target portion, so as to determine a second region of interest corresponding to the second target portion;

[0052] The image scanning trigger module is further configured to generate the CT control parameter if the CT value within the second region of interest reaches the preset threshold.

[0053] Preferably, the region of interest updating module is further configured to identify the second target part in the image based on a preset similar target recognition model and the first target part;

[0054] An area corresponding to the boundary of the second object is determined as the second region of interest.

[0055] Preferably, the training step of the preset similar target recognition model includes:

[0056] Obtain historical scan images of different parts;

[0057] Marking target locations with similar peak time or similar flow velocity in the historical scan images to obtain a data set;

[0058] The data set is input into the target recognition model to obtain the preset similar target recognition model.

[0059] Preferably, the trigger system further includes a threshold setting module;

[0060] The threshold setting module is configured to determine a first threshold corresponding to the target part based on a preset threshold recommendation model, and set the first threshold as the preset threshold;

[0061] or,

[0062] A second threshold is obtained, and the second threshold is set as the preset threshold.

[0063] Preferably, the trigger system further includes an exposure interval setting module;

[0064] The exposure interval setting module is used to obtain the CT value corresponding to the first region of interest or the second region of interest;

[0065] Adjusting the exposure interval of the monitoring layer scan according to the CT value;

[0066] and / or,

[0067] The first target includes a blood vessel or an organ, and the second target includes a blood vessel or an organ.

[0068] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the image scanning triggering method as described above when executing the computer program.

[0069] The present invention also provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the method for triggering image scanning as described above is implemented.

[0070] The positive and progressive effects of the present invention are: obtaining a monitoring layer image by setting a monitoring layer scan; determining a region of interest in the monitoring layer image, the region of interest including a target part; identifying the target part in the region of interest, and updating the region corresponding to the identified target part as the region of interest; if the CT value in the region of interest reaches a preset threshold, generating a CT control parameter based on the CT value in the region of interest, the CT control parameter is used to control the CT sampling exposure, and can accurately determine the region of interest corresponding to the target part, and then determine the optimal scanning time, thereby realizing accurate determination of the trigger scanning time point with the best scanning effect for the region of interest. BRIEF DESCRIPTION OF THE DRAWINGS

[0071] Figure 1 This is a schematic diagram of a first flow chart of a method for triggering image scanning provided by an embodiment of the present invention.

[0072] Figure 2 This is a schematic diagram of a second flow chart of the image scanning triggering method provided by an embodiment of the present invention.

[0073] Figure 3 This is a schematic diagram of a third flow chart of the image scanning triggering method provided by an embodiment of the present invention.

[0074] Figure 4 A schematic diagram of a similar target provided by an embodiment of the present invention.

[0075] Figure 5 This is a schematic diagram of a fourth flow chart of the image scanning triggering method provided by an embodiment of the present invention.

[0076] Figure 6 A schematic diagram of an existing exposure interval provided by an embodiment of the present invention.

[0077] Figure 7 A schematic diagram of an improved exposure interval provided by an embodiment of the present invention.

[0078] Figure 8 A schematic diagram of the modules of the image scanning triggering system provided by an embodiment of the present invention.

[0079] Figure 9 A schematic structural diagram of an electronic device for implementing a triggering method for image scanning provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0080] The present invention is further described below by way of examples, but the present invention is not limited to the scope of the examples.

[0081] References to "embodiments" in this application mean that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute an independent or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described in this application may be combined with other embodiments.

[0082] CTA protocols generally require scanning when the contrast agent concentration in the target vessel reaches its peak to achieve the best imaging results. However, the time at which the contrast agent reaches its maximum concentration (peak time) varies between patients and in different blood vessels. Therefore, before a CTA scan, the intravascular contrast agent concentration is tracked to determine when to begin the CTA scan. This tracking process is a time period. If the patient makes any movements during this time, such as swallowing or breathing (or if the patient moves slightly without the operator noticing), the location where the contrast agent concentration is planned to be observed will change, potentially making it impossible to accurately observe changes in contrast agent concentration.

[0083] Based on this, this embodiment provides a method for triggering image scanning. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0084] The image scanning triggering method provided in this embodiment can be executed in an image scanning device, a computer terminal, a network device, a chip, a chip module or a similar computing device. The image scanning device can be implemented by software and / or hardware.

[0085] like Figure 1 As shown, the image scanning triggering method of this embodiment includes:

[0086] S101. Set a monitoring layer scan to obtain a monitoring layer image.

[0087] It should be noted that the monitoring layer scan is used to monitor the changes in the CT value corresponding to the target area (i.e., the changes in the contrast agent concentration). It can first obtain an image of a layer through an axial scan, which can be an axial or sagittal image, without limitation. Specifically, the monitoring layer scan is to continuously expose and update the same area / area to obtain monitoring layer images at different times, thereby updating the region of interest based on the monitoring layer images at different times. The same area is scanned repeatedly multiple times to obtain a 2D image. Then, the time interval between each exposure is 2s. When the CT value is detected to be close to the threshold (a rule of 20% can be defined, for example, if the threshold is 100, it reaches above 80), the interval time of the detection layer will be shortened to 0.5s interval exposure.

[0088] For example, the target part of the patient (such as the neck in a head and neck CTA scan) can be scanned first to obtain a positioning phase, and a positioning film position can be selected based on the scanned positioning phase. Then, the position of the monitoring layer can be determined according to the positioning film position (for example, by dragging the scanning frame position), and then the contrast agent is injected, and the exposure monitoring is continuously performed to obtain a monitoring layer image of the neck.

[0089] It's also important to note that contrast agents, also known as imaging agents, are chemicals injected into human tissues or organs to enhance imaging, or administered orally. Because contrast agents have a higher or lower density than surrounding tissue, these monitoring layer images can be obtained using certain medical devices. These devices primarily include medical imaging scanners, such as computed tomography (CT) scanners and other scanning modalities, or combinations thereof.

[0090] S102: Determine a region of interest in the monitoring layer image, where the region of interest includes a target site.

[0091] A region of interest (ROI) is determined in the monitoring layer image, that is, an initial region with a target part is determined in the monitoring layer image. This region can be a rough area (enclosed area) selected by the user. For example, the user draws or circles the target part in the monitoring layer image through an input device. Alternatively, a rough area can be automatically pre-selected based on the scan project combined with historical data and human body data. For example, in a head and neck CTA scan, the carotid artery or vertebral artery area of the neck can be pre-selected. This is also applicable to other coronary artery CTA, cerebrovascular CTA, and pulmonary artery CTA scans. This embodiment does not limit this. This embodiment can provide automatic or manual determination of the region of interest, so that even inexperienced users can perform the operation, thereby improving the user experience.

[0092] S103: Identify the target part in the region of interest, and update the area corresponding to the identified target part as the region of interest.

[0093] The target part is identified based on the region of interest (initial region) determined by the user. Due to different tissue structures, their density, morphology, and size are different. Therefore, based on the above characteristics, by extracting pixels with similar CT values, the boundary of the target part can be identified, and then the area corresponding to the precise target part can be obtained, and then the area corresponding to the target part can be updated as the new region of interest. In this way, even if the patient moves or the patient has a slight displacement during the CTA scanning process without the operator noticing, real-time calculations can be performed each time the monitoring layer is scanned to dynamically update the region of interest, thereby ensuring the accurate position of the monitoring region of interest and laying the foundation for accurately determining the peak time of the target part.

[0094] S104 : Generate CT control parameters according to the CT values in the region of interest, where the CT control parameters are used to control CT sampling exposure.

[0095] The CT control parameters are then used to control the CT sampling exposure to achieve triggered image scanning.

[0096] Optionally, this embodiment may further generate a CT control parameter when the CT value in the region of interest reaches a preset threshold.

[0097] It should be noted that the CT value is a unit of measurement used to determine the density of a specific tissue or organ in the human body, commonly referred to as the Hounsfield Unit (HU). The density of the contrast agent is generally higher or lower than the density of the surrounding tissue. To achieve optimal imaging, scanning is typically initiated when the contrast agent concentration in the target area is high, that is, when the CT value is at a high level.

[0098] In other words, this embodiment can accurately determine the region of interest corresponding to the target part, and then determine the optimal scanning time, that is, trigger the image scan when the CT value in the region of interest reaches a preset threshold, thereby accurately determining the trigger scanning time point with the best scanning effect on the region of interest and obtaining the best image data.

[0099] As an optional implementation of this embodiment, the region of interest includes a first region of interest, and the target site includes a first target site. Optionally, the first target in this embodiment includes a blood vessel or an organ.

[0100] like Figure 2 As shown, step S103 of this embodiment includes:

[0101] S103a: Determine the center point of the first region of interest.

[0102] The geometric center of the first ROI determined by the user is extracted to determine the corresponding center point of the first ROI. The shape of the ROI can generally be elliptical, circular, irregular, etc. For example, if the first ROI determined by the user is a circular area, the center point corresponding to the first ROI is the center of the circle.

[0103] S103b: extract similar pixels from the center point to the surrounding area to identify the boundary of the first target part.

[0104] Based on the determined center point of the first region of interest, pixel corrosion and dilation operations are performed around the region to extract similar pixels nearby, which are the target blood vessels, so as to identify the edge or boundary of the target region.

[0105] S103c: Update the area corresponding to the boundary of the first target part as the first region of interest.

[0106] The processed results are updated and displayed as a new first region of interest to facilitate accurate threshold monitoring.

[0107] Step S104 of this embodiment includes:

[0108] S104a: If the CT value in the first ROI reaches a preset threshold, generate a CT control parameter. Optionally, this embodiment may also generate a CT control parameter when the CT value in the first ROI among the ROIs reaches a preset threshold, so as to trigger image scanning.

[0109] Therefore, after determining a rough area, this embodiment can accurately identify the area corresponding to the first target part and update it as a new first region of interest. It can then trigger image scanning by judging whether the first region of interest reaches a preset threshold.

[0110] As another optional implementation of this embodiment, the region of interest further includes a second region of interest, the target site further includes a second target site, and the contrast agent peak time of the second target site is similar to the contrast agent peak time of the first target site. Optionally, the second target includes a blood vessel or an organ.

[0111] It should be noted that the second region of interest is not limited to the second part or region, but may include multiple parts or regions. That is, as long as the blood vessels or organs corresponding to the part or region are similar to the peak time of the contrast agent at the first target part, they can be used as the second region of interest. Therefore, this embodiment does not limit the number of second regions of interest.

[0112] After step S103, the image scanning triggering method of this embodiment further includes:

[0113] S105 : Identify a second target part in the monitoring layer image based on the first target part to determine a second region of interest corresponding to the second target part.

[0114] Identify and segment anatomical locations on the same monitoring layer, extracting all similar parts, such as blood vessels or organs. Similar blood vessels are those where blood flows through multiple vessels with similar flow times during the blood circulation process, which can be used to determine the peak time of the contrast agent.

[0115] In an alternative embodiment, Figure 3 As shown, step S105 of this embodiment includes:

[0116] S105a: Identify a second target part in the monitoring layer image based on a preset similar target recognition model and the first target part.

[0117] like Figure 4 As shown in FIG, the left and right common carotid arteries and the left and right vertebral arteries in the neck have similar peak times. Therefore, no matter which of the vessels is used as the first target site (A is the target vessel), the remaining three can be used as the second target sites (B is similar vessels).

[0118] S105b: Determine the area corresponding to the boundary of the second object as the second region of interest.

[0119] It should also be noted that the second region of interest, like the first region of interest, also needs to be updated in real time. That is, after the second target part in the monitoring layer image is identified through the first target part and the second region of interest is determined, the second region of interest also needs to be updated in real time. The updating process is similar to the first region of interest using the center point to edge similarity extraction, so it will not be elaborated here.

[0120] Alternatively, as Figure 5 As shown, the training steps of the preset similar target recognition model in this embodiment include:

[0121] S201: Acquire historical scan images of different parts.

[0122] S202: Mark target locations with similar peak time or similar flow velocity in the historical scan image to obtain a data set.

[0123] S203: Input the data set into the target recognition model to obtain a preset similar target recognition model.

[0124] It should be noted that the data set mainly comes from contrast agent-enhanced scanning images. These data are analyzed at different time periods to find blood vessels with similar peak times in different locations for identification and marking.

[0125] It should also be noted that the target recognition model includes but is not limited to one or more of the RetinaNet model (a target detection model), the R-CNN model (Region-CNN, an algorithm model that applies deep learning to target detection), the FPN model (Feature Pyramid Network, a feature pyramid model), and the YOLO V3 model (a target detection model).

[0126] Step S104 of this embodiment further includes:

[0127] S104b: If the CT value in the second region of interest reaches a preset threshold, generate a CT control parameter.

[0128] Optionally, this embodiment may also generate a CT control parameter to trigger image scanning when the CT value in a second region of interest within the region of interest reaches a preset threshold. It should also be noted that the trigger threshold (preset threshold) in the second region of interest in this embodiment may be different from the trigger threshold (preset threshold) in the first region of interest.

[0129] This embodiment can extract similar target parts on the same layer, perform multi-region of interest detection and threshold triggering, and can solve the problem of accurate positioning of the region of interest in small blood vessels in the body and inaccurate CT values caused by pathological reasons such as plaques and calcifications in the target blood vessels. Furthermore, similar blood vessels can be used to accurately capture the peak time of the contrast agent, providing a guarantee for obtaining the best image data.

[0130] As another optional implementation of this embodiment, the method for setting the preset threshold in this embodiment includes:

[0131] A first threshold corresponding to the target part is determined based on the preset threshold recommendation model, and the first threshold is set as the preset threshold.

[0132] or,

[0133] A second threshold is obtained and set as a preset threshold. The second threshold can be set based on known medical experience. The specific value depends on different target parts to be scanned for different patients and is not specifically limited in this embodiment.

[0134] It should be noted that the threshold triggering method of this embodiment is divided into manual mode and automatic mode. In manual mode, the user needs to manually set the trigger threshold. Then, the scan will be triggered when the target part reaches the threshold. The scan will also be triggered when the number of similar targets reaches the threshold + the upper threshold limit (for example, reaching 20% of the target threshold). The user can also manually disable the similar target trigger mechanism.

[0135] The automatic mode is determined based on a preset threshold recommendation model. It learns based on different factors such as contrast agent concentration and patient size, and then recommends a threshold. Then, the user can automatically recommend the threshold when selecting the corresponding anatomical part, without the need for the user to set the corresponding threshold. Similar to the manual mode, the target part can be triggered after reaching the threshold. Similar targets need to reach the threshold + the upper threshold limit (for example, reaching 20% of the target threshold) before the scan can be triggered. Users can also manually turn off the similar target triggering mechanism.

[0136] In an optional implementation manner, the image scanning triggering method of this embodiment further includes:

[0137] S301: Obtain a CT value corresponding to a first region of interest or a second region of interest.

[0138] S302: Adjust the exposure interval of the monitoring layer scan according to the CT value.

[0139] It should be noted that the adaptive exposure interval of the monitoring layer scan can reduce the number of unnecessary scans, e.g. Figure 6 and Figure 7 As shown in the figure, in the existing exposure interval control, an equal interval method is usually adopted, that is, the first and second exposure times are fixed, the white dots represent the number of exposures, and the threshold is set at 120HU. Then, when the CT value reaches near the threshold, the time interval is shortened, that is, the number of exposures is increased. This can not only reduce the dose but also increase the number of sampling times near the peak time, thereby improving accuracy.

[0140] Furthermore, the image scan triggering method of this embodiment not only dynamically adjusts the ROI positions of the target site (vessel or organ) and similar sites (vessels or organs), but also updates the ROI positions in real time with each exposure of the monitoring layer to ensure accurate positioning of the monitored region of interest. It also extracts similar vessels within the same layer for multi-ROI detection and threshold triggering. Furthermore, adaptive exposure is performed based on the CT value of the monitoring layer, reducing unnecessary exposures, lowering the dose, and increasing sampling near the peak time to enhance accuracy.

[0141] Corresponding to the image scanning triggering method described above, this embodiment also provides an image scanning triggering system. The following will introduce them separately. Specifically, Figure 8As shown, the image scanning triggering system of this embodiment includes:

[0142] The image acquisition module 1 is used to set the monitoring layer scan to acquire the monitoring layer image.

[0143] It should be noted that the monitoring layer scan is used to monitor the changes in the CT value corresponding to the target area (i.e., the changes in the contrast agent concentration). It can first obtain an image of a layer through an axial scan, which can be an axial or sagittal image, without limitation. Specifically, the monitoring layer scan is to continuously expose and update the same area / area to obtain monitoring layer images at different times, thereby updating the region of interest based on the monitoring layer images at different times. The same area is scanned repeatedly multiple times to obtain a 2D image. Then, the time interval between each exposure is 2s. When the CT value is detected to be close to the threshold (a rule of 20% can be defined, for example, if the threshold is 100, it reaches above 80), the interval time of the detection layer will be shortened to 0.5s interval exposure.

[0144] For example, the target part of the patient (such as the neck in a head and neck CTA scan) can be scanned first to obtain a positioning phase, and a positioning film position can be selected based on the scanned positioning phase. Then, the position of the monitoring layer can be determined according to the positioning film position (for example, by dragging the scanning frame position), and then the contrast agent is injected, and the exposure monitoring is continuously performed to obtain a monitoring layer image of the neck.

[0145] It's also important to note that contrast agents, also known as developer agents, are chemicals injected into human tissues or organs to enhance imaging, or administered orally. Because contrast agents have a higher or lower density than surrounding tissue, they can be captured using certain medical devices, representing the aforementioned monitoring layer images. These devices primarily include medical imaging scanners, such as computed tomography (CT) scanners and other scanning modalities, or combinations thereof.

[0146] The region of interest determination module 2 is used to determine the region of interest in the monitoring layer image, where the region of interest includes the target part.

[0147] Determine a region of interest in the monitoring layer image, that is, determine an initial region with a target portion in the monitoring layer image. This region can be a rough region (enclosed region) selected by the user. For example, the user draws or circles the target portion in the monitoring layer image through an input device. Alternatively, a rough region can be automatically preselected based on the scan project combined with historical data and anthropometric data. For example, in a head and neck CTA scan, the carotid artery or vertebral artery region of the neck can be preselected. This is also applicable to other coronary artery CTA, cerebrovascular CTA, and pulmonary artery CTA scans, and this embodiment does not limit this. This embodiment can provide automatic or manual determination of the region of interest, so that even inexperienced users can perform the operation, thereby improving the user experience.

[0148] The region of interest updating module 3 is configured to identify the target part in the region of interest, and update the region corresponding to the identified target part as the region of interest.

[0149] The target part is identified based on the region of interest (initial region) determined by the user. Due to different tissue structures, their density, morphology, and size are different. Therefore, based on the above characteristics, by extracting pixels with similar CT values, the boundary of the target part can be identified, and then the area corresponding to the precise target part can be obtained, and then the area corresponding to the target part can be updated as the new region of interest. In this way, even if the patient moves or the patient has a slight displacement during the CTA scanning process without the operator noticing, real-time calculations can be performed each time the monitoring layer is scanned to dynamically update the region of interest, thereby ensuring the accurate position of the monitoring region of interest and laying the foundation for accurately determining the peak time of the target part.

[0150] The image scanning trigger module 4 is used to generate CT control parameters according to the CT values in the region of interest, and the CT control parameters are used to control the CT sampling exposure.

[0151] The CT control parameters are then used to control the CT sampling exposure to achieve triggered image scanning.

[0152] Optionally, this embodiment may also generate a CT control parameter when the CT value in the region of interest reaches a preset threshold.

[0153] It should be noted that the CT value, commonly called the Hounsfield unit, is a unit of measurement used to determine the density of a specific tissue or organ in the human body. The density of contrast agents is generally higher or lower than that of surrounding tissue. To achieve optimal imaging, scanning is typically initiated when the contrast agent concentration in the target area is high, that is, when the CT value is high.

[0154] That is to say, this embodiment can determine the optimal scanning time by accurately determining the region of interest corresponding to the target part, that is, triggering the image scan when the CT value in the region of interest reaches a preset threshold, thereby accurately determining the trigger scanning time point with the best scanning effect of the region of interest and obtaining the best image data.

[0155] As an optional implementation of this embodiment, the region of interest includes a first region of interest, and the target site includes a first target site.

[0156] The region of interest updating module 3 is further configured to determine the center point of the first region of interest.

[0157] Similar pixels are extracted from the center point to the surrounding area to identify the boundary of the first target part.

[0158] The area corresponding to the boundary of the first target part is updated as the first region of interest.

[0159] The geometric center of the first ROI determined by the user is extracted to determine the corresponding center point of the first ROI. The shape of the ROI can generally be elliptical, circular, irregular, etc. For example, if the first ROI determined by the user is a circular area, the center point corresponding to the first ROI is the center of the circle.

[0160] Based on the determined center point of the first region of interest, pixel corrosion and dilation operations are performed around the region to extract similar pixels nearby, which are the target blood vessels, so as to identify the edge or boundary of the target region.

[0161] The processed results are updated and displayed as a new first region of interest to facilitate accurate threshold monitoring.

[0162] The image scanning trigger module 4 is further configured to generate a CT control parameter if the CT value within the first region of interest reaches a preset threshold.

[0163] Optionally, this embodiment may further generate a CT control parameter when the CT value in a first region of interest among the regions of interest reaches a preset threshold, so as to trigger image scanning.

[0164] Therefore, after determining a rough area, this embodiment can accurately identify the area corresponding to the first target part and update it as a new first region of interest. It can then trigger image scanning by judging whether the first region of interest reaches a preset threshold.

[0165] As another optional implementation of this embodiment, the region of interest further includes a second region of interest, the target site further includes a second target site, and the contrast agent peak time of the second target site is similar to the contrast agent peak time of the first target site.

[0166] It should be noted that the second region of interest is not limited to the second part or region, but may include multiple parts or regions. That is, as long as the blood vessels or organs corresponding to the part or region are similar to the peak time of the contrast agent at the first target part, they can be used as the second region of interest. Therefore, this embodiment does not limit the number of second regions of interest.

[0167] The region of interest updating module 3 is further configured to identify a second target portion in the monitoring layer image based on the first target portion, so as to determine a second region of interest corresponding to the second target portion.

[0168] Identify and segment anatomical locations on the same monitoring layer, extracting all similar parts, such as blood vessels or organs. Similar blood vessels are those where blood flows through multiple vessels with similar flow times during the blood circulation process, which can be used to determine the peak time of the contrast agent.

[0169] In an optional implementation manner, the region of interest updating module 3 is further configured to identify a second target portion in the monitoring layer image based on a preset similar target recognition model and the first target portion.

[0170] An area corresponding to the boundary of the second object is determined as a second region of interest.

[0171] For example, the left and right common carotid arteries and the left and right vertebral arteries in the neck have similar peak times. Therefore, no matter which one of the blood vessels is used as the first target site (target vessel), the remaining three can be used as second target sites (similar vessels).

[0172] It should also be noted that the second region of interest, like the first region of interest, also needs to be updated in real time. That is, after the second target part in the monitoring layer image is identified through the first target part and the second region of interest is determined, the second region of interest also needs to be updated in real time. The updating process is similar to the first region of interest using the center point to edge similarity extraction, so it will not be elaborated here.

[0173] Optionally, the image scanning triggering system of this embodiment further includes a model training module 5.

[0174] The model training module 5 is used to obtain historical scanning images of different parts, mark the target parts with similar peak time or similar flow rate in the historical scanning images to obtain a data set, and input the data set into the target recognition model to obtain a preset similar target recognition model.

[0175] It should be noted that the data set mainly comes from contrast agent-enhanced scanning images. These data are analyzed at different time periods to find blood vessels with similar peak times in different locations for identification and marking.

[0176] The image scanning trigger module 4 is further configured to generate a CT control parameter if the CT value in the second region of interest reaches a preset threshold.

[0177] Optionally, this embodiment may further generate a CT control parameter when the CT value in the second region of interest within the region of interest reaches a preset threshold, so as to trigger image scanning.

[0178] This embodiment can extract similar target parts on the same layer, perform multi-region of interest detection and threshold triggering, and can solve the problem of accurate positioning of the region of interest in small blood vessels in the body and inaccurate CT values caused by pathological reasons such as plaques and calcifications in the target blood vessels. Furthermore, similar blood vessels can be used to accurately capture the peak time of the contrast agent, providing a guarantee for obtaining the best image data.

[0179] As another optional implementation of this embodiment, the image scanning triggering system of this embodiment further includes a threshold setting module 6 .

[0180] The threshold setting module is used to determine a first threshold corresponding to the target part based on a preset threshold recommendation model, and set the first threshold as the preset threshold.

[0181] or,

[0182] A second threshold is obtained and set as a preset threshold. The second threshold can be set based on known medical experience. The specific value depends on different target parts to be scanned for different patients and is not specifically limited in this embodiment.

[0183] It should be noted that the threshold triggering method of this embodiment is divided into manual mode and automatic mode. In manual mode, the user needs to manually set the trigger threshold. Then, the scan will be triggered when the target part reaches the threshold. The scan will also be triggered when the number of similar targets reaches the threshold + the upper threshold limit (for example, reaching 20% of the target threshold). The user can also manually disable the similar target trigger mechanism.

[0184] The automatic mode is determined based on a preset threshold recommendation model. It learns based on different factors such as contrast agent concentration and patient size, and then recommends a threshold. Then, the user can automatically recommend the threshold when selecting the corresponding anatomical part, without the need for the user to set the corresponding threshold. Similar to the manual mode, the target part can be triggered after reaching the threshold. Similar targets need to reach the threshold + the upper threshold limit (for example, reaching 20% of the target threshold) before the scan can be triggered. Users can also manually turn off the similar target triggering mechanism.

[0185] In an optional implementation manner, the image scanning triggering system of this embodiment further includes an exposure interval setting module 7 .

[0186] The exposure interval setting module 7 is used to obtain the CT value corresponding to the first region of interest or the second region of interest.

[0187] Adjust the exposure interval of the monitoring layer scan according to the CT value.

[0188] It should be noted that the adaptive exposure interval of the monitoring layer scan can reduce the number of unnecessary scans. For example, if the threshold is set at 120HU, then when the CT value reaches near the threshold, the time interval is shortened, that is, the number of exposures is increased. This can not only reduce the dose but also increase the number of sampling times near the peak time, thereby improving accuracy.

[0189] Furthermore, the image scanning trigger system of this embodiment not only dynamically adjusts the ROI positions of the target site (vessel or organ) and similar sites (vessels or organs), but also updates the ROI positions in real time with each exposure of the monitoring layer to ensure accurate positioning of the monitored region of interest. It also extracts similar vessels within the same layer for multi-ROI detection and threshold triggering. Furthermore, adaptive exposure is performed based on the CT value of the monitoring layer, reducing unnecessary exposures, lowering the dose, and increasing sampling near the peak time to enhance accuracy.

[0190] It should be noted that the image scanning trigger system of this embodiment can be, for example: a separate chip, a chip module or an electronic device, or a chip or chip module integrated into an electronic device. Regarding the modules / units contained in the various devices and products described in the above embodiments, they can be software modules / units, hardware modules / units, or partly software modules / units and partly hardware modules / units. For example, for various devices and products applied to or integrated into a chip, the modules / units contained therein can all be implemented in the form of hardware such as circuits, or at least part of the modules / units can be implemented in the form of software programs, which run on a processor integrated inside the chip, and the remaining (if any) modules / units can be implemented in the form of hardware such as circuits; for various devices and products applied to or integrated into a chip module, the modules / units contained therein can all be implemented in the form of hardware such as circuits, and different modules / units can be located in the same component (such as a chip, circuit module, etc.) or different components of the chip module, or at least part of the modules / units can be implemented in the form of hardware such as circuits. The element can be implemented in the form of a software program, which runs on the processor integrated inside the chip module, and the remaining (if any) modules / units can be implemented in the form of hardware such as circuits; for various devices and products applied to or integrated in the terminal, the various modules / units contained therein can be implemented in the form of hardware such as circuits, and different modules / units can be located in the same component (for example, chip, circuit module, etc.) or different components in the terminal, or, at least some modules / units can be implemented in the form of a software program, which runs on the processor integrated inside the terminal, and the remaining (if any) modules / units can be implemented in the form of hardware such as circuits.

[0191] Figure 9 This is a schematic diagram of the structure of an electronic device provided in this embodiment. The electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the image scanning triggering method in the above embodiment is implemented. Figure 9 The electronic device 30 shown is only an example and should not limit the functionality and scope of use of the embodiments of the present invention.

[0192] like Figure 9 As shown, the electronic device 30 may be a general-purpose computing device, such as a server device. Components of the electronic device 30 may include, but are not limited to, the at least one processor 31, the at least one memory 32, and a bus 33 connecting different system components (including the memory 32 and the processor 31).

[0193] The bus 33 includes a data bus, an address bus, and a control bus.

[0194] The memory 32 may include a volatile memory, such as a random access memory (RAM) 321 and / or a cache memory 322 , and may further include a read-only memory (ROM) 323 .

[0195] The memory 32 may also include a program / utility 325 having a set (at least one) of program modules 324, such program modules 324 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0196] The processor 31 executes various functional applications and data processing by running the computer programs stored in the memory 32, such as the triggering method of image scanning described above in the present invention.

[0197] The electronic device 30 may also communicate with one or more external devices 34 (e.g., a keyboard, a pointing device, etc.). Such communication may be performed via an input / output (I / O) interface 35. Furthermore, the model generating device 30 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 36. Figure 9 As shown, the network adapter 36 communicates with the other modules of the model-generated device 30 via the bus 33. It should be understood that, although not shown in the figures, other hardware and / or software modules may be used in conjunction with the model-generated device 30, including but not limited to microcode, device drivers, redundant processors, external disk drive arrays, RAID (RAID) systems, tape drives, and data backup storage systems.

[0198] It should be noted that although several units / modules or sub-units / modules of the electronic device are mentioned in the detailed description above, this division is merely exemplary and not mandatory. In fact, according to embodiments of the present invention, the features and functions of two or more units / modules described above may be embodied in a single unit / module. Conversely, the features and functions of a single unit / module described above may be further divided and embodied by multiple units / modules.

[0199] This embodiment further provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the steps in the image scanning triggering method of the above embodiment are implemented.

[0200] The readable storage medium may include but is not limited to: a portable disk, a hard disk, a random access memory, a read-only memory, an erasable programmable read-only memory, an optical storage device, a magnetic storage device or any suitable combination thereof.

[0201] In a possible implementation, the present invention may also be implemented in the form of a program product, which includes program code. When the program product is run on a terminal device, the program code is used to enable the terminal device to execute the steps in the triggering method for implementing the image scanning described above.

[0202] The program code for executing the present invention may be written in any combination of one or more programming languages, and may be executed entirely on the user device, partially on the user device, as a standalone software package, partially on the user device and partially on a remote device, or entirely on the remote device.

[0203] Although specific embodiments of the present invention have been described above, those skilled in the art will appreciate that these are merely illustrative and that the scope of the present invention is defined by the appended claims. Those skilled in the art may make various changes or modifications to these embodiments without departing from the principles and essence of the present invention, and such changes and modifications are intended to fall within the scope of the present invention.

Claims

1. A method for triggering image scanning, characterized in that: The triggering method includes: Set up monitoring layer scanning to obtain monitoring layer images; Determining a region of interest in the monitoring layer image, wherein the region of interest includes a target site; Identifying the target part in the region of interest, and updating the area corresponding to the identified target part as the region of interest; generating a CT control parameter according to the CT value within the region of interest, wherein the CT control parameter is used to control CT sampling exposure; The region of interest includes a first region of interest, and the target site includes a first target site; The identifying the target part in the region of interest to update the region corresponding to the identified target part as the region of interest includes: determining a center point of the first region of interest; Extracting similar pixels from the center point to the surrounding area to identify the boundary of the first target part; Updating the area corresponding to the boundary of the first target part as the first region of interest; Generating CT control parameters according to the CT value within the region of interest includes: If the CT value within the first region of interest reaches a preset threshold, generating the CT control parameter; The region of interest further includes a second region of interest, the target site further includes a second target site, and the contrast agent peak time of the second target site is similar to the contrast agent peak time of the first target site; After updating the area corresponding to the boundary of the first target part as the first region of interest, the method further includes: identifying a second target part in the monitoring layer image based on the first target part to determine a second region of interest corresponding to the second target part; The generating of CT control parameters according to the CT value within the region of interest further includes: If the CT value within the second region of interest reaches the preset threshold, generating the CT control parameter; The identifying a second target part in the monitoring layer image based on the first target part to determine a second region of interest corresponding to the second target part includes: identifying the second target part in the image based on a preset similar target recognition model and the first target part; An area corresponding to a boundary of the second target site is determined as the second region of interest.

2. The image scanning triggering method according to claim 1, wherein: The training steps of the preset similar target recognition model include: Obtain historical scan images of different parts; Marking target locations with similar peak time or similar flow velocity in the historical scan images to obtain a data set; The data set is input into the target recognition model to obtain the preset similar target recognition model.

3. The image scanning triggering method according to claim 1, wherein: The method for setting the preset threshold includes: Determine a first threshold corresponding to the first target part or the second target part based on a preset threshold recommendation model, and set the first threshold as the preset threshold; or, A second threshold is obtained, and the second threshold is set as the preset threshold.

4. The image scanning triggering method according to claim 1, wherein: The triggering method further includes: Obtaining a CT value corresponding to the first region of interest or the second region of interest; Adjusting the exposure interval of the monitoring layer scan according to the CT value; and / or, The first target site includes a blood vessel or an organ, and the second target site includes a blood vessel or an organ.

5. A trigger system for image scanning, characterized in that: The trigger system comprises: An image acquisition module is used to set a monitoring layer scan to acquire a monitoring layer image; A region of interest determination module, configured to determine a region of interest in the monitoring layer image, wherein the region of interest includes a target site; a region of interest updating module, configured to identify the target part in the region of interest, and update the region corresponding to the identified target part as the region of interest; An image scanning trigger module is used to generate CT control parameters according to the CT values in the region of interest, wherein the CT control parameters are used to control CT sampling exposure; The region of interest includes a first region of interest, and the target site includes a first target site; The region of interest updating module is further configured to determine a center point of the first region of interest; Extracting similar pixels from the center point to the surrounding area to identify the boundary of the first target part; Updating the area corresponding to the boundary of the first target part as the first region of interest; The image scanning trigger module is further configured to generate the CT control parameter if the CT value within the first region of interest reaches a preset threshold; The region of interest further includes a second region of interest, the target site further includes a second target site, and the contrast agent peak time of the second target site is similar to the contrast agent peak time of the first target site; The region of interest updating module is further configured to identify a second target portion in the monitoring layer image based on the first target portion, so as to determine a second region of interest corresponding to the second target portion; The image scanning triggering module is further configured to generate the CT control parameter if the CT value within the second region of interest reaches the preset threshold; The region of interest updating module is further configured to identify the second target part in the image based on a preset similar target recognition model and the first target part; An area corresponding to a boundary of the second target site is determined as the second region of interest.

6. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the image scanning triggering method according to any one of claims 1 to 4 is implemented.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the image scanning triggering method according to any one of claims 1 to 4 is implemented.

Images