Heart scanning method and device, storage medium and scanning equipment

Abstract

The invention discloses a heart scanning method and device, a storage medium and scanning device.The heart scanning method comprises the steps that in the heart scanning process, real-time scanning data are obtained; identifying a cardiac motion phase from the scan data; and if it is determined that scanning covers the target heartbeat range according to the recognized heart motion stage, stopping scanning the heart. According to the heart scanning method, in the process of scanning the heart, the obtained scanning data is recognized to recognize the heart motion stage, after it is determined that scanning covers the target heartbeat range according to the recognized heart motion stage, scanning is immediately ended, the target heartbeat range is accurately scanned, the image quality is guaranteed, the dosage is saved, and the heart scanning efficiency is improved. And unnecessary radiation is reduced.

Description

Technical Field

[0001] The present invention relates to the field of cardiac scanning technology, and in particular to a cardiac scanning method, device, storage medium and scanning equipment. Background Art

[0002] The heart can be scanned without ECG gating, that is, without using ECG signals to scan the heart. The scan can be performed by generating a simulated ECG signal with a fixed heart rate. However, the actual patient's heart rate fluctuates. Using a simulated ECG signal to scan the 0-100% phase range may not necessarily cover a heart cycle or may far exceed the time corresponding to a heart cycle. Moreover, the range of the simulated ECG signal is only a schematic and does not match the patient's actual heart cycle. The patient's heart cycle can also be directly estimated, and a time greater than the estimated heart cycle can be used as the phase range for scanning. There is also the problem that it may not cover a heart cycle or may far exceed the time corresponding to a heart cycle. Summary of the invention

[0003] The present invention aims to solve one of the technical problems in the related art at least to a certain extent. To this end, one purpose of the present invention is to provide a heart scanning method to achieve accurate scanning of a heart cycle, which not only ensures image quality, but also saves dose and reduces unnecessary radiation.

[0004] The second objective of the present invention is to provide a heart scanning device.

[0005] A third object of the present invention is to provide a computer-readable storage medium.

[0006] A fourth objective of the present invention is to provide a scanning device.

[0007] To achieve the above-mentioned purpose, a first aspect of an embodiment of the present invention proposes a heart scanning method, which includes: acquiring real-time scanning data during scanning of the heart; identifying the heart movement stage based on the scanning data; and stopping scanning of the heart if it is determined that the scan covers the target heartbeat range based on the identified heart movement stage.

[0008] According to the cardiac scanning method of an embodiment of the present invention, when performing cardiac scanning without relying on ECG gating, the acquired scanning data is identified to identify the cardiac movement stage. After determining that the scan covers the target heartbeat range based on the identified cardiac movement stage, the scan is terminated immediately, thereby achieving accurate scanning of one heartbeat cycle, thereby ensuring image quality, saving dose, and reducing unnecessary radiation.

[0009] In addition, the heart scanning method proposed in the above embodiment of the present invention may also have the following additional technical features:

[0010] According to one embodiment of the present invention, identifying the cardiac motion stage based on the cardiac scanning data includes: converting the scanning data to a pre-trained first recognition model to obtain a stage type or a stage type and a probability, wherein the trained first recognition model is used to identify the motion stage of the scanning data; and determining the cardiac motion stage based on the stage type or the stage type and the probability.

[0011] According to an embodiment of the present invention, the scan data is raw data or projection data, wherein the projection data is obtained by preprocessing the raw data.

[0012] According to one embodiment of the present invention, the training process of the first recognition model includes: obtaining a heart scan training data set, the heart scan training data set including scan training data with electrocardiogram signals; dividing the scan training data in the systole period in the heart scan training data set into a systolic data training set, and dividing the scan training data in the diastole period into a diastolic data training set according to the release time of the electrocardiogram signal record corresponding to each of the scan training data; establishing a first initial convolutional neural network model; and training the first initial convolutional neural network model using the systolic data training set and the diastolic projection data set to obtain the trained first recognition model.

[0013] According to one embodiment of the present invention, identifying the cardiac motion stage based on the scan data includes: reconstructing the scan data to obtain a cardiac image; inputting the cardiac image into a pre-trained second recognition model to obtain a stage type or a stage type and a probability, wherein the trained second recognition model is used to identify the motion stage of the cardiac image; and determining the cardiac motion stage based on the stage type or the stage type and the probability.

[0014] According to one embodiment of the present invention, the training process of the second recognition model includes: obtaining a heart scan training data set, wherein the heart scan training data set includes scan training data having an electrocardiogram signal; reconstructing each of the scan training data in the heart scan training data set to generate a heart training image and obtain a heart training image set; dividing the heart training images in the heart training image set that are located in the systolic period into a systolic period image training set, and dividing the heart training images in the diastolic period into a diastolic period image training set according to the time of laying out the electrocardiogram signal record corresponding to each of the scan training data; establishing a second initial convolutional neural network model; and training the second initial convolutional neural network model using the systolic period image training set and the diastolic period image training set to obtain the trained second recognition model.

[0015] According to one embodiment of the present invention, identifying the cardiac movement stage based on the scanning data includes: reconstructing the cardiac scanning data to obtain a cardiac image; calculating the current cardiac volume based on the cardiac image, and generating a cardiac characteristic change curve based on the current cardiac volume and the previously calculated cardiac volume; if the cardiac characteristic change curve reaches a minimum point, determining that the cardiac movement stage is end-systole; if the cardiac characteristic change curve reaches a maximum point, determining that the cardiac movement stage is end-diastole.

[0016] According to one embodiment of the present invention, acquiring real-time scanning data during scanning the heart includes: acquiring real-time scanning data in an interval or variable interval manner during scanning the heart, wherein the interval is a time interval or an angle interval.

[0017] According to one embodiment of the present invention, a variable interval method is adopted to acquire real-time scanning data, including: if the identified cardiac motion phase is close to the target cardiac motion phase, the interval is controlled to be shortened or decreased.

[0018] According to an embodiment of the present invention, the method further comprises: if the identified cardiac motion phase includes end-systole and end-diastole, determining that the scan covers the target heartbeat range.

[0019] According to one embodiment of the present invention, the method further includes: before scanning the heart, determining a preset maximum scanning time and a preset minimum scanning time; if it is determined based on the identified heart movement stage that the scan does not cover the target heartbeat range, then when the actual scanning time reaches the preset maximum scanning time, stopping the scanning of the heart; if it is determined based on the identified heart movement stage that the scan has covered the target heartbeat range, and the actual scanning time is less than the preset minimum scanning time, then when the actual scanning time reaches the preset minimum scanning time, stopping the scanning of the heart, wherein the maximum scanning time and the minimum scanning time are determined by a heartbeat cycle corresponding to the average heart rate of the heart, which fluctuates up and down within a preset time range.

[0020] According to one embodiment of the present invention, the method further comprises: scanning the heart without ECG gating.

[0021] To achieve the above-mentioned purpose, the second aspect of the present invention proposes a heart scanning device, which includes: an acquisition module, used to acquire real-time heart scanning data during the process of scanning the heart; an identification module, used to identify the heart movement stage according to the scanning data; and a control module, used to stop scanning the heart when it is determined that the scan covers the target heartbeat range according to the identified heart movement stage.

[0022] To achieve the above objectives, a third aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the heart scanning method provided in the first aspect of the present invention is implemented.

[0023] To achieve the above-mentioned purpose, the fourth aspect of the present invention proposes a scanning device, including a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the heart scanning method proposed in the first aspect of the present invention is implemented.

[0024] Additional aspects and advantages of the present invention will be given in part in the following description and in part will be obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 is a flow chart of a cardiac scanning method according to an embodiment of the present invention;

[0026] Figure 2 is a flow chart of identifying cardiac motion phases according to scan data according to an embodiment of the present invention;

[0027] Figure 3 is a training flow chart of a first recognition model according to an embodiment of the present invention;

[0028] Figure 4 is a flow chart of identifying cardiac motion stages according to cardiac images according to an embodiment of the present invention;

[0029] Figure 5 is a training flow chart of a second recognition model according to an embodiment of the present invention;

[0030] Figure 6 is a flow chart of identifying cardiac motion stages according to a cardiac characteristic change curve according to an embodiment of the present invention;

[0031] Figure 7 It is a schematic diagram of the corresponding relationship between the heart characteristic change curve and the electrocardiogram according to an embodiment of the present invention;

[0032] Figure 8 is a flow chart of a heart scanning method according to another embodiment of the present invention;

[0033] Fig. 9 is a schematic diagram of a heart scanning device according to an embodiment of the present invention;

[0034] Fig.10 4 is a structural block diagram of a scanning device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0035] Embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present invention, and should not be construed as limiting the present invention.

[0036] The heart scanning method, device, storage medium, and scanning equipment of the embodiments of the present invention are described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0037] Figure 1 FIG. 1 is a flow chart of a cardiac scanning method according to an embodiment of the present invention. Figure 1 As shown, the cardiac scanning method may include:

[0038] S101, acquiring real-time scanning data during scanning of the heart;

[0039] S102, identifying the cardiac motion stage according to the scan data;

[0040] S103: If it is determined that the scan covers the target heartbeat range according to the identified cardiac motion stage, the scanning of the heart is stopped.

[0041] In one embodiment of the present invention, the heart is scanned without ECG gating.

[0042] Specifically, when the patient's heart is scanned without ECG gating, real-time scanning data is acquired. The acquired scanning data is identified to identify the cardiac motion stage, and whether the scan covers the target heartbeat range is determined based on the identified cardiac motion stage. After determining that the scan covers the target heartbeat range, the scanning of the heart is stopped immediately. Thereby, even without ECG gating, the target heartbeat range can be scanned more accurately, saving dose and reducing unnecessary radiation. The target heartbeat range refers to the phase range included. For example, the target heartbeat range can be one or more complete heartbeat cycles (ECG RR interval), or it can be part of a heartbeat cycle, such as the end of systole or end of diastole. The target heartbeat range can be set by the operating physician or by default based on the scanning protocol.

[0043] The cardiac scanning method of the embodiment of the present invention identifies the acquired scanning data when performing cardiac scanning without relying on ECG gating, and immediately ends the scanning after determining that the scan covers the target heartbeat range based on the identified cardiac motion stage, thereby achieving accurate scanning of the target heartbeat range, thereby ensuring image quality, saving dose, and reducing unnecessary radiation.

[0044] In a feasible embodiment of the present invention, Figure 2As shown, identifying the cardiac motion phase based on cardiac scan data may include:

[0045] S201, inputting the scan data into a pre-trained first recognition model to obtain a stage type or a stage type and a probability, wherein the trained first recognition model is used to identify the motion stage of the scan data;

[0046] S202: Determine the cardiac motion stage according to the stage type or the stage type and probability.

[0047] Specifically, the scan data is input into a pre-trained first recognition model, and the pre-trained first recognition model outputs a phase type or a phase type and a probability. According to the phase type or the phase type and the probability, the cardiac motion phase can be determined.

[0048] It should be noted that the pre-trained first recognition model is used to identify the motion stage of the scan data and provide a predicted stage type or a stage type and probability.

[0049] In one embodiment of the present invention, the scan data is raw data or projection data, wherein the projection data is obtained by preprocessing the raw data.

[0050] Specifically, the scanning data may be raw data (original scanning data), or may be projection data obtained by preprocessing the raw data.

[0051] In an embodiment of the present invention, the preprocessing includes at least one of beam hardening correction, nonlinear correction and crosstalk correction.

[0052] Specifically, at least one of beam hardening correction, nonlinear correction and crosstalk correction is performed on the raw data to obtain projection data.

[0053] In one embodiment of the present invention, Figure 3 As shown, the training process of the first recognition model may include:

[0054] S301, obtaining a heart scan training data set, where the heart scan training data set includes scan training data having an electrocardiogram signal;

[0055] S302, according to the release time of the electrocardiogram signal record corresponding to each scan training data, divide the scan training data in the systolic period in the heart scan training data set into the systolic period data training set, and divide the scan training data in the diastolic period into the diastolic period data training set;

[0056] S303, establishing a first initial convolutional neural network model;

[0057] S304: Train the first initial convolutional neural network model using the systolic data training set and the diastolic data training set to obtain a trained first recognition model.

[0058] Specifically, a large amount of scan data obtained by scanning the heart with ECG gating can be collected, and the scan data obtained with ECG gating scanning has ECG signals. The scan data obtained by ECG gating scanning is used as scan training data to obtain a heart scan training data set.

[0059] According to the release time recorded in the electrocardiogram signal corresponding to each scanning training data, the scanning training data in the systole period is taken as a group, as the systolic data training set, and the scanning training data in the diastole period is taken as a group, as the diastolic data training set; using the deep learning algorithm, the first initial convolutional neural network model is built, and the first initial convolutional neural network model is trained using the systolic data training set and the diastolic data training set to obtain a trained first recognition model.

[0060] Since each contraction and relaxation of the heart constitutes a cardiac cycle, therefore, the cardiac motion phase includes the systolic phase and the diastolic phase, and the corresponding phase types include the systolic type and the diastolic type. The trained first recognition model is used to recognize the scan data in real time, marking whether the input scan data belongs to the diastolic phase or the systolic phase. In other embodiments, the probability value corresponding to the phase type of the input scan data can also be marked, and the cardiac motion phase is determined according to the phase type and probability at the marked position.

[0061] In one embodiment of the present invention, the cardiac motion phase may include a systolic phase and a diastolic phase, and the phase type includes a systolic type and a diastolic type. Determining the cardiac motion phase according to the phase type and probability may include:

[0062] If the phase type is a contraction type, and the probability corresponding to the phase type is greater than a preset probability threshold, then the cardiac motion phase is determined to be the end-systole phase;

[0063] If the phase type is the diastolic type, and the probability corresponding to the phase type is greater than a preset probability threshold, the cardiac motion phase is determined to be the end diastolic phase.

[0064] In one embodiment of the present invention, the heart scanning method may further include:

[0065] If the identified cardiac motion phase includes the end-systole and the end-diastole, it is determined that the scan covers the target heartbeat range.

[0066] Since the heart motion state at the end of systole and end of diastole is relatively gentle, the reconstructed image effect is better and the probability of motion artifacts is small. Therefore, the stage type and probability output by the trained first recognition model can be combined to determine whether the heart motion stage is at the end of systole or end of diastole.

[0067] Specifically, if the phase type output by the trained first recognition model is a contraction type, and the probability corresponding to the phase type is greater than a preset probability threshold, the cardiac motion phase can be determined to be the end-systole phase. If the phase type output by the trained first recognition model is a diastole type, and the probability corresponding to the phase type is greater than a preset probability threshold, the cardiac motion phase can be determined to be the end-diastole phase.

[0068] It should be noted that since each contraction and relaxation of the heart constitutes a cardiac cycle, if the identified cardiac motion phase includes the end-systole and the end-diastole, it can be determined that the scan covers the target heartbeat range. Therefore, when the identified cardiac motion phase includes the end-systole and the end-diastole, the scan of the heart can be stopped.

[0069] As a specific example, the preset probability threshold can be set to 0.8. When the probability corresponding to the stage type output by the trained first recognition model is greater than 0.8, it can be considered that the end diastole or the end systole has been scanned. It should be noted that the end diastole or the end systole means that most of the diastole or the systole has been covered. Taking into account the time-consuming recognition calculation process and the delay time required to terminate the scan command, when the result with a probability value greater than 0.8 has been identified in both the diastole and the systole, a command to end the scan can be issued to implement the early issuance of the command to end the scan, so that when the scan is completed, a complete heart cycle can be covered.

[0070] In this feasible embodiment, during the scanning process, the acquired scan data is identified, and when the identified cardiac motion phase includes the end-systole and the end-diastole, the scanning is immediately terminated, so as to achieve accurate scanning of the target heartbeat range, so as to reconstruct the image of the phases of the end-diastole and the end-systole with good image effect, and to save dose and reduce unnecessary radiation.

[0071] In another possible embodiment of the present invention, Figure 4 As shown, identifying the cardiac motion phase according to the scan data may include:

[0072] S401, reconstructing the scanned data to obtain a heart image;

[0073] S402, inputting the cardiac image into a pre-trained second recognition model to obtain a stage type or a stage type and a probability, wherein the pre-trained second recognition model is used to identify the motion stage of the cardiac image;

[0074] S403: Determine the cardiac motion stage according to the stage type or the stage type and probability.

[0075] In this embodiment, the acquired scan data is reconstructed to obtain a heart image, and the heart motion phase is identified using the heart image.

[0076] Specifically, the reconstructed cardiac image is input into a pre-trained second recognition model, and the pre-trained second recognition model outputs a phase type or a phase type and a probability corresponding to the phase type. According to the phase type or the phase type and the probability, the cardiac motion phase can be determined.

[0077] It should be noted that the trained second recognition model is used to identify the motion stage of the heart image and provide a predicted stage type and a probability corresponding to the stage type.

[0078] In one embodiment of the present invention, reconstructing the cardiac scan data to obtain a cardiac image may include:

[0079] At each preset time interval, image reconstruction is performed on the heart scan data within the preset time interval to obtain a heart image.

[0080] Specifically, at intervals of a certain time absolute phase, the heart scan data obtained by scanning within the certain time absolute phase is quickly reconstructed in real time. The preset time length in the embodiment of the present invention is determined by the time corresponding to the certain time absolute phase.

[0081] It should be noted that the embodiment of the present invention does not limit the size and clarity of the reconstructed heart image, which may be one image or multiple images including the main parts of the heart, or multiple images including the complete heart.

[0082] The embodiment of the present invention does not limit the value of the preset duration and can be set according to actual needs.

[0083] In one embodiment of the present invention, Figure 5 As shown, the training process of the second recognition model may include:

[0084] S501, obtaining a heart scan training data set, where the heart scan training data set includes scan training data having an electrocardiogram signal;

[0085] S502, reconstructing each scan training data in the heart scan training data set to generate a heart training image, thereby obtaining a heart training image set;

[0086] S503, according to the time of laying out the electrocardiogram signal record corresponding to each scan training data, dividing the heart training images in the systolic period in the heart training image set into the systolic period image training set, and dividing the heart training images in the diastolic period into the diastolic period image training set;

[0087] S504, establishing a second initial convolutional neural network model;

[0088] S505, training the second initial convolutional neural network model using the systolic image training set and the diastolic image training set to obtain a trained second recognition model.

[0089] Specifically, a large amount of heart scan data obtained by scanning the heart with ECG gating can be collected, and the scan data obtained with ECG gating scanning has ECG signals. The heart scan data obtained with ECG gating scanning is used as scan training data to obtain a heart scan training data set.

[0090] Each scan training data in the heart scan training data set is reconstructed to generate a heart training image, thereby obtaining a heart training image set. When the heart scan training data is reconstructed to generate a heart training image, the heart scan data obtained by scanning within a certain time absolute phase is rapidly reconstructed in real time at each certain time absolute phase interval to obtain a heart training image.

[0091] According to the release time recorded in the electrocardiogram corresponding to each heart scan training data and the data range used by the heart image corresponding to the heart scan training data, the heart training images in the systole period are grouped as a systolic image training set, and the heart training images in the diastole period are grouped as a diastolic image training set; using a deep learning algorithm, a second initial convolutional neural network model is built, and the second initial convolutional neural network model is trained using the systolic image training set and the diastolic images to obtain a trained second recognition model.

[0092] Since each contraction and relaxation of the heart constitutes a cardiac cycle, therefore, the cardiac motion phase includes the systolic phase and the diastolic phase, and the corresponding phase types include the systolic type and the diastolic type. The trained second recognition model is used to recognize the cardiac image in real time, marking whether the input cardiac image belongs to the diastolic phase or the systolic phase. In other embodiments, the probability value corresponding to the phase type of the input scan data can also be marked, and the cardiac motion phase is determined according to the phase type and probability at the marked position.

[0093] In one embodiment of the present invention, the phase type includes a contraction type and a diastole type. Determining the cardiac motion phase according to the phase type and the probability may include:

[0094] If the phase type is a contraction type, and the probability corresponding to the phase type is greater than a preset probability threshold, then the cardiac motion phase is determined to be the end-systole phase;

[0095] If the phase type is the diastolic type, and the probability corresponding to the phase type is greater than a preset probability threshold, the cardiac motion phase is determined to be the end diastolic phase.

[0096] In one embodiment of the present invention, the heart scanning method may further include:

[0097] If the identified cardiac motion phase includes the end-systole and the end-diastole, it is determined that the scan covers the target heartbeat range.

[0098] Since the heart motion state at the end of systole and end of diastole is relatively gentle, the reconstructed image effect is better and the probability of motion artifacts is small. Therefore, the stage type and probability output by the trained second recognition model can be combined to determine whether the heart motion stage is at the end of systole or end of diastole.

[0099] Specifically, if the phase type output by the trained second recognition model is a contraction type, and the probability corresponding to the phase type is greater than a preset probability threshold, the cardiac motion phase can be determined to be the end-systole phase. If the phase type output by the trained second recognition model is a diastole type, and the probability corresponding to the phase type is greater than a preset probability threshold, the cardiac motion phase can be determined to be the end-diastole phase.

[0100] It should be noted that since each contraction and relaxation of the heart constitutes a cardiac cycle, if the identified cardiac motion phase includes the end of systole and the end of diastole, it can be determined that a cardiac cycle has been scanned. Therefore, when the identified cardiac motion phase includes the end of systole and the end of diastole, the scanning of the heart is stopped.

[0101] As a specific example, the preset probability threshold can be set to 0.8. When the probability corresponding to the stage type output by the trained second recognition model is greater than 0.8, it can be considered that the end diastole or the end systole has been scanned. It should be noted that the end diastole or the end systole means that most of the diastole or the systole has been covered. Taking into account the time-consuming recognition calculation process and the delay time required to terminate the scan command, when the result with a probability value greater than 0.8 has been identified in both the diastole and the systole, a command to end the scan can be issued to implement the early issuance of the command to end the scan, so that when the scan is completed, a complete heart cycle can be covered.

[0102] In this feasible embodiment, during the scanning process, the acquired scan data is reconstructed, and the reconstructed heart image is identified. When the identified heart movement phase includes the end-systole and the end-diastole, the scanning is immediately terminated. Accurate scanning of the target heartbeat range is achieved, so that images of the end-diastole and end-systole phases with good image effects can be reconstructed, and doses can be saved to reduce unnecessary radiation.

[0103] In yet another feasible embodiment of the present invention, identifying the cardiac motion stage according to the scan data may include:

[0104] S601, reconstructing the scanned data to obtain a heart image;

[0105] S602, calculating the heart volume according to the heart image;

[0106] S603, generating a heart characteristic change curve according to the current heart volume and the previously calculated heart volume;

[0107] S604, if the heart characteristic change curve reaches a minimum value point, then the heart movement stage is determined to be the end-systolic stage;

[0108] S605: If the heart characteristic change curve reaches a maximum value point, it is determined that the heart movement stage is the end diastole.

[0109] Specifically, the acquired scan data is rapidly reconstructed in real time to obtain a heart image. Since the surrounding tissues of the heart can be scanned when the heart is scanned, the reconstructed heart image can be an image or multiple images including the main part of the heart or multiple images of the complete heart. Among them, an image of the main part of the heart is segmented to obtain the area where the heart is located, and features such as the volume occupied by the heart that change over time can be counted to identify the heartbeat cycle experienced by the heart. Multiple images of the main part of the heart or multiple images of the complete heart are segmented to obtain the area where the heart is located, and features such as the volume occupied by the heart that change over time can be counted to identify the heartbeat cycle experienced by the heart.

[0110] According to the heart characteristic change curve, if the curve reaches the minimum point, it is considered to be the end of contraction; if the curve reaches the maximum point, it is considered to be the end of diastole. If both the minimum point and the maximum point in the heart characteristic change curve have been identified, it means that most of the diastole or systole has been covered. Considering the time-consuming recognition calculation process and the delay time required to terminate the scan command, the command to end the scan can be issued in advance, so that when the scan is completed, it can just cover a complete heartbeat cycle. The corresponding relationship between the heart characteristic change curve and the electrocardiogram is shown as follows Figure 7 shown.

[0111] Since there is no ECG-gated scanning, the heart is in any motion state when the scan starts. It may scan the diastole first and then the systole, or it may start at the end of systole or diastole, without generating an extreme point. The embodiment of the present invention continuously performs statistics on the heart image obtained by reconstructing the heart scan data until the extreme points of the end of systole and the end of diastole are identified.

[0112] In one embodiment of the present invention, during the process of scanning the heart, acquiring real-time scanning data includes:

[0113] During the process of scanning the heart, an interval or variable interval method is used to obtain real-time scanning data, wherein the interval is a time interval or an angle interval.

[0114] It is feasible to obtain real-time scanning data in a preset interval manner. In order to make the scan accurately cover the target heartbeat range, the real-time scanning data can be obtained in a variable interval manner.

[0115] Specifically, when real-time scanning data is acquired in a preset interval mode, before scanning the heart, the size of the preset time interval or angle interval is preset, such as the preset time interval is set to 0.03 seconds, or the preset angle interval is set to 45 degrees. During the process of scanning the heart, real-time scanning data is acquired at preset time intervals or preset angle intervals, wherein when real-time scanning data is acquired at a preset time interval (0.03 seconds), scanning data is acquired once every 0.03 seconds. wherein, when real-time scanning data is acquired at a preset angle interval (45 degrees), scanning data is acquired once every 45 degrees.

[0116] It should be noted that the CT scan data is obtained by rotating the frame around the heart, and the angle in the preset angle interval refers to the rotation angle, for example, 0 degrees obtains data, 45 degrees obtains data, and 90 degrees obtains data.

[0117] In one embodiment of the present invention, real-time scanning data is acquired by adopting a variable interval method, including:

[0118] If the identified cardiac motion phase approaches a target cardiac motion phase, the control interval is shortened or reduced.

[0119] Specifically, if the identified cardiac motion phase is close to the target cardiac motion phase, the preset time interval is gradually shortened, or the preset angle interval is reduced, so as to increase the density of acquiring the scan data.

[0120] In an embodiment of the present invention, the target cardiac motion phase includes end-systole and end-diastole.

[0121] It is feasible that when determining the cardiac motion stage according to the recognition model, if the recognized cardiac motion stage is a contraction type and the corresponding probability is 0.6, it can be considered that the recognized cardiac motion stage is close to the end of contraction (target cardiac motion stage), and the preset time interval can be gradually shortened or the preset angle interval can be reduced. If the recognized cardiac motion stage is a diastolic type and the corresponding probability is 0.7, it can be considered that the recognized cardiac motion stage is close to the end of diastole (target cardiac motion stage), and the preset time interval can be gradually shortened or the preset angle interval can be reduced.

[0122] It should be noted that when the probability corresponding to the stage type is closer to the preset probability threshold, it can be determined that the identified cardiac motion stage is close to the target cardiac motion stage. A first threshold can be set, wherein the first threshold is less than the preset probability threshold, and by judging whether the probability corresponding to the stage type is greater than the first threshold, it is determined whether the identified cardiac motion stage is close to the target cardiac motion stage.

[0123] It is feasible that when determining the cardiac motion stage according to the cardiac characteristic change curve, if the identified cardiac motion stage corresponds to the continuous decrease of the cardiac characteristic change curve, it can be considered that the identified cardiac motion stage is close to the end of contraction (target cardiac motion stage), and the preset time interval can be gradually shortened or the preset angle interval can be reduced. If the identified cardiac motion stage corresponds to the continuous increase of the cardiac characteristic change curve, it can be considered that the identified cardiac motion stage is close to the end of diastole (target cardiac motion stage), and the preset time interval can be gradually shortened or the preset angle interval can be reduced.

[0124] In one embodiment of the present invention, Figure 8 As shown, the cardiac scanning method may further include:

[0125] Before scanning the heart, determining a preset maximum scanning time and a preset minimum scanning time;

[0126] If it is determined that the scan does not cover the target heartbeat range according to the identified cardiac motion stage, the scanning of the heart is stopped when the actual scanning time reaches the preset maximum scanning time;

[0127] If it is determined based on the identified cardiac motion stage that the scan has covered the target heartbeat range, and the actual scan time is less than the preset minimum scan time, the scan of the heart is stopped when the actual scan time reaches the preset minimum scan time.

[0128] In one embodiment of the present invention, the preset maximum scanning time length and the preset minimum scanning time length are determined by a heartbeat cycle corresponding to an average heart rate within a preset time range.

[0129] It should be noted that when scanning the heart without ECG gating, if the absolute delay (in milliseconds) from the start of the scan data is used as the representation of the phase, the phase range of the scan generally needs to cover the entire heart cycle. However, due to the lack of ECG gating, it is impossible to obtain the accurate heart cycle in real time. An average heart cycle can only be measured or estimated by other means, and the phase range of the scan is made larger than the estimated average heart cycle, so as to cover the systolic and diastolic periods as much as possible. If the estimated average heart cycle is too small, it may be smaller than the actual heart cycle when the scan is released; if the estimated average heart cycle is large and leaves redundancy for abnormal conditions such as heart rate fluctuations, it will be larger than the actual heart cycle when the scan is released. Although the systolic and diastolic periods are covered, some unnecessary data is scanned, which increases some unnecessary radiation doses.

[0130] In order to accurately scan the target heartbeat range, save dose, and reduce unnecessary radiation, the embodiment of the present invention sets a preset maximum and minimum scanning time before performing a non-ECG-gated scan on the patient's heart, that is, the absolute delay from the start of the scan data is used as the phase representation method, and a minimum scanning time phase and a maximum scanning time phase are set before scanning, and they fluctuate within a certain range within the corresponding time of a heartbeat cycle, respectively. During scanning, according to the recognition of the heartbeat cycle, the heart scan is performed at any time corresponding to the minimum scanning time phase and the maximum scanning time phase. It should be noted that since the patient's real-time heartbeat cycle cannot be obtained, the range between the minimum scanning time phase and the maximum scanning time phase will be set relatively large, and the maximum scanning time phase should try to cover more than one heartbeat cycle, and the minimum scanning time phase should try to cover more than one systolic period or diastolic period.

[0131] Specifically, if the end-systole or end-diastole is not identified according to the heart scan data, or both the end-systole and the end-diastole are not identified, the scan of the heart will be automatically stopped when the actual scan time reaches the preset maximum scan time. If it is determined that the scan has covered the target heartbeat range based on the identified heart movement stage, but the actual scan time is lower than the preset minimum scan time, the scan will continue until the preset minimum scan time. Avoid inaccurate recognition of the heartbeat cycle, resulting in a too short scan time, and the inability to select a phase with good image effect and smooth heart movement.

[0132] In the embodiment of the present invention, the preset maximum scanning time and the preset minimum scanning time can be set by floating up and down within a certain range respectively, based on the time of one heartbeat cycle corresponding to the average heart rate of the patient obtained by other means before scanning, or by the experience value. The maximum scanning time is slightly longer than one heartbeat cycle, and the minimum scanning time is slightly longer than one systolic period or diastolic period.

[0133] The cardiac scanning method of the embodiment of the present invention can save dose and reduce unnecessary radiation while ensuring that the cardiac scanning data that can reconstruct high-quality images are scanned. At the same time, when it is determined that the target heartbeat range is not covered according to the identified cardiac motion stage, normal scanning to the preset maximum scanning time will not cause additional losses and will not affect the original cardiac scanning process. Even if the cardiac cycle recognition is inaccurate, when it is determined that the scan has covered the target heartbeat range according to the identified cardiac motion stage, but the actual scanning time is lower than the preset minimum scanning time, it is still necessary to continue scanning to the minimum scanning time to ensure that at least one systolic or diastolic period is covered, so as to ensure that the phase with good image effect and smooth cardiac movement can be selected.

[0134] The embodiments of the present invention reduce scanning time and can accurately scan a heart cycle without an electrocardiogram signal, thereby ensuring image quality, saving dose, and reducing unnecessary radiation.

[0135] In the process of non-ECG-gated heart scanning, the embodiment of the present invention can quickly identify that a heartbeat cycle has been scanned and immediately end the scanning.

[0136] The embodiment of the present invention identifies the acquired scan data or the heart image reconstructed from the acquired scan data, confirms that a heartbeat cycle including the systolic period and the diastolic period has been scanned, and immediately ends the scan.

[0137] The embodiment of the present invention can quickly reconstruct a heart image in real time, with no limitation on size and clarity, and can be one image or multiple images containing the main parts of the heart, or multiple images containing the complete heart.

[0138] The embodiment of the present invention adopts a deep learning algorithm to build a convolutional neural network model for training. One group of training sets is diastolic heart images or diastolic scan data, and one group of training sets is systolic heart images or systolic scan data. Training is performed so that the model can automatically identify and determine whether the current heart image or scan data is in systole or diastole.

[0139] The embodiment of the present invention takes into account the time consumed in generating cardiac images or scanning data and system statistical calculations or model recognition processing, and uses the consumed time as the delay time. By setting a preset probability threshold, it is possible to make an immediate scan end command in advance, rather than waiting for the entire systole or diastole to be fully covered. In this way, the entire heart cycle can be covered when the scan is actually ended.

[0140] The embodiment of the present invention does not rely on ECG signals during non-ECG-gated scanning, and based on the acquired scanning data or reconstructed cardiac images, immediately terminates the scanning after the identified cardiac motion phases include end-systole and end-diastole, thereby reducing radiation dose.

[0141] The invention provides a heart scanning device.

[0142] Fig. 9 FIG. 1 is a schematic diagram of a heart scanning device according to an embodiment of the present invention. Fig. 9 As shown, the heart scanning device 100 may include: an acquisition module 10 , an identification module 20 and a control module 30 .

[0143] Among them, the acquisition module 10 is used to acquire real-time scanning data during the scanning of the heart; the identification module 20 is used to identify the heart movement stage according to the scanning data; the control module 30 is used to stop scanning the heart when it is determined that the scan covers the target heartbeat range according to the identified heart movement stage.

[0144] It should be noted that other specific implementations of the heart scanning device provided in the embodiment of the present invention may refer to other specific implementations of the heart scanning method in the above embodiment of the present invention.

[0145] The heart scanning device of the embodiment of the present invention, when performing heart scanning without relying on ECG gating, identifies the heart movement stage based on the heart scanning data obtained by real-time scanning, and immediately ends the scan after the identified heart movement stage includes the end-systole and the end-diastole, thereby achieving accurate scanning of the target heartbeat range, ensuring image quality, saving dose, and reducing unnecessary radiation.

[0146] The present invention provides a computer-readable storage medium.

[0147] In this embodiment, a computer program is stored on a computer-readable storage medium, and when the computer program is executed by a processor, the above-mentioned cardiac scanning method is implemented.

[0148] The invention provides a scanning device.

[0149] In this embodiment, the scanning device may include a memory and a processor. The memory stores a computer program. When the computer program is executed by the processor, the above-mentioned cardiac scanning method is implemented.

[0150] Fig.10 4 is a structural block diagram of a scanning device according to an embodiment of the present invention.

[0151] like Fig.10 As shown, the scanning device 500 includes: a processor 501 and a memory 503. The processor 501 and the memory 503 are connected, such as through a bus 502. Optionally, the scanning device 500 may also include a transceiver 504. It should be noted that in actual applications, the transceiver 504 is not limited to one, and the structure of the scanning device 500 does not constitute a limitation on the embodiments of the present invention.

[0152] Processor 501 may be a CPU (Central Processing Unit), a general purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It may implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of the present invention. Processor 501 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0153] The bus 502 may include a path to transmit information between the above components. The bus 502 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus 502 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Fig.10 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0154] The memory 503 is used to store a computer program corresponding to the heart scanning method of the above embodiment of the present invention, and the computer program is controlled and executed by the processor 501. The processor 501 is used to execute the computer program stored in the memory 503 to implement the contents shown in the above method embodiment. Fig.10 The scanning device 500 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0155] The computer-readable storage medium and scanning device of the embodiments of the present invention utilize the above-mentioned cardiac scanning method to identify the cardiac movement stage based on the scanning data obtained by real-time scanning when performing cardiac scanning without relying on ECG gating. After determining that the scan covers the target heartbeat range based on the identified cardiac movement stage, the scan is terminated immediately, thereby achieving accurate scanning of the target heartbeat range, thereby ensuring image quality, saving dose, and reducing unnecessary radiation.

[0156] It should be noted that the logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection portion with one or more wirings (electronic device), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways if necessary, and then stored in a computer memory.

[0157] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0158] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0159] In the description of the present invention, it is to be understood that the terms “center”, “longitudinal”, “lateral”, “length”, “width”, “thickness”, “up”, “down”, “front”, “back”, “left”, “right”, “vertical”, “horizontal”, “top”, “bottom”, “inside”, “outside”, “clockwise”, “counterclockwise”, “axial”, “radial”, “circumferential”, etc., indicating orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the referred device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as limiting the present invention.

[0160] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of the present invention, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0161] In the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements, unless otherwise clearly defined. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0162] In the present invention, unless otherwise clearly specified and limited, a first feature being "above" or "below" a second feature may mean that the first and second features are in direct contact, or the first and second features are in indirect contact through an intermediate medium. Moreover, a first feature being "above", "above" or "above" a second feature may mean that the first feature is directly above or obliquely above the second feature, or simply means that the first feature is higher in level than the second feature. A first feature being "below", "below" or "below" a second feature may mean that the first feature is directly below or obliquely below the second feature, or simply means that the first feature is lower in level than the second feature.

[0163] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.

Claims

1. A cardiac scanning method, characterized in that: The method comprises: During the scanning of the heart, real-time scanning data is obtained; identifying a cardiac motion phase based on the scan data; If it is determined based on the identified cardiac motion phase that the scan covers the target heartbeat range, the scanning of the heart is stopped.

2. The heart scanning method according to claim 1, characterized in that: The step of identifying the cardiac motion stage according to the scan data comprises: Inputting the scan data into a pre-trained first recognition model to obtain a stage type or a stage type and a probability, wherein the pre-trained first recognition model is used to identify the motion stage of the scan data; determining the cardiac motion phase according to the phase type or the phase type and the probability; The scan data is raw data or projection data, and the projection data is obtained by preprocessing the raw data.

3. The heart scanning method according to claim 2, characterized in that: The training process of the first recognition model includes: Acquire a heart scan training data set, wherein the heart scan training data set includes scan training data having an electrocardiogram signal; According to the time of release of the electrocardiogram signal record corresponding to each of the scan training data, the scan training data in the systolic period in the heart scan training data set are divided into the systolic period data training set, and the scan training data in the diastolic period are divided into the diastolic period data training set; Establishing a first initial convolutional neural network model; The first initial convolutional neural network model is trained using the systolic data training set and the diastolic data training set to obtain the trained first recognition model.

4. The heart scanning method according to claim 1, characterized in that: The step of identifying the cardiac motion stage according to the scan data comprises: Reconstructing the scan data to obtain a heart image; Inputting the cardiac image into a pre-trained second recognition model to obtain a stage type or a stage type and a probability, wherein the pre-trained second recognition model is used to identify the motion stage of the cardiac image; The cardiac motion phase is determined based on the phase type or the phase type and the probability.

5. The heart scanning method according to claim 4, characterized in that: The training process of the second recognition model includes: Acquire a heart scan training data set, wherein the heart scan training data set includes scan training data having an electrocardiogram signal; Reconstructing each of the scan training data in the heart scan training data set to generate a heart training image and obtain a heart training image set; According to the time of laying out of the electrocardiogram signal record corresponding to each of the scanned training data, the heart training images in the systolic period in the heart training image set are divided into the systolic period image training set, and the heart training images in the diastolic period are divided into the diastolic period image training set; Establishing a second initial convolutional neural network model; The second initial convolutional neural network model is trained using the systolic image training set and the diastolic image training set to obtain the trained second recognition model.

6. The heart scanning method according to claim 1, characterized in that: The step of identifying the cardiac motion stage according to the scan data comprises: Reconstructing the scan data to obtain a heart image; Calculating the current heart volume according to the heart image; generating a heart characteristic change curve according to the current heart volume and the previously calculated heart volume; If the heart characteristic change curve reaches a minimum value point, it is determined that the heart movement stage is the end-systole; If the heart characteristic change curve reaches a maximum value point, it is determined that the heart movement stage is the end diastole.

7. The heart scanning method according to claim 1, characterized in that: In the process of scanning the heart, obtaining real-time scanning data includes: During the scanning of the heart, real-time scanning data is acquired by using an interval or variable interval method, wherein the interval is a time interval or an angle interval.

8. The heart scanning method according to claim 7, characterized in that: Use variable intervals to obtain real-time scanning data, including: If the identified cardiac motion phase approaches a target cardiac motion phase, the interval is controlled to be shortened or reduced.

9. The heart scanning method according to claim 1, characterized in that: The method further comprises: If the identified cardiac motion phase includes the end-systole and the end-diastole, it is determined that the scan covers the target heartbeat range.

10. The heart scanning method according to claim 1, characterized in that: The method further comprises: Before scanning the heart, determining a preset maximum scanning time and a preset minimum scanning time; If it is determined according to the identified cardiac motion stage that the scan does not cover the target heartbeat range, then when the actual scan duration reaches the preset maximum scan duration, the scan of the heart is stopped; If it is determined based on the identified heart movement stage that the scan has covered the target heartbeat range, and the actual scan time is less than the preset minimum scan time, then when the actual scan time reaches the preset minimum scan time, the scan of the heart is stopped, wherein the preset maximum scan time and the preset minimum scan time are determined by a heartbeat cycle corresponding to the average heart rate of the heart, which fluctuates up and down within a preset time range.

11. The heart scanning method according to claim 1, characterized in that: The method further comprises: The heart was scanned without ECG gating.

12. A heart scanning device, characterized in that: The device comprises: An acquisition module, used for acquiring real-time scanning data during the process of scanning the heart; an identification module, configured to identify a cardiac motion stage according to the scan data; The control module is used to stop scanning the heart when it is determined that the scan covers the target heartbeat range according to the identified heart movement stage.

13. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the heart scanning method according to any one of claims 1 to 11 is implemented.

14. A scanning device, comprising a memory and a processor, wherein a computer program is stored in the memory, wherein: When the computer program is executed by the processor, the heart scanning method according to any one of claims 1 to 11 is implemented.

Images