Medical image processing method and device and storage medium
By identifying and aligning the target phase in cardiac cine images, the problem of inconsistent cardiac cycles at the cardiac level was solved, enabling accurate calculation of cardiac function parameters.
Patent Information
- Application Number
- CN202411010705.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-25
- Publication Date
- 2024-11-12
AI Technical Summary
In existing cardiac cine magnetic resonance imaging, the cardiac cycles at different cardiac layers are not consistent, making it impossible to accurately calculate relevant parameters of overall cardiac function.
By acquiring initial cardiac cine images, the target phase of each cardiac layer is determined, and the initial cardiac cine images are aligned according to the target phase to obtain target cardiac cine images. This includes rearrangement and interpolation processing to ensure the consistency of cardiac cycles across different layers.
This method achieves consistency of cardiac cycles across different layers of cardiac cine images. The aligned images can accurately calculate relevant parameters of overall cardiac function, thus improving the accuracy of quantitative assessment of cardiac function.
Smart Images

Figure CN118941602A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of film imaging, and in particular to a medical image processing method, device and storage medium. Background Art
[0002] Cardiac cine magnetic resonance imaging (CCMRI) technology obtains bright blood images of multiple phases of the same plane in one cardiac cycle, and uses a movie method to continuously display multiple cardiac images at different times in a single plane in one cardiac cycle, which can directly observe the movement of the myocardial wall. Multi-layer cine images are mainly used to evaluate the local and overall function of the heart (ejection fraction, stroke volume, myocardial mass, systolic thickening rate of the heart wall, etc.), and are one of the routine examination sequences of cardiac cine magnetic resonance imaging.
[0003] Cardiac cine MRI can complete data acquisition while the subject is breathing freely by appropriately reducing the spatial resolution, using parallel imaging technology and special reconstruction algorithms. There is no need to hold your breath during the scan and no need for electrocardiogram (ECG) signal triggering. Real-time cardiac cine images can intuitively display the dynamic cyclical motion of each layer of the heart from any starting moment of the heart. However, due to the lack of ECG signal triggering, the cardiac cycles of different cardiac layers in the cardiac cine images are inconsistent, and it is impossible to calculate relevant parameters to quantitatively evaluate the overall function of the heart. The cardiac cycles of different cardiac layers in the cardiac cine images in the prior art are inconsistent. Summary of the invention
[0004] In this embodiment, a medical image processing method, device and storage medium are provided to solve the problem of inconsistency in cardiac cycles of different cardiac layers in cardiac movie images in the prior art.
[0005] In a first aspect, a medical image processing method is provided in this embodiment, the method comprising:
[0006] Acquire an initial cardiac movie image, wherein the initial cardiac movie image includes a plurality of cardiac slices, and the cardiac slices include a plurality of phase images;
[0007] Determining the target phase of each cardiac slice according to the initial cardiac cine image;
[0008] The initial cardiac cine images are aligned according to the target phase to obtain a target cardiac cine image.
[0009] In some embodiments, determining the target phase of each cardiac slice according to the initial cardiac cine image includes:
[0010] Acquiring the ventricular volume of each phase of the initial cardiac cine image;
[0011] The target phase of each cardiac slice is determined according to the ventricular volume of each phase.
[0012] In some embodiments, aligning the initial cardiac cine images according to the target phase to obtain a target cardiac cine image includes:
[0013] Determining the target phase number of each cardiac slice according to the target phase of each cardiac slice;
[0014] The initial cardiac cine images are aligned according to the target phase numbers and the target phases of the respective cardiac slices to obtain a target cardiac cine image.
[0015] In some embodiments, aligning the initial cardiac cine images according to the target phase number and the target phase of each cardiac slice to obtain a target cardiac cine image includes:
[0016] When the target phase numbers of the various cardiac slices are the same, the multi-phase images of the various cardiac slices are rearranged according to the target phases to obtain target cardiac movie images.
[0017] In some embodiments, aligning the initial cardiac cine images according to the target phase number and the target phase of each cardiac slice to obtain a target cardiac cine image includes:
[0018] When the target phase numbers of the various cardiac slices are different, determining the target phase values of the various cardiac slices;
[0019] interpolating the multi-phase images of each cardiac layer according to the target phase value to obtain an interpolated image;
[0020] The interpolated multi-phase images of each cardiac layer are rearranged according to the target phase to obtain a target cardiac movie image.
[0021] In some embodiments, interpolating the multi-phase images of each cardiac layer according to the target phase value to obtain the interpolated image includes:
[0022] Transforming the multi-phase images of each cardiac layer into k-space, interpolating the data between the k-space target phases of each cardiac layer to the target phase value, and obtaining the target data;
[0023] The target data is transformed into the image domain to obtain the interpolated image.
[0024] In some of these embodiments, the target phases include an end-systolic cardiac phase and an end-diastolic cardiac phase.
[0025] In a second aspect, a medical image processing method is provided in this embodiment, the method comprising:
[0026] Acquire real-time cine images of the heart;
[0027] Analyzing the real-time cardiac movie image to determine the end-systolic cardiac phase and the end-diastolic cardiac phase;
[0028] According to the cardiac phase identification result, an image containing a complete cardiac cycle is generated by alignment;
[0029] Analyze the aligned real-time cine images of the heart;
[0030] The results of the analysis are displayed.
[0031] In a third aspect, a medical image processing device is provided in this embodiment, the device comprising:
[0032] An acquisition module, used for acquiring an initial cardiac movie image, wherein the initial cardiac movie image includes a plurality of cardiac slices, and the cardiac slices include a plurality of phase images;
[0033] an identification module, used for determining a target phase of each cardiac slice according to the initial cardiac cine image;
[0034] An alignment module is used to align the initial cardiac movie image according to the target phase to obtain a target cardiac movie image.
[0035] In a fourth aspect, an electronic device is provided in this embodiment, comprising a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute the medical image processing method described in the first aspect or the second aspect.
[0036] In a fifth aspect, in this embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the medical image processing method described in the first aspect or the second aspect are implemented.
[0037] Compared with the prior art, the medical image processing method, device and storage medium provided in this embodiment determine the target phase of the initial cardiac movie image, align the initial cardiac movie image according to the target phase, and obtain an aligned cardiac movie image, i.e., a target cardiac movie image, i.e., cardiac movie images of multiple cardiac layers that are aligned. This solves the problem in the prior art that the image data of different cardiac layers of the cardiac movie image are not aligned, so that the cardiac cycles of different cardiac layers of the cardiac movie image are inconsistent.
[0038] Details of one or more embodiments of the present application are set forth in the following drawings and description to make other features, objects, and advantages of the present application more readily apparent. BRIEF DESCRIPTION OF THE DRAWINGS
[0039] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:
[0040] Figure 1 It is a hardware structure block diagram of a terminal for executing a medical image processing method according to an embodiment of the present application;
[0041] Figure 2 is a schematic diagram of the application environment of an embodiment of the present application;
[0042] Figure 3 is a flow chart of a medical image processing method according to an embodiment of the present application;
[0043] Figure 4 is a flow chart of determining a target phase according to an embodiment of the present application;
[0044] Figure 5 This is a flow chart of obtaining a target cardiac movie image according to an embodiment of the present application;
[0045] Figure 6 is a flow chart of another medical image processing method according to an embodiment of the present application;
[0046] Figure 7 is a schematic diagram of a volume change curve before alignment of an embodiment of the present application;
[0047] Figure 8 is a schematic diagram of the interpolation rearrangement process in an embodiment of the present application;
[0048] Fig. 9 is a schematic diagram of a volume change curve after alignment in an embodiment of the present application;
[0049] Fig.10 It is a structural block diagram of a medical image processing device according to an embodiment of the present application. DETAILED DESCRIPTION
[0050] In order to more clearly understand the purpose, technical solutions and advantages of the present application, the present application is described and illustrated below in conjunction with the accompanying drawings and embodiments.
[0051] Unless otherwise defined, the technical terms or scientific terms involved in this application shall have the general meaning understood by people with ordinary skills in the technical field to which this application belongs. The words "one", "a", "a", "the", "these" and the like in this application do not represent quantitative restrictions, and they can be singular or plural. The terms "include", "comprise", "have" and any variants thereof involved in this application are intended to cover non-exclusive inclusions; for example, a process, method and system, product or device comprising a series of steps or modules (units) is not limited to the listed steps or modules (units), but may include unlisted steps or modules (units), or may include other steps or modules (units) inherent to these processes, methods, products or devices. The words "connect", "connected", "coupled" and the like involved in this application are not limited to physical or mechanical connections, but may include electrical connections, whether directly or indirectly. The "multiple" involved in this application refers to two or more. "And / or" describes the association relationship of associated objects, indicating that there can be three relationships. For example, "A and / or B" can mean: A exists alone, A and B exist at the same time, and B exists alone. Usually, the character " / " indicates that the objects associated with each other are in an "or" relationship. The terms "first", "second", "third", etc. involved in this application are only used to distinguish similar objects and do not represent a specific ordering of the objects.
[0052] The method embodiment provided in this embodiment can be executed in a terminal, a computer or a similar computing device. For example, running on a terminal, Figure 1 is a hardware structure block diagram of a terminal for executing a medical image processing method according to an embodiment of the present application. Figure 1 As shown, the terminal may include one or more ( Figure 1 The terminal may further include a transmission device 106 and an input / output device 108 for communication functions. A person skilled in the art will appreciate that Figure 1 The structure shown is only for illustration and does not limit the structure of the above terminal. Figure 1More or fewer components as shown, or with Figure 1 Different configurations shown.
[0053] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as a computer program corresponding to a medical image processing method in this embodiment. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, to implement the above method. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the terminal via a network. Examples of the above network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.
[0054] The transmission device 106 is used to receive or send data via a network. The above network includes a wireless network provided by the communication provider of the terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (Radio Frequency, referred to as RF) module, which is used to communicate with the Internet wirelessly.
[0055] The medical image processing method provided in the embodiments of the present application can be applied to Figure 2 In the application environment shown. Among them, the terminal 202 communicates with the server 204 through the network. The terminal 202 can collect the real-time movie image of the heart of the object under test and send it to the server 204. The real-time movie image of the heart includes each sequence image corresponding to each acquisition time point of the object under test in a continuous time interval, and each sequence image corresponding to each acquisition time point includes multiple frames of single-layer images. After acquiring the real-time movie image of the heart of the object under test, the server 204 can determine the target phase of the multiple frames of single-layer images from the multiple frames of single-layer images corresponding to each time point. Further, the server 204 can align the initial heart movie image according to the target phase to obtain the aligned heart movie image, that is, the target heart movie image. Among them, the terminal 202 can be various detection devices in medical diagnosis and treatment, such as a magnetic resonance system, etc. The server 204 can be implemented by an independent server or a server cluster composed of multiple servers. The server 204 can also be a general-purpose computer device, etc., which is not specifically limited here.
[0056] This embodiment provides a medical image processing method. Figure 3 is a flow chart of a medical image processing method according to an embodiment of the present application. Figure 3 As shown, the process includes the following steps:
[0057] Step S310, obtaining an initial cardiac movie image, the initial cardiac movie image includes multiple cardiac slices, and the cardiac slices include multiple phase images.
[0058] Among them, a heart movie imaging sequence is used to image the heart, and a real-time movie image of the heart without ECG triggering and free breathing is obtained, that is, an initial heart movie image, which includes short-axis, long-axis and other heart scanning orientation images. The initial heart movie image can intuitively display the dynamic periodic motion of each layer of the heart from any starting time of the heart. In this embodiment, the real-time heart movie image is the dynamic image data of the heart in a certain time interval, and the real-time heart movie image can include dynamic images of multiple heart sections of the object being measured, such as images of multiple sections from the apex to the bottom of the heart, wherein each heart section can be understood as a heart layer. The heart section can include any one of a transverse section, a coronary section and a sagittal section. In this embodiment, the heart movie image of each layer can include multiple frames of images of the corresponding heart section, and each frame of the image indicates the heart phase of the heart section at the corresponding time. For the dynamic image of a certain layer of heart section, it can include multiple frames of images of the whole process from contraction to relaxation of the heart section in a continuous time, such as including N frames of images, then each frame of the image respectively represents the heart phase of the corresponding heart section at N moments. However, due to the lack of ECG signal triggering, the cardiac cycles of different cardiac layers in the initial cardiac movie images are inconsistent, and it is impossible to calculate relevant parameters to quantitatively evaluate the overall cardiac function. The initial cardiac movie images can be obtained through magnetic resonance imaging equipment or computer tomography imaging equipment.
[0059] Step S320, determining the target phase of each cardiac slice according to the initial cardiac cine image.
[0060] In this step, the initial cardiac movie image includes multi-phase images of multiple cardiac layers, that is, dynamic images of multiple cardiac layers in the initial cardiac movie image. The multi-phase images here can be understood as multi-frame images, that is, the initial cardiac movie image includes multi-frame images of multiple cardiac layers. The server determines the target phase of the multi-phase image of each cardiac layer based on the multi-phase image of each cardiac layer. The target phase here includes the end-systolic cardiac phase and the end-diastolic cardiac phase.
[0061] Step S330, aligning the initial cardiac cine image according to the target phase to obtain a target cardiac cine image.
[0062] In this step, the server aligns the initial cardiac movie image according to step S320 determined in step S320 to obtain an aligned cardiac movie image, ie, a target cardiac movie image.
[0063] Through the above steps, the target phase of the initial cardiac movie image is determined, and the initial cardiac movie image is aligned according to the target phase to obtain an aligned cardiac movie image, i.e., a target cardiac movie image, i.e., a cardiac movie image of multiple cardiac layers that are relatively aligned. This solves the problem in the prior art that the image data of different cardiac layers of the cardiac movie image are not aligned, so that the cardiac cycles of different cardiac layers of the cardiac movie image are inconsistent.
[0064] In some of the embodiments, Figure 4 As shown, step S320, determining the target phase according to the initial cardiac cine image, includes the following steps:
[0065] Step S322, obtaining the ventricular volume of each phase of the initial cardiac cine image; the initial cardiac cine image includes multiple cardiac slices, and the cardiac slices include multiple phase images.
[0066] In this step, the initial cardiac movie image is analyzed to obtain the ventricular volume of each phase at each cardiac level. Further, the blood pool portion of the target ventricular myocardium of the multi-phase image of each cardiac level is segmented, and the ventricular volume of the target ventricle of each phase at each cardiac level is determined based on the segmentation result. The target ventricle here can be the left ventricle or the right ventricle, which is not specifically limited here. The segmentation method here includes but is not limited to the use of image processing methods, traditional machine learning image processing methods, and deep learning network model segmentation.
[0067] Step S324, determining the target phase of each cardiac slice according to the ventricular volume of each phase.
[0068] In this step, the target phase of each cardiac layer is determined according to the ventricular volume of each phase determined in step S322. Further, the target phase of the cardiac layer is determined according to the ventricular volume of the target ventricle of each phase of each cardiac layer. Exemplarily, the ventricular volume of the target ventricle of each phase of each cardiac layer is analyzed in phase sequence, and the extreme point is selected according to the volume change trend to determine the target phase, and further, the end-systolic cardiac phase and the end-diastolic cardiac phase are determined according to the analysis results.
[0069] In this embodiment, the characteristics of the ventricular volume of the target phase are used to detect the ventricular volume of each phase of the initial cardiac movie image, and the target phase of each cardiac layer is determined according to the ventricular volume, thereby improving the recognition efficiency of the target phase.
[0070] In some of the embodiments, step S320, determining the target phase according to the initial cardiac cine image, further includes: using a pre-trained recognition model to recognize the initial cardiac cine image to determine the target phase.
[0071] In this embodiment, the multi-phase images of each cardiac layer are input into the pre-trained recognition model, and the recognition model predicts the target phase of the multi-phase image of each cardiac layer. The pre-trained recognition model can be a machine learning model or a neural network model, etc., which is not specifically limited here.
[0072] In this embodiment, the target phase of the multi-phase image of each cardiac layer is predicted by using a pre-trained recognition model, thereby improving the accuracy and efficiency of target phase recognition.
[0073] In some of the embodiments, Figure 5 As shown, step S330, aligning the initial cardiac movie image according to the target phase to obtain the target cardiac movie image, includes the following steps:
[0074] Step S332, determining the target phase number of each cardiac slice according to the target phase of each cardiac slice.
[0075] In this step, the server determines the target phase number of each cardiac layer according to the target phase of each cardiac layer. The target phase number here can be the systolic phase number, the diastolic phase number, or the number of phases in one cardiac cycle. Taking the target phases as the end-systolic cardiac phase and the end-diastolic cardiac phase as an example, after identifying the end-systolic cardiac phase and the end-diastolic cardiac phase of each cardiac layer, the end-systolic cardiac phase and the end-systolic cardiac phase are used to determine the target phase number. For example, for a certain cardiac layer, there are N frames of images (i.e., N phase images), and the first end-systolic cardiac phase is the Nth phase. 1 Frame image, the first end-diastolic cardiac phase is the Nth 2 frame data, the target period phase number can be N 2 -N 1 , where N 1 、N 2 All are less than N, N, N 1 and N 2 All are positive integers.
[0076] Step S334, aligning the initial cardiac cine images according to the target phase number and target phase of each cardiac slice to obtain a target cardiac cine image.
[0077] In this step, the server aligns the initial cardiac movie image according to the target phase number and target phase of each cardiac layer to obtain the target cardiac movie image.
[0078] In this embodiment, the initial cardiac movie images are aligned according to the target phase number and target phase of each cardiac layer to obtain the target cardiac movie images, that is, the cardiac movie images of multiple cardiac layers with aligned phases. This solves the problem in the prior art that the image data of different cardiac layers in the cardiac movie images are not aligned, so that the cardiac cycles of different cardiac layers in the cardiac movie images are inconsistent.
[0079] In some of the embodiments, the initial cardiac cine images are aligned according to the target phase number and target phase of each cardiac layer to obtain a target cardiac cine image, including: when the target phase number of each cardiac layer is the same, the multi-phase images of each cardiac layer are rearranged according to the target phase to obtain a target cardiac cine image.
[0080] In this step, when the target phase numbers of each cardiac layer are the same, the server rearranges the multi-phase images of each cardiac layer according to the target phase to obtain a target cardiac movie image. Further, when the target phase numbers of each cardiac layer are the same, the server rearranges the multi-phase images of each cardiac layer according to the cardiac motion trend of each cardiac layer. Specifically, when the cardiac motion trend of each cardiac layer is more of diastole first and then systole, the multi-phase images of all cardiac layers are rearranged according to diastole images first and then systole images, and the phases of each cardiac layer are aligned to obtain an aligned cardiac movie image, i.e., a target cardiac movie image.
[0081] In some of the embodiments, when the target phase numbers of each cardiac layer are different, the initial cardiac movie images are aligned according to the target phase numbers and target phases of each cardiac layer to obtain a target cardiac movie image, including: determining the target phase values of each cardiac layer; interpolating multi-phase images of each cardiac layer according to the target phase values to obtain an interpolated image; and rearranging the interpolated multi-phase images of each cardiac layer according to the target phase to obtain a target cardiac movie image.
[0082] In some of the embodiments, the target phase value of each cardiac layer may be the average phase number of each cardiac layer, the mode of the phase number of each cardiac layer, the median of the phase number of each cardiac layer, etc. The average phase number of each cardiac layer includes the average systolic phase number and the average diastolic phase number. When the target phase numbers of each cardiac layer are different, the systolic phase number and the diastolic phase number of each cardiac layer are first determined according to the target phase, and the average systolic phase number and the average diastolic phase number of all cardiac layers are determined according to the systolic phase number and the diastolic phase number of each cardiac layer. The average systolic phase number here may be the average value of the systolic phase number of multiple cardiac layers, and the average diastolic phase number here may be the average value of the diastolic phase number of multiple cardiac layers. The server rearranges the interpolated multi-phase images of each cardiac layer according to the cardiac motion trend of each cardiac layer. If the cardiac motion trend of each cardiac layer is more like diastole first and then systole, the interpolated multi-phase images of all cardiac layers are rearranged according to diastole first and then systole, and the phases of each cardiac layer are aligned to obtain an aligned cardiac movie image, i.e., the target cardiac movie image.
[0083] In some of the embodiments, multi-phase images of each cardiac layer are interpolated according to the target phase value to obtain an interpolated image, including: transforming the multi-phase images of each cardiac layer to k-space, interpolating the data between the target phases of the k-space of each cardiac layer to the target phase value to obtain target data; transforming the target data to the image domain to obtain an interpolated image.
[0084] In this step, when the target phase numbers of each cardiac layer are different, the server transforms the multi-phase image of each cardiac layer into k-space, interpolates the data between the target phases of the k-space of each cardiac layer to the average systolic phase number and / or the average diastolic phase number to obtain the target data, transforms the target data into the image domain, and obtains the interpolated image.
[0085] This embodiment also provides a medical image processing method. Figure 6 is a flowchart of another medical image processing method according to an embodiment of the present application. Figure 6 As shown, the process includes the following steps:
[0086] Step S610, obtaining a real-time movie image of the heart.
[0087] In this step, a real-time cardiac movie image of free breathing without ECG signal triggering is obtained, including short-axis, long-axis and other common cardiac scanning orientation images. The real-time cardiac movie image here is the initial cardiac movie image in the above embodiment.
[0088] Step S620, analyzing the real-time cardiac movie image to determine the end-systolic cardiac phase and the end-diastolic cardiac phase.
[0089] In this step, the end-systolic cardiac phase and the end-diastolic cardiac phase are determined by analyzing the real-time movie images of the heart. The blood pool portion of the left ventricular myocardium can be segmented in the multi-phase images of each cardiac layer, and the volume changes of each layer of the left ventricle are plotted according to the segmentation results to determine the target end-systolic cardiac phase and the end-diastolic cardiac phase. Alternatively, the multi-phase images of each cardiac layer can be input into a pre-trained deep learning model to predict the target end-systolic cardiac phase and the end-diastolic cardiac phase. Take the left ventricular volume as an example for explanation, refer to Figure 7 There are 8 heart levels, heart levels 0 to 7. Figure 7 The 8 curves in the figure represent the left ventricular volume change curves at 8 cardiac levels. By analyzing the extreme points of the curves, the end-diastolic phase shown by the red dots, the end-systolic phase shown by the blue dots, and the third phase of a complete cardiac cycle are obtained, which is represented by the green dots. The third phase can be the end-diastolic phase or the end-systolic phase. By analyzing the left ventricular volume change curves, 3 target phases are obtained. Figure 7 The curves of different colors represent the volume change curves of different contraction phases. The icon (M 1 , M 2 ) indicates the Mth 1 Layer M 2 Frame image, M 1 、M 2 is an integer, the horizontal axis represents the frame number, and the vertical axis represents the volume. For example, the icon (6, 8) at the red point of the blue curve represents the 8th frame image of the 6th layer.
[0090] Step S630: align and generate an image containing a complete cardiac cycle according to the cardiac phase recognition result.
[0091] In this step, according to the cardiac phase recognition result, an image containing a complete cardiac cycle is aligned and generated. According to the cardiac phase recognition result, if the phase numbers are consistent, they are directly rearranged, and if they are inconsistent, interpolation calculation is performed. The consistent phase numbers here can be the consistent phase numbers of a complete cardiac cycle, the consistent systolic phase numbers, the consistent diastolic phase numbers, or the consistent systolic phase numbers and diastolic phase numbers.
[0092] When the systolic phase number and / or the diastolic phase number are consistent, such as the diastolic phase number of the 8 cardiac layers are all 10, the multi-phase images of each cardiac layer are rearranged, and the end-systolic cardiac phase and / or the end-diastolic cardiac phase are aligned to generate an image containing a complete cardiac cycle. The rearrangement here can be performed according to the trend of diastole first and then systole or contraction first and then diastole in all layers. For example, if the cardiac movement trend of the 8 cardiac layers is more of diastole first and then systole, the interpolated multi-phase images of all cardiac layers are rearranged according to diastole first and then systole, and the end-systolic cardiac phase and / or the end-diastolic cardiac phase of each cardiac layer are aligned to generate an image containing a complete cardiac cycle.
[0093] When the systolic phase number and / or diastolic phase number are inconsistent, such as the phase number of a complete cardiac cycle in 8 cardiac slices is different, continue to refer to Figure 7 , such as the number of systolic phases in the first layer is 4, the number of systolic phases in the second layer is 6, and the number of systolic phases in the sixth layer is 5, then first calculate the average systolic phase number of the heart to be 5. Perform an inverse k-space transform on the multi-phase data of each heart layer respectively, and interpolate and reconstruct the data between the end-systole and end-diastole of the layer to the average systolic phase number and the average diastolic phase number. Common reconstruction methods include but are not limited to processing k-space data through compressed sensing, sparse image reconstruction, and multi-contrast image reconstruction. Then, according to more trends of diastole followed by contraction or contraction followed by diastole in all layers, the interpolated data changes are rearranged in the image domain, and finally aligned to generate an image containing a complete cardiac cycle. Taking the 6th layer as an example, the entire interpolation and rearrangement process is as follows: Figure 8 As shown, Figure 8 The figure shows the interpolation and rearrangement process of the 6th layer. The red box is the systolic period of the 6th layer, and the green box is the diastolic period of the 6th layer. According to the calculated average systolic phase number and average diastolic phase number of 5 and 10, all phase images in the systolic period are interpolated and reconstructed to the target phase. Then, according to the more changing trend of the heart layer, diastolic first and then systolic, the reconstructed images are rearranged and aligned. The images after all layers are aligned are shown in Figure 1. Fig. 9 shown. Fig. 9 The curves of different colors in the figure represent the volume change curves of the left ventricle at different heart levels after alignment. It can be seen that the volumes of all levels after reconstruction and alignment show synchronous regular changes, first in the diastole and then in the systole.
[0094] Step S640, analyzing the aligned real-time cine images of the heart.
[0095] In this step, cardiac function parameters are calculated and analyzed for the aligned real-time cine images of the heart. Specific parameters include end-diastolic volume, end-systolic volume, stroke volume, ejection fraction, peak emptying rate, peak filling rate, etc., which are not specifically limited here.
[0096] Step S650: display the analysis result.
[0097] Through the above steps, the real-time cardiac movie image is analyzed to determine the end-systolic cardiac phase and the end-diastolic cardiac phase. According to the results of cardiac phase recognition, an image containing a complete cardiac cycle is aligned and generated, and the aligned real-time cardiac movie image is analyzed, that is, the cardiac movie images of multiple cardiac layers with phase alignment. The problem in the prior art that the cardiac cycles of different cardiac layers of the cardiac movie image are inconsistent due to the lack of ECG signal triggering is solved, and the relevant parameters cannot be calculated to quantitatively evaluate the overall cardiac function. Compared with the prior art, the advantage of the present application is that the phase recognition of real-time cardiac data is performed. If the complete cardiac cycle is not included, the end-diastolic and end-systolic images can be provided to calculate some cardiac function parameters. If the complete cycle is included, a complete cardiac cycle rearranged and interpolated data is provided, and the cardiac function parameters are calculated to quantitatively evaluate the cardiac function. In addition, the present application outputs a quality factor, which can prompt the results below the set threshold.
[0098] It should be noted that the steps shown in the above process or the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a 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.
[0099] In this embodiment, a medical image processing device is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. The terms "module", "unit", "subunit", etc. used below can implement a combination of software and / or hardware of predetermined functions. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.
[0100] Fig.10 is a structural block diagram of a medical image processing device according to an embodiment of the present application. Fig.10 As shown, the device comprises:
[0101] An acquisition module 910 is used to acquire an initial cardiac movie image, wherein the initial cardiac movie image includes multiple cardiac slices, and the cardiac slices include multiple phase images;
[0102] An identification module 920, configured to determine a target phase of each cardiac slice according to the initial cardiac cine image;
[0103] The alignment module 930 is used to align the initial cardiac cine image according to the target phase to obtain a target cardiac cine image.
[0104] In some of the embodiments, the identification module 920 is also used to obtain the ventricular volume of each phase of the initial cardiac movie image; the initial cardiac movie image includes multiple cardiac slices, and the cardiac slices include multiple phase images; based on the ventricular volume of each phase, the target phase of each cardiac slice is determined.
[0105] In some of the embodiments, the alignment module 930 is further used to determine the target phase number of each cardiac layer according to the target phase of each cardiac layer; align the initial cardiac movie image according to the target phase number of each cardiac layer and the target phase to obtain a target cardiac movie image.
[0106] In some of the embodiments, the alignment module 930 is further used to, when the target phase numbers of the cardiac slices are the same, rearrange the multi-phase images of the cardiac slices according to the target phases to obtain target cardiac movie images.
[0107] In some of the embodiments, the alignment module 930 is also used to determine the target phase value of each cardiac layer when the target phase numbers of each cardiac layer are different; interpolate the multi-phase images of each cardiac layer according to the target phase value to obtain an interpolated image; and rearrange the interpolated multi-phase images of each cardiac layer according to the target phase to obtain a target cardiac movie image.
[0108] In some of the embodiments, the alignment module 930 is also used to transform the multi-phase images of each cardiac layer into k-space, interpolate the data between the target phases of the k-space of each cardiac layer to the target phase value to obtain target data; and transform the target data into the image domain to obtain an interpolated image.
[0109] It should be noted that the above modules can be functional modules or program modules, and can be implemented by software or hardware. For modules implemented by hardware, the above modules can be located in the same processor; or the above modules can be located in different processors in any combination.
[0110] In this embodiment, an electronic device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.
[0111] Optionally, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.
[0112] Optionally, in this embodiment, the processor may be configured to perform the following steps through a computer program:
[0113] S1, acquiring the initial cardiac cine image;
[0114] S2, determining a target phase of each cardiac slice according to the initial cardiac cine image;
[0115] S3, aligning the initial cardiac cine image according to the target phase to obtain a target cardiac cine image.
[0116] It should be noted that the specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementation modes, and will not be repeated in this embodiment.
[0117] In addition, in combination with a medical image processing method provided in the above embodiment, a storage medium may be provided in this embodiment to implement the method. The storage medium stores a computer program; when the computer program is executed by a processor, any medical image processing method in the above embodiment is implemented.
[0118] It should be understood that the specific embodiments described here are only used to explain this application, rather than to limit it. According to the embodiments provided in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the protection scope of this application.
[0119] Obviously, the drawings are only some examples or embodiments of the present application. For ordinary technicians in the field, the present application can also be applied to other similar situations based on these drawings without creative work. In addition, it is understandable that although the work done in this development process may be complicated and lengthy, for ordinary technicians in the field, certain changes in design, manufacturing or production based on the technical content disclosed in this application are only conventional technical means and should not be regarded as insufficient content disclosed in this application.
[0120] The term "embodiment" in this application refers to a specific feature, structure or characteristic described in conjunction with the embodiment that can be included in at least one embodiment of the present application. The appearance of this phrase in various locations in the specification does not necessarily mean the same embodiment, nor does it mean that it is mutually exclusive with other embodiments and is independent or optional. It is clearly or implicitly understood by those of ordinary skill in the art that the embodiments described in this application can be combined with other embodiments without conflict.
[0121] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of patent protection. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the scope of protection of the present application. Therefore, the scope of protection of the present application shall be subject to the attached claims.
Claims
1. A medical image processing method, characterized in that: The method comprises: Acquire an initial cardiac movie image, wherein the initial cardiac movie image includes a plurality of cardiac slices, and the cardiac slices include a plurality of phase images; Determining the target phase of each cardiac slice according to the initial cardiac cine image; The initial cardiac cine images are aligned according to the target phase to obtain a target cardiac cine image.
2. The medical image processing method according to claim 1, characterized in that: Determining the target phase of each cardiac slice according to the initial cardiac cine image includes: Acquiring the ventricular volume of each phase of the initial cardiac cine image; The target phase of each cardiac slice is determined according to the ventricular volume of each phase.
3. The medical image processing method according to claim 2, characterized in that: The step of aligning the initial cardiac cine image according to the target phase to obtain a target cardiac cine image includes: Determining the target phase number of each cardiac slice according to the target phase of each cardiac slice; The initial cardiac cine images are aligned according to the target phase numbers and the target phases of the respective cardiac slices to obtain the target cardiac cine images.
4. The medical image processing method according to claim 3, characterized in that: The step of aligning the initial cardiac cine images according to the target phase number and the target phase of each cardiac slice to obtain a target cardiac cine image includes: When the target phase numbers of the various cardiac slices are the same, the multi-phase images of the various cardiac slices are rearranged according to the target phases to obtain target cardiac movie images.
5. The medical image processing method according to claim 3, characterized in that: The step of aligning the initial cardiac cine images according to the target phase number and the target phase of each cardiac slice to obtain a target cardiac cine image includes: When the target phase numbers of the various cardiac slices are different, determining the target phase values of the various cardiac slices; interpolating the multi-phase images of each cardiac layer according to the target phase value to obtain an interpolated image; The interpolated multi-phase images of each cardiac layer are rearranged according to the target phase to obtain a target cardiac movie image.
6. The medical image processing method according to claim 5, characterized in that: The step of interpolating the multi-phase images of each cardiac layer according to the target phase value to obtain an interpolated image includes: Transforming the multi-phase images of each cardiac layer into k-space, interpolating the data between the k-space target phases of each cardiac layer to the target phase value, and obtaining the target data; The target data is transformed into the image domain to obtain the interpolated image.
7. The medical image processing method according to any one of claims 1 to 6, characterized in that: The target phases include an end-systolic cardiac phase and an end-diastolic cardiac phase.
8. A medical image processing method, characterized in that: The method comprises: Acquire real-time cine images of the heart; Analyzing the real-time cardiac movie image to determine the end-systolic cardiac phase and the end-diastolic cardiac phase; According to the cardiac phase identification result, an image containing a complete cardiac cycle is generated by alignment; Analyze the aligned real-time cine images of the heart; The results of the analysis are displayed.
9. A medical image processing device, characterized in that: The device comprises: An acquisition module, used for acquiring an initial cardiac movie image, wherein the initial cardiac movie image includes a plurality of cardiac slices, and the cardiac slices include a plurality of phase images; an identification module, used for determining a target phase of each cardiac slice according to the initial cardiac cine image; An alignment module is used to align the initial cardiac movie image according to the target phase to obtain a target cardiac movie image.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the medical image processing method according to any one of claims 1 to 8 are implemented.
