Magnetic resonance spectrum automatic positioning method, device, equipment and medium

Abstract

The invention relates to the technical field of image recognition, in particular to a magnetic resonance spectrum imaging automatic positioning method and device, equipment and a medium, and the method comprises the steps: obtaining historical imaging data of different historical brain diseases; constructing a focus recognition module based on historical iconography data; scanning a transection position, a sagittal position and a coronal position of the brain of the target patient to obtain a scanning result; based on the scanning result and a focus recognition model, performing preliminary recognition on the scanning result, and determining the focus level and area of the brain of the target patient; a mode recognition method is adopted to recognize the focus level and area, and the focus parenchyma center is accurately determined; according to the method, scanning is carried out by taking the focus parenchyma center as the single voxel center and taking the focus parenchyma center and normal tissue positions around the focus area as multiple voxels, positioning of magnetic resonance spectrum imaging is realized, a machine model training mode is adopted, the focus positioning speed can be increased, and thus the accuracy of single voxel and multi-voxel spectrum imaging positioning is improved.

Description

Technical Field

[0001] The present invention relates to the field of image recognition technology, and in particular to a magnetic resonance spectroscopy imaging automatic positioning method, device, equipment and medium. Background Art

[0002] Magnetic resonance spectroscopy is currently the only clinical imaging method that can non-invasively reflect tissue metabolic products. It is different from conventional structural imaging in that it is a local imaging method. Since the imaging area is small, often one or voxels, the positioning requirements are extremely high. Traditional magnetic resonance spectroscopy positioning relies on the subjective judgment of imaging technicians. However, since the essence of the lesions in some patients is not clear, and some of the locations are diverse, it is easy to cause inaccurate positioning of single-voxel and multi-voxel spectroscopy imaging. Due to the influence of factors such as the same symptoms but different diseases, timely subjective judgment is easily disturbed, which leads to positioning errors during magnetic resonance spectroscopy imaging. In order to better achieve positioning, some situations where it is difficult to determine the essence of the lesions require enhanced imaging, which increases the burden on the patients' kidneys.

[0003] Therefore, how to accurately locate the lesion is a technical problem that needs to be solved urgently. Summary of the invention

[0004] In view of the above problems, the present invention provides a method, device and apparatus for automatic positioning of magnetic resonance spectroscopy imaging that overcomes the above problems or at least partially solves the above problems.

[0005] In a first aspect, the present invention provides a method for automatic positioning of magnetic resonance spectroscopy imaging, comprising:

[0006] Obtain historical imaging data of different brain diseases;

[0007] Based on the historical imaging data, construct a lesion recognition model;

[0008] Scan the target patient's brain in transverse, sagittal, and coronal positions to obtain scanning results;

[0009] Based on the scan result and the lesion recognition model, preliminarily identifying the scan result, and determining the lesion level and area of ​​the target patient's brain;

[0010] The lesion level and area are identified by pattern recognition method to accurately determine the lesion parenchymal center;

[0011] The lesion parenchyma center is taken as a single voxel center, and the lesion parenchyma center and normal tissues around the lesion area are taken as multiple voxels for scanning, so as to realize automatic positioning of magnetic resonance spectroscopy imaging.

[0012] Preferably, it also includes:

[0013] When the lesion area is an abnormal hippocampus of an epileptic patient, scanning is performed in a transverse plane parallel to the hippocampus;

[0014] The hippocampus is taken as a single voxel center and the bilaterally symmetrical regions of the hippocampus are taken as multiple voxels for scanning to achieve the positioning of magnetic resonance spectroscopy imaging.

[0015] Preferably, the historical imaging data include: historical magnetic resonance images and areas of hemorrhage, necrosis, cystic change, bone, air and areas of different lesion types marked on the historical magnetic resonance images.

[0016] Preferably, based on the historical imaging data, a lesion recognition model is constructed, including:

[0017] The historical magnetic resonance images in the historical imaging data are used as input data, and the areas of hemorrhage, necrosis, cystic change, bone and air and different lesion type areas marked on the historical magnetic resonance images are used as output data and input into the classification model to train the classification model and construct a lesion recognition model, wherein the lesion recognition model is used to identify lesion type areas and areas of hemorrhage, necrosis, cystic change, bone and air.

[0018] Preferably, the target patient's brain is scanned in transverse, sagittal, and coronal positions, and the scanning sequence used includes any of the following:

[0019] T2 FLAIR, T2WI FSE, DWI and T1WI enhancement.

[0020] Preferably, the lesion level and region are identified using a pattern recognition method to determine the parenchymal center of the lesion, including:

[0021] Obtain N coordinate points of the boundary between the lesion layer and the region;

[0022] Based on the N coordinate points, calculating the mean of the N coordinate points;

[0023] Based on the mean, the parenchymal center of the lesion was determined.

[0024] Preferably, the lesion parenchyma center is used as a single voxel center, and the lesion parenchyma center and normal tissues around the lesion area are used as multiple voxels for scanning to achieve automatic positioning of magnetic resonance spectroscopy imaging, including:

[0025] The automatic tracking saturation band technology is adopted, with the lesion parenchyma center as a single voxel center, and the lesion parenchyma center and normal tissues around the lesion area as multiple voxels, to perform lesion identification and realize automatic positioning of magnetic resonance spectroscopy imaging.

[0026] In a second aspect, the present invention further provides an automatic positioning device for magnetic resonance spectroscopy imaging, comprising:

[0027] An acquisition module, used to obtain historical imaging data of different brain diseases;

[0028] A construction module, used to construct a lesion recognition model based on the historical imaging data;

[0029] A scanning module is used to scan the target patient's brain in transverse, sagittal, and coronal positions to obtain scanning results;

[0030] A first determination module is used to perform preliminary identification on the scan result based on the scan result and the lesion identification model to determine the lesion level and area of ​​the target patient's brain;

[0031] The second determination module is used to identify the lesion level and area using a pattern recognition method to accurately determine the lesion parenchymal center;

[0032] The first recognition module is used to scan with the lesion parenchyma center as a single voxel center and with the lesion parenchyma center and normal tissues around the lesion area as multiple voxels to achieve automatic positioning of magnetic resonance spectroscopy imaging.

[0033] In a third aspect, the present invention further provides a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method described in the first aspect when executing the program.

[0034] In a fourth aspect, the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method described in the first aspect.

[0035] One or more technical solutions in the embodiments of the present invention have at least the following technical effects or advantages:

[0036] The present invention provides an automatic positioning method for magnetic resonance spectroscopy imaging, comprising: acquiring historical imaging data of different brain diseases; constructing a lesion recognition module based on the historical imaging data; scanning the target patient's brain in transverse, sagittal and coronal positions to obtain scanning results; preliminarily identifying the scanning results based on the scanning results and a lesion recognition model to determine the lesion level and area of ​​the target patient's brain; identifying the lesion level and area using a pattern recognition method to accurately determine the lesion parenchyma center; scanning with the lesion parenchyma center as a single voxel center and with the lesion parenchyma center and normal tissues around the lesion area as multiple voxels to achieve automatic positioning of magnetic resonance spectroscopy imaging, adopting a machine model training method to accelerate the speed of lesion positioning, and positioning the center point by scanning in three directions, thereby improving the accuracy of single voxel and multi-voxel spectroscopy imaging positioning. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present invention. Also, throughout the accompanying drawings, the same reference figures are used to represent the same components. In the drawings:

[0038] Figure 1 A schematic diagram of the steps of the automatic positioning method for magnetic resonance spectroscopy imaging in an embodiment of the present invention is shown;

[0039] Figure 2 A schematic diagram of the structure of an automatic positioning device for magnetic resonance spectroscopy imaging in an embodiment of the present invention is shown;

[0040] Figure 3 A schematic diagram of the structure of a computer device for implementing an automatic positioning method for magnetic resonance spectroscopy imaging in an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0041] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0042] Embodiment 1:

[0043] The embodiment of the present invention provides a method for automatic positioning of magnetic resonance spectroscopy imaging, such as Figure 1 As shown, including:

[0044] S101, obtain historical imaging data of different brain diseases;

[0045] S102, constructing a lesion recognition model based on historical imaging data;

[0046] S103, scanning the target patient's brain in transverse, sagittal, and coronal positions to obtain a scanning result;

[0047] S104, based on the scan results and the lesion recognition model, preliminarily identifying the scan results to determine the lesion level and area of ​​the target patient's brain;

[0048] S105, pattern recognition methods are used to identify the lesion level and area, and the lesion parenchymal center is accurately determined;

[0049] S106, taking the center of the lesion substance as a single voxel center, and taking the center of the lesion substance and normal tissues around the lesion area as multiple voxels for scanning, to achieve automatic positioning of magnetic resonance spectroscopy imaging.

[0050] First, S101, historical imaging data of different brain diseases are obtained, wherein the different brain diseases specifically include: metabolic encephalopathy, epilepsy, brain tumor, etc. The historical imaging data include: historical magnetic resonance images and areas of hemorrhage, necrosis, cystic change, bone, air, and different lesion type areas annotated on the historical magnetic resonance images.

[0051] The hemorrhage, necrosis, cystic change, bone, and air are distinguished by the type of lesion.

[0052] Next, execute S102 to construct a lesion recognition model based on historical imaging data.

[0053] Specifically, historical magnetic resonance images in historical imaging data are used as input data, and areas of hemorrhage, necrosis, cystic change, bone and air as well as areas of different lesion types marked on the historical magnetic resonance images are used as output data, which are all input into the classification model to train the classification model and construct a lesion recognition model. The lesion recognition model is used to identify lesion type areas and areas of hemorrhage, necrosis, cystic change, bone and air.

[0054] The historical imaging data can change its signal or volume, etc., to enrich the number of samples to improve the robustness of the lesion recognition model.

[0055] The lesion recognition model can effectively avoid areas of bleeding, necrosis, cystic degeneration, bone and air, and accurately identify lesion type areas.

[0056] Then, execute S103 to scan the target patient's brain in transverse, sagittal, and coronal planes to obtain scanning results; S104 to preliminarily identify the scanning results based on the scanning results and the lesion recognition model to determine the lesion level and area of ​​the target patient's brain.

[0057] In the actual clinical application stage, the target patient's brain is scanned by a magnetic resonance imaging device to obtain the scan result. During the scanning process, the scan sequence that can be used includes any of the following: T2 FLAIR, T2WI FSE, DWI, T1WI enhancement. Then, the scan result is directly input into the lesion recognition model, and the scan result is preliminarily recognized, so that the lesion level and area of ​​the target patient's brain are output through the lesion recognition model.

[0058] The lesion recognition model is used to determine the approximate location of the lesion, thereby improving the efficiency of lesion recognition and avoiding the disadvantage of relying on the subjective judgment of imaging technicians.

[0059] At this time, the lesion area obtained is a rough area with a large position range, and a more detailed position needs to be determined from the lesion area.

[0060] Next, S105 is executed to identify the lesion level and area using a pattern recognition method to accurately determine the lesion parenchymal center.

[0061] Specifically, the transverse plane is perpendicular to the long axis of the body. The sagittal plane is parallel to the side of the body from left to right. The coronal plane is parallel to the front of the body.

[0062] Each direction includes multiple slices. Through scanning in multiple directions, the overlap area of ​​the transverse, sagittal and coronal planes can be determined. The overlap area is an irregular three-dimensional area. Next, in order to determine the center of the overlap area, that is, the center of the lesion substance, it is determined as follows:

[0063] Obtain N coordinate points of the lesion layer and the edge of the region;

[0064] Based on N coordinate points, calculate the mean of N coordinate points;

[0065] Based on this mean, the parenchymal center of the lesion was determined.

[0066] In a specific embodiment, N coordinate points are uniformly selected at the boundary between the lesion layer and the region, that is, (x i ,y i , z i ), i∈[1,N]. Next, the mean of the N coordinate points is calculated. Specifically, the horizontal axis coordinates of all coordinate points are added, and then divided by N to obtain the horizontal axis mean. The vertical axis coordinates of all coordinate points are added, and then divided by N to obtain the vertical axis mean. The same is true for the Z axis. The mean is taken as the parenchymal center of the lesion. The more the number of the N coordinate points, the higher the accuracy of the lesion parenchymal center finally located.

[0067] Finally, S106 , the lesion parenchyma center is used as the single voxel center, and the lesion parenchyma center and the normal tissues around the lesion area are used as multi-voxels for scanning, so as to realize automatic positioning of magnetic resonance spectroscopy imaging.

[0068] Specifically, the automatic tracking saturation band technology is used, with the center of the lesion substance as the center of a single voxel, and the center of the lesion substance and the normal tissue around the lesion area as multiple voxels, to perform lesion identification and achieve positioning of magnetic resonance spectroscopy imaging.

[0069] Among them, in the automatic tracking saturation band technology, the saturation band is often used to saturate the tissue signal in the selected space to reduce the impact of the signal in the selected space on the image. When the center of the lesion substance is taken as the center of a single voxel, other areas outside the center of the lesion substance are determined as saturation bands to avoid signal impact on the scanning of the center of the lesion substance. Similarly, the same is true for multiple voxels.

[0070] Through single-voxel localization and multi-voxel localization, the single voxel is used as a reference to compare multiple voxels and accurately locate the parenchymal point of the lesion.

[0071] The above scheme is aimed at locating the lesions of abnormal hippocampus in patients with epilepsy. For locating the lesions of abnormal hippocampus in patients with epilepsy, the following methods are specifically adopted:

[0072] When the lesion area was abnormal in the hippocampus of patients with epilepsy, the transverse plane was scanned parallel to the hippocampus;

[0073] The hippocampus was taken as the single voxel center and the symmetrical areas on both sides of the hippocampus were taken as multi-voxels for scanning to achieve automatic positioning of magnetic resonance spectroscopy imaging.

[0074] In a specific embodiment, the hippocampus is in the temporal lobe of the brain, which is located on the outer side of the cerebral hemisphere, above the medial wall of the skull and below the occipital part. The hippocampus is named because it looks like a hippocampus and can receive various sensory or perceptual information. The hippocampus is a curved structure, so the conventional transverse position cannot accurately scan the true situation of the hippocampus. Therefore, the transverse position needs to be adjusted to be parallel to the direction of the hippocampus curvature. The symmetrical areas on both sides of the hippocampus are scanned as multiple voxels.

[0075] The hippocampal abnormalities of epileptic patients are also scanned using single-voxel and multi-voxel scanning to locate the lesions.

[0076] One or more technical solutions in the embodiments of the present invention have at least the following technical effects or advantages:

[0077] The present invention provides an automatic positioning method for magnetic resonance spectroscopy imaging, comprising: acquiring historical imaging data of different brain diseases; constructing a lesion recognition module based on the historical imaging data; scanning the transverse, sagittal and coronal positions of the brain of a target patient to obtain a scanning result; preliminarily identifying the scanning result based on the scanning result and a lesion recognition model to determine the lesion level and area of ​​the brain of the target patient, identifying the lesion level and area using a pattern recognition method, and accurately determining the lesion parenchyma center; scanning with the lesion parenchyma center as a single voxel center, and with the lesion parenchyma center and normal tissues around the lesion area as multiple voxels to realize automatic positioning of magnetic resonance spectroscopy imaging, adopting a machine model training method to accelerate the speed of lesion positioning, and positioning the center point by scanning in three directions, thereby improving the accuracy of single voxel and multi-voxel spectroscopy imaging positioning.

[0078] Embodiment 2:

[0079] Based on the same inventive concept, the embodiment of the present invention also provides an automatic positioning device for magnetic resonance spectroscopy imaging, such as Figure 2 As shown, including:

[0080] An acquisition module 201 is used to acquire historical imaging data of different brain diseases;

[0081] A construction module 202 is used to construct a lesion recognition model based on the historical imaging data;

[0082] The scanning module 203 is used to scan the target patient's brain in transverse, sagittal, and coronal positions to obtain scanning results;

[0083] The first determination module 204 is used to perform preliminary identification on the scan result based on the scan result and the lesion identification model to determine the lesion level and area of ​​the target patient's brain;

[0084] The second determination module 205 is used to identify the lesion level and area using a pattern recognition method to accurately determine the lesion parenchymal center;

[0085] The first recognition module 206 is used to perform scanning with the lesion parenchyma center as a single voxel center and the lesion parenchyma center and normal tissues around the lesion area as multiple voxels to achieve automatic positioning of magnetic resonance spectroscopy imaging.

[0086] In an optional implementation, the method further includes: a second identification module, configured to:

[0087] When the lesion area is an abnormal hippocampus of an epileptic patient, scanning is performed in a transverse plane parallel to the hippocampus;

[0088] The hippocampus is taken as a single voxel center and the bilaterally symmetrical regions of the hippocampus are taken as multiple voxels for scanning to achieve the positioning of magnetic resonance spectroscopy imaging.

[0089] In an optional embodiment, the historical imaging data includes: historical magnetic resonance images and areas of hemorrhage, necrosis, cystic change, bone, air and different lesion type areas annotated on the historical magnetic resonance images.

[0090] In an optional implementation, the construction module 203 is used to:

[0091] The historical magnetic resonance images in the historical imaging data are used as input data, and the areas of hemorrhage, necrosis, cystic change, bone and air and different lesion type areas marked on the historical magnetic resonance images are used as output data and input into the classification model to train the classification model and construct a lesion recognition model, wherein the lesion recognition model is used to identify lesion type areas and areas of hemorrhage, necrosis, cystic change, bone and air.

[0092] In an optional embodiment, the target patient's brain is scanned in transverse, sagittal, and coronal positions, and the scanning sequence used includes any of the following:

[0093] T2 FLAIR, T2WI FSE, DWI and T1WI enhancement.

[0094] In an optional implementation manner, the second determining module 205 is configured to:

[0095] Obtain N coordinate points of the boundary between the lesion layer and the region;

[0096] Based on the N coordinate points, calculating the mean of the N coordinate points;

[0097] Based on the mean, the parenchymal center of the lesion was determined.

[0098] In an optional implementation, the first identification module 206 is configured to:

[0099] The lesion parenchyma center is taken as a single voxel center, and the lesion parenchyma center and normal tissues around the lesion area are taken as multiple voxels for scanning to achieve the positioning of magnetic resonance spectroscopy imaging.

[0100] Embodiment 3

[0101] Based on the same inventive concept, an embodiment of the present invention provides a computer device, such as Figure 3As shown, it includes a memory 304, a processor 302, and a computer program stored in the memory 304 and executable on the processor 302. When the processor 302 executes the program, the steps of the above-mentioned magnetic resonance spectroscopy imaging automatic positioning method are implemented.

[0102] Among them, Figure 3 In the embodiment of the present invention, a bus architecture (represented by bus 300) is shown, which may include any number of interconnected buses and bridges, and bus 300 links various circuits including one or more processors represented by processor 302 and memory represented by memory 304. Bus 300 may also link various other circuits such as peripherals, voltage regulators, and power management circuits, which are well known in the art and are therefore not further described herein. Bus interface 306 provides an interface between bus 300 and receiver 301 and transmitter 303. Receiver 301 and transmitter 303 may be the same element, namely a transceiver, providing a unit for communicating with various other devices over a transmission medium. Processor 302 is responsible for managing bus 300 and general processing, while memory 304 may be used to store data used by processor 302 when performing operations.

[0103] Embodiment 4

[0104] Based on the same inventive concept, an embodiment of the present invention provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the steps of the above-mentioned magnetic resonance spectroscopy imaging automatic positioning method are implemented.

[0105] The algorithm and display provided herein are not inherently related to any particular computer, virtual system or other device. Various general purpose systems can also be used together with the teachings based on this. According to the above description, it is obvious that the structure required for constructing such systems. In addition, the present invention is not directed to any specific programming language either. It should be understood that various programming languages ​​can be utilized to realize the content of the present invention described herein, and the description of the above specific languages ​​is for disclosing the best mode of the present invention.

[0106] In the description provided herein, a large number of specific details are described. However, it is understood that embodiments of the present invention can be practiced without these specific details. In some instances, well-known methods, structures and techniques are not shown in detail so as not to obscure the understanding of this description.

[0107] Similarly, it should be understood that in order to streamline the present disclosure and aid in understanding one or more of the various inventive aspects, in the above description of exemplary embodiments of the present invention, the various features of the present invention are sometimes grouped together into a single embodiment, figure, or description thereof. However, this disclosed method should not be interpreted as reflecting the following intention: that the claimed invention requires more features than the features explicitly recorded in each embodiment. More specifically, as reflected in each embodiment, the inventive aspects lie in less than all the features of the single embodiment disclosed above. Therefore, the claims that follow the specific embodiment are hereby expressly incorporated into the specific embodiment, with each claim itself serving as a separate embodiment of the present invention.

[0108] Those skilled in the art will appreciate that the modules in the devices in the embodiments may be adaptively changed and arranged in one or more devices different from the embodiments. The modules or units or components in the embodiments may be combined into one module or unit or component, and in addition they may be divided into a plurality of submodules or subunits or subcomponents. Except that at least some of such features and / or processes or units are mutually exclusive, all features disclosed in this specification (including the accompanying claims, abstracts and drawings) and all processes or units of any method or device disclosed in this manner may be combined in any combination. Unless otherwise expressly stated, each feature disclosed in this specification (including the accompanying claims, abstracts and drawings) may be replaced by an alternative feature providing the same, equivalent or similar purpose.

[0109] In addition, those skilled in the art will appreciate that, although some embodiments herein include certain features included in other embodiments but not other features, the combination of features of different embodiments is meant to be within the scope of the present invention and form different embodiments. For example, in a specific embodiment, any one of the claimed embodiments may be used in any combination.

[0110] The various component embodiments of the present invention can be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. It should be understood by those skilled in the art that a microprocessor or digital signal processor (DSP) can be used in practice to implement some or all functions of some or all components in the automatic positioning device for magnetic resonance spectroscopy imaging and computer equipment according to an embodiment of the present invention. The present invention can also be implemented as a device or device program (e.g., computer program and computer program product) for executing part or all of the methods described herein. Such a program implementing the present invention can be stored on a computer-readable medium, or can have the form of one or more signals. Such a signal can be downloaded from an Internet website, or provided on a carrier signal, or provided in any other form.

[0111] It should be noted that the above embodiments illustrate the present invention rather than limit it, and that those skilled in the art may devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference symbol between brackets shall not be construed as a limitation on the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "one" or "an" preceding an element does not exclude the presence of a plurality of such elements. The present invention may be implemented by means of hardware comprising a number of different elements and by means of a suitably programmed computer. In a unit claim enumerating a number of devices, several of these devices may be embodied by the same hardware item. The use of the words first, second, and third, etc., does not indicate any order. These words may be interpreted as names.

Claims

1. A method for automatic positioning of magnetic resonance spectroscopy imaging, characterized in that: include: Obtain historical imaging data of different brain diseases; Based on the historical imaging data, construct a lesion recognition model; Scan the target patient's brain in transverse, sagittal, and coronal positions to obtain scanning results; Based on the scan result and the lesion recognition model, preliminarily identifying the scan result, and determining the lesion level and area of ​​the target patient's brain; The lesion level and area are identified by pattern recognition method to accurately determine the lesion parenchymal center; The lesion parenchyma center is taken as a single voxel center, and the lesion parenchyma center and normal tissues around the lesion area are taken as multiple voxels for scanning, so as to realize automatic positioning of magnetic resonance spectroscopy imaging.

2. The method according to claim 1, characterized in that Also includes: When the lesion area is an abnormal hippocampus of an epileptic patient, scanning is performed in a transverse plane parallel to the hippocampus; The hippocampus is taken as a single voxel center and the bilaterally symmetrical regions of the hippocampus are taken as multiple voxels for scanning to achieve the positioning of magnetic resonance spectroscopy imaging.

3. The method according to claim 1, characterized in that The historical imaging data includes: historical magnetic resonance images and areas of hemorrhage, necrosis, cystic change, bone, air and different lesion types marked on the historical magnetic resonance images.

4. The method according to claim 3, characterized in that Based on the historical imaging data, a lesion recognition model is constructed, including: The historical magnetic resonance images in the historical imaging data are used as input data, and the areas of hemorrhage, necrosis, cystic change, bone and air and different lesion type areas marked on the historical magnetic resonance images are used as output data and input into the classification model to train the classification model and construct a lesion recognition model, wherein the lesion recognition model is used to identify lesion type areas and areas of hemorrhage, necrosis, cystic change, bone and air.

5. The method according to claim 1, characterized in that The target patient's brain is scanned in transverse, sagittal, and coronal planes using any of the following scanning sequences: T2 FLAIR, T2WIFSE, DWI and T1WI enhancement.

6. The method according to claim 1, characterized in that Pattern recognition methods are used to identify the lesion level and area to determine the parenchymal center of the lesion, including: Obtain N coordinate points of the boundary between the lesion layer and the region; Based on the N coordinate points, calculating the mean of the N coordinate points; Based on the mean, the parenchymal center of the lesion was determined.

7. The method according to claim 1, characterized in that The method uses the center of the lesion substance as a single voxel center, and uses the center of the lesion substance and normal tissues around the lesion area as multiple voxels for scanning to achieve automatic positioning of magnetic resonance spectroscopy imaging, including: The automatic tracking saturation band technology is adopted, with the lesion parenchyma center as a single voxel center, and the lesion parenchyma center and normal tissues around the lesion area as multiple voxels, to perform lesion identification and realize automatic positioning of magnetic resonance spectroscopy imaging.

8. An automatic positioning device for magnetic resonance spectroscopy imaging, characterized in that: include: An acquisition module, used to obtain historical imaging data of different brain diseases; A construction module, used to construct a lesion recognition model based on the historical imaging data; A scanning module is used to scan the target patient's brain in transverse, sagittal, and coronal positions to obtain scanning results; A first determination module is used to perform preliminary identification on the scan result based on the scan result and the lesion identification model to determine the lesion level and area of ​​the target patient's brain; The second determination module is used to identify the lesion level and area using a pattern recognition method to accurately determine the lesion parenchymal center; The first recognition module is used to scan with the lesion parenchyma center as a single voxel center and with the lesion parenchyma center and normal tissues around the lesion area as multiple voxels to achieve automatic positioning of magnetic resonance spectroscopy imaging.

9. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the method according to any one of claims 1 to 7 is implemented.

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

Images