A brain nodule load generation method based on MRI and related equipment

Abstract

The present invention discloses a brain nodule load generation method based on MRI and related equipment, the method comprising: obtaining MRI data of a target object, the MRI data comprising T2W images and FLAIR images, dividing the T2W images and FLAIR images into eight types of classified images according to a preset classification standard; identifying the classified images, obtaining images containing cortical nodule lesions, segmenting and labeling the images containing cortical nodule lesions, and obtaining target images; obtaining the volume of cortical nodule lesions, the number of cortical nodule lesions, and the proportion of the brain occupied by the cortical nodule lesions in the target image, and obtaining the brain nodule load of the target object according to the volume of the cortical nodule lesions, the number of cortical nodule lesions, and the proportion of the brain occupied by the cortical nodule lesions. The present invention takes into account the volume of nodules and the proportion of the brain, and provides a more comprehensive and accurate nodule load generation method than counting alone, which can provide effective reference information for evaluating the user's brain and cognition.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a method for generating brain nodule load based on MRI and related equipment. Background Art

[0002] Histologically, tuberosities are characterized by abnormal laminar structures in the cortex as well as abnormal cells, including malformed neurons and giant cells. In patients with TSC (tuberous sclerosis), the ratio of tuberosities to the brain is directly correlated with the severity of epileptic seizures and inversely correlated with cognitive function. Magnetic Resonance Imaging (MRI), as an advanced medical imaging technique, is widely used to obtain high-quality brain images. It not only plays an important role in the diagnosis of a variety of diseases, but also provides detailed information about the internal structure of the brain.

[0003] Cortical tubers are the main brain manifestation associated with TSC, showing abnormal high or low signals in FLAIR (fluid attenuated inversion recovery sequence). In addition, FLAIR imaging is widely used to study the epileptogenic zone and epilepsy mechanism of TSC. The assessment of the tubercle burden can better judge the patient's brain condition.

[0004] Currently, nodule burden estimates usually rely solely on the number or proportion of nodules, and the differences in this estimate are not only due to clinical heterogeneity, but also affected by scanning sensitivity, lesion identification schemes, and imaging methods. This estimate is often subjective and lacks reproducibility. In addition, counting only the number of nodules may underestimate the impact of large lesions and overestimate the impact of small lesions. Therefore, the relationship between the number of nodules and intelligence is not completely clear, and estimating nodule burden based solely on the number of nodules is not accurate enough to more fully understand the status of the target subject through nodule burden.

[0005] Therefore, the prior art still needs to be improved and developed. Summary of the invention

[0006] The main purpose of the present invention is to provide a method, system, terminal and computer-readable storage medium for generating brain nodule load based on MRI, aiming to solve the problem in the prior art that the result obtained by estimating nodule load only by the number of nodules is not accurate enough and cannot provide effective reference information.

[0007] To achieve the above object, the present invention provides a method for generating brain nodule load based on MRI, and the method for generating brain nodule load based on MRI comprises the following steps:

[0008] Acquire MRI data of a target object, wherein the MRI data includes a T2W image and a FLAIR image, and classify the T2W image and the FLAIR image into eight types of classified images according to a preset classification standard;

[0009] Identify the classified image to obtain an image containing cortical tubercle lesions, segment and annotate the image containing cortical tubercle lesions to obtain a target image;

[0010] The volume of cortical tubercle lesions, the number of cortical tubercle lesions and the proportion of the brain occupied by cortical tubercle lesions in the target image are obtained, and the brain nodule load of the target object is obtained according to the volume of cortical tubercle lesions, the number of cortical tubercle lesions and the proportion of the brain occupied by the cortical tubercle lesions.

[0011] Optionally, the method for generating brain nodule load based on MRI, wherein the T2W image and FLAIR image are divided into eight types of classified images according to a preset classification standard, specifically including:

[0012] The T2W images and FLAIR images are divided into four types: type I lesions, type II lesions, type III lesions, and type IV lesions according to the signals of cortical and subcortical lesions and the morphology of subcortical lesions;

[0013] According to the location of the nodules in the brain region, the T2W images and FLAIR images are divided into four types: frontal lobe nodules, occipital lobe nodules, temporal lobe nodules and parietal lobe nodules.

[0014] Optionally, the MRI-based method for generating brain nodule burden, wherein the type I lesion is defined as a cortical lesion on T2W and FLAIR sequences, uniform or nodular thickening of the cortex, no abnormal changes in cortical signal, and high signal on subcortical T2W;

[0015] The type II lesions were defined as dysplastic cortical lesions, cortical inhomogeneity, nodular cortical thickening, and abnormal cortical signal;

[0016] The type III lesion was defined as a subcortical round nodule with high signal around the lesion and low signal in the center of the lesion on FLAIR sequence;

[0017] The type IV lesions were defined as hyperintense signals in the cortical or subcortical areas on FLAIR sequences with migration lines extending into the lateral ventricles.

[0018] Optionally, the method for generating brain nodule load based on MRI, wherein the step of identifying the classified image to obtain an image containing cortical nodule lesions, and segmenting and labeling the image containing the cortical nodule lesions to obtain a target image, specifically comprises:

[0019] Identify the classified images to obtain a plurality of images containing cortical tubercle lesions, and obtain single-plane images of the plurality of images containing cortical tubercle lesions on a cross-sectional T2-FLAIR sequence;

[0020] The ITK-SNAP tool is used to segment and annotate the cortical tubercle lesions in the single-sided image, thereby obtaining a plurality of target images with annotated locations and sizes of the cortical tubercle lesions.

[0021] Optionally, the method for generating brain nodule load based on MRI, wherein the step of obtaining the volume of cortical nodule lesions, the number of cortical nodule lesions, and the proportion of the cortical nodule lesions in the brain in the target image, further comprises:

[0022] The GetSpacing method in Python's SimpleITK library is used to obtain the spacing Δx, Δy, and Δz of a single voxel in each target image in the three dimensions of x, y, and z. The volume of a single voxel in each target image is obtained based on the spacing Δx, Δy, and Δz in the three dimensions: V voxel =Δx×Δy×Δz.

[0023] Optionally, the method for generating brain nodule load based on MRI, wherein the step of obtaining the volume of cortical nodule lesions, the number of cortical nodule lesions, and the proportion of the cortical nodule lesions in the brain in the target image specifically includes:

[0024] The number of voxels N of each nodule in the target image is obtained according to the size of the cortical nodule lesion. voxel , according to the number of voxels N of the nodule voxel and the volume V of the single voxel voxel , the volume of the cortical tubercle lesion in each target image is obtained: V tuber =N voxel ×V voxel ;

[0025] According to the number of annotations in each target image, the number of cortical tubercle lesions N in each target image is obtained. tuber ;

[0026] Get the brain volume V brain , according to the brain volume V brain and the number of cortical tubercle lesions N tuber Calculate the proportion of the brain occupied by the cortical tubercle lesion in each target image:

[0027] Optionally, the method for generating brain nodule load based on MRI, wherein the step of obtaining the brain nodule load of the target object according to the volume of the cortical nodule lesions, the number of the cortical nodule lesions and the proportion of the cortical nodule lesions in the brain, specifically comprises:

[0028] Calculate the brain nodule load in each target image according to the volume of the cortical tubercle lesions in each target image, the number of the cortical tubercle lesions in each target image, and the proportion of the cortical tubercle lesions in each target image to the brain;

[0029] The brain nodule load in each target image is added according to a preset weight to obtain the brain nodule load of the target object.

[0030] In addition, to achieve the above-mentioned purpose, the present invention also provides a brain nodule load generation system based on MRI, wherein the brain nodule load generation based on MRI includes:

[0031] An image data classification module is used to obtain MRI data of a target object, wherein the MRI data includes T2W images and FLAIR images, and classify the T2W images and FLAIR images into eight types of classified images according to a preset classification standard;

[0032] An image segmentation and annotation module is used to identify the classified image to obtain an image containing cortical tubercle lesions, and segment and annotate the image containing the cortical tubercle lesions to obtain a target image;

[0033] A nodule load calculation module is used to obtain the volume of cortical nodule lesions, the number of cortical nodule lesions and the proportion of the brain occupied by cortical nodule lesions in the target image, and obtain the brain nodule load of the target object according to the volume of cortical nodule lesions, the number of cortical nodule lesions and the proportion of the brain occupied by cortical nodule lesions.

[0034] In addition, to achieve the above-mentioned purpose, the present invention also provides a terminal, wherein the terminal includes: a memory, a processor, and an MRI-based brain nodule load generation program stored in the memory and executable on the processor, wherein the MRI-based brain nodule load generation program, when executed by the processor, implements the steps of the MRI-based brain nodule load generation method as described above.

[0035] In addition, to achieve the above-mentioned purpose, the present invention also provides a computer-readable storage medium, wherein the computer-readable storage medium stores an MRI-based brain nodule load generation program, and when the MRI-based brain nodule load generation program is executed by a processor, the steps of the MRI-based brain nodule load generation method as described above are implemented.

[0036] In the present invention, the MRI data of the target object is obtained, and the MRI data includes T2W images and FLAIR images, and the T2W images and FLAIR images are divided into eight types of classified images according to a preset classification standard; the classified images are identified to obtain images containing cortical tubercle lesions, and the images containing cortical tubercle lesions are segmented and labeled with cortical tubercle lesions to obtain target images; the volume of cortical tubercle lesions, the number of cortical tubercle lesions, and the proportion of the brain occupied by cortical tubercle lesions in the target image are obtained, and the brain nodule load of the target object is obtained according to the volume of cortical tubercle lesions, the number of cortical tubercle lesions, and the proportion of the brain occupied by cortical tubercle lesions. The present invention takes into account the volume of nodules and the proportion of brain, and provides a more comprehensive and accurate nodule load generation method than counting alone, which can provide effective reference information for evaluating the user's brain and cognition. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 It is a flow chart of a preferred embodiment of the method for generating brain nodule load based on MRI of the present invention;

[0038] Figure 2 are T2W and FLAIR images corresponding to the four lesion types in the MRI-based brain nodule load generation method of the present invention;

[0039] Figure 3 It is a schematic diagram of the principle of a preferred embodiment of the brain nodule load generation system based on MRI of the present invention;

[0040] Figure 4 Schematic diagram of the operating environment of a preferred embodiment of the terminal of the present invention. DETAILED DESCRIPTION

[0041] The present application provides a method for generating brain nodule load based on MRI and related equipment. In order to make the purpose, technical solution and effect of the present application clearer and more specific, the present application is further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0042] It will be understood by those skilled in the art that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as those generally understood by those skilled in the art to which this application belongs. It should also be understood that terms such as those defined in general dictionaries should be understood to have meanings consistent with those in the context of the prior art, and will not be interpreted with idealized or overly formal meanings unless specifically defined as here.

[0043] In addition, if there are descriptions involving "first", "second", etc. in the embodiments of the present invention, the descriptions of "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or suggesting their 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 addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the ability of ordinary technicians in the field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such a combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0044] The method for generating brain nodule load based on MRI described in the preferred embodiment of the present invention is as follows: Figure 1 As shown, the MRI-based brain nodule load generation method comprises the following steps:

[0045] Step S100, acquiring MRI data of a target object, wherein the MRI data includes a T2W image and a FLAIR image, and dividing the T2W image and the FLAIR image into eight types of classified images according to a preset classification standard;

[0046] It is understandable that the MRI data of the target object is obtained. Magnetic Resonance Imaging (MRI), as an advanced medical imaging technology, is widely used to obtain high-quality brain images. It not only plays an important role in the diagnosis of various diseases, but also provides detailed information about the internal structure of the brain; the MRI data includes T2W (T2 weighted imaging) images and FLAIR (fluid attenuated inversion recovery) images, both of which are sequences of magnetic resonance imaging. Among them, the target object can be an ordinary user or a TSC (tuberous sclerosis) patient. In this embodiment, the MRI data obtained is preferably the MRI data of a TSC patient, which can better reflect the significance of the present invention.

[0047] Specifically, Figure 2 As shown, the T2W image and FLAIR image are divided into four types: type I lesions, type II lesions, type III lesions and type IV lesions according to the signals of cortical and subcortical lesions and the morphology of subcortical lesions.

[0048] like Figure 2 (a) and Figure 2 As shown in (b), it shows the T2W and FLAIR images of a normal person.

[0049] like Figure 2 (c) and Figure 2 As shown by the red arrow in (d), the type I lesion is defined as cortical lesions on T2W and FLAIR sequences, uniform or nodular thickening of the cortex, no abnormal changes in cortical signal, and high signal on subcortical T2W.

[0050] The type II lesions were defined as cortical dysplasia (i.e., heterogeneous cortical thickening on T2W and FLAIR, such as Figure 2 (e) and Figure 2 (f) as indicated by the red arrow), uneven cortex, nodular cortical thickening, and abnormal cortical signal (as indicated by the red arrow in the figure). Figure 2 (g) and Figure 2 (indicated by the red arrow in (h)).

[0051] like Figure 2 As shown in (i) in the figure, the type III lesion is defined as a subcortical round nodule on the FLAIR sequence, with high signal around the lesion and low signal in the center of the lesion.

[0052] like Figure 2 As shown in (j) in FIG. 5A , the type IV lesion is defined as a migration line showing high signal in the cortical or subcortical area on the FLAIR sequence and the signal extending to the lateral ventricle.

[0053] Furthermore, according to the location of the nodules in the brain region, the T2W images and FLAIR images are divided into four types: frontal lobe nodules, occipital lobe nodules, temporal lobe nodules and parietal lobe nodules.

[0054] It is understandable that the frontal lobe, parietal lobe, occipital lobe, and temporal lobe are all located in the cerebral cortex, and their positions are different. They are located in the frontal bone, parietal bone, occipital bone, and temporal bone, respectively. The frontal lobe is usually located in the frontal bone, specifically behind the frontal lobe and above the occipital lobe. It can receive and process sensory information and participate in language processing; the parietal lobe is usually located in the tibia, which is the most frontal area of ​​the cerebral cortex. It can participate in functions such as movement and thinking, and can also control activities on the left side of the body; the occipital lobe is generally located in the occipital bone, and the specific position is usually after the connection line between the parieto-occipital sulcus and the anterior occipital notch. It is an important center for visual processing; the temporal lobe is usually located in the temporal bone, usually distributed directly below the temporal lobe and parietal lobe, and usually has a certain relationship with emotion and language function. This application divides the T2W image and FLAIR image according to the position structure of the brain area, and divides them into four types: frontal lobe nodules, occipital lobe nodules, temporal lobe nodules, and parietal lobe nodules, and makes a more detailed classification.

[0055] Furthermore, since a total of eight classification standards are set, the T2W image and the FLAIR image are divided according to the classification standards to obtain eight types of classified images, and the eight types of classified images will be processed separately later.

[0056] Step S200: Identify the classified image to obtain an image containing cortical tubercle lesions, segment and annotate the image containing the cortical tubercle lesions to obtain a target image.

[0057] The identifying the classified image to obtain an image containing cortical tubercle lesions, and segmenting and labeling the image containing cortical tubercle lesions to obtain a target image specifically includes:

[0058] The classified images are identified to obtain a plurality of images containing cortical tubercle lesions, and single-plane images of the plurality of images containing cortical tubercle lesions on a cross-sectional T2-FLAIR sequence are obtained.

[0059] The ITK-SNAP tool is used to segment and annotate the cortical tubercle lesions in the single-sided image, thereby obtaining a plurality of target images with annotated locations and sizes of the cortical tubercle lesions.

[0060] It can be understood that among the eight classified images, there may be abnormal images, i.e., images containing cortical tubercle lesions, and there may also be normal images, i.e., images that do not contain cortical tubercle lesions. The eight classified images are identified to obtain several images containing cortical tubercle lesions; the images are obtained by magnetic resonance scanning, with a total of three planes, and single-plane images of several images containing cortical tubercle lesions on the cross-sectional T2-FLAIR sequence are obtained.

[0061] Furthermore, the ITK-SNAP tool (a tool commonly used in medical imaging) is used to segment and annotate the cortical tubercle lesions in the single-sided image, wherein the process of segmenting and annotating the cortical tubercle lesions in the single-sided image is completed by a physician (such as a radiologist), and different lesions are annotated and distinguished with accuracy to the pixel level, thereby obtaining several target images with annotated cortical tubercle lesion locations and cortical tubercle lesion sizes.

[0062] Step S300, obtaining the volume of cortical tubercle lesions, the number of cortical tubercle lesions, and the proportion of the brain occupied by cortical tubercle lesions in the target image, and obtaining the brain nodule load of the target object according to the volume of cortical tubercle lesions, the number of cortical tubercle lesions, and the proportion of the brain occupied by the cortical tubercle lesions.

[0063] The step of obtaining the volume of cortical tubercle lesions, the number of cortical tubercle lesions, and the proportion of the cortical tubercle lesions in the brain in the target image may also include:

[0064] The GetSpacing method in Python's SimpleITK library is used to obtain the spacing Δx, Δy, and Δz of a single voxel in each target image in the three dimensions of x, y, and z. The volume of a single voxel in each target image is obtained based on the spacing Δx, Δy, and Δz in the three dimensions: V voxel =Δx×Δy×Δz.

[0065] It can be understood that by calling the GetSpacing method in Python's SimpleITK library, the spacing Δx, Δy and Δz of a single voxel in each target image in the three dimensions of x, y and z can be directly obtained. According to the spacing Δx, Δy and Δz in the three dimensions, the volume of a single voxel (short for volume pixel, a volume containing voxels can be expressed by stereo rendering or extracting a polygonal isosurface with a given threshold contour) in each target image is obtained: V voxel =Δx×Δy×Δz.

[0066] The obtaining of the volume of cortical tubercle lesions, the number of cortical tubercle lesions, and the proportion of the cortical tubercle lesions in the brain in the target image specifically includes:

[0067] The number of voxels N of each nodule in the target image is obtained according to the size of the cortical nodule lesion. voxel , according to the number of voxels N of the nodule voxel and the volume V of the single voxel voxel , the volume of the cortical tubercle lesion in each target image is obtained: V tuber =N voxel ×V voxel ;

[0068] According to the number of annotations in each target image, the number of cortical tubercle lesions N in each target image is obtained. tuber ;

[0069] Get the brain volume V brain , according to the brain volume V brain and the number of cortical tubercle lesions N tuber Calculate the proportion of the brain occupied by the cortical tubercle lesion in each target image:

[0070] The step of obtaining the brain nodule load of the target object according to the volume of the cortical nodule lesions, the number of the cortical nodule lesions and the proportion of the cortical nodule lesions in the brain specifically includes:

[0071] Calculate the brain nodule load in each target image according to the volume of the cortical tubercle lesions in each target image, the number of the cortical tubercle lesions in each target image, and the proportion of the cortical tubercle lesions in each target image to the brain;

[0072] The brain nodule load in each target image is added according to a preset weight to obtain the brain nodule load of the target object.

[0073] It can be understood that after calculating the volume of cortical tubercle lesions, the number of cortical tubercle lesions and the proportion of the brain occupied by cortical tubercle lesions in each target image, the brain nodule load in each target image is calculated according to the volume of cortical tubercle lesions in each target image, the number of cortical tubercle lesions in each target image and the proportion of the brain occupied by the cortical tubercle lesions in each target image. Specifically, the brain nodule load in each target image is obtained by a comprehensive evaluation formula for the nodule load:

[0074] Burden=(V tuber , N tuber , P);

[0075] Wherein, Burden is the brain nodule load, V brain is the volume of the cortical tubercle lesion, N tuber is the number of cortical tubercle lesions, and P is the proportion of the cortical tubercle lesions in the brain.

[0076] Furthermore, after obtaining the brain nodule load in each target image according to the comprehensive evaluation formula of the nodule load, the brain nodule load in each target image is added according to the preset weight (the weight corresponding to the brain nodule load in each target image can be set according to the importance of the type. For example, if the target image of a certain type has a greater impact on the brain nodule load of the target object, a larger weight can be set for it) to obtain the brain nodule load of the target object.

[0077] It can be seen that the present invention classifies the nodules in MRI images in detail according to their location in the brain (such as frontal lobe, occipital lobe, etc.) and type (such as type I, type II, etc.), and combines the volume, number and proportion of the nodules in the brain to propose a new method for comprehensively evaluating the nodule burden, which provides a more comprehensive perspective for analyzing the relationship between the nodule burden and genotype, epilepsy and cognitive function of TSC patients.

[0078] In summary, the present invention obtains MRI data of a target object, wherein the MRI data includes T2W images and FLAIR images, and the T2W images and FLAIR images are divided into eight types of classified images according to preset classification criteria; the classified images are identified to obtain images containing cortical tubercle lesions, and the images containing cortical tubercle lesions are segmented and labeled with cortical tubercle lesions to obtain target images; the volume of cortical tubercle lesions, the number of cortical tubercle lesions, and the proportion of the brain occupied by cortical tubercle lesions in the target image are obtained, and the brain nodule load of the target object is obtained according to the volume of the cortical tubercle lesions, the number of the cortical tubercle lesions, and the proportion of the brain occupied by the cortical tubercle lesions. The present invention takes into account the volume of the nodules and the proportion of the brain, and provides a more comprehensive and accurate nodule load generation method than counting alone, which can provide effective reference information for evaluating the user's brain and cognition.

[0079] Furthermore, if Figure 3 As shown, based on the above-mentioned MRI-based brain nodule load generation method, the present invention also provides a MRI-based brain nodule load generation system, wherein the MRI-based brain nodule load generation system includes:

[0080] An image data classification module 51 is used to obtain MRI data of a target object, wherein the MRI data includes T2W images and FLAIR images, and classify the T2W images and FLAIR images into eight types of classified images according to a preset classification standard;

[0081] An image segmentation and annotation module 52 is used to identify the classified image to obtain an image containing cortical tubercle lesions, and segment and annotate the image containing the cortical tubercle lesions to obtain a target image;

[0082] The nodule load calculation module 53 is used to obtain the volume of cortical nodule lesions, the number of cortical nodule lesions and the proportion of the brain occupied by cortical nodule lesions in the target image, and obtain the brain nodule load of the target object according to the volume of cortical nodule lesions, the number of cortical nodule lesions and the proportion of the brain occupied by the cortical nodule lesions.

[0083] Furthermore, if Figure 4 As shown, based on the above-mentioned MRI-based brain nodule load generation method and system, the present invention also provides a terminal accordingly, and the terminal includes a processor 10, a memory 20 and a display 30. Figure 4 Only some components of the terminal are shown, but it should be understood that it is not required to implement all of the components shown, and more or fewer components may be implemented instead.

[0084] The memory 20 may be an internal storage unit of the terminal in some embodiments, such as a hard disk or memory of the terminal. The memory 20 may also be an external storage device of the terminal in other embodiments, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), etc. equipped on the terminal. Further, the memory 20 may also include both an internal storage unit of the terminal and an external storage device. The memory 20 is used to store application software and various types of data installed in the terminal, such as the program code of the installation terminal, etc. The memory 20 may also be used to temporarily store data that has been output or is to be output. In one embodiment, a brain nodule load generation program 40 based on MRI is stored on the memory 20, and the brain nodule load generation program 40 based on MRI can be executed by the processor 10, thereby realizing the brain nodule load generation method based on MRI in the present application.

[0085] In some embodiments, the processor 10 may be a central processing unit (CPU), a microprocessor or other data processing chip, used to run the program code or process data stored in the memory 20, such as executing the MRI-based brain nodule load generation method.

[0086] In some embodiments, the display 30 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, etc. The display 30 is used to display information on the terminal and to display a visual user interface. The components 10-30 of the terminal communicate with each other via a system bus.

[0087] In one embodiment, when the processor 10 executes the MRI-based brain nodule load generation program 40 in the memory 20, the following steps are implemented:

[0088] Acquire MRI data of a target object, wherein the MRI data includes a T2W image and a FLAIR image, and classify the T2W image and the FLAIR image into eight types of classified images according to a preset classification standard;

[0089] Identify the classified image to obtain an image containing cortical tubercle lesions, segment and annotate the image containing cortical tubercle lesions to obtain a target image;

[0090] The volume of cortical tubercle lesions, the number of cortical tubercle lesions and the proportion of the brain occupied by cortical tubercle lesions in the target image are obtained, and the brain nodule load of the target object is obtained according to the volume of cortical tubercle lesions, the number of cortical tubercle lesions and the proportion of the brain occupied by the cortical tubercle lesions.

[0091] The T2W image and FLAIR image are divided into eight types of classified images according to the preset classification criteria, specifically including:

[0092] The T2W images and FLAIR images are divided into four types: type I lesions, type II lesions, type III lesions, and type IV lesions according to the signals of cortical and subcortical lesions and the morphology of subcortical lesions;

[0093] According to the location of the nodules in the brain region, the T2W images and FLAIR images are divided into four types: frontal lobe nodules, occipital lobe nodules, temporal lobe nodules and parietal lobe nodules.

[0094] Among them, the type I lesion is defined as cortical lesions on T2W and FLAIR sequences, uniform or nodular thickening of the cortex, no abnormal changes in cortical signal, and high signal on subcortical T2W;

[0095] The type II lesions were defined as dysplastic cortical lesions, cortical inhomogeneity, nodular cortical thickening, and abnormal cortical signal;

[0096] The type III lesion was defined as a subcortical round nodule with high signal around the lesion and low signal in the center of the lesion on FLAIR sequence;

[0097] The type IV lesions were defined as hyperintense signals in the cortical or subcortical areas on FLAIR sequences with migration lines extending into the lateral ventricles.

[0098] The step of identifying the classified image to obtain an image containing cortical tubercle lesions, and segmenting and labeling the image containing cortical tubercle lesions to obtain a target image specifically includes:

[0099] Identify the classified images to obtain a plurality of images containing cortical tubercle lesions, and obtain single-plane images of the plurality of images containing cortical tubercle lesions on a cross-sectional T2-FLAIR sequence;

[0100] The ITK-SNAP tool is used to segment and annotate the cortical tubercle lesions in the single-sided image, thereby obtaining a plurality of target images with annotated locations and sizes of the cortical tubercle lesions.

[0101] Wherein, the step of obtaining the volume of cortical tubercle lesions, the number of cortical tubercle lesions and the proportion of the cortical tubercle lesions in the brain in the target image may also include:

[0102] The GetSpacing method in Python's SimpleITK library is used to obtain the spacing Δx, Δy, and Δz of a single voxel in each target image in the three dimensions of x, y, and z. The volume of a single voxel in each target image is obtained based on the spacing Δx, Δy, and Δz in the three dimensions: V voxel =Δx×Δy×Δz.

[0103] The step of obtaining the volume of cortical tubercle lesions, the number of cortical tubercle lesions, and the proportion of the cortical tubercle lesions in the brain in the target image specifically includes:

[0104] The number of voxels N of each nodule in the target image is obtained according to the size of the cortical nodule lesion. voxel , according to the number of voxels N of the nodule voxel and the volume V of the single voxel voxel , the volume of the cortical tubercle lesion in each target image is obtained: V tuber =N voxel ×V voxel ;

[0105] According to the number of annotations in each target image, the number of cortical tubercle lesions N in each target image is obtained. tubee ;

[0106] Get the brain volume V brain , according to the brain volume V brain and the number of cortical tubercle lesions N tuber Calculate the proportion of the brain occupied by the cortical tubercle lesion in each target image:

[0107] Wherein, obtaining the brain nodule load of the target object according to the volume of the cortical nodule lesions, the number of the cortical nodule lesions and the proportion of the cortical nodule lesions in the brain specifically includes:

[0108] Calculate the brain nodule load in each target image according to the volume of the cortical tubercle lesions in each target image, the number of the cortical tubercle lesions in each target image, and the proportion of the cortical tubercle lesions in each target image to the brain;

[0109] The brain nodule load in each target image is added according to a preset weight to obtain the brain nodule load of the target object.

[0110] The present invention also provides a computer-readable storage medium, wherein the computer-readable storage medium stores an MRI-based brain nodule load generation program, and when the MRI-based brain nodule load generation program is executed by a processor, the steps of the MRI-based brain nodule load generation method as described above are implemented.

[0111] In summary, the present invention proposes a method for generating brain nodule load based on MRI and related equipment, the method comprising: obtaining MRI data of a target object, the MRI data comprising T2W images and FLAIR images, dividing the T2W images and FLAIR images into eight types of classified images according to a preset classification standard; identifying the classified images to obtain images containing cortical nodule lesions, segmenting and labeling the images containing cortical nodule lesions, and obtaining target images; obtaining the volume of cortical nodule lesions, the number of cortical nodule lesions, and the proportion of the brain occupied by the cortical nodule lesions in the target image, and obtaining the brain nodule load of the target object according to the volume of the cortical nodule lesions, the number of the cortical nodule lesions, and the proportion of the brain occupied by the cortical nodule lesions. The present invention takes into account the volume of nodules and the proportion of the brain, and provides a more comprehensive and accurate nodule load generation method than counting alone, which can provide effective reference information for evaluating the user's brain and cognition.

[0112] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or terminal including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or terminal. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the presence of other identical elements in the process, method, article or terminal including the element.

[0113] Of course, those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided by the present invention can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0114] It should be understood that the application of the present invention is not limited to the above examples. For ordinary technicians in this field, improvements or changes can be made based on the above description. All these improvements and changes should fall within the scope of protection of the claims attached to the present invention.

Claims

1. A method for generating brain nodule load based on MRI, characterized in that: The method for generating brain nodule load based on MRI includes: Acquire MRI data of a target object, wherein the MRI data includes a T2W image and a FLAIR image, and classify the T2W image and the FLAIR image into eight types of classified images according to a preset classification standard; Identify the classified image to obtain an image containing cortical tubercle lesions, segment and annotate the image containing cortical tubercle lesions to obtain a target image; The GetSpacing method in Python's SimpleITK library is used to obtain the spacing Δx, Δy, and Δz of a single voxel in each target image in the three dimensions of x, y, and z. The volume of a single voxel in each target image is obtained based on the spacing Δx, Δy, and Δz in the three dimensions: V voxel = Δx × Δy × Δz; Acquiring the volume of cortical tubercle lesions, the number of cortical tubercle lesions, and the proportion of the cortical tubercle lesions to the brain in the target image, and obtaining the brain tubercle load of the target object according to the volume of cortical tubercle lesions, the number of cortical tubercle lesions, and the proportion of the cortical tubercle lesions to the brain; The obtaining of the volume of cortical tubercle lesions, the number of cortical tubercle lesions, and the proportion of the cortical tubercle lesions in the brain in the target image specifically includes: The number of voxels N of each nodule in the target image is obtained according to the size of the cortical nodule lesion. voxel , according to the number of voxels N of the nodule voxel and the volume V of the single voxel voxel , the volume of the cortical tubercle lesion in each target image is obtained: V tuber =N voxel ×V vixel ; According to the number of annotations in each target image, the number of cortical tubercle lesions N in each target image is obtained. tuber ; Get the brain volume V brain , according to the brain volume V brain and the number of cortical tubercle lesions N tuber Calculate the proportion of the brain occupied by the cortical tubercle lesion in each target image: The step of obtaining the brain nodule load of the target object according to the volume of the cortical nodule lesions, the number of the cortical nodule lesions and the proportion of the cortical nodule lesions in the brain specifically includes: Calculate the brain nodule load in each target image according to the volume of the cortical tubercle lesions in each target image, the number of the cortical tubercle lesions in each target image, and the proportion of the cortical tubercle lesions in each target image to the brain; The brain nodule load in each target image is added according to a preset weight to obtain the brain nodule load of the target object.

2. The method for generating brain nodule load based on MRI according to claim 1, characterized in that: The T2W image and the FLAIR image are divided into eight types of classified images according to a preset classification standard, specifically including: dividing the T2W image and the FLAIR image into four types of type I lesions, type II lesions, type III lesions and type IV lesions according to the signals of cortical and subcortical lesions and the morphology of subcortical lesions; According to the location of the nodules in the brain region, the T2W images and FLAIR images are divided into four types: frontal lobe nodules, occipital lobe nodules, temporal lobe nodules and parietal lobe nodules.

3. The method for generating brain nodule load based on MRI according to claim 2, characterized in that: The type I lesions were defined as cortical lesions on T2W and FLAIR sequences, homogeneous or nodular thickening of the cortex, no abnormal changes in cortical signal, and high signal on subcortical T2W; The type II lesions were defined as dysplastic cortical lesions, cortical inhomogeneity, nodular cortical thickening, and abnormal cortical signal; The type III lesion was defined as a subcortical round nodule with high signal around the lesion and low signal in the center of the lesion on FLAIR sequence; The type IV lesions were defined as hyperintense signals in the cortical or subcortical areas on FLAIR sequences with migration lines extending into the lateral ventricles.

4. The method for generating brain nodule load based on MRI according to claim 1, characterized in that: The identifying the classified image to obtain an image containing cortical tubercle lesions, and segmenting and labeling the image containing cortical tubercle lesions to obtain a target image specifically includes: Identify the classified images to obtain a plurality of images containing cortical tubercle lesions, and obtain single-plane images of the plurality of images containing cortical tubercle lesions on a cross-sectional T2-FLAIR sequence; The ITK-SNAP tool is used to segment and annotate the cortical tubercle lesions in the single-sided image, thereby obtaining a plurality of target images with annotated locations and sizes of the cortical tubercle lesions.

5. A brain nodule load generation system based on MRI, characterized in that: The MRI-based brain nodule load generation system includes: An image data classification module is used to obtain MRI data of a target object, wherein the MRI data includes T2W images and FLAIR images, and classify the T2W images and FLAIR images into eight types of classified images according to a preset classification standard; An image segmentation and annotation module is used to identify the classified image to obtain an image containing cortical tubercle lesions, and segment and annotate the image containing the cortical tubercle lesions to obtain a target image; The GetSpacing method in Python's SimpleITK library is used to obtain the spacing Δx, Δy, and Δ of a single voxel in each target image in the three dimensions of x, y, and z. The volume of a single voxel in each target image is obtained based on the spacing Δx, Δy, and Δz in the three dimensions: V voxel = Δx×Δy×Δz; a nodule load calculation module, for obtaining the volume of cortical nodule lesions, the number of cortical nodule lesions, and the proportion of the cortical nodule lesions to the brain in the target image, and obtaining the brain nodule load of the target object according to the volume of cortical nodule lesions, the number of cortical nodule lesions, and the proportion of the cortical nodule lesions to the brain; The obtaining of the volume of cortical tubercle lesions, the number of cortical tubercle lesions, and the proportion of the cortical tubercle lesions in the brain in the target image specifically includes: The number of voxels N of each nodule in the target image is obtained according to the size of the cortical nodule lesion. voxel , according to the number of voxels N of the nodule voxel and the volume V of the single voxel voxel , the volume of the cortical tubercle lesion in each target image is obtained: V tuber =N voxel ×V voxel ; According to the number of annotations in each target image, the number of cortical tubercle lesions N in each target image is obtained. tuber ; Get the brain volume V brain , according to the brain volume V brain and the number of cortical tubercle lesions N tuber Calculate the proportion of the brain occupied by the cortical tubercle lesion in each target image: The step of obtaining the brain nodule load of the target object according to the volume of the cortical nodule lesions, the number of the cortical nodule lesions and the proportion of the cortical nodule lesions in the brain specifically includes: Calculate the brain nodule load in each target image according to the volume of the cortical tubercle lesions in each target image, the number of the cortical tubercle lesions in each target image, and the proportion of the cortical tubercle lesions in each target image to the brain; The brain nodule load in each target image is added according to a preset weight to obtain the brain nodule load of the target object.

6. A terminal, characterized in that: The terminal includes: a memory, a processor, and an MRI-based brain nodule load generation program stored in the memory and executable on the processor. When the MRI-based brain nodule load generation program is executed by the processor, the steps of the MRI-based brain nodule load generation method as described in any one of claims 1 to 4 are implemented.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores an MRI-based brain nodule load generation program, and when the MRI-based brain nodule load generation program is executed by a processor, the steps of the MRI-based brain nodule load generation method as described in any one of claims 1-4 are implemented.

Images