A brain glioma recognition device based on a 5T multi-nuclear magnetic resonance imaging system

Abstract

The application discloses a brain glioma recognition device based on a 5T multi-nuclear magnetic resonance imaging system, which comprises an amide proton imaging acquisition module for receiving a chemical exchange saturation transfer spectrum of amide protons and amide proton concentration; 1 H T2 weighted MRI images, 23 Na MRI images and total sodium concentration maps 23 Na MRI image acquisition module; for receiving 31 P MRS images and phosphorus-containing metabolite concentration of brain regions 31 P MRS image acquisition module; and a recognition module comprising a discrimination network and a segmentation network. The application inputs a sample group into the discrimination network and the segmentation network of the cross-modal data brain tumor, can recognize abnormal signals of different voxels of brain regions, and can outline the boundary of the brain glioma.

Description

Technical Field

[0001] The present invention belongs to the technical field of magnetic resonance imaging, and in particular relates to a brain glioma identification device based on a 5T multi-nuclear magnetic resonance imaging system. Background Art

[0002] Gliomas are tumors that originate from brain glial cells and are the most common primary intracranial tumors. Currently, clinical diagnosis relies primarily on imaging modalities such as computed tomography (CT) and magnetic resonance imaging (MRI). Diffusion-weighted imaging, diffusion tensor imaging, perfusion-weighted imaging, magnetic resonance spectroscopy, functional MRI, and positron emission tomography are crucial for the differential diagnosis and treatment response evaluation of gliomas. MRI offers superior imaging information to CT. CT primarily displays the density difference between glioma lesions and normal brain tissue, characteristic density features such as calcifications, hemorrhages, and cystic lesions, the location of lesion involvement, edema, and mass effect. MRI, with its high spatial resolution, unlimited tissue penetration depth, and excellent soft tissue contrast, is commonly used to assess the signal intensity differences and mass effect of hemorrhage, necrosis, and edema in gliomas, and can also demonstrate the extent of lesion invasion. However, the low sensitivity of MRI limits its ability to accurately detect gliomas. In addition, the information provided by single radionuclide detection is limited. For highly invasive gliomas, it is a huge challenge to accurately identify them at an early stage and accurately outline the boundaries of their infiltration.

[0003] Amide proton transfer (APT) imaging is a novel, noninvasive molecular MRI technique that can quantitatively detect endogenous proteins and peptides in tissues, providing insights into changes in the tumor cell microenvironment and reflecting the characteristic biological behavior of gliomas. The application value of APT imaging in brain tumors has been validated based on biopsy data, and APT imaging has shown significant promise in the study of neurodegenerative diseases and psychiatry. Differences in protein content within brain tumors are considered the primary source of the APT imaging signal, but the intensity of the APT imaging signal can also be confounded by other factors. For example, the protein-rich cystic components of some gliomas with cystic lesions exhibit a high APT imaging signal, but this signal is not correlated with malignancy. Therefore, when analyzing brain tumor APT imaging signals, combining simultaneous multinuclear imaging with other radionuclides allows for more accurate quantitative analysis of amide proton concentrations in brain regions.

[0004] Among the endogenous radionuclides that can be used for MRI, except for protons ( 1 H), and 23 Na and 31 P.1 H is the most abundant magnetic resonance observable nucleus in the human body and has the highest gyromagnetic ratio. Conventional MRI usually uses protons as imaging observation nuclei. 1 H nucleus (endogenous: 23 Na and 31 P, etc.; exogenous: 129 Xe and 19 Multi-nuclear MRI (F, etc.) is being continuously researched and explored, becoming a new tool for brain disease and brain science research. 1 The chemical shift range of H metabolites detected by traditional MRI technology is mainly 0-5ppm. Its chemical shift range is narrow, and the signals of different metabolites are prone to overlap and difficult to distinguish. 1 H has a larger chemical shift range, thus providing more comprehensive functional and metabolic information. In endogenous human multinuclear MRI studies, 23 Na is the second most abundant MRI radionuclide that can be detected in living tissues at natural abundance. + Plays a vital role in many cellular functions. 23 Na MRI has also been used to study many brain diseases (brain tumors, cerebral infarction, stroke, etc.). 31 P is a very important endogenous radionuclide. 31 P magnetic resonance spectroscopy (MRS) can detect macromolecular metabolites and phospholipid membranes in the body, providing important information for energy metabolism. 31 P MRS has been reported to be used in the study of many brain diseases including Alzheimer's disease, Parkinson's disease, multiple sclerosis, migraine, cerebral ischemia, brain tumors, bipolar disorder, major depression and attention deficit / hyperactivity disorder. 31 The unique use of P to directly image brain energy production from the hydrolysis of ATP provides new insights into human brain energetics and its role in supporting neuronal activity and brain function. 31 P MRS imaging has broad application prospects in clinical diagnosis and research. It can provide important information about phosphorus metabolism and its changes in different disease states, which is helpful for early diagnosis of diseases, treatment monitoring and drug development. 31 P MRS imaging research has important scientific significance and application prospects.

[0005] Based on the advantages of high sensitivity and high resolution of 5T high field magnetic resonance system and the fact that the 1.5T and 3T magnetic resonance imaging devices currently used in clinical practice cannot meet the needs of accurate disease diagnosis, 1 H / 23 Na / 31Multi-core MRI can obtain 1 H T2-weighted MRI, APT imaging, and sodium concentration quantification. The high-resolution advantage of the 5T high-field MRI system can distinguish overlapping phosphorus-containing metabolites. 31 P MRS spectral peaks provide more precise quantitative analysis of phosphorus-containing metabolites in glioma regions (compared to 3T or lower field strength magnetic resonance spectrometers), including energy metabolism components such as adenosine triphosphate, adenosine diphosphate, and creatinine phosphate. Leveraging the advantages of high-field and multi-nuclear imaging, this system can accurately identify abnormal signals in different voxels across the brain, which is crucial for the early diagnosis and delineation of glioma boundaries. Summary of the Invention

[0006] The purpose of the present invention is to address the above-mentioned problems existing in the prior art and provide a device for identifying gliomas based on a 5T multi-nuclear magnetic resonance imaging system. Based on the advantages of high sensitivity and high resolution of the 5T high-field magnetic resonance spectrometer, it can perform highly sensitive APT imaging of brain regions and more accurately quantify endogenous proteins and peptides; it can also perform high-sensitivity APT imaging of brain regions and quantify endogenous proteins and peptides more accurately; it can ... 23 Na MRI, obtains the total sodium concentration map of different voxels in the brain; 31 P MRS was used to quantitatively analyze phosphorus-containing metabolites in the brain to obtain the concentrations of phosphorus-containing metabolites in different voxels of the brain. 1 H / 23 Na / 31 P multi-core MRI data, construct a sample group, and import it into the constructed discriminant network and segmentation network of brain tumor based on cross-modal data to determine whether there is a brain tumor and outline the boundary.

[0007] The above-mentioned purpose of the present invention is achieved by the following technical means:

[0008] A brain glioma identification device based on a 5T multi-nuclear magnetic resonance imaging system, comprising:

[0009] An amide proton imaging acquisition module is used to receive chemical exchange saturation transfer maps of amide protons, receive APT images obtained by applying saturation pulses at 3.5 ppm and -3.5 ppm, and also to obtain amide proton concentrations in brain regions;

[0010] 23 Na MRI image acquisition module, used to receive 1 H T2-weighted MRI images, 23 Na MRI images and total sodium concentration maps of brain regions;

[0011] 31 P MRS image acquisition module, used to receive 31 P MRS images and concentrations of different phosphorus-containing metabolites in brain regions;

[0012] The sample group generation module is used to generate sample groups. Each sample group includes 1 H T2-weighted MRI images, chemical exchange saturation transfer maps of amide protons, 23 Na MRI images, 31 P MRS images, amide proton concentration in brain regions, 23 Na concentration, concentrations of various phosphorus-containing metabolites in brain regions, and generating training and test sets based on each sample group;

[0013] The recognition model includes a discriminant network and a segmentation network, which is used to train the discriminant network and the segmentation network based on the training set, and is also used to input a sample group to be identified to obtain a predicted category label and a predicted segmentation label.

[0014] As mentioned above, the discriminant network includes an input layer, a text encoding layer, a first fully connected layer, a first convolutional layer, a second convolutional layer, a first residual block group, a second residual block group, a third residual block group, a fourth residual block group, a global average pooling layer, a second fully connected layer, and an output layer.

[0015] The segmentation network includes an encoder and a decoder.

[0016] In the sample group 1 The H T2-weighted MRI image and the chemical exchange saturation transfer map of amide protons were input into the input layer of the discriminant network built based on the ResNet architecture to obtain the image data feature map, and then the amide proton concentration, 23 The Na concentration and the concentrations of various phosphorus-containing metabolites in the brain area are input into the text encoding layer of the discriminant network for text encoding to obtain a text vector. The text vector is fused with the image data feature map extracted by the input layer of the discriminant network through the first fully connected layer to obtain a fused feature map. The fused feature map is then passed through the first convolutional layer, the second convolutional layer, the first residual block group, the second residual block group, the third residual block group and the fourth residual block group, the global average pooling layer, and the output layer in sequence to obtain the corresponding predicted category label.

[0017] As described above, the first residual block group contains 3 residual blocks, the second residual block group contains 4 residual blocks, the third residual block group contains 6 residual blocks, and the fourth residual block group contains 3 residual blocks.

[0018] The sample group includes 1 H T2-weighted MRI images, chemical exchange saturation transfer maps of amide protons, 23 NaMRI images, 31The P MRS image data is transmitted to the segmentation network based on the U-Net network architecture. In the segmentation network, skip connections are used to connect the layers of the same level in the encoder and decoder parts, and the attention module of multi-scale features is accessed during the skip connection process.

[0019] As mentioned above, the attention module of the multi-scale feature includes a convolution layer, a maximum pooling layer, and an average pooling layer. The feature image for jump connection output by the downsampling layer of the encoder is input into the attention module as the initial feature image. The initial feature image passes through the maximum pooling layer and the average pooling layer of the attention module respectively, and then is spliced ​​on the channel. The spliced ​​feature passes through a 5×5 convolution layer and is linearly multiplied with the initial feature image to obtain the first step result. The first step result then passes through the maximum pooling layer and the average pooling layer of the attention module respectively, and then is spliced ​​on the channel. After passing through a 3×3 convolution layer, it is linearly multiplied with the first step output result to obtain the second step result. The second step output result then passes through the maximum pooling layer and the average pooling layer of the attention module respectively, and then is spliced ​​on the channel. After passing through a 3×3 convolution layer, it is linearly multiplied with the second step output result and then passes through a sigmoid activation function to generate a feature weight map. The feature weight map is output to the upsampling layer of the decoder of the corresponding level layer.

[0020] The total loss function of the recognition model is the sum of the discriminant network loss function Lc and the segmentation network loss function Ls multiplied by the corresponding weights. Based on minimizing the total loss function, the recognition model is trained end-to-end using the training set, and the parameters of the recognition model are saved, where:

[0021] The discriminant network loss function Lc is based on the following formula:

[0022]

[0023] Among them, N is the number of sample groups input into the discriminant network, y i is the actual category label of the i-th sample group, p i is the predicted category label of the i-th sample group, i represents the sequence number of the sample group in each round of training iteration, i∈{1, 2,…N};

[0024] The segmentation network loss function Ls is based on the following formula:

[0025] L s =-(y t log(y p )+(1-y t )log(1-y p ))

[0026] Among them, y tis the actual segmentation label, y p To predict the segmentation label.

[0027] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the amide proton imaging acquisition module, 23 Na MRI image acquisition module, 31 p MRS image acquisition module, sample group generation module, and recognition module.

[0028] A computer readable storage medium stores a computer program, which, when executed by a processor, implements the amide proton imaging acquisition module, 23 Na MRI image acquisition module, 31 p MRS image acquisition module, sample group generation module, and recognition module.

[0029] A computer program product, comprising a computer program, which, when executed by a processor, implements the amide proton imaging acquisition module, 23 Na MRI image acquisition module, 31 p MRS image acquisition module, sample group generation module, and recognition module.

[0030] Compared with the prior art, the advantages and beneficial effects of the present invention are:

[0031] 1. The field strength used in the present invention is 5T, which has higher magnetic resonance sensitivity than the traditional 1.5T and 3T. It can detect substances that are difficult to detect with traditional magnetic resonance technology, and can more sensitively detect key proteins of brain glioma, sodium concentration in the brain area, and phosphorus-containing metabolites.

[0032] 2. The magnetic resonance spectrometer used in the present invention has a field strength of 5T. Compared with the traditional 1.5T and 3T, it has the characteristics of high resolution, can accurately visualize the brain area with smaller voxels, and can perform more accurate quantitative analysis of the concentrations of various metabolites and proteins in the brain area.

[0033] 3. The present invention can perform high-sensitivity amide proton imaging of the brain region, obtain the concentration of amide protons in the brain region, perform quantitative analysis of the protein concentration in the brain region, and analyze the abnormal areas of amide proton concentration by comparing with normal brain tissue.

[0034] 4. The present invention includes a cross-modal data brain tumor discrimination network and segmentation network. During the segmentation process, a multi-scale feature attention module is designed, which uses spatial attention to increase the weight of the key areas of the input features, thereby better restoring the detailed information of these key areas.

[0035] 5. The present invention uses a 5T multi-nuclear magnetic resonance system to obtain amide proton concentrations, total sodium concentration maps, and concentrations of different phosphorus-containing metabolites in different voxels of the brain, and constructs a sample group, which includes 1 H T2-weighted MRI images, chemical exchange saturation transfer maps of amide protons, 23 Na MRI images, 31 P MRS images, amide proton concentration in brain regions, 23 Na concentration, concentrations of various phosphorus-containing metabolites in brain regions, and inputting the sample group into the cross-modal data brain tumor discrimination network and segmentation network can identify abnormal signals of different voxels in the brain region and outline the boundaries of gliomas. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 It is a structural schematic diagram of the present invention.

[0037] Figure 2 Schematic diagram of the structure of the attention module for multi-scale features. DETAILED DESCRIPTION

[0038] The exemplary embodiments of the present application will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present application are shown in the accompanying drawings, it should be understood that the present application can be implemented in various forms and should not be limited by the embodiments described herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present application and to fully convey the scope of the present application to those skilled in the art. It should be noted that, unless otherwise specified, the technical terms or scientific terms used in this application should be the common meanings understood by those skilled in the art to which this application belongs. The following describes a method based on 5T proposed in an embodiment of the present application in conjunction with the accompanying drawings. 1 H / 23 Na / 31 P Brain glioma identification and boundary delineation device for multi-nuclear magnetic resonance imaging system.

[0039] Following the above background technology, in addition to being able to achieve single nuclide imaging, the related technology has a relatively low sensitivity and resolution of MRI due to the low magnetic field strength (1.5T or 3T), which is subject to problems such as high detection limit and inaccurate quantification in the detection of biomarkers for glioma. Single nuclide imaging is difficult to accurately quantify the concentration of tumor markers in different voxels in the brain area, and it is difficult to accurately outline the boundaries of glioma. Based on this, the embodiment of the present application provides a method based on 5T 1 H / 23 Na / 31P multi-nuclear MRI system for glioma identification and boundary delineation. Compared with traditional low-field MRI (1.5T and 3T), the 5T high magnetic field strength can overcome the shortcomings of insufficient sensitivity and resolution of MRI. Compared with single-nuclear MRI, the system can provide 1 H / 23 Na / 31 P multi-nuclear magnetic resonance imaging information is used to obtain the protein concentration, sodium concentration, and phosphorus metabolite concentration of brain glioma. The obtained brain region multi-nuclear magnetic resonance data is imported into the cross-modal data brain tumor discrimination and segmentation network model to determine whether the brain glioma exists and outline its boundaries ( Figure 1 ).

[0040] A brain glioma identification device based on a 5T multi-nuclear magnetic resonance imaging system, comprising: an amide proton imaging acquisition module, 23 Na MRI image acquisition module, 31 P MRS image acquisition module, sample group generation module, and recognition module.

[0041] Amide proton imaging acquisition module:

[0042] The amide proton imaging acquisition module is used to receive the chemical exchange saturation transfer map of amide protons, receive the APT images obtained by applying saturation pulses at 3.5ppm and -3.5ppm, and is also used to obtain the amide proton concentration in the brain area.

[0043] Due to abnormal protein expression in glioma patients, their levels are higher than in normal brain tissue. The chemical exchange rate of amide protons is typically around 30 Hz, which can produce a magnetization transfer effect. However, the relaxation time of mobile proteins and peptides is longer, and the magnetic resonance frequency range of amide groups is narrower, concentrated at ~3.5 ppm. In most tissues, the concentration of amide protons in endogenous mobile peptides and proteins is approximately 5–8 mM. These conditions make mobile amide protons in brain regions suitable for chemical exchange saturation transfer imaging, which can be used to quantify the concentration of amide protons in brain regions.

[0044] Brain amide proton magnetic resonance imaging experiment: First, test the chemical exchange saturation transfer spectrum of amide protons, that is, the Z spectrum. The Y-axis of the chemical exchange saturation transfer spectrum is S / S0, where: S represents the signal intensity of water protons after applying radio frequency pulse excitation at different chemical shift sites, S0 represents the signal intensity of water protons after applying radio frequency pulse excitation, and the X-axis is the saturated chemical shift site. The chemical exchange saturation transfer spectrum is drawn to obtain the chemical exchange saturation transfer spectrum. In the next step, APT imaging of the whole brain is performed. Saturation pulses are applied to the signal site of amide protons at 3.5ppm and the symmetrical chemical shift signal site at -3.5ppm to perform APT imaging of different voxels in the whole brain. The calculation method of the APT imaging effect of different voxels in the brain region is based on the asymmetric magnetization transfer rate MTR at ±3.5ppm. asym (asymmetrical magnetization transfer rate) is calculated by the difference between asym(3.5ppm) =MTR asym(+3.5ppm) -MTR asym(-3.5ppm) , among which, MTR asym(+3.5ppm) is the asymmetric magnetization transfer rate at +3.5ppm, MTR asym(-3.5ppm) The asymmetric magnetization transfer rate at -3.5 ppm is obtained. The higher protein content in brain tumors causes an increase in exchangeable amide protons, and the corresponding APT imaging signal is enhanced.

[0045] 23 Na MRI image acquisition module:

[0046] 23 Na MRI image acquisition module, used to receive 1 H T2-weighted MRI images, 23 Na MRI images and maps of total sodium concentration in brain regions.

[0047] In patients with glioma and healthy volunteers 23 Before Na MRI imaging, a fast spin echo sequence was used on a 5T magnetic resonance spectrometer. 1 H T2-weighted MRI imaging, obtained 1 H T2-weighted MRI images using dual-tuning 23 Na- 1 H birdcage head coil for whole-brain imaging of glioma patients and healthy volunteers 23 Na MRI imaging, obtained 23 Na MRI images. Based on the quantitative analysis software of the 5T magnetic resonance spectrometer, the total sodium concentration (TSC) of the whole brain and the regions of interest defined in the brain of glioma patients and healthy volunteers was quantitatively analyzed to obtain the total sodium concentration (TSC) of the whole brain and the regions of interest defined in the brain. 23Na concentration.

[0048] 31 P MRS image acquisition module:

[0049] 31 P MRS image acquisition module, used to receive 31 P MRS images and concentrations of different phosphorus-containing metabolites in brain regions.

[0050] Glioma patients and healthy volunteers 31 P MRS image use 31 P / 1 H dual-tuned birdcage coil was used for acquisition. First, T1-weighted fast field echo images were obtained in the axial plane by multiplanar reconstruction for the mid-sagittal plane. 31 Uniform positioning of P MRS grids and multivoxel whole brain in glioma patients and healthy volunteers 31 P MRS acquisition, obtain 31 P MRS images. Adiabatic RF pulses were delivered using a broadband decoupling technique and an automated shimming procedure with a maximum acceptable value of 35 Hz. The size of individual voxels was 25 × 25 × 20 mm. Subsequently, T1-weighted MRI images were acquired to ensure that the patient's head position remained the same as at the beginning of the examination. Voxel selection: A large number of voxels was obtained using a 3D atlas approach. However, for practical purposes and to avoid multiple comparison errors, a target number of voxels representing bilateral white matter, deep gray matter, and cortex was determined for analysis. Given that the differences in metabolite concentrations between different tissue types (e.g., gray matter and white matter) exceed the differences between the same tissue types in different brain locations (e.g., temporal lobe and frontal lobe), phosphorus-containing metabolite concentrations were quantified in homologous brain regions from patients with glioma and healthy volunteers.

[0051] LCmodel was used to analyze the brain regions. 31 P MRS maps were used to quantify the concentrations of phosphorus-containing metabolites across different voxels in the brain. Manual steps to converge the maps included zero-order and first-order phase correction, followed by identification of peaks for phosphorus-containing metabolites such as inorganic phosphate and creatine phosphate, and quantification of phosphorus-containing metabolites in the brain.

[0052] Sample group generation module:

[0053] The sample group generation module is used to generate sample groups. Each sample group includes 1 H T2-weighted MRI images, chemical exchange saturation transfer maps of amide protons, 23 Na MRI images, 31 P MRS images, amide proton concentration in brain regions, 23Na concentration, concentrations of various phosphorus-containing metabolites in brain regions, and training and test sets were generated based on each sample group.

[0054] Identification Model:

[0055] Step 1: Get the training set and test set, where the training set and test set contain multiple sample groups, each of which contains 1 H T2-weighted MRI images, chemical exchange saturation transfer maps of amide protons, 23 Na MRI images, 31 PMRS images, amide proton concentration in brain regions, 23 Na concentration and concentrations of various phosphorus-containing metabolites in brain regions. 1 H T2-weighted MRI images, chemical exchange saturation transfer maps of amide protons, 23 Na MRI images, 31 The actual category labels of P MRS image data are tumor and no tumor. 1 H T2-weighted MRI images, chemical exchange saturation transfer maps of amide protons, 23 Na MRI images, 31 The actual segmentation label of the P MRS image data is the tumor segmentation label.

[0056] Step 2: Build a recognition model based on cross-modal data. The recognition model includes a discriminant network and a segmentation network. And set the total loss function.

[0057] Among them, the discriminant network includes an input layer, a text encoding layer, a first fully connected layer, a first convolutional layer, a second convolutional layer, a first residual block group, a second residual block group, a third residual block group, a fourth residual block group, a global average pooling layer, a second fully connected layer and an output layer.

[0058] The segmentation network consists of an encoder and a decoder.

[0059] First, the sample group 1 The H T2-weighted MRI image and the chemical exchange saturation transfer map of amide protons were input into the input layer of the discriminant network built based on the ResNet architecture to obtain the image data feature map, and then the amide proton concentration, 23 The concentration of Na and the concentration of each phosphorus metabolite in the brain area are input into the text encoding layer of the discriminant network for text encoding. The amide proton concentration, 23The text encoding of Na concentration and the concentrations of various phosphorus-containing metabolites in brain regions is converted into a text vector. This text vector is then fused with the image data feature map extracted from the input layer of the discriminative network built based on the ResNet architecture through the first fully connected layer to obtain a fused feature map. The fused feature map is then passed through the first and second convolutional layers, and the output of the second convolutional layer is input into the first residual block group, which contains three residual blocks. The feature image output by the first residual block group is then input into the second residual block group, which contains four residual blocks. The feature image output by the second residual block group is then passed through the subsequent third and fourth residual block groups, which contain six and three residual blocks, respectively. Finally, the feature image output by the fourth residual block group is passed through a global average pooling layer and a second fully connected layer, and then input into the output layer, which outputs the corresponding predicted category label.

[0060] Then the samples that are identified as having tumors are included in 1 H T2-weighted MRI images, chemical exchange saturation transfer maps of amide protons, 23 Na MRI images, 31 The P MRS image data is transmitted to the segmentation network based on the U-Net network architecture. In the segmentation network, skip connections are used to connect the layers of the same level in the encoder and decoder parts. At the same time, the attention module of multi-scale features is accessed during the skip connection process. The attention module includes convolutional layer, maximum pooling layer, and average pooling layer. The feature image output by the encoder's downsampling layer for skip connections is used as the initial feature image and is input to the attention module. The initial feature image passes through the attention module's maximum pooling layer and average pooling layer, and then undergoes channel-wise concatenation. The concatenated features pass through a 5×5 convolutional layer and are linearly multiplied with the initial feature image to obtain the first step result. The first step result then passes through the attention module's maximum pooling layer and average pooling layer, and then undergoes channel-wise concatenation. After passing through a 3×3 convolutional layer, it is linearly multiplied with the first step output result to obtain the second step result. The second step output then passes through the attention module's maximum pooling layer and average pooling layer, and then undergoes channel-wise concatenation. After passing through a 3×3 convolutional layer, it is linearly multiplied with the second step output result and then passes through a sigmoid activation function to generate a feature weight map. The feature weight map is then output to the upsampling layer of the decoder at the corresponding level. Similarly, each skip connection passes through this multi-scale feature attention module. The above channel splicing is to splice the output data after the maximum pooling layer and the output data after the average pooling layer in the channel dimension.

[0061] Step 3: Set the total loss function; the total loss function is divided into two parts: the discriminant network loss function L c and the segmentation network loss function L s The total loss function is the weighted sum of the discriminant network loss function Lc and the segmentation network loss function Ls, as shown in the formula:

[0062]

[0063] Among them, N is the number of sample groups input into the discriminant network, y i is the actual category label of the i-th sample group. In this embodiment, if it is a positive classification example, then y i The value is 1. If it is a negative example, then y i The value is 0; p i is the predicted category label of the i-th sample group, indicating the value of the classification prediction obtained by the discriminant network as a positive example, i represents the sequence number of the sample group in each round of training iteration, i∈{1, 2,…N}.

[0064] L s =-(y t log(y p )+(1-y t )log(1-y p ))

[0065] Among them, y t is the actual segmentation label, which represents the value of the tumor segmentation label of the voxel in the sample group in the training set, y t ∈{0, 1}, the positive example is y t The value is 1, and the negative example is y t Taking the value as 0 makes the segmentation module loss function L s Suitable for evaluation of binary classification tasks; y p To predict the segmentation label, it represents the probability that the voxel in the tumor segmentation result obtained by the segmentation network is a positive example. If the voxel in the tumor segmentation result is a positive example, then y p The value is 1, otherwise, y p The value is 0.

[0066] Step 4: Based on minimizing the total loss function set in Step 3, the brain tumor recognition model constructed in Step 2 for cross-modal data is trained end-to-end using the training set generated in Step 1, and the parameters of the recognition model are saved.

[0067] According to the recognition model built in step 2, the network learning rate is initialized to 0.0001, the batch size is set to 8, and the network training is performed on the PyTorch platform using the Adam optimizer. 1The H T2-weighted MRI images and the chemical exchange saturation transfer maps of amide protons are input into the constructed discriminant network to obtain the predicted category labels, and then the samples in the group with tumors are identified. 1 H T2-weighted MRI images, chemical exchange saturation transfer maps of amide protons, 23 Na MRI images, 31 The P MRS image data was transferred to the brain tumor segmentation network, and the network was trained according to the total loss function set in step 4. After the total number of network training iterations reached 200, the training was stopped and the corresponding network parameters were saved.

[0068] Step 5: Group the samples to be identified 1 The H T2-weighted MRI images and the chemical exchange saturation transfer maps of amide protons are input into the discriminant network of the trained recognition model to obtain the predicted category label; the sample group to be identified is 1 H T2-weighted MRI images, chemical exchange saturation transfer maps of amide protons, 23 Na MRI images, 31 The P MRS image data is input into the segmentation network of the recognition model trained in step 4 to obtain the predicted segmentation label.

[0069] Those skilled in the art will appreciate that the amide proton imaging acquisition module, 23 Na MRI image acquisition module, 31 The entire or partial processes of the P MRS image acquisition module, the sample group generation module, and the identification module can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the amide proton imaging acquisition module, the sample group generation module, and the identification module in the above-mentioned embodiment. 23 Na MRI image acquisition module, 31 The entire or partial process of the P MRS image acquisition module, sample group generation module, and recognition module.

[0070] In one embodiment, a computer device is also provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the amide proton imaging acquisition module of the above-mentioned device is implemented. 23 NaMRI image acquisition module, 31 P MRS image acquisition module, sample group generation module, and recognition module.

[0071] In one 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 amide proton imaging acquisition module,23 Na MRI image acquisition module, 31 P MRS image acquisition module, sample group generation module, and recognition module.

[0072] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the amide proton imaging acquisition module of the above-mentioned device, 23 Na MRI image acquisition module, 31 P MRS image acquisition module, sample group generation module, and recognition module.

[0073] It should be noted that the embodiments described herein are merely illustrative of the spirit of the present invention. Persons skilled in the art may make various modifications, additions, or substitutions to the described embodiments without departing from the spirit of the present invention or exceeding the scope of the appended claims.

Claims

1. A device for identifying gliomas based on a 5T multi-nuclear magnetic resonance imaging system, characterized in that: include: An amide proton imaging acquisition module is used to receive chemical exchange saturation transfer maps of amide protons, receive APT images acquired by applying saturation pulses at 3.5 ppm and -3.5 ppm, and also to obtain amide proton concentrations in brain regions; 23 Na MRI image acquisition module, used to receive 1 H T2-weighted MRI images, 23 Na MRI images and total sodium concentration maps of brain regions; 31 P MRS image acquisition module, used to receive 31 P MRS images and concentrations of different phosphorus-containing metabolites in brain regions; The sample group generation module is used to generate sample groups. Each sample group includes 1 H T2-weighted MRI images, chemical exchange saturation transfer maps of amide protons, 23 Na MRI images, 31 P MRS images, amide proton concentration in brain regions, 23 Na concentration, concentrations of various phosphorus-containing metabolites in brain regions, and generating training and test sets based on each sample group; The recognition model includes a discriminant network and a segmentation network, which is used to train the discriminant network and the segmentation network based on the training set, and is also used to input a sample group to be identified to obtain a predicted category label and a predicted segmentation label.

2. The device for identifying gliomas based on a 5T multi-nuclear magnetic resonance imaging system according to claim 1, characterized in that: The discriminant network includes an input layer, a text encoding layer, a first fully connected layer, a first convolutional layer, a second convolutional layer, a first residual block group, a second residual block group, a third residual block group, a fourth residual block group, a global average pooling layer, a second fully connected layer and an output layer. The segmentation network includes an encoder and a decoder.

3. The device for identifying gliomas based on a 5T multi-nuclear magnetic resonance imaging system according to claim 2, characterized in that: In the sample group 1 The H T2-weighted MRI image and the chemical exchange saturation transfer map of amide protons were input into the input layer of the discriminant network built based on the ResNet architecture to obtain the image data feature map, and then the amide proton concentration, 23 The Na concentration and the concentrations of various phosphorus-containing metabolites in the brain area are input into the text encoding layer of the discriminant network for text encoding to obtain a text vector. The text vector is fused with the image data feature map extracted by the input layer of the discriminant network through the first fully connected layer to obtain a fused feature map. The fused feature map is then passed through the first convolutional layer, the second convolutional layer, the first residual block group, the second residual block group, the third residual block group, the fourth residual block group, the global average pooling layer and the output layer in sequence to obtain the corresponding predicted category label.

4. The device for identifying gliomas based on a 5T multi-nuclear magnetic resonance imaging system according to claim 3, characterized in that: The first residual block group includes 3 residual blocks, the second residual block group includes 4 residual blocks, the third residual block group includes 6 residual blocks, and the fourth residual block group includes 3 residual blocks.

5. The device for identifying gliomas based on a 5T multi-nuclear magnetic resonance imaging system according to claim 3, characterized in that: The sample group includes 1 H T2-weighted MRI images, chemical exchange saturation transfer maps of amide protons, 23 Na MRI images, 31 The P MRS image data is transmitted to the segmentation network based on the U-Net network architecture. In the segmentation network, skip connections are used to connect the layers of the same level in the encoder and decoder parts, and the attention module of multi-scale features is accessed during the skip connection process.

6. The device for identifying gliomas based on a 5T multi-nuclear magnetic resonance imaging system according to claim 5, characterized in that: The attention module of the multi-scale feature includes a convolution layer, a maximum pooling layer and an average pooling layer. The feature image for jump connection output by the downsampling layer of the encoder is input into the attention module as the initial feature image. The initial feature image passes through the maximum pooling layer and the average pooling layer of the attention module respectively, and then performs channel splicing. The spliced ​​feature passes through a 5 × 5 convolution layer and is linearly multiplied with the initial feature image to obtain the first step result. The first step result then passes through the maximum pooling layer and the average pooling layer of the attention module respectively, and then performs channel splicing. After passing through a 3 × 3 convolution layer, it is linearly multiplied with the first step output result to obtain the second step result. The second step output result then passes through the maximum pooling layer and the average pooling layer of the attention module respectively, and then performs channel splicing. After passing through a 3 × 3 convolution layer, it is linearly multiplied with the second step output result and then passes through a sigmoid activation function to generate a feature weight map. The feature weight map is output to the upsampling layer of the decoder of the corresponding level layer.

7. The device for identifying gliomas based on a 5T multi-nuclear magnetic resonance imaging system according to claim 5, characterized in that: The total loss function of the recognition model is the sum of the discriminant network loss function Lc and the segmentation network loss function Ls multiplied by the corresponding weights. Based on minimizing the total loss function, the recognition model is trained end-to-end using the training set, and the parameters of the recognition model are saved, where: The discriminant network loss function Lc is based on the following formula: ； Where N is the number of sample groups input into the discriminant network, is the actual category label of the i-th sample group, is the predicted category label of the i-th sample group, i represents the sequence number of the sample group in each round of training iteration, i∈{1, 2, …, N}; The segmentation network loss function Ls is based on the following formula: ； in, is the actual segmentation label, To predict the segmentation label.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the amide proton imaging acquisition module of the device according to any one of claims 1 to 7 is implemented. 23 Na MRI image acquisition module, 31 P MRS image acquisition module, sample group generation module and recognition module.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the amide proton imaging acquisition module of the device according to any one of claims 1 to 7 is realized. 23 Na MRI image acquisition module, 31 P MRS image acquisition module, sample group generation module and recognition module.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the amide proton imaging acquisition module of the device according to any one of claims 1 to 7 is realized. 23 Na MRI image acquisition module, 31 P MRS image acquisition module, sample group generation module and recognition module.

Images