409 results about "Brain tumor" patented technology

The invention discloses a brain tumor multi-mode large model construction method, device and equipment and a storage medium, and is applied to the technical field of brain tumor imagines.The method comprises the steps that pixel-concept level alignment is conducted on a multi-mode MRI image and a pathological text; constructing a multi-modal feature fusion network for fusing image features and text features by adopting an attention mechanism of pathology perception and combining medical semantic information; training the multi-modal feature fusion network to generate an analysis report and a segmentation result; according to the technical scheme of multi-task cooperation, cross-modal pathological semantic accurate alignment, pathological knowledge graph injection and lightweight and continuous optimization parallelization, full-process coverage of brain tumor accurate segmentation, analysis report generation and prognosis prediction is achieved, the problems that a traditional model lacks pathological semantic support and is insufficient in clinical adaptability are solved, and the clinical adaptability of the traditional model is improved. And the deployment feasibility and the dynamic optimization capability are also considered.

The invention provides an MRI brain tumor image segmentation method based on a state space model and a frequency domain, and relates to the field of image processing. The method comprises the following steps: acquiring a brain tumor MRI image to be segmented and preprocessing the brain tumor MRI image; and inputting the preprocessed brain tumor MRI image into a segmentation network based on a state space model and a frequency domain. The network is based on a U-Net architecture, and global context modeling is performed on feature information by introducing a state space model into a bottleneck layer. In order to optimize feature extraction, a dynamic weight mechanism is designed aiming at features input into a state space model, the importance of feature sequences in three directions is dynamically adjusted according to input data, and the attention to a brain tumor key area is enhanced. By adding a 3D frequency domain fusion module in jump connection, high-frequency noise is reduced, and perception of the overall structure of a brain tumor image is enhanced. According to the method, the state space model and the 3D frequency domain fusion module are introduced, and the importance of the feature sequence is dynamically adjusted, so that brain tumor MRI image segmentation with higher precision is realized.

The invention discloses a brain tumor segmentation method and system based on a diffusion model, and relates to the field of medical images and deep learning. The method comprises the following steps: acquiring a disclosed three-dimensional brain medical image data set, and making a two-dimensional brain medical image through data processing; performing data preprocessing and data enhancement operation on the two-dimensional image, and dividing the two-dimensional image into a training set, a verification set and a test set according to a certain proportion; a DiffIRseg network model is built, a two-stage training strategy is adopted for training, and optimal model weight parameters are stored; and inputting a to-be-segmented brain image to the trained DiffIRseg network, outputting a predicted health image, obtaining a brain tumor segmentation result through difference analysis, and comparing the brain tumor segmentation result with the fine annotation for verification. According to the method, the prior knowledge of the health image and the denoising characteristic of the diffusion model are introduced, so that the labeling cost and complexity are reduced, the accuracy and efficiency of brain tumor segmentation are improved, and reliable technical support is provided for clinical diagnosis and treatment planning.

The invention relates to the field of brain tumor analysis, and discloses a brain tumor image analysis system based on artificial intelligence, comprising: a spatial alignment unit for acquiring original image data of the brain of a subject; performing spatial alignment on the original image data according to a cross-modal registration algorithm to obtain standardized image data; the feature extraction unit is used for performing tumor region initial segmentation on the standardized image data according to a three-dimensional convolutional neural network so as to obtain a coarse segmentation probability graph; and extracting three-dimensional geometric feature parameters of the tumor candidate region according to the coarse segmentation probability graph. According to the method, the original image data is spatially aligned through the cross-modal registration algorithm, and the spatial consistency between different image sources is ensured, so that the image data under different modals can be accurately compared and analyzed, and an accurate spatial reference is provided for subsequent tumor region identification and processing.

The invention discloses a brain MRI image segmentation method based on an RWKV model, and belongs to the technical field of medical image processing and artificial intelligence crossing. Firstly, an RWKV linear self-attention module is introduced into a U-Net network framework, and association between remote pixels is established with relatively low calculation overhead, so that the recognition precision of a brain tumor area is improved, the reasoning time is effectively controlled, and the practicability of a model is enhanced. Secondly, according to the method, multi-scale coding and a feature fusion mechanism are combined, local and global information is extracted in a combined manner, features are mined from different resolution levels, and adaptive fusion is realized, so that the fine-grained segmentation effect is improved. And finally, in order to enhance the generalization ability and lightweight deployment performance of the model, the network structure is further optimized, and the overall computing resource demand is reduced, so that the method can better adapt to cross-patient MRI data in a complex clinical environment, and has good practical value and popularization potential.

The invention relates to the technical field of medical data analysis, in particular to a brain tumor curative effect analysis system which comprises a tumor data sensing layer for collecting multi-department diagnosis and treatment data, tumor image data and patient pathology monitoring data; the tumor feature processing center extracts data features, correlates data and core features before and after treatment through an attention mechanism, and generates a tumor complete-cycle unified feature map; the therapeutic effect dynamic analysis unit evaluates the therapeutic effect in stages, and outputs a therapeutic effect index and a recurrence risk value through a self-supervised model; the dynamic adaptation decision module is used for generating personalized treatment adjustment suggestions based on the dynamic change of the blood brain barrier in combination with the curative effect index, the recurrence risk value and the multi-omics characteristics of the patient; and the AI multi-department consultation unit automatically matches similar cases with field expert suggestions, and formulates a target diagnosis and treatment scheme based on a visual platform and multi-department doctor collaborative consultation in combination with personalized treatment adjustment suggestions. Therefore, the problems of lagging effect evaluation, insufficient diagnosis and treatment suggestions and the like in the prior art are solved.

The invention discloses a cascade multi-scale convolution and modal enhancement brain tumor segmentation method based on a Mama framework, and relates to the technical field of brain tumors. According to the method, an MCME-UNet model integrated with an MCMS module is provided, through a hierarchical feature extraction mechanism and a multi-modal feature fusion strategy optimized by an MEM module, the segmentation precision is remarkably improved while the calculation efficiency is kept, and particularly, an EEM module innovatively applies Sobel operator to be connected with residual errors, so that the tumor boundary continuity and the segmentation accuracy are synchronously improved; moreover, a novel training normal form of a focus Tversky loss function is introduced, so that the problem of class imbalance is effectively solved, the sensitivity of the model to a small tumor region is enhanced, a smoother segmentation boundary can be generated, and the stability and accuracy of a segmentation result are greatly improved.

The invention relates to the technical field of image segmentation, in particular to a missing modal brain tumor image segmentation method based on a multi-axis shift MLP modal mask, which comprises the following steps: constructing a brain tumor image segmentation model which comprises four encoders and a shared decoder, a multi-level cross-modal interaction module and a space weight attention module are introduced between the encoder and the shared encoder; respectively inputting the brain tumor images of the four modalities into corresponding encoders, and outputting encoding features of different levels and different resolutions of each modal image; the multi-level cross-modal interaction module captures complementary features among modals in combination with global context information of the coding features; and the spatial weight attention module re-weights the four modal features from different angles, and inputs the four modal features into a shared decoder for decoding to obtain a segmented image. According to the method, the missing-mode brain tumor image segmentation can be more accurately realized.

The invention belongs to the technical field of medical image analysis, and relates to a brain tumor segmentation method based on uncertainty estimation, and the method comprises the steps: inputting T1, T1c, T2 and Flair images of a brain tumor into a trained image segmentation model which comprises four encoder modules, one decoder module, one Monte Carlo simulation module and one image processing module; the Monte Carlo module repeatedly calls the encoder module and the decoder module for sampling; and the image processing module processes the output to obtain a mean value image, a random uncertainty image, a cognitive uncertainty image, an entropy uncertainty image and a mutual information uncertainty image, thereby realizing accurate segmentation and analysis of the brain tumor. The method improves the segmentation accuracy and the diagnosis reliability, is high in expansibility, and is suitable for various medical image analysis tasks.

The invention discloses a multi-scale brain tumor segmentation method and system based on adaptive KAN, and a storage medium. The method comprises the following steps: preprocessing three-dimensional brain magnetic resonance imaging data; the preprocessed data are input into an encoder, the encoder comprises a plurality of levels, and each level executes convolution operation to extract local features, executes spatial KAN processing to extract spatial features and downsamples a feature map; the output of the encoder is input into a bottleneck layer, and the bottleneck layer captures a multi-scale global context by using a plurality of parallel expansion convolution branches; the output of the bottleneck layer is input into a decoder, the decoder comprises a plurality of stages, and each stage executes transposing a convolution up-sampling feature map, executes cross-scale gating processing to fuse encoder jump connection features and decoder features, and executes spatial KAN processing to optimize features; and the output of the decoder is input into the output module. According to the method, the problems of low calculation efficiency, poor tumor heterogeneity adaptation, insufficient multi-scale context capture and the like in the existing brain tumor segmentation can be effectively solved.

The invention provides a missing-modal brain tumor image segmentation method, device, equipment, medium and product, and belongs to the technical field of image segmentation, a knowledge distillation model architecture is constructed, the knowledge distillation model architecture comprises a teacher network and a student network, the student network comprises at least one feature reconstruction module, and the teacher network comprises at least one feature reconstruction module; the feature reconstruction module is used for reconstructing brain tumor image features of a missing mode based on semantic relevance between brain tumor images of different modes; the student network is trained based on the trained teacher network, an image segmentation model is obtained according to the trained student network, and the image segmentation model is used for performing image segmentation on the to-be-segmented missing modal brain tumor image. The student network can reconstruct the brain tumor image features of the missing mode based on the semantic relevance between the brain tumor images of different modes, can better represent the brain tumor image features of the missing mode, and effectively improves the segmentation accuracy of the brain tumor images of the missing mode.

The invention discloses a brain tumor region segmentation method based on adaptive boundary guided aggregation SAM, and relates to the field of medical image analysis. The fusion output of the multi-modal magnetic resonance image is input into an image segmentation model to obtain image embedding, the boundary embedding of the brain tumor and the real boundary of the tumor are obtained through a boundary mining network, the boundary features are enhanced through an adaptive boundary enhancement model, the image embedding and the boundary embedding are output as fusion embedding by applying dynamic fusion, and the real boundary of the tumor is obtained. Inputting the fused embedded and adaptive enhanced boundary features and the features of the prompt encoder into a mask decoder of a segmentation model to obtain a segmentation result, and obtaining a total loss function in combination with a boundary mining network and a loss function based on region prediction; according to the brain tumor region segmentation method based on adaptive boundary guided aggregation SAM, accurate segmentation of the brain tumor region is realized.

The invention provides a brain tumor classification method based on deep learning, and the method comprises the steps: uniformly segmenting a multi-mode magnetic resonance imaging image into a plurality of small blocks, generating an enhanced puzzle through random geometric transformation, inputting the enhanced puzzle into a ResNet50 backbone network, extracting primary local features, and optimizing feature distribution; multi-scale feature maps of different stages are obtained, lightweight convolution blocks are constructed, and local pathological relevance is enhanced; performing full-connection layer splicing on the multi-scale feature maps in different stages, introducing a learnable weight matrix to dynamically allocate weights in each stage, and generating fusion features; a progressive parameter unfreezing mechanism is adopted to ensure orderly learning of the model from local to global; the sample weight is dynamically adjusted according to the category frequency, and the local discriminant force and the global consistency are balanced in combination with multi-stage classifier loss weighted fusion; and a final classification result is generated through multi-stage prediction probability weighted average and dynamic threshold adjustment, and clinical availability is improved in combination with a sigmoid calibration module.

The invention relates to the technical field of medical image processing, in particular to a nuclear magnetic image brain tumor detection method and system, and the method comprises the steps: obtaining an initial nuclear magnetic brain tumor image, taking a dual-convolution cross-stage division network as a backbone network, taking a partial visual state space network as a feature enhancement network, lightening a YOLOv8 model, and improving the performance at the same time; in the YOLOv8 model with improved performance, the constructed re-parameterized dynamic selectable large-kernel convolutional network is used as a multi-scale feature interaction network in the neck structure, and the performance of the YOLOv8 model is further improved by using re-parameterization, so that the improved YOLOv8 model is obtained; performing iterative optimization training on the improved YOLOv8 model by using the initial image data set to obtain a nuclear magnetic image brain tumor detection model; and inputting the initial image data set into a nuclear magnetic image brain tumor detection model for detection, and outputting a nuclear magnetic brain tumor detection result. According to the invention, the accuracy and efficiency of brain tumor detection can be improved.

The invention relates to the technical field of deep learning, and discloses a brain tumor feature extraction method and system of a multi-scale dynamic calibration detection network based on comparative learning, and the method comprises the steps: inputting a brain tumor image into a self-supervised comparative learning network, extracting key features through self-supervised comparative learning, and outputting a multi-scale feature map; performing down-sampling and up-sampling combined operation on the multi-scale feature map, inputting the multi-scale feature map into a multi-scale adaptive network for dynamic feature calibration, and optimizing multi-scale boundary features through dynamic sampling and shape self-calibration; and the output of the multi-scale adaptive network for dynamic feature calibration is input into the multi-domain attention network for dynamic deformable convolution, and key feature focusing is enhanced through residual connection and dynamic deformable convolution. And the accuracy and reliability of brain tumor feature extraction are improved.

The invention discloses a multi-scale lightweight brain tumor segmentation method based on improved YOLOv8n-Seg, belongs to the technical field of medical image processor artificial intelligence, and designs a novel down-sampling module FLRDown fusing low-rank convolution and Fourier transform to replace standard convolution operation in a YOLOv8n-Seg backbone network. Further improvement is carried out on the basis of a SimAM attention mechanism, and a novel attention module-AdaSimAM is provided; on the basis of an original YOLOv8n-Seg segmentation header, an LCSDSH segmentation header network is designed, the structure of the header network is optimized, and redundant parameters are reduced. According to the method, a structure optimization and feature enhancement mechanism is introduced, the calculation complexity of the model is effectively reduced, meanwhile, the perception ability for a small target area is enhanced, the robustness and generalization ability of the model in multi-scale tumor recognition are improved, and therefore the method is more suitable for the actual requirement for automatic segmentation of the brain tumor in clinical practice.

The invention discloses a brain tumor detection method based on attention mechanism and MRI (Magnetic Resonance Imaging) multi-modal fusion, and relates to the technical field of brain tumor image analysis. Calculating a consistency measurement score of the two heat maps, and if the score does not meet a preset threshold value, starting feedback iteration: merging the images to generate an enhanced training set, performing weighted training on a loss item corresponding to the multi-modal image by taking the normalized measurement score as a quality weight, and iteratively optimizing the model until a condition is met; and finally, outputting a brain tumor detection result with high confidence. According to the invention, by introducing an internal closed-loop verification and adaptive optimization mechanism, the core problem that the confidence of the detection result cannot be self-verified and guaranteed in the prior art is effectively solved. And finally, the accuracy of brain tumor detection confidence closed-loop verification optimization based on attention mechanism and MRI multi-mode fusion is improved.

The invention discloses a multi-mode brain tumor robust segmentation method based on graph-guided adaptive distillation, and the method comprises the steps: firstly constructing a brain tumor segmentation model which comprises a graph-guided adaptive refining module GARM module, a double-bottleneck distillation module BBDM module and a lesion perception reliability module LGRM module; secondly, acquiring a multi-modal brain medical image, executing standardization preprocessing, and then dividing a training set and a test set according to a proportion; and finally, inputting the training set into the brain tumor segmentation model to obtain a segmentation result graph for training, and performing evaluation through the test set. According to the method, the student model can still have higher adaptability and robustness under the condition of lack of modals, the effectiveness and generalization ability of knowledge distillation are greatly improved, and accurate and efficient brain image segmentation is realized.

The invention relates to the technical field of image segmentation, and provides a brain tumor segmentation method based on multi-modal fusion. The method comprises the following steps: 1, obtaining a multi-modal brain tumor image, and preprocessing the multi-modal brain tumor image to construct a multi-modal brain tumor data set; step 2, constructing a brain tumor segmentation network structure, including: selecting a Unet network as a reference model, and adding a multi-scale progressive fusion MFCM module at a jump joint of each coding layer and each decoding layer in the Unet network; 3, training the brain tumor segmentation network structure by using the multi-modal brain tumor data set to obtain a brain tumor segmentation model; and 4, preprocessing a to-be-detected multi-modal brain tumor image, and inputting the preprocessed to-be-detected multi-modal brain tumor image into the brain tumor segmentation model to obtain a segmentation result. According to the method, the segmentation performance of the model can be improved while the multi-modal features are fully utilized.

The invention discloses a multi-axis RWKV-UNet + + multi-mode MRI (Magnetic Resonance Imaging) brain tumor segmentation method, and belongs to the technical field of medical image processing. According to the invention, multi-modal MRI three-dimensional body data is input and preprocessed, and fusion features are output through a modal fusion module; the fusion features are input into an encoder containing multi-axis RWKV sequence modeling, and long-range dependence is extracted; after the output of the encoder is processed by the bottleneck layer, the global Token aggregator converges the global context and reinjects the global context; the enhanced features are input into a UNet + + nested topology decoder, the jump features are fused with the up-sampling features after being subjected to jump RWKV semantic alignment, and finally a three-dimensional segmentation probability graph is generated through mapping. The method is mainly used for accurate three-dimensional segmentation of the multi-mode MRI brain tumor, and provides support for clinical brain tumor diagnosis and treatment.

The invention provides an MRI (Magnetic Resonance Imaging) missing mode generation method based on a learnable frequency domain module, which is used for reconstructing and synthesizing any missing mode of a brain glioma medical multi-mode image. The method comprises the steps that a training set and a test set of brain tumor multi-mode MRI images are acquired, the training set and the test set comprise a plurality of samples, each sample comprises four original mode images, and each original mode image is an available mode or a missing mode; a missing modal brain tumor generation network model is constructed, and the missing modal brain tumor generation network model comprises a learnable frequency domain module and a condition diffusion module based on modal attention; inputting the training set into the model for training, setting a joint loss function, and optimizing parameters of the model through the joint loss function of each sample to obtain an optimized model; and inputting the multi-mode MRI image in the test set into the optimized model to obtain a generated image corresponding to the missing mode.

The invention belongs to the technical field of image processing, and particularly relates to a semi-supervised coarse-to-fine multi-mode brain tumor image segmentation method based on comparative learning. Inputting the image into a preset semi-supervised coarse segmentation network model based on comparative learning for comparative learning segmentation to obtain a whole tumor segmentation mask; cutting background images of the four modal images based on the guidance of a whole tumor segmentation mask to obtain four modal image data only retaining a tumor area; and inputting the image data of the four modes into a preset cross semi-supervised fine segmentation network model, obtaining a fine segmentation result containing a tumor core, an enhanced tumor and an overall tumor through cross pseudo-supervised operation, and drawing a tumor region in the FLAIR image by adopting an initial coarse segmentation network. These coarse segmentation results generate a tumor mask, which is then applied to other modalities. And refining segmentation is carried out in the multi-modal MR image through a semi-supervised learning strategy, and the segmentation precision is gradually improved through a global-to-local refining process.

The invention relates to the technical field of brain tumor image segmentation, in particular to a brain tumor segmentation method and system based on anatomical perception symmetric comparison and cross-modal migration. The method comprises the following steps: carrying out data preprocessing on acquired multi-modal MRI image data; constructing a brain tumor segmentation model based on anatomical perception symmetric comparison and cross-modal migration; performing model training based on a two-stage decoupling training strategy; and performing model reasoning by using the trained model, and outputting a brain tumor segmentation result. Through a self-supervised learning framework, pre-training is carried out by using unmarked MRI data, dependence on a large-scale marked data set is greatly reduced, the problems of time consumption and high cost of medical image marking are solved, and the applicability of a model in a limited data scene is improved.

The invention discloses a multi-modal MRI (Magnetic Resonance Imaging) brain tumor image segmentation method. The method comprises the following steps: data preprocessing and feature extraction: collecting and processing image data from different MRI sequences; adaptive feature selection and alignment: dynamically selecting the most representative modal features for alignment according to the information of the brain tumor; multi-scale feature fusion enhancement: introducing an extra network layer to perform feature fusion, the network layer being responsible for learning a weight distribution strategy, dynamically adjusting a fusion weight and strategy, inputting a fused feature map into a segmentation network, performing preliminary segmentation, and on the basis of the preliminary segmentation, performing multi-scale feature fusion enhancement; introducing an attention mechanism to guide the segmentation network to pay attention to the tumor region; reinforcement learning optimization: adopting a reinforcement learning algorithm to optimize the parameters and the structure of the segmentation network; uncertain region optimization: further optimizing the uncertain region in the segmentation result by adopting a post-processing method; and obtaining a three-dimensional tumor segmentation result: outputting the three-dimensional tumor segmentation result.

The invention provides an FTO (fluorine-doped tin oxide) inhibitor as well as a preparation method and application thereof, and particularly discloses 2-(substituted benzene miscellaneous group) aromatic formic acid as shown in the following general formula (I), derivative compounds of the 2-(substituted benzene miscellaneous group) aromatic formic acid and pharmaceutically acceptable salts, hydrates or solvates of the 2-(substituted benzene miscellaneous group) aromatic formic acid, which can be used as an FTO target inhibitor for treating diseases related to the FTO target. The compound can be used for treating human myelodysplastic syndrome, such as leukemia, lymphoma, myelodysplastic syndrome, obesity, metablic syndrome (MS), type II diabetes (Type 2 diabetes, T2D), Alzheimer's disease, breast cancer, kidney cancer, colorectal cancer, pancreatic cancer, liver cancer, small cell lung cancer, human bone marrow rhabdomyoma, pancreatic cancer, malignant glioblast brain tumor and the like. # imgabs0 #

This invention relates to benzodiazepine derivatives, compositions comprising therapeutically effective amounts of those derivatives and methods of using those derivatives or compositions in treating cognitive impairment associated with CNS disorders. It also relates to the use of an α5-containing GABAA receptor agonist (e.g., an α5-containing GABAA receptor positive allosteric modulator) in treating cognitive impairment associated with CNS disorders in a subject in need or at risk thereof, including age-related cognitive impairment, Mild Cognitive Impairment (MCI), amnestic MCI, Age-Associated Memory Impairment, Age Related Cognitive Decline, dementia, Alzheimer's Disease (AD), prodromal AD, PTSD, schizophrenia, bipolar disorder, ALS, cancer-therapy-related cognitive impairment, mental retardation, Parkinson's disease, autism spectrum disorders, fragile X disorder, Rett syndrome, compulsive behavior, and substance addiction. It also relates to the use of an α5-containing GABAA receptor agonist (e.g., an α5-containing GABAA receptor positive allosteric modulator) in treating brain cancers (including brain tumors, e.g., medulloblastomas), and cognitive impairment associated therewith.

The invention belongs to the technical field of medical nano-materials, and particularly relates to a lactoferrin nano-material for sonodynamic regulation and control of blood-brain barrier permeability as well as a preparation method and application of the lactoferrin nano-material. The nanomaterial is nanoparticles LCe6 formed by self-assembly of lactoferrin and chlorin e6, can target brain microvascular endothelial cells, and can temporarily, reversibly and targeting open BBB by using the sonodynamic effect of the LCe6 in combination with transcranial ultrasonic stimulation, so that the accumulation of the nanoparticles LCe6 at a focus part is improved; in addition, the nanoparticle LCe6 also has a targeting property on brain tumor cells, the tumor cells can be accurately killed by utilizing the sonodynamic effect of the nanoparticle under secondary transcranial ultrasound, and the effect of sonodynamic treatment on brain glioma is exerted to the maximum extent; the nanoparticles LCe6 have excellent biocompatibility and low toxicity; according to the invention, the intracerebral delivery efficiency of the drug can be obviously improved, and a novel method for targeting open brain disease BBB is provided.

The invention discloses a preparation method of a polymer vesicle capable of crossing a blood brain barrier, and belongs to the field of high polymer materials and medical engineering. The preparation method of the polymer vesicle capable of crossing the blood brain barrier comprises the following steps: synthesizing an amphiphilic block copolymer by utilizing ring-opening polymerization reaction of polycaprolactone and anhydride in an amino acid ring, then assembling the polymer into the polymer vesicle, and modifying a monoclonal antibody of a transferrin receptor on a polypeptide chain. The polymer vesicle prepared by the invention is simple and convenient in preparation process, short in period, good in stability, good in biocompatibility and good in biodegradability, can be used as an excellent carrier of chemotherapeutic drugs, and can effectively realize drug delivery of targeting brain tumor cells across a blood brain barrier. Compared with a commercial drug delivery carrier, the polymer vesicle has the advantage that the permeability of the drug in a bionic blood brain barrier and the targeted uptake rate of brain tumor cells are remarkably improved.

The invention provides a multi-modal MRI (Magnetic Resonance Imaging) brain tumor image segmentation method based on fusion of Transform and U-Net, belongs to the field of semantic segmentation, and aims to improve the speed and precision of MRI brain tumor image segmentation. The invention provides a novel method, existing knowledge and experience are utilized, Transform and U-Net models are fused and applied to an MRI brain tumor image segmentation task, an attention mechanism and an inverse residual module are introduced at the same time, and the model performance and generalization ability are remarkably improved. The MRI brain tumor image segmentation method is superior to a traditional segmentation method in the aspect of MRI brain tumor image segmentation, the accuracy of MRI brain tumor segmentation is improved, and important practical significance and guidance are provided for development of medical auxiliary diagnosis and treatment.

The invention relates to a brain tumor image segmentation method based on multi-modal fusion and cascade segmentation, and belongs to the field of digital image processing. The method comprises the following steps: S1, acquiring brain tumor images of different modalities, unifying the sizes of the images, preprocessing the images, and dividing the images into a training set and a test set; s2, constructing a brain tumor image segmentation model, and inputting the training set into the model for training; s3, performing multi-modal feature extraction, multi-modal fusion and cascade segmentation on the input image data by the model in each round of training, and by taking the weighted Dice Loss sum of segmented regions as a loss function, comparing with a label, calculating loss and performing back propagation on training model parameters until the model parameters converge; and S4, segmenting the brain tumor image by using the trained brain tumor image segmentation model to obtain a brain tumor segmentation result. According to the invention, complementary information between multi-modal images can be fully utilized, and a network is helped to pay attention to boundaries between regions.