82 results about "Fusion image" 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 discloses a remote sensing image space-time fusion method and device based on a selective state space model, and belongs to the technical field of remote sensing image processing and computer vision crossing. The method comprises the following steps: acquiring high-resolution and low-resolution image input, and extracting multi-scale features through a multi-layer encoder; capturing an anisotropic space structure in the remote sensing image by using a four-way two-dimensional selective scanning mechanism; designing a state space fusion module, decoupling and cooperatively processing space details and time dynamic information through a space and time sequence selective scanning fusion sub-module, and performing feature fusion by adopting adaptive gating parameters; and finally, reconstructing a high-resolution image through a symmetric decoder, and carrying out model optimization by adopting a composite loss function. On the premise of ensuring the linear calculation complexity, the spatial detail fidelity, the time continuity and the overall efficiency of the fused image are remarkably improved, and the method is suitable for large-scale remote sensing data processing.

The invention discloses a CT image analysis method and system based on a neural network, and relates to the technical field of CT image analys.The method comprises the steps that an original CT image is obtained after user authorization, a Laplace operator is adopted to strengthen a focus boundary, and a circular region of interest is intercepted to remove edge sensitive information; extracting edge and texture information in the standardized image; focus area features are focused step by step; executing characteristic distillation balance based on category sample distribution, and outputting a focus characteristic graph with local perception enhancement and sample balance characteristics; segmenting the lesion feature map into serialized units, embedding position codes, inputting the serialized units into a plurality of layers of encoders, and fusing an image structure and text indication information through a dynamic adjustment mechanism; performing linear classification on the global semantic vector to output a diagnosis result, generating a focus thermodynamic diagram, and superposing the focus thermodynamic diagram to an original image for visualization; and performing dynamic optimization based on doctor feedback. The accuracy of feature analysis is improved; the overall operation efficiency of the system is improved.

The invention relates to the technical field of medical images, in particular to a multi-modal medical image registration and fusion analysis method, which comprises the following steps of: eliminating image noise and artifacts based on a modal adaptive filtering strategy; constructing a pyramid type feature extraction network to realize multi-scale feature extraction, calculating feature matching degrees among different modal images, and dynamically adjusting matching weights by combining feature differences among modals; a focus area attention mask is constructed, targeted enhancement of registration image features is realized, and a hierarchical fusion strategy is adopted to evaluate the quality of a fused image; and constructing a multi-task deep learning model to complete focus automatic detection, segmentation and benign and malignant preliminary judgment on the fused image. According to the multi-modal medical image registration and fusion analysis method, a three-layer feature pyramid is constructed, a multi-feature fusion matching cost function is introduced, and cross-modal feature matching is optimized through an adaptive weight iteration nearest point ICP algorithm, so that the information richness, marginal definition and focus discrimination of a fused image reach the standard.

The invention provides a ship detection-oriented multi-source remote sensing image fusion method, a ship detection-oriented multi-source remote sensing image fusion medium and a ship detection-oriented multi-source remote sensing image fusion system, and belongs to the technical field of remote sensing images. Constructing an electromagnetic scattering constraint model based on physical optical approximation and a geometric diffraction theory to calculate a predicted value of the backscattering cross section of the target, introducing a fusion cost function, generating a fusion weight matrix by adopting an adaptive feature weighting model, and performing multi-scale fusion on the image through hypercomplex wavelet transform; and iteratively optimizing the fusion result by using an information diffusion heat conduction equation, and performing physical consistency correction to output an enhanced fusion image, thereby solving the technical problem of poor physical consistency of the fusion result caused by lack of physical model constraint when the synthetic aperture radar image and the multispectral image are fused.

The invention provides a three-dimensional medical image segmentation method and system for thyroid-related eye diseases, and is applied to the technical field of data processing. Multi-modal medical image data, a coarse-grained segmentation result and a fine-grained segmentation result are obtained, the multi-modal medical image data comprise a CT image and an MRI image, the multi-modal medical image data are preprocessed, a fused image body is generated, and the fused image body is formed by registration and feature fusion of the CT image and the MRI image; processing the fused image body and the coarse-grained segmentation result to generate a fine segmentation result; processing the fine segmentation result to generate a preliminary segmentation mask; processing the preliminary segmentation mask and the multi-modal medical image data to generate a mixed loss function; and processing the preliminary segmentation mask, the mixed loss function and the extraocular muscle attachment point position based on a dynamic post-processing strategy to generate a final segmentation result.

The present disclosure provides a multi-temporal remote sensing image fusion method, device, equipment and storage medium. The method of the present disclosure comprises: reading and preprocessing multi-temporal remote sensing image data; performing linear normalization for each band of the multi-temporal remote sensing image data and saving global normalization parameters; initializing an adaptive Kalman filter for each pixel point in the multi-temporal remote sensing image data, the initialization of each adaptive Kalman filter comprising setting a forgetting factor of the adaptive Kalman filter; performing processing using the adaptive Kalman filter to determine the pixel value of each pixel point in the fused image data to obtain fused image data, the processing of the adaptive Kalman filter comprising a prediction operation and an update operation, the update operation comprising adjusting an observation noise covariance matrix using the forgetting factor; de-normalizing the fused image data according to the global normalization parameters; saving the fused image data and setting its geographic information. The present disclosure can improve the multi-temporal remote sensing image fusion quality.

The invention relates to the technical field of image fusion, in particular to a territorial space planning region boundary determination method and system based on a remote sensing image, and the method comprises the steps: obtaining a target multispectral image and a target panchromatic image which are spatially aligned under a target region; performing multi-scale and multi-direction transformation on the target panchromatic image and the target multi-spectral image to obtain a low-frequency sub-band and a plurality of high-frequency sub-bands corresponding to each image; fusing each pair of high-frequency sub-bands based on the gradient difference and the boundary significance difference between each pair of high-frequency sub-bands to obtain a plurality of fused high-frequency sub-bands; performing multi-scale and multi-direction inverse transformation based on the plurality of fused high-frequency sub-bands and the low-frequency sub-bands of the target multispectral image to obtain a target fused image; and determining a region boundary based on the target fusion image. According to the method, a target fusion image with high resolution and clearer boundary can be obtained, and a more accurate and reliable region boundary can be obtained.

This invention proposes an image processing method and a display device using this method. The method includes: converting an original image to a first color space to generate a reference image corresponding to the first color space; detecting image regions with high-frequency signals in the reference image to generate a detection result; performing an operation on the detection result according to a preset gain value to generate a first operation result; evaluating the detection result and the first operation result, and selecting a reference gain value; performing an operation on the detection result according to the reference gain value to generate a second operation result; selecting at least one of the brightness values ​​of a first pixel in a first fused image and a second pixel in a second fused image according to the first operation result and the second operation result to generate the brightness values ​​of pixels in a third fused image; and converting the third fused image to a second color space to generate an output image corresponding to the second color space. The display device of this invention makes the displayed image clearer and suppresses the white-edge effect.

This invention belongs to the field of remote sensing image processing technology and discloses a method and system for spatiotemporal fusion of remote sensing images. This method introduces Mamba modules in both the spatial and frequency domains to enhance the extraction and modeling capabilities of multi-scale features and structural information. In the spatial domain, the Mamba module is used to capture the local structure and geometric details of the image; in the frequency domain, the Mamba module is introduced for feature extraction of the high-frequency subbands after wavelet transform, thereby more fully exploring the contextual dependencies and structural features of high-frequency information. Through channel attention and spatial attention mechanisms, dual-domain interactive fusion is achieved, improving the spatial clarity and spectral consistency of the fused image. It possesses strong generalization and adaptability, fully utilizing information from both the spatial and frequency domains, and improving the accuracy and efficiency of acquiring remote sensing images.

This invention discloses a multimodal image real-time registration and fusion system and method for cardiac interventional surgery, comprising: a multimodal image acquisition module, an image data transmission module, an intraoperative twin image registration and analysis platform, an algorithm calculation module, a parameter adjustment module, and an image fusion output module. After acquiring image data, the multimodal image acquisition module sends it to the intraoperative twin image registration and analysis platform via the image data transmission module. The platform incorporates a cardiac deformation adaptive optical flow algorithm, a multi-resolution hierarchical mapping algorithm, and a large-deformation cardiac image registration algorithm. The algorithm calculation module performs registration calculations, and the parameter adjustment module optimizes the fusion parameters based on the calculation results. Finally, the image fusion output module generates and outputs the fused image. This invention achieves real-time and accurate multimodal image registration and fusion, providing reliable image support for cardiac interventional surgery and improving surgical accuracy and safety.

The invention discloses a deep learning lung segment segmentation and lung function quantitative analysis method and system based on SPECT / CT, and belongs to the field of medical image analysis and nuclear medicine. The method comprises the following steps: firstly, collecting clinical SPECT / CT fusion image data for preprocessing; then, a 3D ResU-Net deep learning network improved by a loss function is utilized to carry out automatic lung segment segmentation on the preprocessed CT structure image, and morphological post-processing is carried out; secondly, performing spatial alignment on the preprocessed SPECT function image and the morphological post-processed CT structure image by adopting multi-strategy registration, and performing multi-dimensional lung function parameter quantification; and finally, carrying out machine learning modeling analysis. The implementation system comprises a data acquisition module, an image preprocessing module, a deep learning segmentation module, an SPECT / CT registration module, a lung function quantization parameter module, a health state evaluation module and a result display module. According to the invention, precise and automatic segmentation of 18 lung segments is realized; the accuracy of function information extraction is ensured; the analysis efficiency and the clinical practicability are improved.

The present application relates to the field of liver cancer immunotherapy efficacy evaluation method combining imageomics and deep learning, and specifically discloses a liver cancer immunotherapy efficacy evaluation method combining imageomics and deep learning. The method comprises the following steps: acquiring multi-modal medical images and clinical information of a liver cancer patient; performing standardization preprocessing and automatic lesion segmentation on the images; extracting features through a multi-scale deep network and realizing semantic alignment by using a cross-modal attention mechanism; fusing the images and the clinical data to construct a multi-source heterogeneous feature matrix; adopting a hierarchical model structure, modeling the spatial distribution of tumor immune microenvironment by using a graph neural network at the bottom layer, dynamically tracking the evolution of efficacy by using a gated recurrent unit at the upper layer, and finally outputting an immune response probability, a tumor load trend and a treatment response grade. The present application can objectively and quantitatively evaluate the efficacy of liver cancer immunotherapy, and improve the precision and automation level of individualized diagnosis and treatment decision-making.

The invention relates to a hyperspectral calculation imaging technology, and aims to solve the problems that in an actual remote sensing observation environment, a single imaging mode is limited by a physical sensor, high space resolution and hyperspectral resolution are difficult to obtain at the same time, and geometry and spectrum complementarity exists among multi-source images. The invention provides a hyperspectral fusion imaging method based on topology perception and a differential homeomorphic mechanism. According to the method, differential homeomorphic transformation is introduced to construct spatial degradation priori, a dual learning framework is adopted to jointly optimize high-resolution generation and bidirectional reconstruction tasks, meanwhile, a topology sensing Transform module is utilized to explicitly model a spectrum-space double-domain manifold structure, complementary correlation among multi-source data is fully mined, and the spectrum-space double-domain manifold structure is constructed. The spatial structure consistency and the spectral fidelity of the fused image are effectively improved, the problem of fusion quality reduction caused by geometric deformation and spectral variation in a complex ground feature scene is significantly improved, and a more reliable data support is provided for applications such as remote sensing monitoring and environmental perception.

The present application relates to the technical field of marine remote sensing and water depth inversion, and discloses a water depth inversion method fusing multi-temporal information and geographic spatial perception mechanism, single-temporal remote sensing images of the same water area at different time points are acquired first to construct a multi-temporal remote sensing image sequence, then a robust principal component analysis method RPCA is used to fuse and process the multi-temporal remote sensing image sequence to obtain a fused image; then a plurality of core units are cascaded together to complete step-by-step feature extraction, and the last core unit is connected to a regression head to output continuous water depth values, thereby completing the construction of a water depth inversion network model; finally, the water depth inversion network model is trained by using the fused image combined with the geographic spatial position, and the trained water depth inversion network model is used to perform water depth inversion on the data-processed remote sensing image to be detected.

This invention discloses a dynamic segmentation method for three-dimensional brain networks based on deep learning. The method comprises the following steps: S1. Constructing temporally and spatially consistent fused image volume data; S2. Generating a multi-scale sparse Transformer encoded feature pyramid; S3. Obtaining the same-scale brain region map structure; S4. Using the cross-scale node-aligned fused map structure as the initial output of the cross-scale node-aligned fusion mechanism; S5. Obtaining the node embedding features of the first round of fused brain region map; S6. Obtaining the updated multi-scale sparse Transformer encoded feature pyramid, and repeating steps S3 to S5 until the multi-scale sparse Transformer-GNN interactive update is completed; S7. Obtaining the dynamic segmentation result of the three-dimensional brain region. This invention achieves the collaborative extraction of local fine-grained and global coarse-grained features, which not only effectively suppresses redundant information but also enhances the modeling ability of spatial structure and functional connectivity features in cross-modal fused images.

The application relates to the technical field of image fusion, in particular to a land space planning regional boundary determination method and system based on remote sensing images. The method comprises the following steps: acquiring target multispectral images and target panchromatic images which are spatially aligned in a target region; performing multi-scale multi-direction transformation on the target panchromatic images and the target multispectral images to obtain a low-frequency subband and a plurality of high-frequency subbands corresponding to each image; fusing each pair of high-frequency subbands based on gradient difference and boundary saliency difference between the high-frequency subbands to obtain a plurality of fused high-frequency subbands; performing multi-scale multi-direction inverse transformation on the plurality of fused high-frequency subbands and the low-frequency subband of the target multispectral images to obtain a target fusion image; and determining a regional boundary based on the target fusion image. The method can obtain a target fusion image with higher resolution and clearer boundaries, and obtain a more accurate and reliable regional boundary.

The invention discloses a panchromatic image and multispectral remote sensing image fusion method, which comprises the following steps: S1, acquiring remote sensing image data of a target area and preprocessing the remote sensing image data to obtain preprocessed remote sensing image data; the remote sensing image data comprises a panchromatic image and a low-resolution multispectral image; s2, inputting the preprocessed remote sensing image data into the trained kernel estimation network to obtain an estimation fuzzy kernel of the low-resolution multispectral image; and S3, sequentially inputting the preprocessed remote sensing image data and the estimated fuzzy kernel into the trained fusion network to obtain a fusion image.

This disclosure presents a method and apparatus for simulating landslide area generation in post-earthquake secondary disasters. One specific implementation of the method includes: acquiring panchromatic and multispectral image sets, and obtaining original images and elevation datasets; fusing the panchromatic image with each multispectral image in the multispectral image set to generate a fused image; identifying landslide areas on the fused image to generate an identification result; in response to the identification result indicating that the post-earthquake risk area includes landslide areas, performing landslide area edge detection based on the original image, elevation dataset, and fused image to generate a first edge coordinate sequence and a second edge coordinate sequence; and performing landslide area simulation processing based on the original image, fused image, first edge coordinate sequence, and second edge coordinate sequence to generate the landslide surface area and landslide coverage area. This implementation can improve the accuracy of the generated landslide surface area and landslide coverage area.

The embodiment of the application discloses a river flow inversion method based on multi-source optical remote sensing images, relates to the technical field of hydrological monitoring, and comprises the following steps: acquiring multi-source remote sensing images containing a target research basin, processing to obtain a plurality of reference image pairs, fusing to-be-fused images and matched reference image pairs to obtain high-resolution fused images; a monitoring area is divided from the target research basin, and a monitoring pixel is screened based on an indication index value and a flow correlation coefficient; a function relationship between an indication index mean value of each date of each type of indication index and river flow is determined to construct a river flow inversion model; and the river flow of the corresponding date of the to-be-predicted remote sensing image is predicted through the river flow inversion model. According to the application, the flow inversion can be carried out by using the disclosed optical remote sensing images without relying on river surface features and hydraulic parameters, missing runoff data can be supplemented, and even hydrological stations can be replaced, so that the time and labor cost of flow observation are reduced.

The application discloses a SAR and optical image fusion method and system based on morphological feature decomposition, and belongs to the field of image processing. First, the optical image and the SAR image are preprocessed, then, a differentiated multi-layer feature decomposition strategy is adopted to decompose the image into main structure information, morphological feature information and edge detail information, wherein the main structure information is extracted by a local total variation method, the morphological feature information is obtained by a generalized total variation model and residual suppression, and the edge detail information is decomposed by jointing bilateral filtering and a least square model. Then, different feature layers are respectively fused by a saliency guided fusion, a local weighted fusion and a fusion strategy combining edge preservation and sparse detail compensation. Finally, color information is restored by IHS inverse transformation to obtain a fused image with clear structure, complete morphology and rich details, so that fine fusion from structure to morphology and then to details is realized.

This application presents a method for classifying land features along railway lines using remote sensing imagery based on morphological entropy fusion. The method includes: acquiring Sentinel-1 radar imagery, Sentinel-2 optical imagery, and a fused image of the target area from a GEE platform, and preprocessing the data; generating masks on the Sentinel-1, Sentinel-2, and fused images respectively, and calculating and extracting circumferential morphological entropy, radial morphological entropy, and joint morphological entropy; extracting polarization and texture features from the Sentinel-1 imagery, and spectral and exponential features from the Sentinel-2 imagery, and constructing corresponding composite features on the fused imagery; combining these features with morphological entropy features from corresponding data sources; training a random forest classification model based on each feature set, and using the trained model to classify four typical land features along the railway line: buildings, railways, vegetation, and highways. This method, by fully utilizing multi-source remote sensing information, effectively characterizes the structural complexity and irregularity of land feature outlines through morphological entropy, significantly improving the accuracy and reliability of the classification results.

This invention discloses a landslide monitoring method based on remote sensing data, comprising: acquiring high-resolution optical remote sensing images and synthetic aperture radar images of the study area; performing registration processing on the optical and radar remote sensing images to obtain remote sensing images with accurate spatial location and geometric shape; generating a high-spectral-resolution fused image of the landslide area; obtaining matched high-resolution DEM data; calculating slope parameters of the study area based on the matched high-resolution DEM data, and determining a slope threshold according to slope distribution characteristics and prior knowledge; extracting slope aspect parameters of the study area using a grid-and-vector-based slope aspect algorithm, and filtering out landslide-prone areas in conjunction with the slope threshold; obtaining a landslide hazard distribution map; obtaining the probability and hazard level of landslide occurrence, and obtaining the landslide situation based on the probability and hazard level of landslide occurrence. This invention achieves accurate identification and dynamic monitoring of landslide disasters.

The application relates to the technical field of real-time monitoring, and discloses a greenhouse plant product harvesting monitoring method and system based on a knowledge graph, which comprises the following steps: calculating corresponding image values according to pre-acquired multi-modal images in a greenhouse, and constructing a value heat map; identifying key points of each modal image respectively, and screening out corresponding key regions; configuring a dynamic fusion mechanism, fusing the key regions of each modal image respectively, and obtaining a fused image; analyzing the fused image through a pre-constructed plant harvesting graph, identifying a harvesting region, and harvesting plant products in the harvesting region; through joint analysis of multi-modal images, the adaptability to changes in the greenhouse environment during the harvesting process of the plant products can be improved, low-quality information can be removed while retaining the advantageous features of each modal image, the quality of the fused image can be improved, the harvesting region can be quickly identified in combination with the knowledge graph, and the accuracy and efficiency of the harvesting process of the plant products in the greenhouse can be improved.

The invention relates to the technical field of sports management, in particular to a match playback image optimization method, device and equipment, and the method comprises the steps: analyzing match image data according to a preset fragment duration, a playback demand, a preset collection condition and a preset image encoder, so as to obtain a first ROI region and a playing resolution; performing image quality restoration on the first ROI region according to a preset color channel, a preset gradient variance and a preset adjustment coefficient set to obtain a restored ROI region; generating a fused image segment according to the restored ROI region, a preset high code rate parameter and a preset low code rate parameter; performing frame rate adjustment on the fused image segment according to a preset playback speed and a preset playing resolution to obtain a playback image segment; by accurately analyzing playback requirements, optimizing the ROI, repairing image problems, fusing different code rate parameters and adjusting the frame rate according to requirements, the method is integrally adaptive to multiple competition and multiple terminals, user experience is optimized, and competition playback is assisted to be efficiently presented.

The invention discloses a digestive system department focus recognition method and system based on object recognition, and relates to the technical field of digestive system departments, and the technical scheme is characterized in that the method comprises the following steps: setting a cross-modal monitoring unit associated with different modal to-be-fused image sub-regions according to the modal type and imaging parameters of a digestive system department multi-modal image; the abnormal structure monitoring unit is used for extracting focus structure feature data of the to-be-fused image sub-regions according to the cross-modal monitoring unit, and analyzing the focus structure feature data to obtain a structure abnormal coefficient and the cross-modal monitoring unit; the abnormal blood flow monitoring unit is used for extracting focus blood flow characteristic data of the to-be-fused image sub-region according to the cross-modal monitoring unit, and analyzing the focus blood flow characteristic data to obtain a blood flow abnormal coefficient of the to-be-fused image sub-region and an abnormal blood flow monitoring unit of the cross-modal monitoring unit; the method is convenient for obtaining the recognition result of the key focus.

The application discloses a kind of desert remote sensing image lake extraction methods based on SSI and water body index fusion, comprising the following steps: based on the remote sensing image data obtained by GEE platform, calculate suspended sediment index (SSI) and water body index;Suspending the fusion processing of silt index and water body index, obtain fusion image, to enhance the distinguish degree of lake area and background area;Proposed classification method is segmented by single index threshold value;Based on the proposed classification method, the fusion image is classified, and the lake area is accurately extracted. It can effectively improve the accuracy of lake extraction in desert environment, especially in the lake area containing high concentration of silt and the desert area with strong surface reflection. Through the fusion of the two technologies, the advantages of different spectral indexes can be fully utilized to achieve more accurate water body identification in complex environment.

The invention discloses a detection and counting method for image fusion of wild animals in an open area. The method comprises the following steps: synchronously acquiring a visible light image and a thermal infrared image of a target area and carrying out image preprocessing; thirdly, inputting the pre-processed visible light image and thermal infrared image into the trained fusion model, and outputting a fusion image; then, based on feature point matching and weighted fusion, seamless splicing of a plurality of fused images is carried out, and a spliced fused image of the target area is obtained; and finally, inputting the spliced and fused image of the target area into a counting model, and obtaining an animal population quantity statistical result of the target area based on output processing of the counting model. The advantages of two types of images are integrated, the problems that a traditional method is low in efficiency and poor in precision are solved, large-area high-precision animal counting is achieved, and a reliable means is provided for wild animal protection.

The application discloses a kind of multi-modal image's synergic registration fusion method, system, electronic equipment and storage medium, the method includes: S1 obtains the multi-modal image group of target area, the multi-modal image group is divided into full-color image and multispectral image image;S2 the full-color image and multispectral image image are preprocessed, obtain the full-color image and multispectral image image after preprocessing;S3 the full-color image and multispectral image image after preprocessing are input into synergic registration fusion network model, obtain target fusion image.The synergic registration fusion network model constructed by the application includes image registration network, semantic extraction network and image fusion network, can effectively eliminate the artifact caused by parallax between multi-modal image, and introduce semantic feature in fusion image, improve the quality of fusion image, meet the demand of subsequent advanced visual task.

The invention belongs to the technical field of image segmentation, and particularly relates to an intelligent segmentation method and system for an acute pancreatitis CT image, and the method comprises the steps: simulating a normal pancreatic CT image, carrying out the virtual lesion generation, fusing a virtual CT image set with a real CT image, extracting the topological structure features of the pancreatic tissue of the fused image, and carrying out the segmentation of the pancreatic tissue; performing unsupervised clustering on the topological structure image by adopting a topological perception diffusion coacervation method, and distinguishing pancreas and background regions; differentiated mechanical parameters are distributed to all areas of the preliminary segmentation mask, and boundary deformation is corrected; carrying out fine correction on the pixels of the optimized mask by adopting an entropy optimization threshold method; and according to the region segmentation mask, automatically calculating a necrotic volume ratio and an exudation maximum sectional area, and outputting a region segmentation result. According to the method, a virtual image is generated through fluid diffusion, topological guide segmentation and mechanical correction are carried out, accurate partitioning and quantitative grading are achieved, and clinical diagnosis is assisted.