281 results about "Tissue architecture" patented technology

The invention relates to the technical field of image classification, in particular to a training method and system of a cervical pathological image classification model based on multiple modes. The method comprises the following steps: acquiring a cervical tissue image and carrying out tissue structure segmentation, forming a nucleus-interstitial-epithelium three-distribution framework, collecting development historical data, confirming a prediction trend of each layer, carrying out environment field simulation through the image, generating a simulated cervical environment field, and carrying out hierarchical evolution prediction on the framework. Evolution mapping images are generated according to the evolution data and classified, finally, a visual basic model is obtained through combined modeling training, image-text fusion is achieved, and a cross-center deployment model system is generated. According to the method, vision-language combined modeling is realized, and the stability and controllability of the whole model structure in image space deformation modeling, semantic cross-modal alignment construction and task-level response flow scheduling are improved.

The invention relates to the technical field of image processing, in particular to an image segmentation system for medical diagnosis, which comprises a regional characteristic analysis module, a modal selection optimization module, an image local enhancement module, an edge characteristic analysis module and a boundary optimization adjustment module. According to the medical image segmentation method, the gray level distribution, the texture density and the structure contour of the tissue structure in the image layer are analyzed, the system is allowed to accurately measure the characteristic deviation between different modes, the accuracy of medical image segmentation is improved, especially on the processing of the complex tissue structure, the adjacent tissues with different properties can be better analyzed and distinguished, and the medical image segmentation accuracy is improved. Real-time evaluation and adjustment of local contrast enable details of the image to be clearer, image quality is improved, accuracy of edge recognition is improved, by analyzing edge curvature and morphological characteristics, the system can optimize edge trend and reconstruct a boundary path, overall performance of image segmentation is further improved, and image segmentation efficiency is improved. Therefore, the treatment and prognosis effects of the patient are ensured.

The invention discloses an image video super-resolution enhancement method based on a degradation generative adversarial network, and relates to the field of image processing, and the method comprises the steps: carrying out the image collection and preprocessing; building and training a super-resolution enhancement model; and carrying out super-resolution enhancement on the image based on the degradation generative adversarial network model. According to the method, an image content self-adaptive dynamic degradation kernel generation mechanism is adopted, the degradation process of the image under different equipment and organization structures is truly simulated, a dynamic up-sampling and residual error correction network guided by the degradation kernel is adopted, the detail reduction capability and the structure fidelity of the super-resolution image are remarkably improved, and the super-resolution image quality is improved. The image texture authenticity and key organization density consistency are effectively enhanced, the balance of training games between a generator and a discriminator is realized, and the model stability and convergence quality are improved.

The invention relates to the field of medical image processing, and discloses a medical image enhancement processing and tissue boundary intelligent identification method, and the method comprises the steps: constructing a medical image segmentation model, and enabling a learnable filter module to comprise a Gabor filter group and an LoG filter group which are parallel; the multi-modal feature fusion module fuses the texture features output by the plurality of Gabor filters, the edge features output by the plurality of LoG filters and the original input image; the Swin Transform is used for dividing the fusion feature map into an image block sequence and extracting a multi-scale feature map from the image block sequence; the segmentation head is used for recovering the multi-scale feature map to the original resolution and outputting a segmentation mask; training the constructed medical image segmentation model; and performing image segmentation processing on a clinical medical image by using the trained medical image segmentation model, and outputting pixel-level segmentation masks capable of clearly displaying different tissue structures and tissue boundaries. The method can effectively improve the recognition precision of the tissue boundary in the medical image.

The invention relates to the technical field of disease diagnosis, and comprises a disease diagnosis method and system based on neural network cognitive diagnosis, and the method comprises the following steps: obtaining medical image data, calculating the gray level change rate, gradient direction distribution and edge continuity of a lesion region, counting the lesion tissue damage area, and analyzing the pathological tissue damage degree. And obtaining a lesion distribution consistency index. According to the invention, through comprehensive calculation of the medical image data and the pathological tissue slice data, fine-grained description of a focus area is realized, association among different lesion features is realized, and calculation of a lesion propagation path matching rate is realized, so that identification of lesion diffusion conditions is more accurate, and development trends of diseases in different tissue structures can be effectively predicted; the calculation of the cross-modal feature error is combined with the adjustment of the distribution weight of the lesion region, misdiagnosis caused by modal difference and extraction of abnormal signals in a lesion diffusion range are reduced, so that screening of potential diseases is more targeted, and the accuracy of disease recognition is improved.

The invention discloses a breast cancer neoadjuvant chemotherapy curative effect prediction method and system, and relates to the medical image processing and analysis technology, and the method comprises the steps: carrying out the Macenko dyeing normalization of a sample HE pathological image of a patient; extracting a tissue region from the normalized sample HE pathological image by using an HEST method; inputting the extracted tissue region into a Prov-GigaPath network, extracting a feature vector of a specified dimension under set parameters, and performing dimension reduction on the extracted feature vector; inputting the feature vectors subjected to dimension reduction into an ABMIL model, and training the feature vectors; and predicting the HE pathological image of the patient based on the trained ABMIL model, and visualizing the prediction result by using the attention score of the trained ABMIL model. According to the method provided by the invention, multi-level complex features such as cellular morphology and tissue structure in the HE image can be automatically mined, and the accuracy and reliability of prediction are greatly improved.

According to the invention, the multi-mode time-frequency domain conversion and the deep learning technology are combined, and a multi-component mixed Raman spectrum unmixing method is developed, so that clinical in-vivo and in-situ detection and disease diagnosis of novel Raman probes, instruments and the like are facilitated. The method comprises the following steps: (1) converting a mixed Raman spectrum from a time domain to a frequency domain by using fast Fourier transform (FFT), discrete cosine transform (DCT) and discrete sine transform (DST), and extracting frequency domain features; (2) extracting multi-scale local time-frequency domain characteristics of the mixed spectrum by using short-time Fourier transform (STFT) and discrete wavelet transform (DWT); (3) carrying out spectral unmixing calculation in each mode in combination with a one-dimensional attention mechanism U-shaped neural network model; and (4) fusing various modal unmixing results by using a meta-learning method, and analyzing the weight of each modal to obtain an accurate unmixing spectrum. Compared with a traditional Raman spectrum analysis method, the Raman spectrum multi-component signal unmixing method based on multi-modal time-frequency domain transformation and deep learning can accurately separate independent Raman signals of different tissue structures and biochemical components in a complex environment in a living body, so that the unmixing accuracy of the Raman spectrum multi-component signal is improved. Therefore, convenience is provided for subsequent disease mechanism analysis and diagnosis. The method provides an innovative and potential solution for in-vivo and in-situ detection analysis and disease diagnosis of medical clinical Raman spectroscopy.

The invention provides a digital pathological section scanner control system based on the Internet of Things. The digital pathological section scanner control system comprises a user management module, a product classification module, an equipment management module, a pathological image data service module, a remote real-time monitoring and operation module and an intelligent fault diagnosis and early warning module. The system has the following beneficial effects: the product classification module realizes efficient classification management of pathological section scanner equipment; an intelligent section type identification sub-module in the pathological image data service module can automatically identify HE staining types and tissue features, and dynamically adjust scanning parameters according to staining quality, so that the stability of scanning quality is improved; a 3D digital slice reconstruction sub-module in the pathological image data service module can construct a three-dimensional organization structure view, so that the accuracy and reliability of pathological diagnosis are greatly improved; the intelligent fault diagnosis and early warning module adopts a machine learning technology to carry out fault prediction and real-time diagnosis, and equipment faults are effectively prevented.

The invention relates to the technical field of medical information, in particular to an anomaly recognition system for trend characteristics of chronic disease monitoring data. The system comprises a chronic disease monitoring data integration module, a chronic disease feature change analysis module, a chronic disease composite feature analysis module and a chronic disease trend feature anomaly recognition module, and can perform chronic disease classification and associated chronic disease integration according to real-time chronic disease monitoring data. Generating integrated associated chronic disease data; performing tissue structure mapping reconstruction of the chronic disease patient and disease mutation characteristic factor analysis of the chronic disease patient according to the integrated and associated chronic disease data, and generating disease mutation characteristic factor data of the chronic disease patient; according to the disease mutation characteristic factor data of the chronic disease patient, performing disease composite characteristic analysis on the chronic disease patient, and performing chronic disease trend abnormal characteristic analysis to generate chronic disease trend abnormal characteristic data. According to the invention, accurate identification of chronic disease trend abnormity is realized.

A computer device performs feature extraction on two-dimensional medical images included in a three-dimensional medical image, to obtain image features corresponding to the two-dimensional medical images. The three-dimensional medical image are obtained by continuously scanning a target tissue structure. The computer device determines offsets of the two-dimensional medical images in a target direction based on the image features. The computer device performs feature alignment on the image features based on the offsets, to obtain aligned image features. The computer device performs three-dimensional segmentation on the three-dimensional medical image based on the aligned image features, to obtain three-dimensional layer distribution of the target tissue structure in the three-dimensional medical image.

The invention discloses an ultrasonic image denoising method based on variational mode decomposition and local space sparse fusion, which comprises the following steps of: firstly, adaptively optimizing key parameters of variational mode decomposition by using a grey wolf optimization algorithm to realize stable and efficient decomposition of an ultrasonic image; then, classifying the modal components according to the structural features of the modal components, and implementing differentiated denoising strategies for different types of modals to separate noise and reserve useful information; after modal reconstruction, a sparse expression method based on local space information is further introduced, according to the method, accurate boundary detection is carried out through gradient vector flow and gray scale proportion analysis, self-adaptive partitioning is carried out on an image according to boundary information, and finally sparse reconstruction is carried out through double dictionaries trained for different areas. According to the method, speckle noise in the ultrasonic image can be effectively suppressed, and meanwhile, the capability of keeping the edge and detail information of a tissue structure is remarkably improved, so that the ultrasonic image with higher quality is obtained.

The utility model relates to the technical field of fixation and preservation of biological tissue samples, and provides an embedding mold for multiple frozen tissues, which comprises a base, a plurality of clamping pieces, a plurality of clamping pieces and a plurality of clamping pieces, and is characterized in that the top surface is provided with a pair of centrosymmetric supporting blocks; the sleeve is detachably arranged outside the pair of supporting blocks in a sleeving manner; wherein the pair of supporting blocks are arranged at an interval of 180 degrees, and the outer side walls of the supporting blocks are attached to the inner side wall of the sleeve in a transition fit mode; the sleeve is as high as the supporting block, and an accommodating cavity is defined by the inner side wall of the sleeve and is used for embedding the plurality of strip-shaped frozen tissue blocks in a vertical form. The containing cavity formed in the sleeve is changed into a columnar shape with enough depth from an existing flat shape with limited depth, the problems that the tissue structure is incomplete and an OCT embedding medium overflows are directly solved, the edge of a tissue combined block is smooth, slicing is facilitated, meanwhile, a plurality of strip-shaped frozen tissue blocks are embedded in a vertical mode, and the working efficiency is improved. The height of the tissue block is unified, the size of the tissue block is fixed, and the problems that sample loss is large and tissue arrangement is too close to the edge are solved.

The utility model relates to the technical field of cell culture, and discloses a chamber structure adaptive to Faraday wave assembly, which comprises a pore plate, N mounting grooves are formed in the top surface of the pore plate, and N is greater than or equal to 1; the N container bodies are arranged on the pore plate in a rectangular array mode or a central symmetry mode and correspondingly arranged in the N mounting grooves, a plurality of culture grooves used for cell assembly are sequentially formed in the container bodies in the longitudinal direction from the top face to the bottom face, and the widths of the culture grooves are gradually decreased. According to the device, internal cells or cell microspheres can be gathered into a sound potential well of a standing wave sound field under the action of acoustic pressure, gravity and buoyancy under the action of the sound field and are tightly arranged according to an expected pattern, and a culture solution is longitudinally stacked in a plurality of culture tanks of which the widths are gradually reduced; longitudinal shape limitation on the tissue structure is realized, and complex three-dimensional longitudinal arrangement is constructed through mutual combination of the two. Therefore, the requirement of constructing any multi-scale and complex cell structure is met. And forming a multi-layer structure.

The invention discloses a microscopic visual detection method for mixing animal-derived adulterated raw materials into fish meal, and particularly relates to the technical field of feed raw material evaluation, and the method comprises the steps of S1, data set construction, S2, sample pretreatment and image acquisition, S3, model construction and training, and S4, model application and result display. The microscopic visual detection method can effectively capture the appearance form, tissue structure, fiber texture, color and luster characteristics and other tiny characters of fish meal and abnormal adulterants under a microscope, and improves the adaptability of the model to environments with different complexity degrees. A visual, accurate and efficient microscopic vision automatic identification method is provided for an adulteration detection link in fish meal quality detection.

The embodiment of the invention provides a detection device and electronic equipment, relates to the technical field of health data detection, and is used for solving the problem of relatively low health detection data precision caused by complex organization structure of a to-be-detected part of a user. In the detection device, a first photoelectric converter is arranged between every two adjacent first light sources, and a second light source is located in a detection area defined by the multiple first light sources and the multiple first photoelectric converters. A first distance H1 and a second distance H2 are respectively arranged between the first light source and at least two of the first photoelectric converters. A third distance H3 and a fourth distance H4 are respectively arranged between the second light source and at least two of the first photoelectric converters. A first light source, a second light source and a first photoelectric converter are distributed in the distribution area of the detection device. A PPG module can be formed between each light source and the corresponding photoelectric converter, the distances between the light sources and the photoelectric converters are different, and the effective depth of the detected skin can be different.

The invention discloses a noise determination model training method and a medical image generation method and device, and belongs to the technical field of computers. The method comprises the following steps: determining sample knowledge, wherein the sample knowledge represents visual information of a tissue structure in a first medical image at a plurality of visual angles; performing noise addition on the image features of the second medical image for multiple times to obtain feature data after noise addition for each time; determining first de-noising data corresponding to each noise addition based on the sample knowledge and the feature data after each noise addition through a neural network model; and training a neural network model based on the first de-noising data corresponding to each noise addition to obtain a noise determination model. The added noise is accurately predicted based on the sample knowledge guide model, the accuracy of the first de-noised data is improved, the accuracy of the noise determination model is improved, the noise determination model can accurately predict the noise data needing to be removed, and by removing the noise data, the noise removal efficiency is improved. And obtaining target medical images of the tissue structure in the source medical image at different visual angles.

The invention provides a myopia grading method driven by coupling of mechanical and morphological characteristics of corneal cells, and belongs to the technical field of myopia eye disease diagnosis and occurrence and development mechanisms based on artificial intelligence. The surface topography, Young modulus, adhesive power and other mechanical characteristics of corneal cells of patients with low, medium and high myopia are measured, corneal cell surface topography images obtained by an atomic force microscope are used as a cytoskeleton quantitative analysis data set, and edge extraction, brightness detection and multi-scale image segmentation methods are utilized to determine the surface topography of the corneal cells of the patients with low, medium and high myopia. The overall cytoskeleton distribution characteristics are quantified through the cytoskeleton region average complexity and cytoskeleton region average similarity, the method does not depend on dyeing, the tissue structure of the cytoskeleton can be evaluated more comprehensively, the method is suitable for more diversified cytoskeleton structures including complex clusters, a myopia grading model is established, and the myopia grading efficiency is improved. And a more direct cellular-level experimental basis is provided for the research on the occurrence and development mechanism of myopia.

The invention relates to the technical field of facial ultrasonic image recognition, and particularly discloses a facial structure artificial intelligence recognition, quantification and contrastive analysis method and system, and the method comprises the steps: obtaining facial ultrasonic images at multiple angles; based on a trained image recognition model, recognizing tissue structures of the facial ultrasonic image, and obtaining masks of the tissue structures; calculating a quantitative index of each organization structure based on the mask of each organization structure; the quantitative indexes comprise an average thickness quantitative index, an average area quantitative index and an average volume estimation quantitative index; and comparing the quantitative indexes of the plurality of angles to finish analysis. According to the method, the image segmentation neural network is trained based on the section images of a large number of facial structures, a customized model can be provided for the complexity of the facial ultrasonic image, the accuracy and robustness of tissue structure recognition are remarkably improved, and a high-quality mask is provided for subsequent quantitative analysis.

The invention discloses a laparoscopic surgery image enhancement and real-time auxiliary system, and relates to the technical field of medical image processing and intelligent auxiliary surgery. According to the laparoscopic surgery image enhancement and real-time auxiliary system, a laparoscopic image flow is obtained and cleaned through the video input and preprocessing module, image enhancement processing is carried out through a deep learning model, then spatial position features of a tissue structure and an instrument are extracted, and a structure recognition index and a spatial safety index are analyzed; according to the invention, through cooperative work of the image preprocessing module and the depth image enhancement model, brightness compensation, edge enhancement, denoising, smoke suppression and other operations are performed on the laparoscope image stream, the depth model is utilized to extract multi-scale image features and reconstruct details, and an enhanced video image stream is generated; therefore, the intraoperative abdominal cavity structure and instrument boundary is clearer, the positioning judgment precision of a doctor is remarkably improved, and the misjudgment risk caused by image blurring is reduced.

The invention discloses a plastic surgery auxiliary strategy generation method and system based on a multi-modal medical image, and relates to the technical field of auxiliary strategy generation. After the multi-modal medical image is collected, multilevel organization structure information is extracted, and a facial structure function linkage graph is constructed; identifying a structure coupling region with a correlation influence relationship in the function linkage graph as an intervention region; reversely querying an operation strategy knowledge base based on the intervention area to obtain a candidate operation fragment set; according to the structure conflict relation matrix and the recovery time dependence matrix between the candidate operation segments, constructing an initial operation path diagram; according to aesthetic preference parameters set by a user, generating an aesthetic offset information field, and acting on the initial operation path diagram to form a structural deformation map; and based on the structural deformation map, injecting control constraints, generating a reversible control chart, and outputting a personalized operation execution path. Personalized operation path generation is realized, and dissection safety and aesthetic requirements are considered.

Segmentation or other classification of digital pathology images with a deep learning model allows for sophisticated spatial features for cancer diagnosis to be extracted in an automated, fast, and accurate manner. A tiered analysis of tissue structure based in part on deep learning methods is provided. First, tissues depicted in a digital pathology image are segmented into cellular compartments (e.g., epithelial and stromal compartments). Second, the heterogeneity in the different cellular compartments are examined based on a clustering algorithm. Tissue can then be characterized in terms of inertia (or other spatial measures or features), which can be used to recognize disease. In some instances, multidimensional inertia (i.e., inertia computed in different cellular compartments or clustered components) can be used as an indicator of disease and its outcome.

The invention provides a regional anesthesia puncture path planning method and system under ultrasonic guidance, and relates to the technical field of ultrasonic image.According to the regional anesthesia puncture path planning method and system, dynamic motion information of a tissue structure is obtained by collecting ultrasonic image data of a target region and conducting motion analysis, and electrocardiosignals are synchronously collected to determine heart beat time phase information; determining a vascular movement mode based on the two, learning a time change rule by using a long-short-term memory network, and establishing an association relationship between a vascular spatial position and a heart beat phase; constructing a motion prediction model to predict the future motion trend of the blood vessel, and fusing the respiratory motion information to correct to obtain the blood vessel motion information; and finally, a safe puncture window is calculated according to the information, a regional anesthesia puncture path is planned, vascular movement prediction and safe puncture window calculation based on vascular movement rule learning and breathing correction in regional anesthesia under ultrasonic guidance can be achieved, and then the puncture path is precisely planned.

The invention discloses a method and a device for solving direction perception disorder caused by a rotating mirror, and solves the problem that an adjacent tissue structure outside a part is difficult to determine after endoscopic examination rotation in a similar upper digestive tract wall internal lesion. The method comprises the following steps: acquiring pose information of an endoscope in an electromagnetic navigation system of a lumen target position and a corresponding image in the lumen as a reference pose; obtaining a track pose of the endoscope after the view field is adjusted in the electromagnetic navigation system and a corresponding intraluminal image, and determining an Euler angle of each track point according to the track pose; obtaining a track pose of the endoscope after the view field is adjusted in the electromagnetic navigation system and a corresponding intraluminal image, and determining an Euler angle of each track point according to the track pose; performing three-dimensional reconstruction on the lumen and the adjacent tissue thereof according to the lumen image map, and performing corresponding rotation according to the rotating mirror angle and the corresponding image in the lumen to obtain the rotated lumen and the adjacent tissue thereof; according to the invention, after the endoscope rotates to the optimal visual field, the adjacent tissues outside the endoscope can be clearly known.

The invention discloses a hierarchical optimization multi-instance learning method for digital pathological section brain tumor classification. The hierarchical optimization multi-instance learning method comprises the following steps: extracting and aggregating multi-instance features through alternate training of a feature encoder and an aggregator; a region of interest is automatically searched in a low-magnification image, and then feature extraction and classification are performed on a high-magnification region of interest. According to the method, the region-of-interest is detected by using low magnification, and then the tumor category is comprehensively judged in multiple magnification near the region-of-interest in stages. More importantly, in a model training link, a feature extractor is trained by utilizing a pseudo tag of patch in a region of interest, so that features are better extracted for a specific task and a data set. In order to reduce the noise of the false label, the patent provides a label correction mechanism to ensure the purity of the false label. In general, the HOMIL combines low-magnification tissue structure characteristics and high-magnification cell characteristics, comprehensively predicts brain tumors, and greatly reduces the model reasoning time.

The invention discloses an organizational structure division method for spatial transcriptome data, which comprises the following steps of: firstly, performing coordinate calibration, hypervariable gene screening and gene expression standardization preprocessing on original spatial transcriptome data, and constructing a standardized data set containing a spatial adjacency relation and a standardized gene expression profile; an initial hyperedge is generated based on a k-nearest neighbor algorithm, cross-domain noise is dynamically eliminated in combination with a hyperedge decomposition algorithm guided by gene expression, and a hypergraph structure with double constraints of spatial proximity and gene expression homogeneity is formed; designing an auto-encoder architecture comprising a hypergraph attention layer, compressing high-dimensional data to a low-dimensional potential space, reconstructing a loss optimization architecture by using gene expression, and generating low-dimensional representation with topology retentivity and function consistency; and finally, organizational structure division is carried out on the low-dimensional representation clustering based on a Gaussian mixture model. According to the method, the spatial continuity of organization structure division is remarkably improved, and a semantic gap of cross-resolution data is effectively bridged.

The invention discloses a deformation registration method and device, a storage medium and electronic equipment, and relates to the field of medical science and technology and the field of image processing. The method comprises the following steps: acquiring reference data and floating data; according to the organ type, data separation is carried out on the reference data and the floating data, and the data separation is used for separating the reference data and the floating data to obtain image data of each independent organ; performing deformation registration on the image data of each independent organ to obtain a deformation field corresponding to each independent organ; and fusing the deformation field corresponding to each independent organ into a target deformation field, and performing deformation registration on the floating data through the target deformation field. The technical problem that in the prior art, when a registration algorithm is adopted for dose accumulation in radiotherapy, due to the fact that alignment is redundant or insufficient in the registration process of a local organ tissue structure, dose accumulation in an organ boundary area is inaccurate is solved.

The invention discloses a CT image metal artifact correction method and device based on a U-Net model, electronic equipment and a storage medium, and belongs to the technical field of image processing, and the method comprises the steps: obtaining a to-be-corrected CT image; inputting a CT image to be corrected into the U-Net network model to obtain a CT image which is output by the U-Net network model and is subjected to metal artifact correction; wherein the U-Net network model comprises a multi-scale attention mechanism and an adaptive fusion module. According to the method, a multi-scale attention mechanism is introduced to a U-Net network model, multi-scale feature extraction can be performed in jump connection, metal artifact regions and organization structure features are highlighted, the correction precision of metal artifacts is improved, a correction strategy is dynamically adjusted through an adaptive fusion module, over-fitting or under-fitting is avoided, and the correction precision of the metal artifacts is improved. The artifact residual is effectively reduced; and the metal artifact correction quality is improved.

The invention relates to the technical field of medical image processing and three-dimensional reconstruction, and particularly discloses a reconstruction and analogue simulation method based on a cardiac image. The method comprises the following steps: firstly, preprocessing an input CT or MRI medical image, and automatically segmenting a heart multi-tissue structure by using an nnUNetv2 model, including a plurality of anatomical regions such as atrium, ventricle, myocardial tissue and blood pool; and then performing topology repair, smoothing processing and label resampling on the segmentation result to obtain a three-dimensional label body with a continuous structure and a complete boundary. And based on the optimized tag body, constructing a heart three-dimensional surface model by adopting a Marching Cubes algorithm, and generating a multi-material volume grid suitable for finite element analysis. According to an electrode position and a radio frequency parameter set by a user, a radio frequency ablation simulation model based on a Pennes biological heat conduction equation and an Arrhenius model is established, a temperature field and a tissue thermal damage range are calculated, and a simulation result is displayed in a three-dimensional mode in an overlapping mode. According to the method, the integrated process from medical image automatic segmentation to heart three-dimensional reconstruction and thermal simulation is realized, the segmentation precision, the modeling efficiency and the simulation reliability are improved, and the method can be applied to application scenes such as surgical planning, preoperative evaluation and medical teaching.

The invention discloses a multi-layer heterogeneous network unicellular organism network inference method based on meta-path enhancement, which mainly comprises a gene regulation knowledge base enhanced multi-layer heterogeneous network construction module for integrating an external gene interaction network and multiple omics data such as scRNA-seq, scATAC-seq, ST and the like; constructing a single-cell multi-omics multilayer heterogeneous network containing cell-cell, cell-gene and gene-gene relationships, and fusing spatial constraints to consider cell positions and tissue structures; and the feature enhancement module based on the meta-path explores complex semantics of the network by designing a multi-hop meta-path mode, designs an adaptive multi-view learning framework and a multi-round enhancement mechanism, and optimizes feature representation by using cell-gene interaction and cross-modal attention fusion. The unicellular biological network can be effectively deduced, the deduction accuracy and biological interpretation are remarkably improved, the method plays an important role in understanding the cell biological process, developing and treating diseases and the like, has good expandability, and can further integrate multi-modal omics data such as proteomics and metabonomics.

The invention provides a pathological image analysis method and device based on multi-instance learning, equipment and a storage medium, and the method comprises the steps: receiving a lung pathological section image, segmenting the lung pathological section image into a plurality of 256 * 256 pixel image blocks, and screening and reserving effective image blocks containing a tissue structure; extracting a high-dimensional feature vector of each effective image block by using a self-supervised pre-trained deep neural network on the large-scale dyeing pathological image; the features are input into a multi-branch attention module containing 15 parallel branches, self-attention, cross-attention and global attention mechanisms are executed respectively, and local spatial dependence, cross-image block similarity and global relevance are modeled; and carrying out weighted aggregation on the basis of the processed attention weight to generate a global feature of the slice image, outputting a pathological category through a classification network, and supporting heat map visualization and feature clustering analysis. According to the method, unlabeled region information is effectively utilized, and the pathological classification precision and the model generalization ability are improved.