50 results about "Clinical imaging" patented technology

The invention relates to the technical field of image processing, in particular to a clinical focus auxiliary segmentation system based on a nuclear magnetic resonance image. The system comprises an MRI image processing module, a lesion auxiliary segmentation module, a probability segmentation correction module and a lesion boundary smoothing module, a corresponding clinical nuclear magnetic resonance image set of a patient can be obtained, image position alignment and gray level adjustment processing can be carried out, and meanwhile a corresponding clinical image lesion segmentation model is constructed to carry out multi-scale fusion auxiliary segmentation. Generating a clinical focus region segmentation fusion image; obtaining a focus confidence probability corresponding to each pixel point in the segmentation image through the clinical focus region segmentation fusion image, and carrying out probability segmentation boundary correction on the clinical focus region segmentation fusion image to obtain a clinical focus region segmentation correction result image; and performing focus edge shape smoothing processing on the clinical focus region segmentation correction result map to generate a clinical focus edge shape segmentation optimization result. According to the invention, high-precision segmentation of the focus in the MRI image can be realized.

The invention discloses a multi-modal image registration processing method and system based on deep learning, and relates to the technical field of medical image processing, and the method comprises the steps: calculating a mutual information loss value after registration through a mutual information loss method, optimizing a CNN model and UNet model parameters in combination with the total loss generated by the fusion of global and local deformation fields, and obtaining a registered sCT image. A CNN model and a UNet model are combined to generate global and local deformation fields, overall rigid transformation and local nonlinear deformation are effectively captured, the spatial alignment precision of sCT and reference CT is improved, model parameters are optimized through mutual information loss and total loss, the intensity distribution consistency is ensured, feature weights and treatment plan parameters are automatically adjusted through registration quality feedback, and the accuracy of the treatment plan is improved. The coverage precision and efficiency of the radiotherapy plan are remarkably improved, automatic and high-precision image registration and treatment plan optimization are realized, and the reliability and practicability of clinical image processing are enhanced.

The invention discloses a hepatocellular carcinoma postoperative early recurrence prediction method based on multi-modal fusion. The method comprises the following steps: firstly, integrating clinical data of a training set, a preoperative enhanced CT image and a postoperative full-view digital pathological image, and carrying out standardized correction; then, traditional image omics features and deep learning features are extracted from the CT image, cell nucleus morphological features and tumor microenvironment spatial configuration features are extracted from the pathological image, and key feature signatures are screened out through a maximum correlation minimum redundancy algorithm (mRMR) and LASSO regression in combination with clinical features. And then carrying out progressive model construction by adopting an XGBoost algorithm, sequentially establishing a clinical single-mode model, an image single-mode model, a pathological single-mode model and a multi-mode fusion model, and explaining and visualizing the models by utilizing an SHAP value and a Grad-CAM technology. Finally, the performance of the model is evaluated in a multi-dimensional mode through internal cross validation, foresight and external independent validation, risk layering is carried out based on the prediction probability, and individualized postoperative management is guided.

The invention discloses a model-based cardiovascular image analysis, comparison and recognition system, which relates to the technical field of intelligent diagnosis and comprises an artifact preliminary detection module, an artifact recognition module, a boundary reconstruction module, an authenticity verification module, an interference learning module and a closed-loop regulation and control module, based on frequency domain analysis and spatial feature deconstruction, a multi-scale artifact analysis model is constructed, and preliminary positioning and signal separation of an artifact region are realized; and the artifact identification module is used for executing gray gradient aggregation and structural symmetry comparison based on a positioning result of the artifact analysis model, and generating an artifact mode label containing interference intensity, spatial distribution and morphological difference information. According to the invention, accurate separation of artifacts and real tissues and dual verification of lesions are realized through cooperation of multiple modules, a feedback optimization mechanism is constructed to improve recognition stability, misdiagnosis and excessive intervention risks are effectively reduced, and intelligent recognition capability and application security in clinical images are enhanced.

The invention discloses a method for determining brain PET standardized reconstruction parameters based on clinical brain MRI and PET data, and relates to the field of medical image processing. The method comprises the following steps: firstly, collecting clinically paired MRI (Magnetic Resonance Imaging) and PET (Positron Emission Tomography) images for preprocessing, carrying out virtual reconstruction by combining a partial volume correction algorithm and system parameters of equipment to estimate'real 'brain activity distribution so as to obtain a first simulated PET image, and calculating difference or similarity between the first simulated PET image and a clinical PET image; through multiple iterations, obtaining an optimal'real 'brain activity distribution diagram, and processing the optimal'real' brain activity distribution diagram into a'standardized PET image 'according to standardized Gaussian filtering; then, constructing different candidate combinations of reconstruction parameters, inputting an optimal'real 'brain activity distribution diagram, traversing a second simulated PET image generated by simulation reconstruction under each combination, and respectively performing difference or similarity calculation with the'standardized PET image', so as to obtain an optimal'real 'brain activity distribution diagram; and selecting the group of candidate reconstruction parameters with the minimum difference or the highest similarity as final standardized reconstruction parameters. The method gets rid of dependence on a physical motif.

The invention relates to the technical field of medical image artificial intelligence, in particular to an auxiliary interpretation method for medical image rapid diagnosis of acute abdominal disease in combination with deep learning, and the method comprises the steps: 1, organ targeted segmentation: obtaining CT sequences of an arterial phase, a venous phase and a delay phase, and carrying out the dynamic calculation of an interpolation interval according to the layer thickness parameter of scanning equipment, and carrying out the spatial standardization; synchronously generating an intestinal canal mask, a blood vessel mask and a peritoneum mask by adopting an acute abdominal disease directional segmentation network, wherein the network introduces an anatomical size adaptive multi-scale cavity convolution group into a deep layer of an encoder; 2, quantifying dynamic pathological signs; step 3, performing clinical-image gating fusion; and 4, multi-task cooperative diagnosis: inputting the fusion features into a pre-trained multi-task network, and outputting an acute abdominal disease cause classification probability and an operation urgency evaluation value in parallel. The multi-dimensional analysis capability of acute abdominal disease diagnosis is improved through multi-task cooperative diagnosis, and accurate classification of disease causes and evaluation of operation urgency can be carried out at the same time.

The invention discloses a liver cancer prognosis risk assessment method and system based on data analysis, and relates to the technical field of intelligent medical treatment. The method is realized through the following steps: firstly, acquiring and standardizing clinical, image, genome and other multi-modal data of a patient; then constructing an individualized dynamic causal graph based on the medical knowledge base, and dynamically adjusting a causal edge weight by using a graph attention network; inputting the causal diagram into a prognosis evaluation model to obtain a basic risk trajectory, performing intervention simulation by modifying a treatment node state, and calculating an anti-factual risk trajectory to quantify an individual treatment effect; and finally, outputting a risk assessment result and generating natural language interpretation containing the quantitative contribution degree. The corresponding system comprises a data sensing layer, a causal calculation layer, an intelligent decision-making layer and an interactive presentation layer. According to the method, causal reasoning and deep learning are creatively combined, and dynamic, accurate and interpretable prognosis evaluation and intervention guidance of the liver cancer are realized.

The invention discloses a method for establishing a column diagram model for diagnosis and prediction of different types of temporal lobe epilepsy. The method comprises the following steps: acquiring clinical data and an MRI image of a temporal lobe epilepsy patient; constructing a clinical feature prediction model by utilizing Logistic regression; preprocessing the MRI image, segmenting a hippocampus region of interest (ROI) and extracting radiomics features, establishing a Radscore model based on screened image features, and combining the Radscore model with clinical features to construct a joint model; performing performance evaluation on the clinical model, the radiomics model and the joint model; and constructing a temporal lobe epilepsy typing prediction column diagram based on the joint model, and realizing prediction result visualization and individualized risk assessment. According to the method, the clinical-image combined model is developed by integrating high-throughput radiomics characteristics and clinical independent factors, high-precision prediction of the temporal lobe epilepsy type is achieved, and the method can provide a reliable basis for clinical early-stage typing diagnosis, precise intervention and personalized treatment.

An electronic device is disclosed. The device receives retinal images and patient data corresponding to the retinal images. The device can train a first machine learning model (“model”) based on a first group of the retinal images and patient data corresponding to the first group and a second model based on a second group of the retinal images and patient data corresponding to the second group. The electronic device can generate a first prediction based on the first subset of a third group of the retinal images and a second prediction based on the second subset of the third group. After training the first model and the second model, the device can train a third model to predict a geographic atrophy progression in an eye of a patient based on the first and second predictions, the first and second subsets, and patient data corresponding to the first and second subset.

The invention belongs to the field of medical image processing, particularly relates to a general medical image segmentation method and system based on semantic aggregation, and aims to solve the problem that an existing model is poor in generalization ability when facing a new data field. The core of the method is that an expectation maximization semantic aggregation mechanism is adopted, and iterative purification is performed on visual features extracted from an image and language features extracted from a text so as to enhance semantic compactness of the features and form stable text semantic anchor points; then, through a depth alignment strategy, carrying out cross-attention fusion on the text semantic anchor point and the most abstract feature of the visual network; and finally, accurately guiding pixel-level segmentation decoding by using the fused features. According to the method, the segmentation performance and robustness of the model on unseen data are remarkably improved by forcing the model to learn an invariant internal semantic structure in the field, and the method can be widely applied to multi-center and cross-equipment clinical image intelligent analysis.

Systems and methods for machine learning assisted authenticity enhanced virtual clinical imaging preserving baseline truth values. Non-paired images are trained to an image network to migrate a realistic style derived from a real patient image to a simulated image generated using a phantom.

The present invention discloses a method for simulating aneurysm virtual stent implantation based on a spring analogy method. The method comprises: reconstructing a three-dimensional model of the preoperative parent vessel and the parent vessel after aneurysm restoration based on clinical imaging data; extracting the centerline of the first vessel to construct a virtual stent initialization model; deploying the virtual stent initialization model using a spring analogy virtual stent fast algorithm to determine the three-dimensional model of the virtual stent after deployment in the individualized vessel; and calculating efficacy evaluation parameters using a fast algorithm based on the arc surface porosity of the virtual stent neck. The present invention can simulate the actual motion of stent deployment and significantly shorten the simulation calculation time and efficacy evaluation time of simulated stent deployment within a vessel, thereby achieving real-time guidance during virtual aneurysm intervention.

The application discloses a clinical image lesion classification method based on adaptive frequency domain learning and anti-aliasing complex convolution, comprising: carrying out pretreatment and normalization treatment on an original clinical image to obtain a time domain image; converting the time domain image into a frequency domain image through a position consistency module to generate a frequency spectrum capable of preserving local and position information; carrying out masking and supervision on the generated frequency spectrum through a high-frequency self-encoder module to obtain a self-encoding frequency spectrum; inputting the self-encoding frequency spectrum into an anti-aliasing complex convolution model for training to learn specific features of different clinical lesions in the image; and integrating and classifying the specific features learned by the anti-aliasing complex convolution model to obtain a clinical image lesion classification result. The method can better utilize frequency domain information of the image on the basis of preserving time domain features of the clinical image, solves the problems of brightness imbalance and inter-class confusion in lesion classification, and greatly improves the accuracy of automatic classification.

The invention relates to the technical field of medical artificial intelligence prediction, and discloses a method for predicting the total lifetime of bladder cancer through a multi-modal fusion deep learning model. The method includes quality control and normalized preprocessing by collecting clinical, image and genetic data of a patient. Then multi-modal features are extracted, and high-value features are screened out through feature importance evaluation to form an enhanced feature set; a feature interaction network is adopted to learn a complex dependency relationship among different modal features, and deep fusion is realized to generate integrated feature representation. And finally, constructing a depth prediction model based on the representation, and capturing a mapping relation between the depth prediction model and the total lifetime. Through the deep fusion and feature screening technology, multi-modal information is integrated, the defect that a traditional method neglects interaction between modals is overcome, and the accuracy and reliability of predicting the total lifetime of the bladder cancer patient are improved.

This invention discloses a method and system for pontine infarct segmentation and END prediction based on multimodal joint learning. The method includes acquiring and preprocessing multimodal data; constructing a wavelet transform-based feature encoding network to perform multi-scale decomposition and detail preservation of features; constructing a dual-task guided fusion module to align the deep semantics of clinical variables and imaging features and generate task-specific representations; constructing a Mamba-based global feature aggregation module to model sequence dependencies using a state-space model; constructing a multimodal second-order fusion classifier to enhance the clinical-image interaction modeling using second-order statistics; and employing a two-stage joint training strategy for training and prediction, and outputting the prediction results. This invention utilizes the DWT / IWT mechanism to significantly improve the accuracy of capturing small pontine infarct lesions; it achieves explicit interaction between segmentation evidence and prediction signals, significantly improving the segmentation accuracy of small lesions and the reliability of stroke risk assessment.

An intelligent system for optimizing radiotherapy for personalized radiotherapy, consisting of: • a genome data acquisition module configured to acquire and process a patient's genomic, molecular, and biomarker information; • a multimodal medical imaging module configured to acquire medical image data from one or more imaging modalities; • an image processing and automatic segmentation module configured to preprocess the acquired medical images, register multimodal images, segment tumors and organs at risk, and extract quantitative image features; • an artificial intelligence and data integration module configured to integrate genome data, imaging data, radiomic features, and clinical information to generate a patient-specific predictive model;• A treatment planning and dose optimization module configured to automatically generate and optimize a personalized treatment plan based on the integrated patient-specific model; • A digital twin and adaptive therapy module configured to simulate the patient-specific treatment response and continuously adjust the treatment plan during therapy; • A treatment monitoring and outcome prediction module configured to predict treatment response, disease progression, and radiation-induced toxicity based on longitudinal patient data; • A clinical decision support module configured to generate personalized treatment recommendations and support clinical decision-making;• A communication and data management module configured for the secure exchange, synchronization, and storage of clinical, imaging, genomic, and treatment-related information; and • An autonomous learning and systems management module configured to continuously improve predictive models and treatment optimization algorithms based on collected treatment outcomes, with the modules working together to generate, optimize, monitor, and continuously adapt personalized radiotherapy based on integrated genomic and multimodal medical imaging information.

The present application relates to the technical field of image processing, and particularly relates to a clinical lesion auxiliary segmentation system based on nuclear magnetic resonance images. The system comprises an MRI image processing module, a lesion auxiliary segmentation module, a probability segmentation correction module and a lesion boundary smoothing module, can obtain corresponding patient clinical nuclear magnetic resonance image sets and perform image position alignment and gray scale adjustment processing, simultaneously construct corresponding clinical image lesion segmentation models for multi-scale fusion auxiliary segmentation, and generate a clinical lesion region segmentation fusion image; through the clinical lesion region segmentation fusion image, obtain the lesion confidence probability corresponding to each pixel point in the segmentation image, and correct the probability segmentation boundary of the clinical lesion region segmentation fusion image, to obtain a clinical lesion region segmentation correction result image; perform lesion edge shape smoothing processing on the clinical lesion region segmentation correction result image, to generate a clinical lesion edge shape segmentation optimization result. The present application can realize high-precision segmentation of lesions in MRI images.

The application belongs to the technical field of image processing, and discloses an image enhancement processing method for a visual bronchoscope. The method is applied to a visual bronchoscope with a distal eccentric integrated imaging module and a non-coaxial sputum suction channel inside the integrated imaging module. First, current frame original image data collected by the integrated imaging module and real-time posture data of the visual bronchoscope are acquired, and global spatial parameters are calculated in combination with pre-calibration parameters. Then, image correction is completed according to the global spatial parameters to obtain a standardized corrected image. Corresponding enhancement processing is performed on the corrected image in a regional manner, and an operation view image is obtained after feature alignment fusion and coordinate conversion, and is output in real time after optimization. The method combined with the eccentric bronchoscope can improve the definition and uniformity of the bronchoscope image, ensure the matching of the view and the operation path, and meet the clinical imaging requirements.

The invention provides a bone health assessment and fracture risk prediction system based on a cross-scale mechanical model, and the system comprises a data obtaining unit which is used for obtaining clinical image data of a user and user information data; the data processing unit is used for performing multi-scale feature extraction on the clinical image data to obtain macroscopic geometric morphology features, density distribution features, regional scale features and texture scale features of the skeleton; the mechanical response parameter calculation unit is used for calculating mechanical response parameters of the skeleton under various load working conditions on the basis of the user information data, a preset skeleton template library and macroscopic geometrical morphology characteristics and density distribution characteristics of the skeleton; and the integrated risk assessment unit is used for determining the fracture risk probability based on the regional scale features, the texture scale features and the mechanical response parameters. According to the invention, the accuracy and comprehensiveness of fracture risk assessment can be improved.

The invention relates to the technical field of image feature extraction, and provides a staged myocardial fibrosis imaging feature extraction method and system. The method comprises the following steps: synchronously acquiring myocardial FAPI-PET and CT images, and generating a fusion image through standardization processing and mutual information registration; dividing multiple stages according to a myocardial fibrosis pathologic evolution rule; a clinical image set is collected, and a development feature extraction model set is constructed through staged training; and performing stage matching and feature extraction on the image based on the model set, and determining a target feature set. The technical problems that in the prior art, refined image feature extraction cannot be carried out on myocardial fibrosis at different pathological stages, feature specificity is insufficient, and different pathological stages are difficult to accurately distinguish are solved, and the aim of accurately distinguishing the different pathological stages through multi-modal image fusion and staged model training is achieved. The technical effects of precise staging of the myocardial fibrosis pathological process and high-specificity extraction of imaging characteristics are achieved, and the disease staging precision is improved.

The application discloses a pneumoconiosis staging recognition method and system based on multi-modal artificial imaging feature fusion, and relates to the technical field of medical image recognition. The method comprises the following steps: standardizing and pre-processing an input chest X-ray image and extracting a lung field region; in the lung field region, detecting and counting micro nodules based on clinical imaging prior knowledge, and extracting micro nodule quantity features reflecting the quantity and spatial distribution characteristics of nodular lesions; calculating the first-order entropy features of the lung field region image to quantify the complexity of lung parenchyma texture, and extracting high-dimensional features representing gray heterogeneity and structure statistical characteristics by using an imaging feature analysis method. The multi-class artificial imaging features are standardized and fused in a unified feature space, and the fused features are input into a learning classification model for pneumoconiosis period recognition. The application improves the stability and interpretability of pneumoconiosis staging recognition through multi-modal artificial imaging feature fusion modeling.

The embodiment of the application discloses a kind of vitiligo auxiliary diagnosis methods, devices and storage medium of multi-modal medical image collaborative segmentation and classification, wherein the method comprises: obtaining the multi-modal image pair of the clinical image and Wood lamp image of the same examinee;According to the imaging characteristics of two kinds of modalities, the image pair is preprocessed and modality-specific data enhancement;The multi-modal image pair after processing is input into the feature extraction network to obtain each modality feature, and spatial guidance information for subsequent segmentation is generated;Each modality feature is input into vector quantization fusion module for cross-modal feature fusion to obtain semantic consistent fusion feature;Based on the fusion feature, a segmentation branch and a classification branch are constructed to realize the joint output of lesion region segmentation and disease activity classification, and the collaborative effect of the two tasks is improved through inter-task interaction. By using the present application, end-to-end joint optimization of vitiligo lesion segmentation and disease activity classification can be realized, and the diagnostic performance is improved.

The present disclosure relates to [18F]-labeled imidazopyridine derivatives or salts thereof as positron emission tomography (PET) radiotracers suitable for imaging the stress-signaling non-receptor tyrosine kinase c-abl, and their use in in vivo diagnosis, preclinical and clinical imaging, patient stratification on the basis of mutational status of c-abl and assessing response to therapeutic treatments. The present disclosure further relates to the use of [18F]-labeled imidazopyridine derivatives as PET radiotracers. The disclosure also provides a process for the radiosynthesis of [18F]-labeled imidazopyridinederivatives.

The invention belongs to the technical field of disease screening, and particularly relates to an ear-nose-throat disease intelligent screening system and method based on multi-modal data, and the method comprises the steps: constructing an ear-nose-throat anatomical parameterized model according to a clinical image, and generating a virtual image; extracting interpretable anatomical features according to the mixed image data set, mapping the interpretable anatomical features to an ear-nose-throat disease knowledge graph, and establishing a diagnosis association rule through predicate logical reasoning; the method comprises the following steps: reading pixel features of a clinical image, matching a map rule, iterating a closed loop through a manual correction rule, and converting diagnosis adjustment into map rule supplementation; constructing a federal rule sharing framework, uploading rule correction parameters, and aggregating results through a federal average algorithm; and designing a hierarchical screening process according to the diagnosis rule model, and pushing high-confidence positive cases to superior hospitals to form a screening system. According to the invention, on the basis of virtual-real fusion data construction, a highly-adaptive and universal ear-nose-throat disease intelligent screening system is constructed through symbolized logical reasoning and federal rule sharing.

The invention discloses a non-enhanced CT kidney stone automatic detection method based on multi-scale feature fusion, and relates to the technical field of clinical image diagnos.The method includes the steps that non-enhanced CT coronal position kidney image data are collected, de-identification processing is conducted on the collected non-enhanced CT coronal position kidney image data, and the non-enhanced CT coronal position kidney image data are obtained; processing the de-identified non-enhanced CT coronary position kidney image data through a data standardization and image enhancement method, extracting key image features by adopting a convolutional neural network, and establishing a kidney stone automatic detection model based on the extracted key image features; and finally, the final automatic kidney stone detection model is deployed to a high-performance workstation with GPU (Graphic Processing Unit) acceleration capability or is integrated with the existing PACS (Picture Archiving and Communication System) of a medical institution, so that a clinical automatic detection function is realized, automatic and efficient detection of kidney stones is realized, and the detection efficiency is improved. And powerful technical support is provided for clinical diagnosis.

The invention discloses an intelligent coordination method and system for a single-model CT image reconstruction style. A training stage of the intelligent coordination method for the single-model CT image reconstruction style comprises two steps. And the inference stage is to input the to-be-coordinated source CT image, the to-be-coordinated source reconstruction style identifier corresponding to the to-be-coordinated source CT image and the target reconstruction style identifier into the trained image style coordination model to obtain a target coordination CT image. The method supports flexible conversion of multiple reconstruction styles, can adapt to a complex clinical imaging protocol, and breaks through the limitation that a traditional method is only limited to specific reconstruction styles. In addition, high-quality chain type continuous style conversion is achieved for the first time, the integrity of the anatomical structure can be effectively kept, and noise accumulation and artifact introduction are avoided. The method is specially designed for a single-type CT system, does not need to depend on multi-device and multi-center pairing data for training, and greatly reduces the threshold and cost of clinical deployment.

The invention belongs to the field of artificial intelligence, and provides a skeleton microstructure change real-time tracking decision management system, which comprises an image data access module, a dynamic structure analysis unit and an interactive decision output module, the image data access module is used for receiving skeleton three-dimensional time sequence data streams from the high-resolution microscopic imaging equipment and the clinical imaging equipment in real time; the dynamic structure analysis unit comprises a bone microstructure evolution identification module, a mechanical property prediction module and an intervention strategy generation module. Through cooperative work of the image data access module, the dynamic structure analysis unit and the interactive decision output module, full-chain closed-loop management from microstructure perception and mechanical property deduction to intelligent intervention decision is realized, and the ability of early warning and accurate intervention of skeleton diseases is significantly improved.

The invention belongs to the technical field of clinical image processing, and particularly relates to an intracranial aneurysm multi-center clinical image data standardized labeling and sharing platform which comprises a multi-center operation end and a sharing platform management end, the multi-center operation end receives and preprocesses data, labeling is carried out in an artificial dominant and AI auxiliary mode, and the sharing platform management end is connected with the multi-center operation end. The model is optimized based on local manual correction data increment; and the sharing platform management end synchronously and uniformly marks specifications, generates a standardized data set through automatic checking and expert rechecking, and performs grading sharing according to roles. According to the method, data cross-center unified multiplexing is realized, the labeling efficiency is improved, sharing and privacy security are balanced, and multi-center research and clinical diagnosis and treatment are assisted.

The present application relates to the technical field of medical imageomics, and particularly relates to a pancreatic cancer early recurrence prediction method and system based on an interpretable machine model, comprising the following steps: extracting intratumoral and peritumoral imageomics features in CT images; performing single factor analysis and multivariate logistic regression analysis on body composition parameters and clinical pathological data to obtain clinical features; constructing six groups of classifier models based on the intratumoral and peritumoral imageomics features through six machine learning algorithms, and obtaining an imageomics model according to model performance comparison; constructing a clinical-imageomics combined model by combining the clinical features and the imageomics model, and performing an interpretable SHAP analysis on the clinical-imageomics combined model. The present application combines intratumoral and peritumoral CT imageomics features with body composition parameters, constructs a machine learning model for predicting the early recurrence risk of PDAC after resection, and incorporates the interpretable SHAP analysis to enhance the transparency of the machine learning model decision-making process.

The multi-task bone joint CT / MRI fusion tissue precise segmentation modeling method and device can realize image noise point interference removal under different modalities, get rid of manual labeling tissue segmentation operation, and improve bone joint bone tissue and soft tissue segmentation and modeling accuracy. The method comprises the following steps: (1) for clinical medical image CT / MRI, image enhancement is carried out through cascade supervision denoising and weak supervision; (2) the enhanced clinical image is fed back to the edge attention supervision for hard tissue segmentation; (3) soft tissue segmentation is realized through double priori supervision, and the hard tissue segmentation result generated by the former is used as priori guidance.