74 results about "Enhanced ct" patented technology

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 rectal cancer tumor T stage differentiation labeling method based on an enhanced CT image, and relates to the field of medical image data processing, and the method comprises the following steps: a standardized manual labeling module which is used for constructing three-dimensional pixel-level labeling data of a rectal cancer tumor T stage according to a medical image and a pathological stage standard; the data set construction module is used for uniformly storing and organizing the original CT image, the annotation mask file and the matched label description document to form a structured data set which can be used for modeling; according to the rectal cancer tumor T-stage differentiation labeling method based on the enhanced CT image, a high-quality and standardized three-dimensional T-stage labeling data set is constructed, a three-dimensional pixel-level stage labeling process for the rectal cancer enhanced CT image is provided based on the AJCC eighth version tumor stage standard, the labeling content covers tumor focuses and normal intestinal wall structures around the tumor focuses, and the three-dimensional T-stage labeling data set is established. A plurality of high-annuity imaging department doctors perform independent blind marking, expert re-checking, quality rating and the like.

The invention discloses an image recognition and enhanced CT image generation method based on a plain-scan CT image. The method comprises the following steps: acquiring an NCE-CT image and CE-CT image pairing data set; calculating hemodynamic parameters of the aortic true cavity by using CFD, and obtaining physical prior features through feature selection; constructing and training a PIAD deep learning model; the PIAD deep learning model comprises an encoder guided by physical prior features through a cross attention mechanism, a Transform global information extraction module, and three functional heads for respectively outputting a classification result, a CE-CT image and a segmentation mask; training a PIAD deep learning model; and applying the trained PIAD deep learning model to a reasoning stage of only inputting an NCE-CT image, and synchronously obtaining a corresponding CE-CT image, a true cavity and false cavity segmentation result and an aortic dissection recognition result. According to the method, physical prior information is integrated, and a real cavity and false cavity segmentation task and a CE-CT generation task are combined, so that complementary information of NCE-CT and CE-CT is effectively utilized, and dependence on expensive and complex CE-CT equipment is reduced.

The invention discloses a liver tumor diagnosis method based on a self-supervision and multi-phase contrast enhanced CT image. The method comprises the following steps: collecting and preprocessing a CT image of a liver tumor; training a target detection model by using the marked CT image; processing the preprocessed CT image by using the trained target detection model, obtaining a focus detection frame, performing cutting and data enhancement according to the focus detection frame, performing resampling, adding a real joint label to the focus detection frame, and constructing a second training set and a test set; constructing a classification diagnosis model based on multiphase data based on self-supervision and knowledge distillation, performing iterative training by using the second training set, and adjusting parameters according to a total loss function of the classification diagnosis model in the training process to obtain a final liver tumor classification diagnosis model; and inputting the CT image in the test set into the final liver tumor classification diagnosis model to obtain a diagnosis result. The precision, accuracy and efficiency of liver tumor diagnosis can be improved.

The invention provides a navigation method and system for percutaneous transhepatic duct puncture, and the method specifically comprises the steps: S1, reading a liver enhanced CT image, and determining a target bile duct to be punctured; s2, integrating the electromagnetic tracking navigation system and the ultrasonic system to form an ultrasonic-electromagnetic fusion workstation; s3, electromagnetic sensors are installed in the ultrasonic probe and the puncture needle respectively; s4, starting a magnetic field generator to obtain object space vector information; s5, acquiring an ultrasonic medical image, and generating a positioning image according to the object space vector information; s6, setting the positioning image and the ultrasonic medical image according to the same space size proportion; s7, obtaining a superimposed image, and outputting the superimposed image on a display monitor in real time; s8, simulating puncture, offsetting magnetic field interference through parameter adjustment, and adjusting puncture precision; s9, puncturing along the puncturing path; and the like. The percutaneous transhepatic duct puncture navigation system can quickly and accurately complete percutaneous transhepatic duct puncture navigation, is flexible and free of radiation, is short in learning curve, and can be popularized in a homogenized manner.

The invention belongs to the technical field of medical auxiliary instruments. In order to solve the problems that when an existing device is used, the comfort degree is poor, and discomfort caused by the fact that the upper limbs of a patient are kept still for a long time cannot be relieved, the arm fixing device for radiotherapy positioning enhanced CT scanning comprises a mounting frame, a large arm fixing mechanism, a small arm fixing mechanism and a relieving mechanism; wherein the big arm fixing mechanism is respectively connected with the mounting frame and the small arm fixing mechanism, and the relieving mechanism is arranged on the small arm fixing mechanism; the height of the big arm fixing mechanism and the forearm fixing mechanism can be adjusted so as to be suitable for patients with different figures, and the relieving mechanism can drive the fingers of the patients to slightly move so as to avoid discomfort caused by the fact that the upper limbs of the patients keep still for a long time.

The utility model belongs to the field of films, particularly relates to a special film for enhancing a CT (Computed Tomography) indwelling needle, and aims to solve the problems that the conventional film cannot improve the stability and comfort of the film on the skin of a patient, so that the film is loosened and falls off or the patient feels uncomfortable, and the comfort and safety are reduced. A hollow hole matched with the shape of an indwelling needle is formed in the center of the top of the film body, and the film body comprises a protective layer, a breathable layer and an adhesive layer; the fixing assembly is arranged on the membrane body and used for reinforcing fixation of the membrane body. Through the combination of the fixing assembly, the hollow holes and the film body, the stability of the sticking film on the skin of a patient is remarkably improved, the sticking film is effectively prevented from loosening or falling off, safety and stability of an indwelling needle in the examination process are ensured, meanwhile, discomfort of the patient is relieved, and comfort and safety are improved.

The application belongs to the technical field of liver images, and provides a liver image synthesis method for generating three-phase enhanced images based on plain CT, S1, an upper abdominal plain CT image of a patient to be processed is acquired; S2, a pre-trained liver mask guided corrector module is used to respectively perform affine transformation and dense deformation registration on real arterial phase, portal phase and delayed phase enhanced CT images matched with the plain CT image, to obtain registered enhanced images and corresponding liver masks in the liver region which are aligned with the plain CT image at the voxel level; S3, the plain CT image, a 2.5D input tensor formed by the plain CT image and its adjacent upper and lower slices, and the current layer plain image as a residual base are input into a pre-trained Liver-GAN generator, and an attention mechanism based on the liver mask is used to weight the features, and a predicted enhanced residual is output; S4, the enhanced residual and the residual base are added to generate a virtual arterial phase, portal phase or delayed phase enhanced image corresponding to the plain CT image.

The application discloses a classification method and device for pancreatic neuroendocrine tumors. The classification method comprises the following steps: segmenting tumor masks from enhanced CT images; for each tumor mask, generating a first peritumoral region and a second peritumoral region; dividing the tumor into multiple habitats for each tumor mask; extracting 3D radiomics features, multiple peritumoral microenvironment features, multiple tumor habitat features, multiple local pathological features and multiple global context features; selecting multiple target features for each enhanced CT image and calculating a radiomics score; inputting the radiomics score and clinical variables into a logistic regression model for training to obtain a trained logistic regression model; and using the trained logistic regression model to classify the enhanced CT images to be classified. The application can quickly and accurately realize G-grade classification of pancreatic neuroendocrine tumors, and provides a reliable non-invasive evaluation tool for clinical decision-making.

The application provides a breast cancer patient lymph node metastasis prediction model without clinical pathological characteristics, comprising the following steps: after three-dimensional reconstruction of two-dimensional lung enhanced CT films, an axillary lymph node atlas is established, all axillary lymph nodes in the atlas are selected as ROI regions, and more than 5 combined image features of each axillary lymph node are selected to distinguish whether breast cancer has axillary lymph node metastasis; and a logistic regression machine learning prediction model is used to construct the breast cancer patient axillary lymph node metastasis prediction model. The model established by the application can non-invasively predict whether breast cancer has axillary lymph node metastasis, the clinical pathological characteristics of the patient are not included in the model, and the image cutting in the model is not based on breast tumors, but based on axillary lymph nodes; the model is used to determine a suitable axillary treatment scheme, thereby avoiding unnecessary axillary surgery and complications, and helping to carry out more accurate surgery and adjuvant therapy mode of breast cancer.

The invention relates to the technical field of medical image processing, and discloses a liver cancer rupture bleeding embolism treatment curative effect image evaluation method and system, and the method comprises the steps: S1, obtaining enhanced CT image data of a patient after liver cancer rupture bleeding embolism treatment, carrying out the preliminary region division of a focus region of the enhanced CT image data, and carrying out the image segmentation of the focus region; obtaining a preliminary region division result; s2, when an interaction correction mark made by a user on at least one sub-region of the preliminary region division result is received, the preliminary region division result is adjusted in real time, the boundary of the adjusted sub-region is obtained, and the interaction correction mark indicates the real organization type of the sub-region; s3, circularly executing the step S2 to perform interactive iteration correction on the boundary of the sub-region until the user confirms a final division result; and S4, performing volume quantitative evaluation on different types of tissues of the final division result, and generating an evaluation report. According to the invention, misjudgment caused by fuzzy and overlapped image features is effectively avoided.

The invention provides an intelligent response type platinum nano contrast agent. The intelligent response type platinum nano contrast agent comprises an amphiphilic polymer with a Schiff base bond and oleylamine modified hydrophobic platinum nanoparticles wrapped by the amphiphilic polymer. Compared with an iodine-based CT contrast agent, the platinum nano contrast agent has good biocompatibility, the platinum element with a high atomic number has a higher X-ray mass attenuation coefficient, the amphiphilic PEG shell prolongs the blood circulation half-life period of the platinum nano contrast agent, the carried Schiff base bond can intelligently respond to tumor acidic microenvironment fracture, and the stability of the platinum nano contrast agent is improved. The released La-PtNPs are aggregated in situ through hydrophobic interaction, and enhanced CT imaging and radiotherapy sensitization of tumors can be realized at the same time.

The invention discloses a bladder cancer early screening method based on plain-scan CT and MRI time sequence fusion, which realizes high-precision lesion recognition and positioning under the condition of low-dependence enhanced scanning through knowledge distillation and bimodal feature fusion. The method comprises the following steps: constructing a multi-modal data set including plain scanning, arteriovenous phase enhanced CT and MRI; a key frame sparse annotation and linear interpolation complementation strategy is adopted to reduce the annotation cost; performing preprocessing such as window level adjustment, normalization and zooming on the image; a CT / MRI recognition and positioning network is constructed, each sub-network comprises a 2D positioning branch and a 3D classification branch, and the characterization capability of plain scanning data is enhanced through a teacher-student knowledge distillation mechanism; and finally, integrating the bimodal information through a feature fusion module, and outputting a classification and positioning result. According to the method, time sequence consistency and modal consistency constraints are introduced, the recognition robustness of small focus and unclear boundary areas is improved, the manual film reading burden is remarkably reduced, the screening efficiency and safety are improved, and the method is suitable for early large-scale screening scenes of bladder cancer and has important clinical popularization value.

The invention provides a bone evaluation method based on neural network enhancement and finite element analysis. The bone evaluation method comprises the following steps: acquiring an ultrahigh-resolution CT image of a living vertebra; performing domain conversion processing on the CT image by adopting a generative neural network; carrying out resampling and segmentation on the enhanced CT image; constructing a bone trabecula microstructure model in the cancellous bone mask area; assembling the RVE unit and the cortical bone model into a complete vertebral finite element model, and applying a multi-working-condition load to the RVE unit to calculate anisotropic material parameters; and carrying out axial compression finite element analysis on the complete centrum model, and judging the bone health state. According to the method, information of two dimensions of bone mass and bone, especially contribution of a bone trabecula microstructure to bone strength, is comprehensively considered, bone degeneration and fracture high-risk patients can be recognized earlier, and a scientific basis is provided for clinical early intervention.

The present application relates to the field of medical imaging technology, disclose a biliary tract cancer CT image prediction method and system based on momentum attention and large model verification, the method comprises: based on the pre-training visual-linguistic large model extracts the visual features of the patient's upper abdominal non-enhanced CT image, constructs a high-dimensional visual embedding vector, initializes the historical momentum attention map and the initial reasoning text sequence, and the first momentum attention map is obtained by guiding and updating through the momentum mechanism; again extract the key image patch set and the initial reasoning text sequence, and the first reasoning text is obtained by interlacing fusion of the image and the text; repeatedly execute attention update and image-text fusion operation until the reasoning thought chain and the preliminary diagnosis conclusion are generated; the correlation degree of reasoning and diagnosis is evaluated by a pure text logical verifier to obtain a logical consistency score, and the target intelligent auxiliary diagnosis report is generated by assembling the score, the present application can improve the efficiency of biliary tract cancer CT image prediction.

The utility model provides an identification bracelet capable of distinguishing patients subjected to enhanced CT (Computed Tomography) examination, and belongs to the technical field of enhanced CT. Comprising a watchcase, a watch body structure is installed inside the watchcase, a watchband structure is movably installed outside the watchcase, a detection reminding structure is installed on the side wall surface of the watch body structure, and a non-detection reminding structure is installed on the side wall surface of the watch body structure; the watch body structure comprises a battery, a positioning module, a communication module, a loudspeaker, a touch screen and a watch body processor; the battery is installed inside the watchcase, the positioning module is installed above the battery, the communication module is installed above the battery, and the loudspeaker is installed above the battery; a patient is recognized through the warning lamps located on the back of the hand, the warning lamps are not prone to being shielded at the back of the hand, a worker can conduct screening more easily, meanwhile, the warning lamps are divided into red and green, the color difference is large, and the operator can conduct screening on the patient conveniently.

The application belongs to the field of diagnosis and treatment, and particularly relates to a lung cancer EGFR mutation non-invasive prediction model based on unsupervised decoupling and gate fusion. A multi-modal fusion model is constructed based on enhanced CT images and clinical data of non-small cell lung cancer patients. The application adopts a mask image modeling task, and autonomously learns morphological and texture primitive features of tumors from three-dimensional enhanced CT images without EGFR mutation labels. The application overcomes the dependence on a large amount of labeled data, enables the model to learn visual representations with high discriminability and generalization ability from unlabeled data, and significantly improves feature expression capability. A multi-modal fusion architecture based on a gate mechanism is designed, which can dynamically adjust the contribution weights of deep features, imaging features and clinical information in different samples. Personalized feature fusion for different cases is realized, the limitations of traditional static fusion methods are overcome, and complementary information between multi-source heterogeneous data is fully mined.

According to an aspect of the present invention, there is provided a method for imaging vasa vasorum density of a vessel in the body such as coronary and carotid arteries and the aorta and thereby assessing the risk of adverse health outcomes for a patient, comprising administering a contrast agent to the patient; performing a contrast-enhanced CT scan to measure Hounsfield distribution and heterogeneity related to vasa vasorum density in and around the vessel wall of a patient; analyzing the data to determine a metric related to the density of the vasa vasorum; and recommending a diagnostic and / or therapeutic next step to the patient to prevent adverse health outcomes based at least in part on the metric related to the vasa vasorum density.

The application discloses a CTA image generation method based on a state space diffusion network, and relates to the field of medical image processing. The method uses a state space diffusion network to generate a CTA image according to a non-enhanced CT image. The state space diffusion network introduces an improved state space model in a diffusion generation process to enhance the modeling capability of long-range dependent information, thereby improving the continuity and topological consistency of a blood vessel structure. Meanwhile, an adversarial learning mechanism is combined in the generation framework, and the image detail expression capability is strengthened through a local region discrimination strategy, so that the generated CTA image is closer to a real CTA image in terms of boundary definition and texture restoration. The method can realize high-quality conversion from a non-enhanced CT image to a CTA image, and the generated CTA image is good in terms of blood vessel structure reconstruction accuracy, image fidelity and clinical readability.

The invention discloses a postoperative abdominal organ ischemia risk assessment method and system based on image analysis, and relates to the technical field of image analysis. The method comprises the following steps: acquiring an abdomen enhanced CT image of a target patient, and outputting the abdomen enhanced CT image after standardization processing; an improved 3D U-Net + + architecture of multi-task collaborative learning is adopted to perform joint segmentation on organs of a target patient and a target area, and geometric prior and a topological reasoning mechanism are fused; the method is technically characterized in that multi-task segmentation is adopted to enable RPPR calculation to focus on a real ischemic area, average dilution signals of all organs are avoided, and topological correction ensures that blood vessel features reflect real anatomy; in addition, through conjoint analysis of a hypoperfusion area prediction mask and a blood vessel VTIF, two ischemic subtypes of structural occlusion and functional hypoperfusion are disclosed, individualized development of a clinical intervention strategy is promoted, and the condition of required blood vessel intervention or conservative treatment is defined, so that the whole scheme has innovativeness and clinical landing value.

The invention discloses a marker group for screening and diagnosing kidney cancer and application of the marker group, and belongs to the technical field of molecular biology. The marker group comprises at least four of polypeptides as shown in sequences SEQ ID NO. 1 to 38. The marker combination constructed by the invention has more excellent sensitivity and specificity when being used for auxiliary diagnosis and early screening of kidney cancer. The auxiliary diagnosis result of the kit is superior to that of imaging examination which is one of main schemes for clinical diagnosis of kidney tumors at present, and CT is enhanced (the sensitivity and the specificity are 78.67% and 87.88% respectively). The early screening result is superior to that of a high-frequency color Doppler ultrasonic instrument (the diagnosis sensitivity is 94.87%, and the specificity is 80%) which is applied to routine examination of the abdomen in physical examination at present; the sensitivity is 62.9%, and the specificity is 87.0%.

This invention relates to an automatic colorization method for CT images, the method comprising: Step 1: Preprocessing the CT image to obtain a contrast-enhanced CT image; Step 2: Establishing a first network for acquiring texture-enhanced CT images, and training the first network based on a pre-acquired training dataset to obtain a trained first network; wherein the training dataset includes multiple pairs of images; wherein each pair of images includes: a trained CT image and a trained PET image; Step 3: Establishing a generative discriminant network for colorizing CT images, and training the generative discriminant network based on a pre-acquired initial training set to obtain a trained generative discriminant network; Step 4: Obtaining the final CT color visualization result based on the contrast-enhanced CT image, the trained first network, and the trained generative discriminant network.

The utility model discloses a contrast agent extravasation alarm device for enhanced CT (Computed Tomography) examination, which comprises a flexible belt body, an outer peripheral surface, an inner peripheral surface and a lateral contour edge positioned on the common edge of the outer peripheral surface and the inner peripheral surface, the injection window penetrates through the outer circumferential surface and the inner circumferential surface of the flexible belt body and extends in the annular circumferential direction of the flexible belt body; the inflatable bag is arranged in the flexible belt body and comprises an outer ring and an inner ring communicated with the outer ring through a connecting channel, the outer ring is arranged along the side contour edge, and the inner ring is arranged along the contour of the injection window; a pressure sensor; an acousto-optic unit; and a wet dressing layer. The skin around an injection part is slightly pressed through the inflatable bag, the influence of muscle vibration on the needle head can be reduced, the flexible belt body and the inflatable bag can effectively face irregular muscle part contours so as to be better attached to the skin, the injection part is effectively stabilized, and the possibility that the needle head moves is reduced.

The present invention relates to a method for generating patient-customized CT collateral images using blood flow time segmentation of dynamic contrast-enhanced CT images performed by an electronic device, and for simultaneously implementing 3D subtraction CT arteriography, 3D subtraction CT venography, and color-coded 4D CT angiography.

The application discloses a kind of health multi-phase image guided multi-phase lesion image segmentation methods, this method mainly includes: using healthy multi-phase contrast-enhanced CT training deep learning network, freeze its parameters, then send lesion CT image into trained healthy image network and another network structure consistent with the lesion image network to be trained.Healthy image network acts as normal tissue feature extractor, assist lesion image network training;Wherein, the loss function of healthy image network adopts the combination of Dice loss function and cross-entropy loss function, the loss function of lesion image network includes the mean square error loss function of feature map extracted by healthy image network and lesion image network to lesion image in addition to above-mentioned two loss functions.The application scheme distinguishes healthy tissue and lesion tissue by guiding lesion image network with healthy image, and the segmentation precision of lesion tissue is improved.

The application discloses a marker group for kidney cancer screening and diagnosis and application thereof, and belongs to the field of molecular biological technology.The marker group comprises at least four polypeptides shown in sequences of SEQ ID NO.1-38.The marker group constructed by the application has more excellent sensitivity and specificity when used for the auxiliary diagnosis and early screening of kidney cancer.The auxiliary diagnosis result is better than that of one of main current clinical diagnosis schemes for kidney tumors, i.e., imaging examination, and enhanced CT (sensitivity and specificity are 78.67% and 87.88%, respectively).The early screening result is better than that of a high-frequency color Doppler ultrasound instrument (diagnostic sensitivity is 94.87%, and specificity is 80%) applied to the routine examination of the abdomen in a health examination; and multi-gene methylation combined analysis (sensitivity is 62.9%, and specificity is 87.0%).

This invention provides a method for constructing a small bowel CT image recognition and segmentation network model and a recognition method. The construction method includes the following steps: acquiring several small bowel CT images showing lesions and constructing an image dataset, dividing the dataset into a training set and a test set proportionally; enhancing the image dataset in the above steps using dynamic stochastic resonance enhancement; constructing a U-Net network model and training the network model using the enhanced training set obtained in the above steps; testing the network model using the enhanced test set obtained in the above steps, and completing the model construction. This invention proposes a method for enhancing CT images based on dynamic stochastic resonance, which can effectively enhance useful signals in the original image. Since medical image processing is mainly used to assist doctors in diagnosis, the input is an image, and the output is also an image that is easier for doctors to use. This invention establishes a U-shaped neural network that meets this requirement.

The application discloses a dual-space-constraint-based enhanced CT image generation method and device, encodes a real enhanced CT image to obtain a parameterized distribution of the real enhanced CT image in a latent space, provides additional training supervision information as a label in the latent space to optimize model parameters, and combines a real segmentation binary image of an enhanced region to explicitly guide a region which should be focused on by the model, improves the weight of the real segmentation binary image region in a reconstruction loss, improves the attention degree of the model to fine anatomical structures in a plain CT image, and enables the model to complete enhancement of the fine anatomical structures; and the conversion encoder increases a channel-space attention module as a conversion encoder on the basis of an encoder of a VAE model to realize mapping from an image space of the plain CT image to the latent space of the real enhanced CT image.

The utility model belongs to the CT enhancement scanning auxiliary device field especially, and it is more particularly to a urinary system abdominal compression enhancement CT scanning pressurization restraint device. The technical includes the restraint band, the restraint band front side inner wall is provided with the pressurization piece, and the pressurization piece is oval structure, and the restraint band front side outer wall is provided with the adjusting assembly for driving pressurization piece left and right movement. The utility model discloses through the cooperation of restraint band and pressurization piece, is convenient for when scanning and places pressurization piece in patient abdominal side bilateral sacroiliac joint level, delays contrast agent excretion, makes contrast agent temporarily in ureter renal pelvis calyx, renal pelvis calyx expansion, and then utilizes post-processing technology to make contrast agent and lesion show good contrast, thereby benefit the position of judging stone and the relationship with renal pelvis, calyx, ensure the accurate detection and evaluation of kidney stone, also convenient for adjusting the position of pressurization piece according to different patients during use, make the stability and accuracy of scanning result higher while making the applicability higher.

The invention discloses a system, a method, equipment and a medium for generating diffusion from craniocerebral CT to craniocerebral CTA under self-adaptive characterization guidance, and belongs to the technical field of medical image processing and artificial intelligence. The system comprises an adaptive representation extraction module used for extracting a depth feature vector representing a blood vessel and an anatomical structure from an input non-enhanced CT image; the conditional potential diffusion model is used for executing a de-noising diffusion process in a potential space by fusing U-Net of a cross attention mechanism under the condition of the feature vector to generate target feature representation; and the image reconstruction module is used for decoding and reconstructing the potential features into a synthetic CTA image. According to the method, the diffusion generation process is guided through the self-adaptively extracted anatomical priori depth, high-quality and high-anatomical-consistency three-dimensional craniocerebral CTA image synthesis without an iodine contrast agent is realized, and the defects of dependence on the contrast agent, inaccurate blood vessel reduction and poor three-dimensional continuity in the prior art are effectively overcome.