62 results about "Magnetic image" patented technology

The invention discloses a brain nuclear magnetic imaging focus reasoning method based on a multi-hop memory network. The method comprises the following steps: S1, acquiring brain nuclear magnetic resonance imaging data and corresponding clinical annotation data; s2, generating preprocessed brain nuclear magnetic resonance image data; s3, constructing a medical priori knowledge graph; s4, constructing a multi-hop memory network model; s5, generating an image feature vector; s6, generating an image feature vector fused with the prior knowledge; s7, storing the updated features in a memory unit; s8, performing hop-by-hop calibration on the judgment of the focus position, the focus range and the focus property, and outputting a focus reasoning result; and S9, performing fusion display with the original brain nuclear magnetic resonance image data. According to the method, remarkable innovation is achieved on the algorithm level, and meanwhile the accuracy and clinical applicability of the focus reasoning result are remarkably improved.

A wide-field dynamic magnetic imaging device and method. The wide-field dynamic magnetic imaging device comprises: a probe assembly (1), comprising a diamond (101) containing NV centers; a microwave magnetic field assembly (2) configured to generate a uniform microwave field and a uniform bias magnetic field in the vicinity of the diamond (101), so as to regulate the spin energy level of the diamond (101) and the quantum state evolution process; a laser modulation assembly (3) configured to output an initial uniform pulsed laser to excite the diamond (101) to emit fluorescence; a fringe light modulation assembly (4) configured to modulate the initial uniform pulsed laser to output a fringe pulsed laser, causing the fluorescence emitted by the diamond (101) to be fringe fluorescence, or to modulate the fluorescence emitted by the diamond (101) into fringe fluorescence; a fluorescence detection assembly (5) configured to perform spatial imaging on the fringe fluorescence to obtain magnetic field information of a sample under test (7), thereby obtaining an initial magnetic image of said sample (7); and a data processing assembly (6) configured to perform Fourier transform and inverse Fourier transform on the initial magnetic image to obtain a first magnetic image.

The invention provides a nuclear magnetic resonance and image intelligent bimodal unfrozen water dynamic identification method and system, and belongs to the technical field of frozen soil engineering and geophysical exploration, and the method comprises the steps: sealing a frozen soil sample in a nuclear magnetic sample tube, and achieving the gradient cooling of the sample in a preset low temperature range through temperature control; scanning by using a nuclear magnetic resonance technology to obtain transverse relaxation time T2 spectrums and nuclear magnetic images of the frozen soil sample at different temperature nodes; after image preprocessing is carried out on the nuclear magnetic image, a temperature-signal intensity curve in the nuclear magnetic image is automatically extracted by utilizing an image recognition technology; carrying out integral calculation on a liquid water signal in the T2 spectrum, and dynamically calculating the content of the unfrozen water at each temperature based on a nuclear magnetic signal intensity formula; according to the method, a pore-fracture co-evolution matrix is constructed, accurate analysis of unfrozen water dynamic and pore evolution in the freezing and thawing process is realized, the method is suitable for hydrothermal coupling characteristic analysis of Qinghai-Tibet soil in a complex freezing and thawing environment, and reliable technical support is provided for stability evaluation of frozen soil engineering.

Belongs to the technical field of biomedical engineering, and discloses a method, a device, equipment, a product and a storage medium for identifying skull defects by constructing a characteristic spectrum through a nuclear magnetic image to solve the problem that a defect area is mistakenly divided into skull areas in existing automatic skull segmentation. Converting the human brain nuclear magnetic image to an anatomical space based on the plurality of anatomical points, and implementing preliminary segmentation to obtain a primary segmentation region of the skull; calculating coordinates of voxel points in the primary segmentation region in an anatomical point coordinate system, establishing a matrix, calculating a plurality of nuclear magnetic gray statistical characteristics of the primary segmentation region, and drawing a characteristic spectrum; and performing multi-condition feature threshold judgment on the feature map to obtain a logic binary map, and extracting a region of which a connected domain is greater than a specified threshold as a skull defect region. According to the method provided by the invention, a plurality of gray features are utilized, the misrecognition of the skull in the prior art is effectively corrected, the method can be further used for judging the filling tissue of the skull defect area, and the skull defect recognition capability can be improved.

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

The invention belongs to the technical field of medical robots and minimally invasive surgery, and provides a robot control system and method for blue laser vaporization surgery of prostatic hyperplasia. Mapping the nuclear magnetic image volume data to a deformation field under an ultrasonic acquisition coordinate system, and deforming the preoperative nuclear magnetic image to an intra-operative ultrasonic space by using the deformation field to complete image registration; fusing the registered image with a stereoscopic vision system; the spatial depth of the surface of the target tissue is obtained from the endoscopic image so as to supplement navigation information; according to the utility model, the prostate deformation and probe posture change adaptive capacity in an operation is improved, the real-time visual closed-loop regulation and control capacity is improved, and the characteristics of small light spots, shallow heat diffusion, excellent hemostasis and the like of blue laser are combined, so that the vaporization and hemostasis precision in a tiny blood vessel dense area is ensured, and the problems of large tissue trauma and the like are avoided.

The invention discloses a method for non-destructively identifying the gender of a transformed young duck egg based on a singing tube nuclear magnetic image, and belongs to the technical field of poultry egg detection.The method comprises the steps that a low-field nuclear magnetic resonance technology is utilized, a breeding duck egg is positioned in a nuclear magnetic system, the optimal imaging section of a singing tube is determined, an image is collected and preprocessed, and a high-quality singing tube nuclear magnetic image is obtained; and through analyzing relaxation characteristics, inverting nuclear magnetic signals to identify a buzzer tube structure and extracting characteristics, finally constructing a gender decision-making model, and combining physical constraints to obtain a gender discrimination result as a sorting reference. According to the method, lossless, early-stage and high-accuracy sex identification is realized through a special imaging technology and algorithm by utilizing sex difference nuclear magnetic characteristics of a singing tube structure, hatching and breeding strategies can be optimized in laying duck and meat duck breeding, and intelligent development of the industry is promoted.

This invention discloses an auxiliary design method for a banknote magnetic feature authentication module with a long-side feed, comprising: feeding the banknote along its long side and scanning it along its short side using a magnetic image sensor to obtain a magnetic image of the banknote; setting the detection width, number of channels, and sensitivity of the magnetic feature sensor; selecting a series of intensity values ​​from the banknote magnetic image column to simulate the magnetic feature sensor scanning signal; performing morphological dilation of the structural elements along the long side of the banknote magnetic image to simulate the magnetic feature sensor scanning image; and simulating multi-mode magnetic feature sensor scanning signals at the long side position of the banknote. This method displays the banknote magnetic image and the simulated magnetic feature sensor scanning image, allowing selection of a suitable scanning position from both. Simultaneously, based on the selected position, three sets of signal references are output to confirm suitability, thus completing the auxiliary design.

The application discloses a cloud transmission method for MRI image information and belongs to the technical field of nuclear magnetic image transmission. The cloud transmission method for MRI image information comprises the following steps: step 1, a terminal device generates original information to be sent, and converts the original information into encrypted information; step 2, the terminal device sends the encrypted information and domain name information of the terminal device to a cloud server; and the encrypted information is downloaded from the cloud server, and then the encrypted information is decrypted into the original information by using a decryption key. According to the scheme, a safe and efficient transmission framework is constructed for sensitive MRI image data shared across institutions through encrypted transmission, source authentication and hierarchical key mechanism; and the original data is transmitted after being encrypted, so that information leakage in the transmission process is effectively prevented.

The invention discloses a full-automatic real-time precise positioning puncture needle and a positioning method thereof. The full-automatic real-time precise positioning puncture needle comprises a puncture needle body and a visual navigation module. The puncture needle is used for lung biopsy sampling and comprises a needle body part and a handle part. The needle body part is in a slender cylinder shape, the front end is sharpened, tissue can be conveniently penetrated, the handle part is designed to be in a holding shape, handheld operation is convenient, and a shell is in a streamline shape. The visual navigation module is used for navigation positioning assistance in the puncture process. The visual navigation module is in a T shape; by combining the puncture needle and the nuclear magnetic image, path planning and real-time puncture angle monitoring are completed, and complications caused by insufficient precision and path information loss in a traditional percutaneous puncture operation are prevented.

The present disclosure provides a wide-field dynamic magnetic imaging device and method, which includes: a probe assembly including a diamond containing NV color centers; a microwave magnetic field assembly adapted to generate a uniform microwave field and a uniform bias magnetic field near the diamond to regulate the spin energy level and quantum state evolution process of the diamond; a laser modulation assembly adapted to output an initial uniform pulse laser to excite the diamond to emit fluorescence; a stripe light modulation assembly adapted to modulate the initial uniform pulse laser to output a stripe pulse laser so that the fluorescence emitted by the diamond is stripe fluorescence; or to modulate the fluorescence emitted by the diamond into stripe fluorescence; a fluorescence detection assembly adapted to perform spatial imaging of the stripe fluorescence to obtain magnetic field information of a sample to be tested, thereby obtaining an initial magnetic image of the sample to be tested; and a data processing assembly adapted to perform Fourier transform and inverse Fourier transform processing on the initial magnetic image to obtain a first magnetic image.

The invention discloses a multi-mode nuclear magnetic image brain tumor segmentation system based on optical flow method pixel correlation, relates to the field of image processing, and solves the problems that complex physiological correlation among multiple modes cannot be captured and specific characteristics of a tumor area are difficult to reproduce in an existing missing mode completion method. The segmentation system comprises a data preprocessing module, a cross-modal optical flow estimation module, a pixel association weight calculation module, a missing modal complementation module and a fusion segmentation module. The system is simple in structure and reasonable in design, breaks through the limitation that a traditional optical flow model depends on a gray level consistency hypothesis, and adapts to the characteristic that the gray level difference of the multi-mode MRI is remarkable. By capturing the consistency of the gray gradient direction of the same anatomical structure in different modals, cross-modal pixel correlation mapping is accurately established, optical flow estimation deviation caused by gray mismatching is avoided, a reliable correlation basis is provided for subsequent deletion completion, and the accuracy of cross-modal information transmission is guaranteed.

The invention discloses a heart multi-modal image feature extraction method and device, equipment, a medium and a product, and relates to the technical field of medical image processing, and the method comprises the steps: obtaining multi-modal heart image data, patient information and case information in a multi-center imaging department and an ultrasound department; labeling the multi-modal heart image data, and constructing a multi-modal iconography feature database; establishing a database platform comprising a server storage control terminal and a data screening and uploading terminal; opening a communication link after verifying the identity of the requester; training is carried out based on the marked multi-mode heart data and a deep learning algorithm so as to obtain heart structure features of heart ultrasound and nuclear magnetic images through coronary angiography (CCTA) image data; finally, the system is deployed and applied clinically. According to the method, the heart structure features of the other two modal images are predicted based on the single-modal CCTA image data, the diagnosis range based on the CCTA image data is expanded, the medical overhead is saved, and the diagnosis and treatment efficiency and accuracy are improved.

The utility model provides an image registration body surface mark for tumor radiotherapy. The image registration body surface mark comprises a registration strip, a contrast agent and a bonding piece. The registration strip is a flexible part and is provided with a top face and a bottom face, the outer contour of the top face is in a circular arc shape, and the registration strip is provided with a containing cavity. The contrast agent is arranged in the containing cavity, and the bonding piece is arranged on the bottom face and used for being bonded to the body surface of a patient. A patient adheres to the body surface through the adhesive part according to the tumor position, then CT and nuclear magnetism are conducted, the bottom face of the plane cannot sink into the skin, radiotherapy measurement is prevented from being affected, the mark can serve as a mark for fusion registration of a CT image and a nuclear magnetism image due to the fact that the mark is developed at the same time in CT and nuclear magnetism, the registration accuracy is improved, and the radiotherapy accuracy is improved. The CT and nuclear magnetic registration mark for tumor radiotherapy is provided for tumors (such as body surface tumors) far away from bones and involving soft tissues, and the image matching accuracy is improved, so that the radiotherapy accuracy is improved, the curative effect is improved, and the side effects are reduced.

The application provides a nuclear magnetic resonance and image intelligent dual-mode unfrozen water dynamic identification method and system, and belongs to the technical field of frozen soil engineering and geophysical exploration, and comprises the following steps: sealing a frozen soil sample in a nuclear magnetic sample tube, and realizing gradient cooling of the sample in a preset low temperature range through temperature control; scanning and acquiring a transverse relaxation time T2 spectrum and a nuclear magnetic image of the frozen soil sample at different temperature nodes by using a nuclear magnetic resonance technology; automatically extracting a temperature-signal intensity curve in the nuclear magnetic image by using an image recognition technology after image preprocessing of the nuclear magnetic image; performing integral calculation on liquid water signals in the T2 spectrum, and dynamically calculating the content of unfrozen water at each temperature based on a nuclear magnetic signal intensity formula; and constructing a pore-fracture collaborative evolution matrix, so that accurate analysis of the dynamic unfrozen water and pore evolution in a freezing and thawing process is realized, the water-heat coupling characteristics of Qinghai-Tibet soil under a complex freezing and thawing environment are analyzed, and reliable technical support is provided for stability evaluation of frozen soil engineering.

The application relates to the technical field of image processing, and discloses a method and device for prostate image fusion by adopting a posture sensor, which comprises the following steps: fixing the posture sensor on an ultrasonic probe; locking the depth position of the ultrasonic probe when the ultrasonic probe detects a prostate position; collecting ultrasonic images by rotating the ultrasonic probe; recording the rotation information of the ultrasonic probe by the posture sensor; obtaining multi-angle ultrasonic images of the prostate and corresponding posture sensor data; rotating the ultrasonic images of each angle according to the coordinate alignment rotation angle of the multi-angle ultrasonic images and the corresponding posture sensor data; obtaining a two-dimensional ultrasonic image sequence and performing interpolation processing on the ultrasonic images; and constructing a three-dimensional ultrasonic image; and fusing the nuclear magnetic image and the real-time two-dimensional ultrasonic image according to the pre-obtained nuclear magnetic image to obtain a fusion image; the application is a new method for realizing multi-modal fusion images by adopting a posture sensor.

The application discloses an artificial intelligence-based image analysis method and system for degenerative cervical spinal cord disease, relates to the technical field of artificial intelligence, and solves the technical problems of the existing technology, such as non-uniform image report standards, rough image analysis, increased patient anxiety, wasted medical resources, significant observer bias in DCM evaluation, and low efficiency of degenerative cervical spinal cord disease image analysis. A cervical vertebra dissection segmentation model is used to obtain a segmentation label; an intervertebral canal stenosis quantification grading model is used to obtain an intervertebral canal stenosis prediction grade of the segmentation label for the intervertebral canal; a spinal cord compression classification model is used to obtain a spinal cord compression result of the segmentation label for the cervical spinal cord; and a cervical vertebra image analysis model is used to obtain an analysis report of the cervical vertebra nuclear magnetic image. The image report is standardized, improved segmentation models are used, classification models are used in cooperation, and cervical vertebra image analysis models are used for processing, so that the accuracy of analysis is improved, and the efficiency of degenerative cervical spinal cord disease image analysis is improved.

The present invention discloses a magnetic imaging recognition method and a magnetometer based on deep learning. The method includes: preprocessing the collected magnetic field data to obtain encrypted and reconstructed magnetic map data; calculating magnetic gradient tensor components based on the encrypted and reconstructed magnetic map data, and extracting magnetic field gradient features by using different combination methods of the magnetic gradient tensor components; identifying magnetic field anomaly information by analyzing the magnetic field gradient features, combining the magnetic source boundary with the encrypted and reconstructed magnetic map data, performing pseudo-color coding, and establishing a magnetic image data set; training an improved R-CNN pipeline defect detection model by using the magnetic image data set, where the input of the pipeline defect detection model is a magnetic image and the output is the position and type of pipeline defects; and using the trained pipeline defect detection model to identify pipeline defects in newly input magnetic images. The present invention improves the accuracy, efficiency and adaptability of pipeline defect detection through advanced data processing technologies and artificial intelligence algorithms.

The invention relates to the technical field of oil production engineering, in particular to an online nuclear magnetic imaging experimental device and method for evaluating shale hydration secondary cracks. The experimental device comprises a rock core, a rock core holder and an online nuclear magnetic device, a rock core is arranged in the rock core holder, and the rock core holder is arranged in the online nuclear magnetic device; one side of the core holder is sequentially connected with a pressure gauge, a constant-flux pump and a liquid inlet tank through a pipeline, and fracturing fluid is placed in the liquid inlet tank; the other side of the core holder is connected with a waste liquid tank; and the other side of the core holder is connected with a hand pump for pressurizing. According to the online nuclear magnetic imaging experimental device and method for evaluating the shale hydration secondary fractures, continuous online nuclear magnetic imaging experiments can be conducted on the shale hydration secondary fractures, hydration secondary fracture distribution evaluation can be conducted on different types of shale cores, the shale reservoir fracturing transformation effect and the after-fracturing production capacity are optimized, and the shale hydration secondary fractures can be evaluated. And the full life cycle single well productivity of the shale oil-gas well is improved.

The invention discloses a magnetic resonance image enhancement and model combined training method and device. The method comprises the following steps: traversing historical low-field nuclear magnetic images in training samples; inputting the historical low-field nuclear magnetic image into a preset conditional diffusion generation model, and outputting a corresponding confidence map for quantifying the reliability of each pixel position generation structure and a restored anatomical structure map; inputting the historical low-field nuclear magnetic image, the confidence map of the historical low-field nuclear magnetic image and the anatomical structure map into a preset confidence perception enhancement module, and outputting a corresponding enhanced low-field nuclear magnetic image; based on the enhanced low-field nuclear magnetic image, presetting a conditional diffusion generation model, and calculating cycle consistency loss; and when the loop consistency loss reaches the minimum, stopping iteration and generating a pre-trained conditional diffusion generation model and a confidence perception enhancement module. By adopting the method and the device, the defects of the existing GAN in training stability, image generation reliability and interpretability are overcome, and the stability and the image generation reliability are improved.

The embodiment of the present application discloses a compound molecular structure formula similarity comparison method based on nuclear magnetic hydrogen spectrum data, comprising: comparing the nuclear magnetic data of a target compound with the nuclear magnetic data of known compounds to obtain a nuclear magnetic data similarity score; comparing the nuclear magnetic image of the target compound with the nuclear magnetic image of the known compounds to obtain a nuclear magnetic image similarity score; weighting the nuclear magnetic data similarity score and the nuclear magnetic image similarity score to obtain a final similarity score; if the final similarity score is the highest and is higher than a preset threshold, the known compound corresponding to the final similarity score with the highest score is the same as the target compound; otherwise, the target compound is determined to be a new compound. The present application can reduce human intervention, reduce spectrum analysis time, effectively obtain similar chemical structure formulas for researchers to refer to, and improve efficiency by combining nuclear magnetic spectrum information and nuclear magnetic data information.

The embodiment of the invention provides a dynamic nuclear magnetic image processing method and device, equipment and a storage medium. The method comprises the steps of obtaining an original dynamic nuclear magnetic image based on a time sequence; dividing all the original dynamic nuclear magnetic images into a plurality of image groups according to a sliding window with a preset size and a preset sliding step length; and determining a target image corresponding to each original dynamic nuclear magnetic image based on the image group, and processing through the image group, so that the quality of the dynamic nuclear magnetic images can be improved.

The application relates to a multi-modal magnetic imaging device and method based on the fusion of NV color centers and a MEMS atomic gas chamber layer. The device comprises: a composite sensing chip, which is sequentially integrated from bottom to top with an NV color center sensing layer, a spacing coupling layer and a MEMS atomic gas chamber layer; the NV color center sensing layer can detect a near-field magnetic signal to generate an NV fluorescence signal in an excited state; the spacing coupling layer can isolate and couple the near-field magnetic signal to the MEMS atomic gas chamber layer; the MEMS atomic gas chamber layer can detect a coupled magnetic signal to generate a magnetic response light signal in a SERF working state; and a processing system can enable the NV color center sensing layer to be in the excited state, enable the MEMS atomic gas chamber layer to be in the SERF working state, and generate a fusion magnetic image based on the two types of signals. The application can solve the problem that related technologies cannot realize efficient magnetic flux coupling between an NV color center sensing unit and an atomic magnetometer of the SERF at a chip level, and realize high-sensitivity and high-fineness magnetic imaging.

The application discloses a kind of nuclear magnetic resonance image prediction model construction methods, main design concept is in, from the information between using multi-stage liver cancer nuclear magnetic image data start to improve the prediction performance of the prediction model constructed, specifically, propose by multiple multilayer convolutional neural network as the extraction part of image feature, in this link, introduce multi-sequence image difference extraction pyramid module, difference information is mined between the input two two image stages and is integrated into image feature extraction operation, then the feature map containing difference information extracted by convolutional neural network is sent into multi-sequence image correlation attention module, learn the correlation between the input different stage nuclear magnetic image, and then provide rich reference information for subsequent accurate prediction classification.The present application can make full use of the difference information and correlation information between the images of different stages in the enhanced nuclear magnetic image, so as to effectively improve the prediction performance of the model based on image information.

The application provides a real-time lightweight nuclear magnetic image enhancement method and system based on regional grading, relating to the technical field of image enhancement processing. The method first acquires a nuclear magnetic image with a first resolution, performs automatic regional segmentation processing on the nuclear magnetic image with the first resolution, and the processed nuclear magnetic image with the first resolution includes multiple regions. Then, the images of the multiple regions are classified to obtain three regions, and the images in the three regions are respectively input into different residual groups for image processing after sparse dilated convolution processing. The images processed by different residual groups are added in pixel results to obtain an enhanced nuclear magnetic image. Through automatic regional segmentation and classification processing, different regions in the nuclear magnetic image can be accurately processed individually to improve the image quality. The use of sparse dilated convolution and residual group processing effectively enhances the detail features of the nuclear magnetic image and improves the image clarity and diagnostic accuracy.

The specification discloses an obstacle avoidance prompt method, device, medium and equipment. According to the pose of a human optical beacon collected by a tracker and the pose of a surgical equipment optical beacon, the actual position of the working end of the surgical equipment and the actual position of the human optical beacon are determined. A CT image containing the working end and the human optical beacon collected during surgery is obtained, and a nuclear magnetic image collected before surgery is obtained. The working end and the human optical beacon in the CT image are identified, and according to the actual position of the working end and the actual position of the human optical beacon, a first transpose matrix of the CT image and the tracker is determined. A second transpose matrix of the CT image and the nuclear magnetic image is determined, and according to the first transpose matrix and the second transpose matrix, the position of the working end in the nuclear magnetic image is determined. The target object in the nuclear magnetic image is identified, and the position of the target object in the nuclear magnetic image is determined. According to the position of the working end and the position of the target object, obstacle avoidance prompt information is determined and displayed.

This invention discloses a graph convolutional neural network (GCN) disease prediction system based on multimodal brain MRI images, belonging to the field of medical image analysis and disease prediction technology. The system includes: an image preprocessing module that acquires and standardizes raw functional and structural magnetic resonance imaging (fMRI) data to generate a corresponding dataset; a dynamic supernet construction module that extracts spatiotemporal fusion variability features of brain regions; a multimodal fusion module that fuses features and constructs an adjacency matrix; a GCN prediction module that calculates prediction results such as disease progression grading; and a results visualization module that locates abnormal brain regions and generates a clinical reference report. This invention integrates multimodal brain MRI data from functional and structural magnetic resonance imaging to build a full-process disease prediction system. Through various algorithms, it mines the spatiotemporal dynamic characteristics of brain regions and integrates multimodal features to achieve dual-task prediction of Alzheimer's disease progression grading and brain age. Furthermore, through standardization processing and feature screening, it generates clinical reports to assist in disease diagnosis and treatment.

The application discloses an evaluation method for open-pit mine blasting block size, and belongs to the technical field of mining engineering, comprising the following steps: obtaining ore and rock samples in blasting piles after blasting, and building the piles into laboratory blasting piles; collecting nuclear magnetic imaging data of N similar water-retaining models of the blasting piles based on a nuclear magnetic instrument; pre-processing the nuclear magnetic image data of the N similar water-retaining models of the blasting piles, and three-dimensionally reconstructing the internal structure of the similar water-retaining models of the blasting piles to form a three-dimension block size distribution average curve; calculating the ratio of the surface block size distribution curve of the laboratory blasting piles and the three-dimension block size distribution average curve to obtain a correction coefficient, and correcting the surface grading curve of the blasting piles on site; performing normalization processing on the corrected block size grading curve of the blasting piles, dividing n discrete points according to a certain particle size interval, calculating the difference value RMSE between the actual value and the fitting value based on the n discrete points, and then performing uniformity grade division to realize the evaluation of the internal block uniformity of the blasting piles on site.

The invention relates to a cognitive disorder prediction method and device and electronic equipment, and the method comprises the steps: obtaining a human brain 3D structure nuclear magnetic image of a patient; segmenting the human brain 3D nuclear magnetic image through an AAL-90 standard brain template to obtain 90 3D brain region images; identifying and predicting the 90 3D brain region images through a cognitive impairment prediction model to obtain a prediction result; the cognitive impairment prediction model comprises a multi-brain region feature extraction module, a feature weighting module and a feature fusion module, a human brain 3D nuclear magnetic image is segmented to obtain 90 3D brain region images, and then the multi-brain region feature extraction module performs 3D convolution operation on the 90 3D brain region images to extract 90 brain region features. Therefore, the effective brain region features contained in each small-range image are fully extracted, and the problem that the cognitive impairment type cannot be accurately predicted in the prior art is solved.

The invention discloses a urethra protection device for radiotherapy of prostatic cancer, and relates to the technical field of radiotherapy, and the urethra protection device comprises a CT which obtains a CT image of a prostate area of a user; the 3D T2WI nuclear magnetic sequence is used for obtaining a three-dimensional nuclear magnetic image sequence of the prostate area of the user; the radiotherapy dose and frequency determination module is used for determining the total radiotherapy dose and frequency of the user; the radiotherapy planning module is used for performing three-dimensional fusion processing on the CT image and the three-dimensional nuclear magnetic image sequence to obtain a three-dimensional fusion image sequence containing a prostate cancer target region and a whole urethra contour, and dividing the whole urethra contour in the three-dimensional fusion image sequence into a plurality of urethra protection regions according to the prostate cancer target region, according to the total radiotherapy dose, the number of times and the plurality of urethra protection areas, determining each radiotherapy dose of each urethra protection area; and the linear accelerator is used for carrying out radiotherapy treatment according to the radiotherapy dosage of each urethra protection area.