25 results about "Organ region" patented technology

The invention discloses a four-dimensional cone beam CT (Computed Tomography) reconstruction method based on an anatomical prior constraint diffusion model, which mainly solves the problem of poor quality of a reconstructed image in the prior art, and adopts the implementation scheme that the method comprises the following steps: acquiring CT original full-projection data of a batch of patients, and carrying out sparse sampling on the CT original full-projection data; performing data set division and reconstruction on the original full projection data and the sparse projection data to obtain a reference true value and a low-quality CT image containing a large number of artifacts; preliminarily enhancing the CT image containing a large number of artifacts by using the pre-trained ResViT network to obtain a CT image without artifacts; segmenting the CT image without artifacts by using a body segmentation network to obtain anatomical information of each organ; constructing a four-dimensional cone beam CT motion compensation reconstruction model based on anatomical prior constraints, and training and verifying the four-dimensional cone beam CT motion compensation reconstruction model; and inputting the tested data into the trained reconstruction diffusion model to obtain a reconstruction result. According to the method, artifacts of sparse cone beam CT in a specific organ area can be thoroughly eliminated, the reconstructed image is clear in details, and the method can be used for tracking and positioning tumor movement caused by respiration.

The invention discloses an organ coverage scanning real-time planning method and device for avoiding skeleton occlusion, and the method comprises the steps: carrying out the processing based on an obtained ultrasonic image, obtaining the coordinates of an organ region and the coordinates of a skeleton region, and updating an octree map to obtain a perception map; generating a plurality of candidate paths based on the perception map; calculating energy consumption scores of all the ranked candidate paths; performing light projection simulation on each sequenced candidate path to obtain a light projection score; performing weighted calculation on the basis of the energy consumption score and the light projection score of each sequenced candidate path to obtain a pose score; based on all the pose scores, an optimal path is obtained through screening, the ultrasonic robot is controlled to execute path nodes in the optimal path, and a new ultrasonic image is obtained; and circularly executing the process on the basis of the new ultrasonic image until full-coverage scanning of the organ is completed. Skeleton shielding can be dynamically sensed, a scanning path can be autonomously planned, and the organ coverage rate is increased.

The application discloses a field determination method and device, electronic equipment and computer readable storage medium, and relates to the field of medical technology. The method comprises the following steps: acquiring a first score of each field in N fields, which is used for determining the score of the field under the constraint condition set for a planning target volume; acquiring a second score of each field, which is used for determining the score of the field under the constraint condition set for an organ at risk; acquiring a third score of each field, which is used for determining the score of the field under the constraint condition set for other organ regions, wherein the other organ regions are organ regions other than the organ at risk and the planning target volume; and determining M fields as target fields from the N fields according to the first score, the second score and the third score. The application solves the technical problem that the number of fields is minimized and the quality of radiotherapy is high enough in the prior art by relying on expert experience or fixed rules to determine the fields.

This invention discloses a region-based, multi-index, multi-organ medical image segmentation model evaluation system, comprising a data acquisition module, an organ region delineation module, a data preprocessing module, a medical image segmentation model training module, a medical image segmentation model testing module, and a medical image segmentation model evaluation module. This system proposes a multi-index, multi-organ medical image segmentation model evaluation method that simultaneously quantifies multi-organ segmentation results, multiple accuracy indices, and confidence estimates in a concise and unified metric. It also provides information on the model's overall performance and its clinical usability, providing a novel and intuitive standard for clinically evaluating multi-index and multi-organ medical image segmentation models.

The application discloses a liver and bile duct stone positioning analysis method and system based on image processing, relates to the technical field of image data analysis, and comprises the following steps: removing artifacts and noise from multi-modal medical images, reducing the influence of interference factors, and providing a reliable basis for subsequent image feature extraction and analysis. The foreground region represents the liver and bile duct region, and the additional foreground region represents the organ region near the liver and bile duct region, which can also reflect the condition of the stone. The image features of all modes are integrated to determine the direct content and indirect content of the liver and bile duct stone, and the position information and related information of the liver and bile duct stone are inferred by combining the direct content and indirect content of the liver and bile duct stone, so that the direct and indirect manifestations of the stone on the image are comprehensively reflected and analyzed to reflect and analyze the condition and position of the liver and bile duct stone, the accuracy and adaptability of liver and bile duct stone positioning analysis are improved, the reliability of the doctor's reference is ensured, and the treatment and reference of the doctor are indirectly helped.

This invention discloses an intelligent identification method for hepatobiliary and renal stones based on ultrasound images, belonging to the field of stone identification technology. The method includes the following steps: acquiring an ultrasound image to be detected and marking it as a real-time detection image; obtaining real-time detection grayscale values ​​based on the real-time detection image; obtaining organ grayscale thresholds based on ultrasound images in a database; obtaining real-time organ regions based on the real-time detection grayscale values ​​and organ grayscale thresholds; constructing real-time stone detection values ​​based on the real-time organ regions; obtaining historical normal boundary values ​​based on ultrasound images in a database; obtaining stone boundary thresholds based on the historical normal boundary values; and determining whether gallstones are present based on the real-time stone detection values ​​and stone boundary thresholds. This invention addresses the problem that existing stone identification technologies suffer from poor accuracy due to significant noise in ultrasound images.

This invention discloses a minimally invasive surgical planning method and system based on image navigation, belonging to the field of medical information technology. Specifically, it includes: acquiring a three-dimensional model of the patient through CT scanning; performing structural analysis on the three-dimensional model and dividing the organ region into meshes; calculating the grayscale differences between meshes; identifying lesion meshes; calculating the shortest distance from any in vitro candidate point to the geometric center of the lesion region based on the three-dimensional coordinates of the skin region and the lesion mesh; calculating the optimal score of any in vitro candidate point based on the three-dimensional Euclidean distance; selecting the optimal puncture point; and generating an in vivo and in vitro candidate point set through orthogonal projection and vertical extension. This process is repeated until any puncture point reaches the lesion region. Finally, all puncture points are connected to obtain the final puncture path. This invention automatically obtains the optimal ablation path through iterative optimization, improving the efficiency of liver tumor ablation.

This application proposes a three-dimensional organ image segmentation method, apparatus, and computer device. It extracts features from three-dimensional organ images to obtain multiple three-dimensional organ feature maps at different scales. The application proposes to calibrate the feature maps at corresponding scales using spatial and semantic correlation information between features at different levels, thereby enhancing the representation of target objects in contexts at different scales. Specifically, three-dimensional organ feature maps at different scales can be input, and an organ feature calibration model trained based on spatial and semantic attention mechanisms can be used. This model utilizes more complete and accurate spatial detail information and target semantic information to accurately and completely identify the edges and categories of target objects in the three-dimensional feature maps. Based on this, the three-dimensional organ image is segmented, greatly improving the organ region segmentation effect, i.e., accurately identifying target objects of different sizes contained in the three-dimensional organ image, such as tumors of different sizes.

The present invention discloses a method for multi-organ segmentation of abdominal CT images based on deep learning. The method is specifically implemented as follows: (1) constructing a training dataset containing abdominal CT images and their corresponding multi-organ segmentation results; (2) designing a segmentation network based on a dual self-attention mechanism and multi-scale feature fusion; (3) constructing a network loss function by combining Dice loss and Focal loss; (4) training the network using the training dataset; and (5) using the trained network to segment the various organ regions in the abdominal CT images. By adopting the dual attention and multi-scale feature fusion mechanisms, the present invention can establish long-range dependencies in a more targeted manner while introducing a very small number of parameters and floating-point calculations, thereby solving the problem of low segmentation accuracy of irregularly shaped long organs.

The invention relates to the field of data enhancement, in particular to a data enhancement system and method for small sample medical image annotation, and the system comprises the steps: setting a lesion analysis module, a data processing module, an annotation interference module and a data enhancement module, determining a plurality of illness state affected organs, carrying out the lesion analysis, calculating a lesion occurrence characterization value, and determining a lesion analysis organ. Determining a texture discrete characterization value and an organ covering characterization value, determining an organ adhesion area based on the texture discrete characterization value, analyzing the edge texture trend of the organ adhesion area to obtain a reference path band so as to determine an interference organ area, calculating a labeling interference coefficient, and calling a data enhancement model to obtain an enhanced organ area, and completing labeling of the medical image picture of the enhanced organ region. According to the method, for the organs which may have lesions, the adhesion areas are divided, the interfering organ areas are determined, the data enhancement model is called according to the annotation interference coefficient, data annotation is completed, and the accuracy and efficiency of data annotation are improved.

The invention discloses a minimally invasive surgery planning method and system based on image navigation, and belongs to the technical field of medical information. The method specifically comprises the steps that a three-dimensional model of a patient is obtained through CT scanning; performing structure analysis on the three-dimensional model, performing grid division on the organ region, calculating gray value difference among grids, identifying a lesion grid, calculating the shortest distance from the three-dimensional distance from any in-vitro candidate point to the dangerous region to the geometric center of the lesion region according to the three-dimensional coordinates of the skin region and the lesion grid, and calculating the three-dimensional distance from any in-vitro candidate point to the dangerous region; and calculating an optimal score of any in-vitro candidate point based on the three-dimensional Euclidean distance, selecting an optimal puncture point, generating an in-vivo and in-vitro candidate point set through orthogonal projection and vertical extension, repeating the process until any puncture point reaches the lesion area, connecting all puncture points to obtain a final puncture path, and completing the in-vivo and in-vitro candidate point set. The optimal ablation path is automatically obtained through repeated iterative optimization, and the liver tumor ablation efficiency is improved.

Disclosed is a system for improving visibility of a lesion, the system including: a visibility v improvement device configured to implement a function of improving the visibility of the lesion contained in a medical image, the function including: segmenting an organ region of interest and a surrounding region by inputting the medical image to a deep learning model trained in advance, generating rendering images suitable for improving the visibility of the organ region of interest and the surrounding region, respectively, and generating a readable image by merging the rendering image of the organ region of interest and the rendering image of the surrounding region.

The application discloses a kind of progressive medical image cross-modal generation method and device of certainty guidance based on deep learning, comprising: obtaining real CT image and real MR image photographed to same part and constructing sample data, with CycleGAN as benchmark, by increasing multiscale MR organ region discriminator and / or multiscale MR lesion region discriminator, form cross-modal generation framework;When constructing loss function, increase the adversarial loss function based on MR organ region and / or the adversarial loss function based on MR lesion region, form the total loss function of cross-modal generation framework;Utilize total loss function to optimize the parameter of cross-modal generation framework, so that the progressive adversarial generation network of single discriminator to multiple different complexity discriminators is used, with the purpose of certainty guidance, focus on organ region and / or target region such as lesion region, generate higher quality image.

The application discloses a kind of medical image segmentation methods and systems for abdominal CT image, it is related to medical image processing technical field, including: obtaining three-dimensional CT body data, is divided into training dataset and inference dataset;Training data set is input into segmentation model and is trained, and the segmentation model after training is obtained;Inference data set is input into the segmentation model after training, executes segmentation step and obtains class probability graph, class label graph is obtained by processing class probability graph, finally obtains three-dimensional segmentation body;Three-dimensional segmentation body is post-processed using connected domain post-processing rule, and finally multi-class segmentation result is obtained.The application adopts the above-mentioned medical image segmentation method and system for abdominal CT image, through the joint design of training stage, inference stage and post-processing stage, improve the segmentation precision and output stability of complex boundary region, small organ region and target organ overall structure.

The application discloses a kind of space-time puncture path planning system and method based on linear constraint, it is related to puncture path optimization technical field.The method collects CT image data of patient chest and abdomen under different respiratory phase, constructs displacement vector field and organ movement heat map based on CT image data;Based on preset skin needle entry point, tumor target and organ movement heat map, determine candidate intermediate point in chest and abdominal organ region, and generate key point set;Based on the connection rule, the skin needle entry point in the key point set, candidate intermediate point and tumor target are connected to form at least one path edge;According to organ movement heat map, the comprehensive weight of path edge is calculated, and the weighted directed graph is constructed;Path search is carried out in the weighted directed graph, and candidate path set is generated;According to the cost of each candidate path calculated according to the comprehensive weight, the final puncture path is selected, which improves the intraoperative puncture precision and reduces the risk of complications.

The invention is entitled "Augmenting visualization of organ electrical activity." The invention discloses methods, apparatuses, and systems for medical procedures, and the method includes sensing, by one or more electrodes on a catheter, a plurality of tissue potentials at an organ region of an organ, determining, from the plurality of first tissue potentials, a number of peak potentials such that the peak potentials exceed a potential threshold, determining, based on the number of peak potentials, a first visual characteristic, and displaying a rendering of the organ including the organ region such that the rendering of the first organ region includes the first visual characteristic.

To efficiently diagnose a tubular organ by referring to an image.SOLUTION: An image processing system comprises an image acquisition part, a region extraction part, and a display control part. The image acquisition part acquires an input image being a three-dimensional image obtained by imaging a tubular organ. The region extraction part extracts an organ region being a region expressing the tubular organ in the input image. The display control part superimposes and displays an organ image expressing the organ region and a direction designation image showing a direction from a predetermined position on the organ region toward an end point along the path of the organ region, on a display device.SELECTED DRAWING: Figure 5

The invention discloses a data processing method applied to radiotherapy and a related device. The method comprises the following steps: acquiring a plurality of two-dimensional images corresponding to an object to be subjected to radiotherapy; in response to an organ selection operation of an operator, displaying a three-dimensional organ region corresponding to the selected organ on the three-dimensional sketching interface; in response to a three-dimensional sketching operation of an operator on the three-dimensional sketching interface, determining a three-dimensional sketching area corresponding to the three-dimensional sketching operation in the three-dimensional organ area; and based on the plurality of two-dimensional images and the three-dimensional delineation areas, determining the three-dimensional delineation areas and a plurality of two-dimensional delineation areas in one-to-one correspondence with the plurality of two-dimensional images, the plurality of two-dimensional delineation areas being used for performing radiotherapy on the object to be subjected to radiotherapy. According to the method, an operator is enabled to perform three-dimensional sketching on the three-dimensional organ region, then the three-dimensional sketching region corresponding to the three-dimensional sketching is inversely analyzed into the plurality of two-dimensional images, and the plurality of two-dimensional sketching regions can be obtained through one-time three-dimensional sketching, so that the sketching efficiency is improved on the premise of ensuring the sketching accuracy.

The present application relates to the technical field of puncture path planning, in particular to a puncture path planning method for severe acute pancreatitis abdominal puncture drainage. First, a three-dimensional model of the abdominal cavity is constructed by fusing CT images and MRI images and tissue regions (organ regions, blood vessel regions, lesion regions) are segmented, and candidate paths are generated based on target positions and preset body surface entry points. Then, risk coefficients are calculated based on the geometric characteristics (angle, length, and proximity to tissue regions) of the candidate paths, and the preliminary optimal paths are screened. Further, the puncture body position and the direction of the gravity component are determined in combination with the sagittal / coronal position relationship, the tissue density distribution is analyzed, and the tissue deformation interference index is quantified. Finally, the risk coefficients and the deformation index are fused to realize the re-screening of the paths, determine the optimal and alternative paths, so as to effectively avoid key tissue structures and reduce the risk of intraoperative displacement, and improve the puncture accuracy and stability.

The invention relates to the technical field of AR glasses assisted doctor surgery, and discloses a doctor assisted operation system and method based on AR glasses, and the system comprises an image collection module, an image processing module, a path planning module, and an AR glasses display module. Real-time images of a patient are obtained through CT equipment and the like, comprehensive body information is provided for doctors, the images are processed through gray and color features, and blood vessel and visceral organ areas are accurately recognized; a safe operation range is delimited by means of safe area analysis, and the operation injury risk is reduced; and the AR glasses display information required by the surgery in real time in a visual and visual manner, so that a doctor is helped to operate more accurately. Meanwhile, the position of the surgical instrument is tracked in real time, the distance between the surgical instrument and a dangerous area is monitored through an Euclidean distance algorithm, and an alarm is given once the distance is too close to avoid mistaken touch; and through effective training of the support vector machine classifier, the reliability of image recognition is further guaranteed. And the safety and the accuracy of the operation are greatly improved.

The invention relates to the technical field of fish detection, in particular to an automatic evaluation method for a fish liver fat deposition state based on image segmentation and color feature analysis, and the method comprises the following steps: obtaining an image; segmenting organs; feature extraction: extracting an organ image based on the segmentation mask of the organ region, converting the organ image into an HSV color space, calculating color moment features of each channel of H, S and V, the color moment at least including a first moment, a second moment and a third moment; and fat deposition determination: inputting the color moment characteristics into a classification model to obtain a fat deposition state evaluation result of the liver, and the method can automatically identify a target organ region in an anatomical image and perform objective and quantitative evaluation on the fat deposition state of the liver based on the color characteristics with clear physical significance. By constructing an image processing flow consisting of organ segmentation, color feature extraction and classification judgment, the method can realize efficient, standardized and interpretable automatic evaluation of the fish liver fat deposition state.

The application discloses an organ segmentation modeling method and terminal based on medical images, receives inputted continuous medical images, obtains a first image containing a target organ from the continuous medical images, receives positive and negative control points marked on the first image, identifies the target organ on the first image according to the marking result, continuously tracks the organ in the continuous sequence images in the section based on the identified organ region, and further completes automatic identification of the whole organ, generates a three-dimensional model of the organ based on the original section continuous images, establishes at least two other section continuous medical images according to the inputted continuous medical images, and identifies and models the organ in the other section continuous medical images. Finally, the three-dimensional segmentation model of the target organ is obtained by calibrating all the section models, and accurate organ segmentation results are ensured.

The invention discloses a space-time puncture path planning system and method based on linear constraint, and relates to the technical field of puncture path optimization. The method comprises the following steps: acquiring CT image data of the chest and abdomen of a patient under different breathing phases, and constructing a displacement vector field and an organ movement heat map based on the CT image data; determining candidate intermediate points in the thoracic and abdominal organ region based on a preset skin needle insertion point, a tumor target point and an organ movement heat map, and generating a key point set; on the basis of a preset connection rule, the skin needle inserting points, the candidate intermediate points and the tumor target points in the key point set are connected to form at least one path edge; calculating the comprehensive weight of the path edge according to the organ movement heat map, and constructing a weighted directed graph; performing path search in the weighted directed graph to generate a candidate path set; the cost of each candidate path is calculated according to the comprehensive weight, the final puncture path is selected, the intraoperative puncture precision is improved, and the complication risk is reduced.

A data processing method applied to radiotherapy, and a related apparatus. The method comprises: acquiring a plurality of two-dimensional images corresponding to an object to be subjected to radiotherapy; in response to an organ selection operation of an operator, displaying, on a three-dimensional delineation interface, a three-dimensional organ region corresponding to a selected organ; in response to a three-dimensional delineation operation of the operator on the three-dimensional delineation interface, determining a three-dimensional delineation region in the three-dimensional organ region which corresponds to the three-dimensional delineation operation; and on the basis of the plurality of two-dimensional images and the three-dimensional delineation region, determining a plurality of two-dimensional delineation regions of the three-dimensional delineation region which correspond to the plurality of two-dimensional images on a one-to-one basis, wherein the plurality of two-dimensional delineation regions are used for performing radiotherapy on said object. By means of the method, an operator first performs three-dimensional delineation on a three-dimensional organ region, and then inversely parses onto a plurality of two-dimensional images a three-dimensional delineation region corresponding to the three-dimensional delineation, and thus a plurality of two-dimensional delineation regions can be obtained by means of one instance of three-dimensional delineation, thereby improving the efficiency of delineation while ensuring the accuracy of delineation.

The present application relates to the technical field of image processing, and particularly relates to an automatic positioning method and device based on head clinical image, which performs coordinate transformation on the head anatomical structure of CVH according to spatial direction mapping relationship and spatial size mapping relationship, and obtains CVH registration head anatomical structure; the CVH registration head anatomical structure and the position mark and organ name of each organ region in the CVH registration head anatomical structure constitute a new CVH anatomical knowledge graph. The patient head clinical image is subjected to multi-planar reconstruction, and the patient head anatomical structure is obtained; there is a real-time mapping relationship between the patient head anatomical structure and the CVH registration head anatomical structure, so that the position mark and organ name of each organ region in the patient head anatomical structure and the CVH registration head anatomical structure have a one-to-one correspondence. The interested region is selected from the anatomical knowledge graph, and the corresponding position of the interested region in the patient head anatomical structure is automatically positioned, so that the recognition difficulty of the patient head clinical image is reduced.