29 results about "Maximum intensity projection" patented technology

The invention discloses an intracranial aneurysm rupture risk assessment method, device and equipment and a storage medium, and the method comprises the steps: firstly, generating a time sequence image containing flow field information based on the maximum density projection and center line extraction processing of a two-dimensional angiography image sequence in combination with contrast agent concentration change curve analysis; performing three-dimensional reconstruction, region-of-interest extraction and opening extension processing by using the three-dimensional image sequence to obtain detailed morphological parameters and a region-of-interest model after extension processing; secondly, displaying a time sequence image with flow field information and a region-of-interest model of which an opening is not prolonged in an overlapping manner, further optimizing setting of boundary conditions and performing hydrodynamic simulation by calculating a flow field vector in an observation ball and determining an actual blood flow direction, and calculating key hemodynamic parameters; and finally, in combination with the morphological parameters, the hemodynamic parameters and clinical information of the patient, obtaining an evaluation result of the aneurysm rupture risk.

The invention discloses a sparse view angle 3D-DSA reconstruction method based on a three-dimensional Poisson generative model. The method comprises the following steps: obtaining pairing data of a sparse view angle 2D-DSA projection drawing and a 3D-DSA reconstruction image; extracting features of a projection image by using a projection domain encoder, then converting features of two-dimensional projection into a three-dimensional image domain according to a geometrical relationship of the cone beam CT, and then obtaining a prior image by using an image decoder; the method comprises the following steps: constructing a three-dimensional Poisson generation model, adding noise to a three-dimensional image patch in a training stage to obtain a disturbance image, outputting a network reconstruction image by taking a prior image as a condition and the three-dimensional image patch before noise addition as a target image, and calculating loss of the output image and the target image to update network parameters; the mean square error loss and the mean square error loss of the maximum intensity projection images of the three orthogonal planes are used during loss calculation; in the sampling stage, random noise is used as input, a prior image is used as a condition, noise of a noise image is continuously denoised within a limited step length, and finally a reconstructed 3D-DSA image is obtained.

Systems and methods for delineating tumour boundaries using a three-dimensional (3D) image stack, such as photoacoustic image slices, comprising a plurality of images. Multiple maximum intensity projections (MIPs) are derived from the stack, and level set segmentation is performed on those MIPs, to derive a boundary that bounds a region of interest (i.e., a tumour boundary). Structural and functional information is then derived for the region of interest, to analyse the tumour tissue.

It is disclosed a method processing imaging data of a patient having cancer, for instance lymphoma, comprising:—Providing three-dimensional imaging data of the patient,—computing from said three-dimensional imaging data, at least one two-dimensional Maximum Intensity Projection image. corresponding to the projection of the maximum intensity of the three-dimensional imaging data along one direction onto one plane,—extracting a mask of the MIP image corresponding to cancerous lesions by application of a trained model. Using the extracted mask it is possible to compute one or more cancer prognosis indicators.

The invention discloses an image processing method and system based on an in-situ hybridization technology and a medium, and relates to the technical field of biological information, and the method comprises the following steps: converting a cell DAPI dyeing result into two-dimensional data from three-dimensional data by utilizing Z-axis maximum intensity projection, identifying and separating a single cell from the two-dimensional data by utilizing cell segmentation, and when the cell segmentation is used for processing an overlapping region, identifying and separating the single cell from the two-dimensional data. Using a registration algorithm Ashlar to calculate an error between adjacent visual fields of the same round to obtain cell position information; an imaging result after hybridization of the fluorescent probe and the gene is subjected to multiple rounds of registration through a registration algorithm Ashlar to generate a spliced image, local maximum values of the spliced image under different rounds are marked by using a fluorescent dot recognition algorithm, so that position information of each fluorescent dot is obtained, the position information of each fluorescent dot corresponds to the gene in a transcript, and the position information of each fluorescent dot corresponds to the gene in the transcript. Obtaining gene position information; distributing genes into cells by utilizing the cell position information and the gene position information to obtain a cell gene matrix and displaying the cell gene matrix; according to the image processing method and system and the medium, accurate matching of sequencing data and spatial information is achieved, and then the distribution rule of gene expression in space is better revealed.

The present disclosure provides an intracranial artery stenosis detection method and system. The present disclosure obtains artery stenosis detection results based on a first maximum intensity projection (MIP) image and a second MIP image obtained by preprocessing a medical image by adopting a detection model based on an adaptive triplet attention module and generates an auxiliary report and visualization results according to target category information in the artery stenosis detection results. Therefore, the problem that existing manual interpretation methods are easily affected by the subjective experience of doctors and are time-consuming and laborious can be solved, thus improving accuracy and efficiency of intracranial artery stenosis detection. Moreover, by inserting the adaptive triplet attention module into a backbone network of YOLOv4, the present disclosure can realize focus on key regions of high-dimensional features, reduce focus on irrelevant features, and provide characterization ability of the detection model.

The invention relates to the technical field of image fusion processing, and discloses a multi-source fundus lesion image characteristic-based image collaborative fusion processing method, which comprises the following steps of: performing scale normalization processing on a color fundus image and tomography data through resampling to obtain a standard color fundus image and standard tomography data; the method comprises the following steps: respectively fitting an inner boundary membrane curved surface for standard tomography data, expanding to a plane, performing maximum intensity projection according to a preset layer thickness range, and generating a two-dimensional structure layer image; extracting a normalized gray matrix of the standard color fundus image, combining the normalized gray matrix with the normalized two-dimensional structure layer image, and constructing a quaternion matrix containing color and structure information; performing pyramid decomposition on the quaternion matrix to obtain a pyramid high-frequency layer and a pyramid low-frequency layer; and determining the focus energy weight based on the gradient significance of the standard color fundus image and the standard tomography data and the local energy of the high-frequency layer and the low-frequency layer of the pyramid.

A cerebrovascular disease learning apparatus may be provided. The cerebrovascular disease learning apparatus may include a maximum intensity projection magnetic resonance angiography (MIP MRA) configuration unit configured to receive 3D time-of-flight magnetic resonance angiography (3D TOF MRA) and to construct MIP MRA including a plurality of image frames, a space characteristic learning unit configured to construct a space characteristic learning model, a frame characteristic learning unit configured to receive the space characteristics and to construct a frame characteristic learning model based on a recurrent neural network (RNN) learning method, and a lesion characteristic learning unit configured to receive the frame characteristics and to construct a lesion characteristic learning model based on the CNN learning method.

The present disclosure is related to systems and methods for image processing. The method includes obtaining an original image. The original image includes at least one blood vessel region and at least one scalp region. The method includes determining an intermediate image by removing the at least one scalp region from the original image. The method includes generating at least one target image by performing a maximum intensity projection operation on the intermediate image. The at least one target image represents the at least one blood vessel region in the original image.

The invention provides a whole body PET image-based blood input function automatic extraction method and system. The method comprises the following steps: S1, obtaining a maximum intensity projection image of a sagittal plane of an upper body of a patient; s2, performing cardiovascular typical image layer positioning based on the maximum-intensity projection image of the sagittal plane of the upper body to obtain a plurality of cardiovascular typical layer images; s3, descending aorta positioning based on K-means clustering is carried out on the multiple cardiovascular typical layer images, and a descending aorta area selection result is obtained; and S4, extracting a blood input function based on a descending aorta region selection result. According to the method, full-automatic descending aorta blood signal, namely blood input function extraction is achieved, the parameter analysis and imaging efficiency is effectively improved, and more efficient and accurate dynamic PET pharmacokinetic analysis is helped to be achieved.

The present invention discloses a classification method for identifying intracranial large vessel occlusion based on bilateral contrast difference information, which mainly relates to the technical field of medical image classification. The method comprises the following steps: S1, collecting data images and performing maximum density projection operation to convert the original image format data into image format data; S2, preprocessing the image; S3, sending the left hemisphere image and the right hemisphere image into the main network respectively to extract the image features FM of the corresponding hemisphere. left ,FM r‑flip ; S4, the FM obtained left ,FM r‑flip Send it to the symmetric information processing module to obtain the classification loss #imgabs0#S5, and the obtained FM left ,FM r‑flip The deep supervision module is sent to obtain the contrast loss #imgabs1#S6, and the model is updated using #imgabs2# and #imgabs3# until the effect converges. The present invention can solve the problem of poor automatic identification effect of the responsible blood vessels for intracranial large blood vessel blockage in the existing system.

The method and device for introducing distribution and region constraints and enhancing blood vessel structure can obtain real information of liver blood vessels simply and quickly, assist doctors in preoperative planning, are favorable for expanding the use range of liver blood vessel data, and increase the flexibility of use. The method comprises the following steps: (1) obtaining three-dimensional image data, manually sketching the liver boundary to obtain a corresponding liver mask; (2) pre-processing the image based on liver labeling; (3) estimating the tissue distribution in the liver by using a Gaussian mixture model; (4) introducing distribution and region constraints, and calculating the liver blood vessel enhancement value under single-scale Gaussian filtering; and (5) calculating all scales, using maximum density projection on the image of each scale to obtain a liver blood vessel enhancement image.

The invention discloses a millimeter wave radar enhanced point cloud-based human body action recognition method, which comprises the following steps of: firstly, processing a radar echo signal through frame difference processing, 2D-FFT and a secondary density clustering algorithm, and enhancing the quality of a three-dimensional point cloud; then, organizing continuous seven frames of point clouds into a time sequence sample at a sliding step length of 2, independently performing voxelization processing on each frame of point clouds, performing maximum intensity projection frame by frame along the Y axis and the X axis, and generating a double-view projection image sequence of XOZ and YOZ planes; and finally, inputting the double-view-angle image sequence into an improved DVP-TransNet network which adopts double-branch ResNet50 to perform feature extraction, adaptively fusing double-view-angle features through a trainable weight module, and capturing time sequence dynamic features by using a Transformer encoder to finally realize high-precision classification of human body actions. According to the method, the action recognition accuracy rate up to 99.67% is achieved in a complex environment.

The embodiment of the invention provides a large-scale three-dimensional image data video generation method and device, and the method comprises the steps: determining a high-complexity region in a to-be-processed image according to a plurality of to-be-processed images and the entropy values or gradient intensities of the to-be-processed images, receiving a preset space region parameter or a preset volume feature parameter, and obtaining a large-scale three-dimensional image data video. Adjusting spatial region parameters or preset volume characteristic parameters, dynamically segmenting each to-be-processed image to obtain a plurality of to-be-processed data blocks corresponding to the to-be-processed image, extracting maximum intensity information included in each voxel in each rendering frame according to a maximum intensity projection algorithm, and combining the maximum intensity information into a single video frame corresponding to each to-be-processed image, according to the technical scheme, the three-dimensional space relation among the multiple to-be-processed images is determined, the video frames are spliced according to the three-dimensional space relation, error minimization is carried out on the spliced video frames, the three-dimensional video of the object is obtained, the clearer and more accurate three-dimensional video can be obtained, and the visual effect and the generation efficiency of the three-dimensional video are improved.

The present invention discloses a method for segmenting the bone structure of knee MRI based on 2D-3D feature fusion. The present invention first calculates the maximum intensity projection image (MIP) of the sagittal direction of MR data, thereby constructing a high-precision convolutional encoding and decoding neural network architecture for automatic segmentation of the knee joint: 1) a 2D bypass network for extracting global features based on MIP; 2) a 3D backbone network for extracting local detail features based on MR, and 3) a feature fusion module for 2D global information and 3D local detail information. In particular, the global feature, as position information, will be fused with the local detail network at each resolution of the encoding path to increase the contextual information of the local network and improve the segmentation accuracy. This method has been verified on a public data set, and the average dice similarity coefficients of the femur, femoral cartilage, tibia, and tibial cartilage are as high as 97.78%, 84.83%, 97.93%, and 84.80%, respectively, and the segmentation performance is significantly better than other methods.

The present application discloses a method, device, terminal and storage medium for establishing a large vessel occlusion recognition model. The method includes the following steps: obtaining a standard CT image of the brain and performing angiography to obtain angiography image sets of multiple stages respectively; preprocessing the angiography image sets of multiple stages, and then performing vascular segmentation processing to generate two-dimensional maximum intensity projection images of multiple stages; creating a training set combination to obtain multiple groups of model training sets and performing deep learning model training one by one to obtain multiple deep learning models; selecting a deep learning model with the best evaluation result as a large vessel occlusion recognition model. The present application greatly improves the diagnostic detection rate of LVO, not only optimizing the workflow of radiologists in detecting LVO, but also screening out patients who meet the conditions for thrombectomy.

Disclosed herein is an image reconstruction system for outputting a three-dimensional (3D) synthesized image from a two-dimensional (2D) X-ray image based on artificial intelligence, the image reconstruction system including: an artificial intelligence learning unit configured such that a correct answer 3D image in which bones are segmented and extracted is generated from a sample 3D computed tomography (CT) image, a sample 2D image is generated from the correct answer 3D image, a sample 3D synthesized image is generated from the 2D image, and an artificial intelligence learning model is constructed as the generated sample 3D synthesized image is learned; a Maximum Intensity Projection (MIP) image conversion unit configured such that a target 2D MIP image is generated; and a final 3D synthesized image output unit configured such that the target 2D MIP image is input to the learning model, and thus, a final 3D synthesized image is output.

The present invention relates to a method and system for evaluating the efficacy of tumors based on medical images. The method includes: acquiring first PET-CT images and second PET-CT images of a hematological tumor patient before and after treatment, and determining lesion change information of the lesion area based on the first PET-CT images and the second PET-CT images; performing maximum intensity projection on the first PET-CT images and / or the second PET-CT images along different directions to generate maximum intensity projection images from multiple perspectives; determining global image information of the lesion area based on the maximum intensity projection images from multiple perspectives; determining a Deauville score corresponding to the efficacy of the tumor patient based on the global image information; and fusing the lesion change information and the Deauville score to generate tumor efficacy evaluation information.

The present application relates to a method, apparatus, device, and medium for processing digital breast tomosynthesis images. The method includes: generating tomographic images based on projection images at different scanning angles; obtaining respective fused images according to the maximum intensity projection imaging of each tomographic image and the projection images at a target angle in each projection image; and superimposing the respective fused images in the generation order of each tomographic image to obtain a fused time-sequence image. Using this method can improve the efficiency of film reading.

The invention provides a deep learning-based opto-acoustic microscopic imaging noise reduction method and system. The method comprises the following steps of: 1, performing block preprocessing on input original opto-acoustic microscopic imaging volume data; step 2, constructing and training a noise reduction network, namely, a 3D U-Net network with spatial structure sensing capability, and after the noise reduction network is trained, inputting the preprocessed sub-blocks to be subjected to noise reduction and outputting a noise reduction result; and step 3, inputting a noise reduction result into a data fusion projection layer, carrying out weighted splicing and boundary fusion on all noise reduction sub-blocks, carrying out maximum intensity projection along the depth direction, generating a final high-quality photoacoustic microscopic image, and completing end-to-end noise reduction of the photoacoustic microscopic image based on deep learning. The system is used for implementing the method.

The invention provides a brain magnetic resonance angiography report generation method and device, and the method comprises the steps: obtaining a brain magnetic resonance angiography (MRA) image of a patient; performing image preprocessing on the brain MRA image to obtain a center MRA image and a plurality of maximum density projection MIP images corresponding to the brain MRA image; respectively inputting the central MRA image and the plurality of MIP images into a pre-trained visual language model to obtain a first target image semantic feature corresponding to the central MRA image and a second target image semantic feature corresponding to the plurality of MIP images output by the visual language model; and inputting the first target image semantic feature and the second target image semantic feature into a pre-trained large language model to obtain a prediction structured report for the brain of the patient.

The invention belongs to the field of image processing, and relates to an image generation method and device, equipment and a medium, and the method comprises the steps: obtaining three-dimensional image data, constructing a target grid according to a cutting direction, dividing the three-dimensional image data into a plurality of data blocks, calculating the maximum density value of all voxels in each data block, and calculating the maximum density value of all voxels in each data block; according to the method, the maximum density values of all complete data blocks in a target volume of three-dimensional image data are determined, then boundary slices of the target volume in the projection direction are identified, the maximum density values of all the boundary slices are obtained, then the global maximum density value of the target volume is determined, and finally a maximum density projection image is generated according to the global maximum density value. According to the invention, the generation efficiency of the maximum-density projection image can be improved.

The present invention discloses a method, device, equipment and storage medium for intracranial aneurysm rupture risk assessment. First, based on the maximum intensity projection and centerline extraction processing of a two-dimensional angiographic image sequence, and combined with the analysis of the contrast agent concentration change curve, a time series image containing flow field information is generated; then, three-dimensional reconstruction, region of interest extraction and opening extension processing are performed on the three-dimensional image sequence to obtain detailed morphological parameters and a region of interest model after extension processing; then, the time series image with flow field information is overlapped and displayed with the region of interest model without extended opening, and by calculating the flow field vector sum in the observation sphere to determine the actual blood flow direction, the setting of boundary conditions is further optimized and fluid dynamics simulation is carried out to calculate the key hemodynamic parameters; finally, combining the morphological parameters, hemodynamic parameters and the patient's clinical information, the assessment result of the aneurysm rupture risk is obtained.

The present invention relates to a method for automatically generating registration parameters for interactive 2D and 3D medical images, which solves the defects of poor search accuracy and low search efficiency of initial registration parameters compared with the prior art. The present invention includes the following steps: loading three-dimensional image data; implementing three-dimensional model rendering and reconstruction on a window, performing two-dimensional mapping on the three-dimensional model, and aligning and displaying the image after real-time mapping with the X-ray image to be registered; loading the two-dimensional image to be registered and drawing it on the window in the form of a two-dimensional texture; dragging the mouse to align the three-dimensional model with the two-dimensional image to obtain appropriate registration parameters. The present invention comprehensively considers the difference in the image quality of the three-dimensional volume data drawn on the window after maximum intensity projection and the image quality of the X-ray image to be registered, can complete the alignment of the two images with high quality, can obtain a set of appropriate initial registration parameters and print and output them on the console.

To correct a metal artifact.SOLUTION: The metal artifact correction includes projecting X-rays to scan a volumetric region of an object, the projecting generating corresponding cone beam computed tomography (CBCT) image data, reconstructing from the CBCT image data an extended CBCT volume representing the volumetric region and a volume outside the volumetric region, generating from the extended CBCT volume and a projection geometry a maximum intensity projection on a virtual plane, detecting attenuation image areas in the maximum intensity projection corresponding to metal, matching the detected attenuation image areas corresponding to metal to the CBCT image data, and reconstructing a final CBCT volume using the CBCT image data by suppression of areas of the CBCT image data corresponding to the detected attenuation image areas of the maximum intensity projection.SELECTED DRAWING: Figure 1

The application provides a blood input function automatic extraction method and system based on whole-body PET images, and the method comprises the following steps: S1, acquiring a maximum intensity projection image of the upper body of a patient in a sagittal plane; S2, positioning a typical cardiovascular image layer based on the maximum intensity projection image of the upper body in the sagittal plane to obtain a plurality of typical cardiovascular layer images; S3, positioning a descending aorta based on K-means clustering for the plurality of typical cardiovascular layer images to obtain a descending aorta region selection result; and S4, extracting a blood input function based on the descending aorta region selection result. The application realizes automatic extraction of blood signals in the descending aorta, i.e. blood input functions, effectively improves the efficiency of parameter analysis and imaging, and helps to realize more efficient and accurate dynamic PET pharmacokinetic analysis.

The embodiment of the invention provides a maximum intensity projection image generation method and related equipment. The maximum intensity projection image generation method comprises the following steps: preprocessing original three-dimensional medical image data to obtain enhanced three-dimensional medical image data; processing the enhanced three-dimensional medical image data by using a preset segmentation model to generate a preliminary cerebrovascular mask; on the basis of the preliminary cerebrovascular mask, identifying a blood vessel seed point for growth repair to obtain three-dimensional blood vessel image data; based on the three-dimensional blood vessel image data, multi-angle projection positioning lines are automatically calculated, and a maximum-intensity projection image is generated. According to the technical scheme, manual intervention is not needed in the whole cerebral vessel MIP generation process, and the generation result is superior to a traditional manual process in the aspects of blood vessel continuity, image contrast and view angle consistency.

The present invention relates to a computed tomography perfusion (CTP)-based venous output function (VOF) detection method and system, and the CTP-based VOF detection method performed by the CTP-based VOF detection system, according to the present invention, comprises: removing bias noise from a contrast agent concentration graph in a brain region of a CTP image; excluding a graph that has a peak earlier than the peak time of an arterial input function (AIF) and aligning, to the same position as the peak of the AIF, peak values of remaining graphs; calculating a Pearson correlation coefficient with the AIF so as to select a graph having a Pearson correlation coefficient greater than or equal to a predefined threshold; generating a mask on the basis of a peak value range of a VOF candidate group selected from the selected graphs, so as to extract a final VOF graph; generating a maximum intensity projection (MIP) from the CTP image and extracting a blood vessel image; and checking a veinous positions through an operation between the mask and the VOF candidate group so as to select, as a final VOF, the VOF candidate closest to a center relative to the midline.

Metal artifact correction including projecting x-rays to scan a volumetric region of an object, the projecting generates corresponding cone beam computed tomography (CBCT) image data, reconstructing an enlarged CBCT volume from the CBCT image data, the enlarged CBCT volume representative of the volumetric region and a volume outside the volumetric region, generating from the enlarged CBCT volume and a projection geometry, maximum intensity projections on a virtual plane, detecting attenuated image areas in the maximum intensity projections corresponding to metal, corresponding the detected attenuated image areas corresponding to the metal to areas of the CBCT image data, and reconstructing a final CBCT volume using the CBCT image data by suppression of the areas of the CBCT image data corresponding to the detected attenuated image areas of the maximum intensity projections. Systems for metal artifact correction are also disclosed.