263 results about "Tomographic image" patented technology

The invention discloses a tunnel cross-sectional image analysis method based on image processing, and aims to solve the problems that a surface image is not clear in correspondence with a transient seismic wave method, a geological radar and a resistivity imaging section space, and anomalies at a certain distance in front are difficult to map to a tunnel face. According to the method, anisotropic reforming is carried out by adopting a Fourier neural operator, cross-modal Transform registration of a micro attention mask based on sector geometry, curve mileage and section polar coordinate position coding is combined, analytic geometry mapping and uncertainty propagation are matched, tunnel face structure traces and water seepage texture evidences are fused, and the tunnel face structure traces and the water seepage texture evidences are combined. The technical effects of accurate positioning of abnormity on the tunnel face, position confidence range estimation, risk grading early warning, stripe artifact suppression, abnormal boundary reservation and output of structured results of mileage stake numbers, azimuth angles, distance intervals and the like are achieved.

The invention discloses a glass-based circuit board defect detection method and system, and relates to the technical field of glass substrate defect detection.The method comprises the steps that an optical coherence tomography system with the fixed scanning resolution of 320 * 320 is used for collecting a tomographic image of a target area, three-dimensional reconstruction is conducted on the tomographic image, and a three-dimensional body data model is obtained; extracting a plurality of three-dimensional morphological characteristics such as defect depth, transverse distribution profile and defect internal refractive index unevenness from the model; and inputting the features into a defect classifier constructed based on a three-dimensional convolutional neural network for identification, and performing spatial position verification in combination with a known design layout to generate a final detection report. According to the method, the standardization of the detection process is realized through the fixed scanning resolution, and the efficiency and the result consistency are improved; by quantifying the refractive index non-uniformity in the defect, the optical property variation type defect in the material is effectively identified, and the detection depth and accuracy are enhanced.

The invention relates to the technical field of image reconstruction, in particular to a compressed sensing driven terahertz tomography reconstruction method based on an adaptive strategy. According to the technical scheme, the method comprises the following steps that a terahertz continuous wave imaging system is used for collecting intensity data P of a corresponding view angle at equal-interval sparse angles, and a sinogram of a sparse sampling view angle is obtained; performing data preprocessing on the intensity data to unify the data scale; relevant parameters of the algorithm are initialized, wherein the relevant parameters comprise step length and regularization parameters; through a core parameter dynamic adjustment mechanism, cooperative improvement of imaging quality, reconstruction efficiency and environmental adaptability is successfully realized, clearer and more accurate terahertz tomographic images can be obtained, reconstruction can be completed at a faster calculation speed, and the method is suitable for wider practical application scenes and has good application prospects. And the comprehensive performance is obviously superior to that of a traditional non-adaptive method.

A method and system for correcting detector defects in an X-ray microscope system based on deep learning. Normal geometry projections and offset geometry projections are collected for a given detector, mappings between defective regions and healthy regions are created, and a machine learning system is trained using these projections. The trained neural network system is then used to correct the tomographic projection dataset, thereby improving the image quality of the resulting reconstructed tomographic image volume set.

The application provides a human transcranial ultrasound irradiation method, device, electronic equipment and storage medium. The target head sagittal plane tomographic image and the transverse plane tomographic image are acquired; a vertical coordinate system is established based on the sagittal plane tomographic image, and the target point coordinates of the insula in the vertical coordinate system are determined; based on the transverse plane tomographic image, the horizontal distance from the insula to the target head brain midline is measured; the world coordinate point of the insula is mapped in the world coordinate system according to the target point coordinates and the horizontal distance; and the ultrasound transducer is controlled to irradiate the real position of the insula, so that accurate targeted irradiation can be realized, the use cost of the low-intensity focused ultrasound technology is effectively reduced, and the operation is simpler.

A medical image processing apparatus includes a catheter including a sensor and insertable into a blood vessel, a display, and a processor configured to: control the catheter to acquire tomographic images of the vessel, input the images into a model and acquire information indicating a condition of a part of the blood vessel, generate a histogram of a plaque area ratio in the vessel, acquire a length of a stent to be placed or a lesion to be treated, calculate a threshold for the ratio using the first histogram and the length, generate a graph indicating the ratio at each part of the blood vessel, and control the display to display the graph and the threshold in an overlapping manner.

The invention provides a textile composite material impact energy absorption simulation method, system and device and a medium, and the method comprises the steps: carrying out the connected domain analysis of a tomography image, and determining the equivalent diameter distribution characteristics of pore defects in a textile composite material; performing stochastic simulation based on the equivalent diameter distribution characteristics in combination with a mesoscopic geometric model of the textile composite material to obtain stochastic pore space distribution of the textile composite material in the resin enrichment area; geometric difference is carried out on the random pore space distribution and the mesoscopic geometric model, and then a mesoscopic finite element model containing pore defects is constructed; and endowing the mesoscopic finite element model with material attributes and carrying out explicit kinetic analysis on impact load, and further determining the impact energy absorption performance of the textile composite material prepared in the batch according to an analysis result. By adopting the scheme of the invention, systematic deviation of impact energy absorption performance prediction caused by model idealization can be reduced.

A system is provided that includes one or more sources used to irradiate one or more solids extracted from a reservoir with an energy source and one or more detectors used to acquire one or more transmission images, wherein the one or more transmission images comprise one or more scans. The system also includes a processing circuitry and a memory, accessible by the processing circuitry, the memory storing instructions that, when executed by the processing circuitry cause the processing circuitry to perform operations. The operations may include collecting one or more scans of the one or more solids moving through an imaging zone, reconstructing one or more tomographic images of the one or more solids based on the one or more scans, and extracting one or more physical properties of the solids based on the one or more tomographic images.

Provided are a radiography system, an image processing device, an image processing method, and an image processing program that prevent an image of a correction marker from being included in a reconstructed region of a tomographic image obtained by reconstructing a plurality of projection images. A radiography system includes a correction marker that is used to obtain a marker image included in at least one of a plurality of projection images obtained by tomosynthesis imaging, is provided in an irradiation path of radiation in a radiation emitting unit, and is disposed at the position where the marker image is included in a region other than a reconstructed region in the projection image, the reconstructed region being a region used in a case in which the tomographic image is reconstructed from the plurality of projection images among the regions included in the plurality of projection images.

The present application belongs to the field of CT tomographic reconstruction technology and artificial intelligence, and discloses a limited-angle CT reconstruction artifact suppression method based on a multi-domain feature fusion network. In view of the problem that the reconstruction result of traditional CT scanning under limited-angle conditions is prone to artifacts and structural distortion, thereby affecting the image quality and defect detection accuracy, the present application constructs a multi-domain feature fusion artifact suppression network, takes the limited-angle reconstruction result as input, and realizes artifact suppression and detail recovery through the synergistic effect of the encoder part, the decoder part, the feature enhancement part and the feature conversion part. The present application can obtain high-quality tomographic images under limited-angle conditions, effectively reduces the scanning angle and time of industrial CT detection, improves the imaging clarity and reliability without increasing the radiation dose, is suitable for industrial detection of complex structure workpieces, and has important industrial application value.

The invention discloses an ultrasonic tomography image enhancement method and device, and the method comprises the steps: taking an ultrasonic B scanning image of a reinforced concrete member, carrying out the labeling according to the cross-section crack condition, generating a cross-section crack image corresponding to the ultrasonic B scanning image, and constructing a data set according to the ultrasonic B scanning image and the cross-section crack image; building a generative adversarial network based on a pixel-to-pixel structure, wherein the generative adversarial network comprises a generator and a discriminator; training the generative adversarial network by using the data set and adopting a game means to obtain an image generation model for generating a virtual ultrasonic B-scan image; and inputting the self-made cross-section crack image into the image generation model to obtain a corresponding virtual ultrasonic B scanning image, and taking the self-made cross-section crack image and the corresponding virtual ultrasonic B scanning image as an enhanced data set for expanding the data collective quantity. The method can solve the problem that automatic nondestructive testing of the concrete structure is inconvenient to apply deep learning subsequently due to small experimental data volume.

An image processing device generates a measurement image in a measurement space that differs from real space, based on measurement data of a subject acquired by a tomography device. The device inputs the measurement image into a CNN, which then generates a tomographic image in real space. The CNN is based on a U-Net structure comprising an encoder unit 21, a decoder unit 22, and a bottleneck unit 23, and further comprising a projection link unit 24. The projection link unit 24 performs projection processing from a sinogram space (the measurement space) to real space on an arbitrary feature map in the encoder unit 21 and, after the projection processing is complete, connects the feature map to the feature map of the same size in the decoder unit 22.In this way, an image processing device is realized that is able to suppress an increase in the amount of data required for training a CNN and to improve the performance of generating a tomographic image by the CNN.

The invention discloses an image reconstruction method and device, electronic equipment and a storage medium, and relates to the technical field of C-arm X-ray equipment and the like, the image reconstruction method is applied to the C-arm X-ray equipment, and the image reconstruction method comprises the following steps: acquiring first truncated projection data; performing projection domain reconstruction on the first truncated projection data based on a projection domain recovery network model to obtain first non-truncated projection data; performing three-dimensional reconstruction on the first non-truncated projection data to obtain a first non-truncated cross-sectional image, and performing image domain reconstruction on the first non-truncated cross-sectional image based on an image domain recovery network model to obtain a first reconstructed image; and carrying out front projection on the first reconstructed image, fusing the first reconstructed image with the first truncated projection data, and carrying out three-dimensional reconstruction to obtain a target image. According to the image reconstruction method provided by the invention, the full information reconstruction of the three-dimensional expanded view of the C-arm X-ray equipment system is realized, and the quality of the reconstructed image is improved.

The invention discloses a multilayer imaging method for terahertz near-field system tomography, and belongs to the technical field of terahertz near-field imaging. Aiming at the problem that internal depth quantitative calibration is difficult to realize in existing terahertz near-field three-dimensional imaging, the method proposes that a signal with deepest internal imaging is determined through primary scanning, then multiple data processing is carried out through secondary or multiple scanning, bias voltages of different acquired signals are respectively adjusted under the same magnification times, and the internal depth quantitative calibration is realized in the terahertz near-field three-dimensional imaging. The offset values are arranged in an arithmetic progression, thereby obtaining imaging data representing different linear depths. According to the method, multilayer imaging of internal depth calibration can be realized, a three-dimensional tomographic image with quantitative depth information is formed, and the method is suitable for observation of internal structures of biological cells and nondestructive testing of internal defects of materials.

The application relates to a medical imaging system, a medical imaging method and a computer readable storage medium. The method comprises the following steps: obtaining first projection data by detecting radioactive rays passing through a first scanning field of view, and simultaneously detecting a part of radioactive rays in radioactive rays not passing through the first scanning field of view but passing through a second scanning field of view to obtain second projection data, wherein the second scanning field of view is larger than the first scanning field of view, and the first scanning field of view is located in the second scanning field of view; obtaining third projection data corresponding to the second scanning field of view based on the first projection data and the second projection data; and reconstructing a tomographic image in the second scanning field of view based on the third projection data. Through the application, the problem that the signal in the extended scanning field of view obtained by speculation is greatly different from the real signal in the related art is solved, and the reconstruction quality of the computer tomographic image is improved.

The invention provides an image determination method and device and electronic equipment, and can be applied to the technical field of medical image processing. The method comprises the steps that a coincidence area of an anatomical image and a target body surface fluorescence distribution image is masked, a target mask image is obtained, and the target body surface fluorescence distribution image represents fluorescence intensity distribution of fluorescent molecules overflowing out of the body surface of a target object in a three-dimensional space; reconstructing the target body surface fluorescence distribution image by using the target reconstruction function to obtain an initial fluorescence molecular cross-sectional image which represents initial density space distribution of fluorescence molecules in the tumor tissue; extracting a structure prior feature corresponding to the target mask image, a density space feature corresponding to the initial fluorescent molecular cross-sectional image, and an optical feature corresponding to the target body surface fluorescent distribution image; and fusing the structure prior features, the density space features and the optical features based on an attention mechanism to obtain a target fluorescent molecular tomographic image.

The application relates to an image synthesis method and device, computer equipment and a storage medium. The method comprises the following steps: performing projection processing on a plurality of to-be-synthesized tomographic images to obtain a first image corresponding to the plurality of to-be-synthesized tomographic images and a second image corresponding to the plurality of to-be-synthesized tomographic images; performing filtering processing on the first image and the second image respectively to obtain a low-frequency component image corresponding to the plurality of to-be-synthesized tomographic images and a high-frequency component image corresponding to the plurality of to-be-synthesized tomographic images; and obtaining a synthesis image corresponding to the plurality of to-be-synthesized tomographic images according to the low-frequency component image and the high-frequency component image. The method can improve the image synthesis efficiency.

Embodiments of the present application disclose a method and device for extracting root canal feature morphology based on CBCT data, equipment and medium, belong to the field of oral medicine and medical image technology, wherein the method comprises: filtering and denoising CBCT images and performing pulp segmentation processing, and performing surface rendering three-dimensional reconstruction on tooth root canals to generate a three-dimensional model; based on the regular point cloud data in the three-dimensional model, a point-surface method is used to realize surface reconstruction to generate a root canal entity model; the root canal entity model is subjected to coordinate alignment processing in a three-dimensional space, and the approximate center line of the fitted root canal is used to measure the root canal length, root canal opening direction, root canal curvature and pulp depth. The present application quickly reconstructs the corresponding three-dimensional model based on the CBCT tomographic images obtained by scanning the teeth of a patient, and obtains relevant data such as pulp depth and root canal opening size from the three-dimensional model of the teeth to assist the performance of oral surgery.

The invention relates to a method for the tomographic analysis of a composite part (20) comprising fibers (21), the method comprising the following steps: - acquiring (ACQ) at least one tomographic image of the part (20) by means of a tomography device (1); - dividing (DIV) the tomographic image into elementary sub-portions; - measuring (MES) variations in at least one first quantity (G), characteristic of the greyscale in the sub-portion; - obtaining (OBT) variations in a comparison quantity (C) in at least one reference part; and - comparing (COMP) the variations in the first quantity (G) with the variations in the comparison quantity (C). The method comprises a step of: - registering (REC) the comparison quantity (C) in order to compensate for an offset (u) between the first quantity (G) and the comparison quantity (C).

The present invention relates to an image processing apparatus, method, and program that reduce the difference in image quality between high-absorbent regions and adjacent regions in a tomographic image. [Solution] The system includes a processor, which identifies high-absorbent regions in a projection image obtained by imaging a subject containing high-absorbent materials using a CT scanner, and derives a corrected projection image by performing a correction on the high-absorbent regions in the projection image to suppress the image quality difference between the high-absorbent regions and other regions other than the high-absorbent regions.

The invention discloses an offset scanning CBCT image reconstruction method. The method comprises the following steps: virtual detector conversion of projection data; carrying out geometric weighting on the data; carrying out data continuation and filtering; parker weighting is carried out on the data; and reconstructing bias back projection. According to the invention, aiming at the scanning mode of radiation source and detector bias, the FDK algorithm cannot be directly used for reconstruction, the virtual detector is introduced to convert the scanning mode into the scanning mode of detector bias, the data is subjected to continuation processing to solve the problem of data truncation, and the filtered data is subjected to Parker weighting aiming at the repeated scanning area to solve the problem of bias artifacts. And finally, carrying out three-dimensional reconstruction by adopting an FDK reconstruction method. The reconstruction method is high in speed, and the obtained cross-sectional image is high in definition.

An image processing device detects a spicula candidate region having a radial line structure from each of a plurality of tomographic images indicating a plurality of tomographic planes of an object, selects, as a tomographic image group, a plurality of the tomographic images corresponding to a plurality of the spicula candidate regions indicating the same radial line structure among a plurality of the detected spicula candidate regions, and generates a composite two-dimensional image using the selected tomographic image group.

To provide a measuring device and a measuring method capable of separately determining a diffusion coefficient of particles contained in a fluid and an advection velocity of the fluid, and determining a shear viscosity characteristic and a temporal characteristic of a non-Newtonian fluid by on-site observation, in the measuring device formed by combining OCT and DLS.SOLUTION: A coupling optical unit that couples reflected or scattered light with reference light that is not reflected or scattered by the observation object, a detection unit that detects coupled light coupled by the coupling optical unit, and a control unit that acquires an optical coherence tomographic image of the observation object on the basis of the coupled light, the control unit records an optical coherence tomographic image of the fluid from the acquired optical coherence tomographic image of the observation object, obtains each of characteristic values representing degrees of thermal motion and advective motion of particles contained in the fluid based on the optical coherence tomographic image of the fluid, and outputs position information of each of the characteristic values in a two-dimension space and time information representing a temporal change of the characteristic value.SELECTED DRAWING: Figure 2-1

The application relates to the technical field of digital human body models, in particular to a digital human body muscle model posture generation method and device. The method comprises the following steps: obtaining a tomographic image of an initial posture of a human body by using high-precision CT, and inversely modeling a geometric model of human body bones and muscles according to the tomographic image; calculating a first motion influence weight of each muscle node attached to a bone node according to each muscle node and the bone node; calculating a second motion influence weight of each muscle node according to the influence of adjacent muscle nodes on each muscle node; calculating a comprehensive weight of each muscle node according to the first motion influence weight and the second motion influence weight; and calculating a Laplace coordinate of a next moment of a current muscle node according to the comprehensive weight of the current muscle node, the position of the current muscle node and adjacent muscle nodes. The application generates a high-fidelity muscle geometric model by using a Laplace mesh deformation constraint technology.

An optical coherence tomography apparatus generates a tomographic image of measurement target based on an interference signal generated by synthesizing reflected light of measurement light reflected in the measurement target with reference light. The optical coherence tomography apparatus includes: a first mirror reflecting the reflected light of the measurement light reflected deep in the measurement target to a first direction for synthesis with the reference light and causing the measurement light to scan the measurement target by rotation with a first axis as an axis of rotation; and an image capturer capturing an image of a surface of the measurement target by using object light that is visible light emitted from the surface of the measurement target. The first mirror is fixed in an orientation for reflecting the object light to a direction of the image capturer in a case where the image capturer is in an image capture state.

The application provides a three-dimensional face animation generation method and system based on physiological prior art, and belongs to the fields of computer vision and computer simulation, and comprises the following steps: S1: obtaining an initial three-dimensional face model based on CT and MRI scanning section images; correcting, mesh processing and filling the initial three-dimensional face model to obtain a three-dimensional face physiological model; S2: using an unstructured Delaunay algorithm to realize unstructured tetrahedral partitioning on the three-dimensional face physiological model to obtain a three-dimensional face physiological model mesh partitioning result; S3: performing biomechanical modeling on the three-dimensional face physiological model mesh partitioning result; S4: adding contact constraints and boundary conditions between different tissues of the three-dimensional face physiological model to construct a finite element analysis model to simulate facial deformation; and S5: solving and analyzing the finite element model to obtain a three-dimensional face animation. The method can generate high-quality three-dimensional face animations based on a small amount of samples.

Systems, methods, and computer readable memory are disclosed for constructing a three-dimensional tomogram using a gravity-fed tomography system. A gravity-fed tomography system may generate a three-dimensional image through a barrier. The system may include a chute. The chute may be configured to receive a three-dimensional object having x-, y- and, z-dimensions. The chute may be configured to be non-perpendicular to a gravitational vector such that gravity facilitates movement of the object through the chute. The system may include one or more sources. The sources may emit electromagnetic radiation toward the object when the object is disposed in the chute. The system may include one or more receivers, which may receive at least a portion of the electromagnetic radiation emitted by the one or more sources.

An image generation device, an image generation method, and a program capable of improving the generation accuracy of a pseudo two dimensional image as compared with a case where an image generation model learned using a combination of a plurality of projection images or a plurality of tomographic images and a normal two dimensional image captured separately from tomosynthesis imaging for obtaining the plurality of projection images or the plurality of tomographic images is used are obtained.SOLUTION: The image processing apparatus 16 as an image generation apparatus includes an image generation model that is learned in advance by a plurality of combinations of a plurality of projection images or a plurality of tomographic images and a normal two dimensional image captured by irradiating the breast compressed by the compression member with radiation in tomosynthesis imaging for obtaining the plurality of projection images or the plurality of tomographic images.SELECTED DRAWING: Figure 5

A method and system for editing a lumen contour of a tomographic image. A method comprises: receiving image data corresponding to a plurality of tomographic images acquired by an imaging catheter scanning a blood vessel; obtaining, by a processor, an automatically-generated lumen contour of the blood vessel from a tomographic image of the blood vessel; displaying, on a display, the automatically-generated lumen contour overlaid on the tomographic image of the blood vessel; identifying a true lumen edge of the blood vessel in the tomographic image; estimating a percentage of matching between a shape of the automatically-generated lumen contour to a shape of the true lumen edge; and receiving editing operations from a user via a touchscreen interface for editing at least part of the automatically-generated lumen contour based on the estimated percentage of matching. Plural editing modes are available based on the percentage of matching meeting one or more thresholds.