29 results about "Streaking Artifact" patented technology

The invention discloses a sparse finite angle CBCT reconstruction method and system based on residual diffusion and a storage medium, and the method comprises the steps: carrying out the CBCT sparse finite angle scanning of a to-be-detected target, and obtaining sparse projection data; fDK reconstruction is carried out on the sparse projection data to obtain an initial CBCT image; generating a first optimized CBCT image from the initial CBCT image through an image pre-training network; through the first optimized CBCT image and the sparse projection data, using the trained residual diffusion model to determine a residual image of the to-be-detected target; summing the first optimized CBCT image of the to-be-detected target and the residual image of the to-be-detected target to obtain a second optimized CBCT image of the to-be-detected target, and the second optimized CBCT image is a final CBCT reconstruction image. According to the method, the problems of stripe artifacts and low-contrast tissue annihilation under limited angle scanning are solved, the large-view CBCT reconstruction resolution is improved, and the radiation dose is reduced.

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.

A method and a system for simulating magnetic resonance echo-planar imaging artifacts. Firstly, for K-space artifacts, K-space data are restored through normal magnetic resonance images, and the K-space data are modified pertinently, and then images with artifacts are reconstructed; for susceptibility artifacts, a susceptibility model is constructed through normal magnetic resonance images, and the magnetic field distribution is reconstructed, and then the images with distortion artifacts are reconstructed. According to the present disclosure, a large number of artifact data sets with different artifact types and artifact degrees can be quickly created through a small number of normal images, thus laying a foundation for the research of identifying artifacts, eliminating or weakening artifacts. A simulation algorithm is designed according to the principle of generation of EPI sequence artifacts, and the obtained images such as stripe artifacts, Moer artifacts, Nyquist artifacts, susceptibility artifacts and the like have good scientificity, accuracy and interpretability.

The invention belongs to the technical field of medical imaging and deep learning, and discloses a mixed domain iteration sparse view CT reconstruction method based on self-attention and convolution fusion. According to the method, firstly, a multi-branch module (FSACM) fusing self-attention and convolution is provided, and interaction of global and local feature information can be effectively achieved. Based on the module, an initialization enhancement network, a projection restoration network and a residual error restoration network are designed, and the three networks are reasonably connected and construct an iteration block to jointly cooperate to complete a sparse view CT reconstruction task. A special framework is designed for the three networks, and a gradient updating module is added into an iteration block to optimize initial projection and images; meanwhile, a comprehensive loss function is introduced to balance the reconstruction precision of a projection domain and an image domain. The method can effectively eliminate stripe artifacts and reserve detail structures while maintaining iteration efficiency, realizes high-quality reconstruction, and greatly reduces radiation dose accepted by patients.

The invention provides a method and system for removing ring artifacts of a CT image and a storage medium, and the method comprises the steps: obtaining original projection data corresponding to the CT image of which the ring artifacts are to be removed, classifying the original projection data according to scanning parameters during the scanning of CT equipment, and obtaining a plurality of projection classification data; calculating the mean projection of each piece of projection classification data; reconstructing the mean projection of each projection classification data to obtain the reconstructed mean reconstruction projection of each projection classification data; and removing ring artifacts according to the difference between the mean projection and the mean reconstruction projection of the projection classification data. According to the method, in order to accurately remove the ring artifacts, regression and strip artifact correction are respectively carried out on each classified mean value projection, so that the segmentation continuous attribute of the strip artifacts in the projection domain is fully utilized, the ring artifacts are removed, and the accuracy and efficiency of removing the ring artifacts are improved.

The invention discloses a ridge regression and detail conduction-based CT image reconstruction method and system, and belongs to the technical field of CT image reconstruction, and the method comprises the steps: constructing a mask, and carrying out the fusion of an FBP reconstruction image filtering result and an SART reconstruction image filtering result through the mask, and obtaining a guide image; calculating detail information of the FBP reconstructed image, capturing local detail change of the FBP reconstructed image, and obtaining a detail layer result of the FBP reconstructed image; combining the calculated detail layer result of the FBP reconstructed image with the filtering result of the FBP reconstructed image, fusing the mask with the filtering result of the SART reconstructed image to obtain a final image, and filtering the filtering result of the SART reconstructed image by taking the final image as a guide image to obtain an initial value of SART iteration; and enabling the initial value of the SART iteration to participate in a SART reconstruction process for iteration until a final reconstructed image is obtained. According to the method, the inherent limitation of SART in the aspect of keeping high-frequency information is effectively made up, stripe artifacts are reduced, and the overall quality and fidelity of a reconstructed image are improved.

The invention discloses an ultra-sparse CBCT (cone beam computed tomography) reconstruction method, system and equipment based on an ordinary differential equation, belongs to CBCT reconstruction in the field of artificial intelligence, and aims to solve the technical problem of low quality of CBCT reconstructed images. The method comprises the following steps: acquiring sample data, preprocessing the data, constructing and training a CBCT-CT nonlinear relation reconstruction model, and performing real-time reconstruction; during preprocessing, converting the three-dimensional image volume data into simulated X-ray projection data, and reconstructing the simulated X-ray projection data by adopting an FDK reconstruction algorithm to obtain an FDK-CBCT image; the CBCT-CT nonlinear relation reconstruction model comprises an encoder, a NODE module and a decoder; in the training process, the CBCT-CT nonlinear relation reconstruction model is trained through the obtained CT sample image and the FDK-CBCT image. In the reconstruction model, through continuous evolution of NODE modeling image features, the model can model a continuous evolution mapping process from a sparse low-quality image to a high-quality CT image during training, so that stripe artifacts and structural distortion do not easily exist in the reconstructed image, and the reconstruction quality is high.

A sparse helical CT image reconstruction method based on a differentiable helical reconstruction operator. First, actual helical scanning geometric parameters of a subject and corresponding full-angle helical projection data are acquired, and a final reconstructed image is acquired by means of seven steps. In the present invention, actual scanning geometry is used to perform forward projection on a reconstructed sparse-angle image, thereby providing geometric prior guidance for missing projections; moreover, on the basis of the similarity and redundancy characteristics of adjacent projections in helical scanning, a projection completion network is constructed, and by learning bidirectional motion fields of adjacent angles and in combination with geometric prior projections, intermediate missing projection data is jointly synthesized; in addition, the global streak artifact restoration of the image is realized; and finally, the joint training of a projection domain and an image domain is realized, thereby facilitating integral restoration by using projection-image dual-domain information, and data collected within two pitches is used for restoration, thereby effectively avoiding an excessive computational load.

The present application relates to the technical field of medical image processing, and particularly relates to a CBCT data enhancement method and system based on anatomical region constraint and physical consistency; a human body region mask is acquired and a data enhancement model only exerting enhancement disturbance on the human body anatomical tissue region is constructed, a plurality of enhancement disturbances conforming to the CBCT imaging physical mechanism are combined, the CBCT data after enhancement is strictly limited to the anatomical range, non-physical disturbance introduced by the air region is avoided, and the CBCT data after enhancement is close to the real imaging degradation process; at least one enhancement disturbance including gray scale shift, Gamma nonlinear transformation, compound noise, low-frequency scattering field and stripe artifact is executed on the CBCT image after preprocessing, real imaging degradation factors such as device calibration error, detector nonlinear response, electronic noise, photon statistical noise, scattering effect and reconstruction artifact can be simulated, and the adaptability and robustness of the model to different devices, scanning parameters and patient individuals are significantly improved.

The invention provides a finite angle CT iterative reconstruction method and system based on tight frame wavelet transform, and relates to the technical field of image processing, and the method comprises the steps: obtaining a pre-image and finite angle CT projection data of a to-be-detected object; total variation regularization constraint is carried out based on the pre-image of the to-be-detected object, and an initial optimization model is established; solving the initial optimization model to obtain a high-quality pre-CT image, and performing transformation by adopting tight frame wavelet transform to obtain a tight frame wavelet frequency domain coefficient; based on limited angle CT projection data and a to-be-detected object before reconstruction, a dual regularization CT reconstruction optimization model is established in combination with the tight frame wavelet transform frequency domain coefficient; and solving the dual regularization CT reconstruction optimization model, and outputting a reconstructed CT image. According to the method, the double regularization CT reconstruction optimization model of the tight frame wavelet transform domain sparse characteristic finite angle is established, strip artifacts and noise appearing in the finite angle CT image can be effectively restrained, the quality of the reconstructed image is greatly improved, and the clinical diagnosis quality is improved.

The application discloses an industrial CT image reconstruction method and device, electronic equipment and storage equipment, comprising obtaining projection image data and preprocessing to obtain target image data; based on the pre-trained U-Net variant lightweight network, the target image data is processed to obtain fine gradient direction prediction data and structure level similarity data, the U-Net variant lightweight network is trained based on the projection image data and the true value image data, and the loss function of the U-Net variant lightweight network comprises a structure similarity loss; based on the target image data, the fine gradient direction prediction data and the structure level similarity data, the target function is iteratively updated by using an alternating direction multiplier method to obtain reconstructed image data, and the target function is a high-order regularization function constructed based on the second-order total generalized variation and the structure level non-local mean of the iterative image data. The application can inhibit the streak artifact and photon noise of sparse images, so as to meet the requirements of fast scanning and sparse image reconstruction quality.

The present invention belongs to the technical field of medical image processing, and provides a CBCT artifact correction system and method based on a multi-stage reconstruction network. The system includes: an image preprocessing module, a model training module, and an image generation module. The image preprocessing module is used to reconstruct the projection data collected by CBCT scanning to obtain a reference CBCT and a sparse-angle CBCT; the model training module is used to train a multi-stage hybrid attention reconstruction network based on the sparse-angle CBCT and the reference CBCT to obtain a sparse-angle CBCT artifact correction model; the image generation module is used to input the actual sparse-angle CBCT into the sparse-angle CBCT artifact correction model to generate a corrected CBCT. The present invention effectively reduces the common streak artifacts and noise in sparse-angle reconstruction through multi-stage fusion in the image domain and the projection domain, and improves the clarity and clinical usability of CBCT.

The present application provides a kind of night image halo removal method, including constructing prior knowledge, according to prior knowledge, construct initialization network and depth unfolding network, using initialization network to extract variable initial value set from night halo pollution image;Night halo pollution image and variable initial value set are input into depth unfolding network and are operated multiple iterations, and the final halo removal image is extracted from night halo pollution image;Wherein, depth unfolding network includes multiple proximal networks, and each proximal network participates in an iteration operation.The present application makes full use of prior knowledge, uses the depth unfolding network with multiple proximal networks to iterate mapping diagram, halo-free feature map, constraint variable and halo removal image, so as to extract the final halo removal image, to better preserve image texture and restore image details, under the premise of not increasing application cost, the halo and stripe artifact in image are preferably removed.

The application discloses a texture feature guided texture preserving low dose CT image denoising method, and belongs to the field of medical image processing.The application specifically discloses a multi-scale deep residual attention network model with texture feature guidance, which is applied to low dose CT imaging.The main network model comprises four sub-models, one is a multi-scale initial denoising network model for denoising low dose CT, and the other network is used for extracting texture details after the initial denoising network, and the two network parts work cooperatively.The extracted texture details and the initial low dose CT are fused through a multi-scale image and texture feature fusion network model, and then enter a multi-scale main denoising network for further denoising of the low dose CT, which is beneficial to the main denoising network to learn more unobvious details.The low dose CT image denoising method disclosed by the application efficiently removes the noise and stripe artifacts in the low dose CT image, and meanwhile, the structural information and texture feature detail information in the image are preserved.

The invention discloses a method for eliminating autocorrelation artifacts of a polarization sensitive optical coherence tomography image. Comprising the following steps: carrying out sample detection by using a PS-OCT (Polarization Sensitive Optical Coherence Tomography) system to obtain interference signals of two polarization channels; performing inverse Fourier transform on the interference signal of one channel to obtain an airspace signal of the interference signal; finding a self-correlation horizontal fringe artifact signal with the maximum intensity in the interference signals of the airspace, and setting the intensities of other positions to be zero; calculating an unwrapping phase of the self-correlation artifact in each A-scan, and taking a minimum value of the unwrapping phase as a reference phase; interpolating the spectral phases of the original interference signals of the two polarization channels according to a reference phase; and performing inverse Fourier transform and polarization parameter calculation to obtain an OCT intensity image and a polarization image with autocorrelation artifacts eliminated. According to the image phase information-based self-correlation artifact removal method, the self-correlation artifacts in the PS-OCT image can be effectively eliminated, additional hardware facilities do not need to be introduced, and the method is simple and effective.

The invention discloses a method and a system for removing breathing artifacts of an animal micro-CT image. The method comprises the following steps: preprocessing projection data of an animal to obtain label information; training label information by using a depth target detection network to obtain thoracic cavity diaphragm positions, classifying the thoracic cavity diaphragm positions, extracting target limiting projections at the end of diastole and the end of systole, and performing unequal interval filtering back projection reconstruction on the target limiting projections to obtain a breathing artifact-removed image; correcting the breathing artifact-removed image by using an improved deep noise reduction network to obtain a breathing and stripe artifact-removed image; in-phase projection is extracted in a projection domain and is reconstructed, so that respiratory artifacts are effectively removed from the source; and the improved deep noise reduction network is used to enhance the quality of the sparse reconstruction image, so that the image quality is remarkably improved, and a clearer and more accurate image basis is provided.

The invention discloses a method for removing flicker stripes of a rolling shutter camera based on a self-supervision mechanism. The method comprises the following steps: S1, generating a rolling shutter image with a flicker effect; s2, acquiring two training images containing flickering stripes in the same scene; s3, inputting the first flicker image into a neural network model to obtain a prediction output image; s4, the second flicker image is used for processing, and a supervision signal serving as a prediction output image is generated; s5, calculating the loss between the prediction output image and the supervision signal; and S6, according to the loss, adjusting parameters of the neural network model by using a back propagation algorithm based on gradient descent. According to the method provided by the invention, the stroboscopic stripes on the picture can be removed, and the stripe-free picture is output; the problem that fringes are not thoroughly removed due to the fact that an existing non-supervision method lacks clear supervision signals is solved. The problem that a general loss function is insufficient in specific stripe artifact suppression capability is solved.

The invention provides a nighttime image halo removing method, which comprises the following steps of: constructing prior knowledge, constructing an initialization network and a deep expansion network according to the prior knowledge, and extracting a variable initial value set from a nighttime halo polluted image by adopting the initialization network; inputting the nighttime halo pollution image and the variable initial value set into a deep expansion network for multiple iterative operations, and extracting a final halo-removed image from the nighttime halo pollution image; wherein the deep expansion network comprises a plurality of near-end networks, and each near-end network participates in one iterative operation. Under the condition that priori knowledge is fully utilized, a deep expansion network with a plurality of near-end networks is adopted to carry out iteration on a mapping graph, a halo-free feature graph, a constraint variable and a halo-removed image, so that a final halo-removed image is extracted, image textures are better reserved, image details are better recovered, and the image quality is improved. On the premise that the application cost is not increased, light spots and stripe artifacts in the image are well removed.

This paper relates to the field of image processing, and more particularly to a method and apparatus for eliminating stripe artifacts in light-sheet fluorescence microscopy images. The method includes: acquiring multiple striped images obtained by scanning a biological tissue sample at the same location from multiple angles using a light-sheet fluorescence microscope; constructing a stripe-free image based on the multiple striped images; using the multiple striped images and their corresponding stripe-free images as training datasets; training a deep adversarial network (DAN) based on the training datasets; and using the trained DAN to eliminate stripe artifacts in the striped images of the target biological tissue sample. The embodiments described in this paper eliminate stripe artifacts in striped images of biological tissue samples obtained by light-sheet fluorescence microscopy by training a DAN model, improving the clarity of the stripe-free image obtained after stripe artifact removal. Furthermore, this method is applicable to various light-sheet fluorescence microscopy systems, improving the adaptability of the stripe artifact removal method.

The application discloses a tunnel fault image analysis method based on image processing, and aims at solving the problems that the surface image cannot be corresponded with the spatial profile of the transient seismic wave method, the geological radar and the resistivity imaging profile, and the abnormality in a certain distance in front cannot be mapped to the working face, wherein the anisotropic regularization is performed through the Fourier neural operator, the cross-modal Transformer registration based on the differentiable attention mask and the curve mileage and the cross-section polar coordinate position coding of the sector geometry is combined, the analytical geometry mapping and the uncertainty propagation are matched, the working face structure trace and the water seepage texture evidence are fused, the accurate positioning of the abnormality in the working face, the position confidence range estimation and the risk grading early warning are realized, the stripe artifact is inhibited, the abnormal boundary is reserved, and the technical effects of outputting the structured results such as the mileage post number, the azimuth angle and the distance interval are achieved.

The application discloses a high-speed CT intelligent image reconstruction method for transient detection, which is applied to a distributed multi-source transient CT imaging system, acquires sparse angle projection data of multiple fixed X-ray sources under different projection angles, and constructs a linear imaging system equation; an accelerated random differential equation framework is constructed, multi-scale dynamic modeling is carried out by introducing an integer scale index, and time resolution and noise intensity are decoupled; a quasi-equivalent Markov chain solver is used for image reconstruction sampling, and the sampling process is sequentially divided into a non-Markov bridge stage, a link path stage and a Markov bridge stage; after each sampling step, a data consistency constraint is applied to correct the sampling state, and a reconstructed image is obtained; and the application effectively suppresses stripe artifacts under the condition of extremely sparse viewing angles by means of multi-scale decoupling and a three-stage sampling strategy, and ensures the image reconstruction quality.

The present invention provides a multi-scale non-local low-dose CT image denoising method based on regional adaptation. The method adopts an adaptive search window, an adaptive multi-scale block size, and an adaptive filter coefficient for different image regions. Specifically, in non-edge regions, an isotropic square search window of 29 pixels in length and 29 pixels in width is used as a similar point region; in regions containing edges, an isotropic square search window of 15 pixels in length and 15 pixels in width is used as a similar pixel candidate point. Then, based on pixel point classification information and edge extraction information, an anisotropic similar point region along the edge direction is obtained. Then, multi-scale weighted non-local mean denoising is used to calculate denoised pixel values ​​in the determined similar point region. In addition, to better remove stripe artifacts and speckle noise, the denoising smoothing parameter and multi-scale action coefficient are adaptively changed according to noise intensity and intuitionistic fuzzy divergence theory. Therefore, the method effectively solves the problems existing in the prior art.

This invention discloses a method, system, medium, and device for NNBI visual tomographic image reconstruction, relating to the field of neutral beam imaging technology using negative ion sources. The NNBI visual tomographic image reconstruction method and system provided by this invention utilizes a tomographic reconstruction algorithm to invert the observed projection map of an NNBI multi-angle beam image, obtaining an initial reconstructed image and constructing its ROI mask. Then, the mask is input into a pre-trained residual denoising network via two channels to acquire the residual image and calculate the denoised image. This suppresses interference from background and noise outside the ROI and improves the stability of denoising, thereby improving image reconstruction efficiency and image quality. Furthermore, based on a forward projection operator constructed using camera calibration parameters and the observed projection vector, the reprojection residual of the denoised image is calculated and a correction value is generated. This correction value is used to perform data consistency correction on the denoised image to obtain the target reconstructed image, maintaining projection consistency and preventing consistency degradation caused by depth denoising. This invention effectively suppresses isolated points and stripe artifacts during image reconstruction, improving the quality of image reconstruction.

The invention discloses a 4D-CBCT motion compensation reconstruction method based on priori feature hidden space deformation constraint, which comprises the following steps: firstly, designing a 4D-CBCT image restoration network model based on priori feature hidden space deformation constraint, then training the image restoration network model by adopting a two-stage strategy, and finally, reconstructing the 4D-CBCT image restoration network model based on the priori feature hidden space deformation constraint. A two-stage strategy is adopted to train a three-dimensional image registration network to carry out rapid and accurate motion estimation, and a high-quality 4D-CBCT image sequence with motion resolution, remarkable artifact suppression and effective detail enhancement is obtained. According to the 4D-CBCT motion compensation reconstruction method based on priori feature hidden space deformation constraint disclosed by the invention, stripe artifacts caused by insufficient sampling in a single-phase image can be effectively removed, the 4D-CBCT image quality is enhanced, and lung motion information is clearly displayed. The method is an unsupervised reconstruction algorithm, does not need real pairing of 4D-CBCT data for training, can be very conveniently used for processing data of different equipment manufacturers, and has great clinical application potential.

The invention discloses a self-adaptive ring artifact removal method, device and equipment based on mean projection and a medium, and the method comprises the steps: carrying out reconstruction operation on original mean projection according to a first spatial parameter to obtain pre-reconstructed mean projection, and detecting a non-linear region in the pre-reconstructed mean projection, performing a reconstruction operation on the nonlinear region according to the second spatial parameter to obtain a reconstruction mean projection; and carrying out artifact removal on projection data according to the original mean projection and the reconstructed mean projection. According to the method, the original mean projection is pre-reconstructed by using the first spatial parameter, and the nonlinear region in the pre-reconstructed mean projection is optimized and reconstructed by using the second spatial parameter, so that the accuracy of the nonlinear region is improved on the basis of ensuring the smoothness of the reconstructed mean projection, the removal effect of stripe artifacts is effectively ensured, and the user experience is improved. Therefore, the removal effect of the ring artifacts in the reconstructed CT image is improved.

A phase contrast X-ray imaging system includes an X-ray source, a plurality of gratings, a detector for detecting X-rays, a grating movement mechanism, and a controller. The controller generates a phase contrast image based on intensity changes that represent changes in pixel values of pixels detected by the detector while moving a scanning grating, which is at least one of the plurality of gratings, using the grating movement mechanism. The controller acquires an analysis period representing a period of the intensity change to reduce a moire artifact, and adjusts a set value of movement of the scanning grating for generating the phase contrast image based on the analysis period acquired.

The invention belongs to the technical field of X-ray detection, and provides an X-ray image processing method and device based on deep learning, and the method comprises the steps: recognizing a fog scattering region in an X-ray image; performing stripe artifact analysis under coupling combination of different jig vibration frequencies and X-ray pulse frequencies, and identifying a high-probability vibration-pulse frequency group with stripe artifacts; comparing and judging whether the X-ray image has a periodic stripe artifact risk or not; if the X-ray image exists, determining the direction and spacing of the stripe artifacts through gray gradient analysis of the X-ray image, and marking a stripe artifact coverage area; according to the method, a scattering artifact overlapping area is identified through overlapping analysis of a foggy scattering area and a stripe artifact coverage area, regional artifact removal is carried out through a deep learning network, a global artifact-removed image is output in combination with multi-area weight fusion, and the detection precision is improved.

The present invention discloses a training method based on a dual-domain neural network and a corresponding photoacoustic image reconstruction method, including: constructing a DI-net network model, wherein the DI-net network model includes a data domain D-net network, an image domain I-net network, and a back-projection layer between the data domain D-net network and the image domain I-net network; obtaining a training sample data set, the training sample data set including photoacoustic signals and photoacoustic images; training the DI-net network model based on the training sample data set to obtain a trained DI-net network model. Inputting sparse-view photoacoustic signals into the DI-net network model to obtain a reconstructed image. Using the trained DI-net network model for image reconstruction can suppress stripe artifacts caused by sparse views and improve image quality.

The present application belongs to the technical field of image denoising, and particularly relates to a low-dose CT image denoising method. The low-dose CT scanning technology can effectively reduce the radiation received by the patient, but at the same time, it also leads to the reduction of the image quality, especially the strip noise in the image, which brings not small challenge to the denoising work. In view of this problem, the present application firstly uses the weighted kernel norm minimization to preliminarily denoise the image and remove the speckle noise; then the preliminarily denoised image is rotated, a direction total variation regularization term is introduced, and a low-rank method is combined to extract the stripe artifact noise; then the preliminarily denoised image is subtracted from the image after the inverse transformation of the rotated image with the stripe artifact noise, and the final denoising result is obtained. The experimental results show that the algorithm can effectively remove the strip noise of the low-dose CT image, and better preserve the image details.