254 results about "Image Artifact" patented technology

Systems and techniques are provided for automatically analyzing and processing domain-specific image artifacts and document images. A process can include training a domain-adapted ML network using a domain-specific training dataset including a plurality of training data inputs corresponding to a lexicon of domain-specific terminology. A first fine-tuning training of the domain-adapted ML network yields a domain-adapted general QA ML network, based on using a first question answering (QA) dataset comprising a first plurality of question-answer training pairs that do not correspond to the lexicon of domain-specific terminology. A second fine-tuning training of the domain-adapted general QA ML network yields a fine-tuned domain-adapted general QA ML network, and uses a second QA dataset comprising a second plurality of question-answer pairs generated based on a corpus of text narratives utilizing the lexicon of the domain-specific terminology.

In a method, for training an artificial neural network (ANN) to reduce noise and / or artefacts in an electron microscopy image, a plurality of training image pairs is generated. For each pair, an undistorted synthetic specimen image and a distorted image are created by simulating additional noise and / or artefact features. The ANN is trained, in which the distorted images are used as input and the corresponding undistorted images as output. An adversarial training strategy is used in which the ANN is trained, as a generator network, in conjunction with concomitantly training a further ANN, as a discriminator network, to differentiate output produced by the generator network from synthetic images in the training set. In training, parameters of the ANN and further ANN are optimized using a generator loss function and a discriminator loss function, in which a dependency exists between said loss functions to train the networks in an adversarial manner.

Systems and techniques are provided for automatically analyzing and processing domain-specific image artifacts and document images. A process can include obtaining a plurality of document images comprising visual representations of structured text. An OCR-free machine learning model can be trained to automatically extract text data values from different types or classes of document image, based on using a corresponding region of interest (ROI) template corresponding to the structure of the document image type for at least initial rounds of annotations and training. The extracted information included in an inference prediction of the trained OCR-free machine learning model can be reviewed and validated or corrected correspondingly before being written to a database for use by one or more downstream analytical tasks.

The invention relates to the technical field of image processing, and provides an image artifact detection method and system based on a deep learning technology, and the method comprises the following steps: carrying out the preprocessing of an obtained to-be-processed image, and carrying out the feature extraction of the preprocessed image; position coding is carried out on the extracted feature map A, and the extracted feature map A is fused with the feature map A; performing multi-layer encoding and decoding on the fused feature map through an encoder and a decoder to obtain a feature map B containing an artifact target area; and generating an anchor frame of an artifact region for a target region in the feature map B, and dynamically adjusting the size and position of the anchor frame according to local information of the down-sampling rate, texture complexity and edge strength of the feature map B to obtain an artifact region detection result after the anchor frame is labeled. Automatic artifact detection and quantitative evaluation of the influence degree can be achieved, the accuracy and efficiency of medical image interpretation are improved, and more reliable data support is provided for clinical decision making.

The invention belongs to the technical field of image processing, and particularly relates to a motion artifact adaptive correction method based on multi-modal MRI fusion, which comprises the following steps: acquiring sMRI and fMRI of a patient, preprocessing the sMRI and fMRI, creating a cross-modal feature fusion model, and inputting the preprocessed sMRI and fMRI into the cross-modal feature fusion model for double-branch feature extraction; the cross-modal feature fusion model carries out cross-modal feature interaction fusion on the extracted double-branch features and carries out multi-scale feature reconstruction; detecting image artifacts based on the reconstructed multi-scale features, and performing dynamic space-time attention correction on the detected image artifacts; and establishing a three-level loss function system to carry out multi-task joint optimization. By integrating sMRI and fMRI information and based on image processing and deep learning, the defect that various complex head movement conditions cannot be completely handled in the prior art is overcome, and the technical problems of information loss between image modalities and insufficient feature utilization are solved.

The invention discloses an image artifact restoration method and system based on an anti-fact diffusion model, and relates to the technical field of image processing, and the method comprises the steps: obtaining multi-modal data, and carrying out the data screening of the multi-modal data; preprocessing the screened data, and constructing a standardized data set; constructing an image artifact repairing model based on an anti-fact diffusion model; training the image artifact repair model through a standardized data set; and carrying out artifact restoration on the image polluted by the artifact through the trained image artifact restoration model. Only artifact-free data is used in the training stage, and the limitation of the lack of paired data on the current artifact repair technology is solved; the method is not limited to a single part of a single mode during restoration, and when images of different modes are processed, the quality of the restored images can still be ensured, and the high resolution and details of the images are kept; the image quality can be effectively improved, key details in the image are reserved, and the accuracy of the image is improved.

The invention relates to an image correction technology, and discloses a CBCT (cone beam computed tomography) image osteosclerosis artifact correction method, which comprises the following steps: acquiring a high-energy projection image and a low-energy projection image of a target object, performing image reconstruction, and calculating to obtain a primary artifact-free image; extracting a bone image and a soft tissue image from the primary artifact-free image based on threshold segmentation, calculating a bone weight, taking the artifact image of the target object as training input data, taking the bone image and the soft tissue image as reference data, and training to obtain a dual-channel artifact correction model; and outputting a preprocessed bone image and a preprocessed soft tissue image according to the to-be-processed osteosclerosis artifact image by using a dual-channel artifact correction model, and carrying out weighted fusion on the preprocessed bone image and the preprocessed soft tissue image according to a bone weight to obtain an artifact-free reconstructed image. The invention further provides a CBCT image osteosclerosis artifact correction device, electronic equipment and a storage medium. According to the invention, the image artifact correction effect can be improved.

A display system includes a display panel, a first reflector, and a second reflector. The display panel provides first image light representative of a displayed image to the first reflector and provides second image light representative of at least a portion of the displayed image to the second reflector without first being reflected by the first reflector. The first reflector reflects the first image light toward the second reflector. The second reflector reflects the first image light toward an eyepiece. The second reflector is positioned relative to the second image light and a polarization direction of the second image light incident on the second reflector has a first orientation such that reflectance of a portion of the second image light from the second reflector is approximately zero. A light control device behind the display panel may control a distribution angle of image light from the display panel.

The invention discloses a high-robustness demosaicing bilinear interpolation method for polarization hyperspectral imaging, relates to the field of polarization spectral imaging, and solves the problems that in the prior art, when an optical system is located on a platform, vibration occurs, frames of collected images are lost, and spectrum aliasing exists in the optical system. The method comprises the following steps: collecting a group of polarized hyperspectral images, and carrying out high-robustness demosaicing reconstruction on the collected group of polarized hyperspectral images; the image I is recorded as the image of the obtained Kth spectral band, and the mosaic image II is an empty matrix and is used as an interpolation space of the image I; performing assignment on the mosaic image II in the horizontal direction; filling by using boundary conditions to complete interpolation in the horizontal direction; extracting polarization channel intensity images in four different directions in the mosaic image II, and performing vertical direction interpolation on the polarization channel intensity images; and polarization demosaicing reconstruction of the Kth spectral band image is completed. The method is suitable for the field of suppressing image artifacts generated in reconstruction.

The invention discloses a variable attention low illumination underwater image enhancement method based on Retinex. The problem of complex degradation caused by insufficient illumination and underwater scattering in a low-illumination underwater image enhancement task is considered. According to the method, an illumination-guided variable attention module is designed, semantic information provided by a brightness feature map is utilized to help to enhance a dark region, and the adaptive enhancement capability of the model is improved; constructing a space-frequency domain feature fusion module, and improving the significance of image texture information through multi-scale feature extraction and feature fusion among different levels; a medium transmission module is introduced, and image artifacts caused by underwater scattering in the enhancement process are further solved. Compared with other frontier methods, the method has the advantages that the image degradation can be effectively recovered while the brightness is improved, and the enhanced image has a better visual perception effect.

Systems and techniques are provided for automatically analyzing and processing domain-specific image artifacts and document images. A process can include obtaining a plurality of document images comprising visual representations of structured text. An OCR-free machine learning model can be trained to automatically extract text data values from different types or classes of document image, based on using a corresponding region of interest (ROI) template corresponding to the structure of the document image type for at least initial rounds of annotations and training. The extracted information included in an inference prediction of the trained OCR-free machine learning model can be reviewed and validated or corrected correspondingly before being written to a database for use by one or more downstream analytical tasks.

An analysis apparatus analyses a video image signal comprising successive frames of imaging an endoscopy procedure. A machine learning block analyses the video image signal using a machine learning technique that classifies regions of the frames as belonging to one of plural classes corresponding to respective types of image artefact. The classes include a motion blur class corresponding to motion blur of the image, at least one erroneous exposure class corresponding to a type of erroneous exposure of the image, and at least one noise artefact class corresponding to a type of image artefact that is noise. A quality score block derives quality scores representing image quality of the successive frames based on the classified regions.

The invention discloses an image processing system and method for distinguishing xerophthalmia types, and relates to the technical field of image processing, and the method comprises the steps: firstly carrying out the standardization preprocessing of an original infrared meibomian gland image, further introducing an artifact perception link, and actively recognizing and positioning the interference regions, such as eyelash shielding and uneven illumination, in the image; and guiding the subsequent meibomian gland segmentation process by using the sensed artifact information, thereby realizing the accurate extraction of the meibomian gland form under the complex background. On the basis, multi-dimensional quantification is carried out on the precisely segmented gland form, and image features are converted into objective numerical indexes. And finally, carrying out comprehensive judgment on the numerical indexes by utilizing a decision tree model, and outputting standardized MGD severity grade. In this way, interference information brought by image artifacts can be intelligently suppressed, and therefore more robust and accurate MGD severity grading is achieved in a clinical image with poor quality.

The invention discloses an X-ray image artifact definition automatic correction and enhancement method based on deep learning, and belongs to the technical field of image artifact correction, and the method specifically comprises the steps: obtaining an X-ray image, employing frequency domain decomposition and edge detection to generate an artifact image and a sharpness image, and extracting an imaging parameter set and an anatomical region label; establishing a parameter-driven artifact migration network, inputting an imaging parameter set and an artifact graph, learning an artifact vector field and phase prior, and forming reversible representation of an artifact source; constructing a double-branch decoder, dissecting branches to generate a structural skeleton diagram, and performing cross attention fusion to obtain a candidate correction field; according to the candidate correction field, geometric remapping and sub-band compensation are carried out on the image to obtain an intermediate correction result image, and an artifact vector field is sent to a feedback loop; and the consistency of the sharpness graph and the structural skeleton graph is taken as a loss item, artifact residual constraint is combined, a correction field and decoder parameters are optimized, and non-anatomical textures are suppressed.

The invention discloses a medical image artifact identification and elimination method based on a big data technology, and relates to the technical field of medical image processing, and the method comprises the steps: carrying out the preprocessing of collected image data based on gray normalization, and then carrying out the semantic segmentation and ROI positioning of the image content; and performing lesion segmentation on the positioned image content, selecting lesion features for quantification and fusion, performing model verification, and performing distributed deployment on the verified lesion segmentation model. According to the method, the problems of high missed detection rate of small nodules and high missed diagnosis risk of malignant lesions are solved through the lesion detection model, the false positive rate is reduced, the recall rate of the malignant lesions is improved, and through the lesion segmentation model, the segmentation adaptability to lesions of different sizes is improved, clear segmentation boundaries are obtained, surgical planning is assisted, and boundary positioning errors are reduced.

Methods and systems are provided for interventional ultrasound imaging. In one embodiment, a method comprises acquiring an ultrasound image of an anatomical region, segmenting an interventional device from the ultrasound image to obtain a segmented image, restoring an image quality of the ultrasound image to a reference image quality to obtain a restored ultrasound image, combining the segmented image with the restored ultrasound image to obtain a corrected ultrasound image, and displaying the corrected ultrasound image. In this way, ultrasound imaging may be used to image the position of an interventional device such as biopsy needle in an anatomical region, in real-time, with reduced image artifacts caused by the interventional device.

To reduce image artifacts and non-uniformity associated with a display pixel of an electronic display, processing circuity may adjust a luminance value corresponding to a display pixel according to a per-pixel gain mask, a per-pixel anode mask, or both. To further correct for the non-uniformity, the processing circuitry may convert the luminance value to a digital code based on a curve associated with an anode on which the display pixel is located.

The invention relates to a preprocessing method for an infrared focal plane image sequence, which comprises the following steps of: averaging each pixel point of an image in a time domain to obtain a time domain mean value; then local nonlinear filtering is used, the maximum value and the minimum value in a window are removed in the sliding window of the image, dynamic threshold detection is carried out on the time domain mean value of each point, the local mean value of the window and the maximum value and the minimum value in the window, and pixels exceeding the threshold are marked as blind pixels; after median filtering compensation is carried out on blind pixels, a time-space domain difference operator non-uniformity correction model is established for an infrared image sequence, and the infrared image sequence is solved by using an alternating direction operator method, so that the infrared image sequence is pre-processed in a self-adaptive manner. When the method is used for preprocessing, the accuracy of blind pixel compensation is high, the non-uniformity noise correction effect is good, and image artifacts are effectively reduced.

The invention discloses a low-orbit image artifact rapid elimination method based on a pulse coupling neural network. The method comprises the following steps: S1, acquiring original low-orbit image data; s2, inputting the original low-orbit image data into a satellite-borne hierarchical progressive pulse coupling neural network model; s3, forming an artifact candidate region, and generating an artifact probability graph based on the synchronization pulse connectivity and the information entropy increment; s4, generating preprocessed low-orbit image data, and synchronously generating a reversible repair log; s5, generating an artifact-rejected high-quality image product; and S6, updating the coupling gain coefficient and the link strength threshold of the spaceborne hierarchical progressive pulse coupling neural network model according to the processing state of the artifact-rejected high-quality image product. The system is stable in closed-loop operation, the image quality is remarkably improved, the processing delay meets the quick remote sensing service requirement, and the engineering feasibility is achieved.

Disclosed herein is a medical system (100, 300) comprising a memory (110) storing machine executable instructions (116) and a super resolution neural network (118). The super resolution neural network is configured to receive an initial magnetic resonance image (114, 114′) descriptive of a subject (318), having a first resolution, and containing an image distortion artifact. The image distortion artifact is a Gibbs ringing image artifact. The super resolution neural network is configured to output an enhanced magnetic resonance image in response to receiving the initial magnetic resonance image. The enhanced magnetic resonance image has a second resolution, that is higher than the first resolution, and has a reduction or removal of the image distortion artifact. Execution of the machine executable instructions causes a computational system (104) to: receive (200) the initial magnetic resonance image and receive (204) the enhanced magnetic resonance image in response to inputting the initial magnetic resonance image in to the super resolution neural network.

There is provided a method for suppressing an image artifact in an ultrasound data set of an anatomical structure, the anatomical structure comprising a volume of biological tissue having a first acoustic attenuation and a fluid-filled cavity having a second acoustic attenuation lower than the first acoustic attenuation. The method comprises obtaining a first ultrasound data set of the anatomical structure including the biological tissue and a fluid-filled cavity, the first ultrasound data set comprising a region of interest; processing the first ultrasound data set using computer implemented signal or image processing techniques, wherein the processing includes compensating for the lower acoustic attenuation in the fluid-filled cavity; and obtaining a second ultrasound data set of the anatomical structure including the biological tissue and the fluid-filled cavity, wherein the second ultrasound data set comprises said region of interest and where image artifacts related to the lower acoustic attenuation of said fluid-filled cavity are suppressed relative to said first ultrasound data set.

The disclosure relates to multiplanar reformation of three-dimensional medical images. In particular, the invention provides a method for reformatting image sequences by determining a landmark plane intersecting a volume, acquiring an image sequence, reformatting the image sequence along the landmark plane to produce a first reformatted image sequence, perturbing the landmark plane to produce a perturbed landmark plane, reformatting the first reformatted image sequence along the perturbed landmark plane to produce a second reformatted image sequence, mapping the second reformatted image sequence, the image sequence, and the landmark plane, to a resolution enhanced image sequence using a trained image enhancement network, and displaying the resolution enhanced image sequence via a display device. The present disclosure provides approaches which may reduce image artifacts in retrospectively reformatted image sequences, particularly in cases of retrospective reformatting of medium or low-resolution image sequences, without relying on acquisition of high-resolution 3D images.

An electronic device may include a stereoscopic display that is configured to display three-dimensional content for a viewer. The stereoscopic display may include a lenticular lens film with lenticular lenses that extend across the length of the display and may be referred to as a lenticular display. The lenticular display may have convex curvature. The lenticular display may include a color filter layer with color filters and an opaque masking layer. The color filter layer may be interposed between the lenticular lens film and an array of display pixels for the display. The color filter layer may mitigate ghost image artifacts and reflections of ambient light. Microlenses may be included between the lenticular lens film and the array of display pixels to improve the efficiency of the display. The display may include a Fresnel lens layer. The lenticular lens film may include lenticular lenses having different shapes.

The invention provides a radiographic inspection real-time quality inspection system and device based on artificial intelligence and cloud edge collaboration, and relates to the technical field of radiographic inspection quality inspection.The system mainly comprises a data acquisition and preprocessing module, an AI analysis module and an early warning response and feedback module which are sequentially arranged; the data acquisition and preprocessing module comprises a medical image unit, a hospital information unit, an equipment parameter unit and a data association unit; the AI analysis module comprises a medical image recognition unit, an anatomical feature and left and right identifier analysis unit and a data fusion comparison and risk assessment unit. According to the scheme, abnormal conditions such as mismatching between the inspection application and the actual operation and image artifacts can be recognized and early warned in an extremely early stage, so that the probability of operation errors is remarkably reduced, medical quality accidents are effectively avoided, and the standardization and safety of radiation inspection are improved.

A method comprising: receiving 4D-tomographic image data, said 4D-tomographic image data including a plurality of 3D-tomographic image data of an examination object, and the plurality of 3D-tomographic image data corresponding to a plurality of time points; applying a segmentation algorithm to the 3D-tomographic image data, wherein the segmentation algorithm is configured to segment at least one organ in the 3D-tomographic image data to which the algorithm is applied; applying a scoring function to the segmented organ(s), wherein the scoring function is configured to determine a scoring value(s) for the segmented organ(s), and wherein the scoring value includes and / or corresponds to a metric quantifying an extent to which a vicinity of voxels at a surface of the segmented organ(s) contain(s) an image artifact; comparing the scoring value(s) with a threshold value; and providing a user notification, when at least one scoring value exceeds the threshold value.

The invention discloses an underwater image enhancement method based on space-frequency feature interaction, and the method achieves the high-quality enhancement of an underwater image through the deep learning technology. The underwater image enhancement network mainly comprises an amplitude sub-network, a phase sub-network and a degradation feature extraction module, and a space-frequency feature interaction module is introduced. The amplitude sub-network is used for improving color and contrast features of an underwater image, the phase sub-network is used for recovering texture details and structure information of the image, and the degradation feature extraction module is used for pertinently guiding an enhancement process of degradation features. The space-frequency feature interaction module realizes complementary learning of global and local features, and solves the problem of lack of global consistency caused by convolution operation locality. Besides, a special frequency domain loss function is designed in the method, frequency components are constrained, and image artifacts caused by frequency deviation are suppressed.

The invention relates to quantum MRI (Magnetic Resonance Imaging) equipment for rapid and intelligent scanning for cerebral hemorrhage conversion detection, which belongs to the technical field of medical instruments and comprises a scanning bed, an MRI scanning coil support is fixed at the upper end of the head of the scanning bed, a quantum coding disc is arranged in the middle of the support, a patient self-adaptive fixing device is mounted at the top of the bed, and the side edge is connected with a control system signal acquisition module. The quantum coding disc is connected with the support through a deep groove ball bearing and is driven by a mechanical transmission device. The patient self-adaption fixing device comprises a pressure sensor array, an image recognition camera, a mechanical clamping arm and a flexible fixing pad. The device uses the quantum coding disc to perform fast coding, combines the patient adaptive fixing device to reduce image artifacts, can adapt to different patients, significantly improves the detection efficiency and the image quality, integrally controls the device through the central controller to realize intelligent automatic operation, effectively solves the problems that the traditional MRI detection time is long, the image is susceptible to interference and the like, and improves the detection efficiency and the image quality. And an efficient and accurate solution is provided for cerebral hemorrhage conversion detection.

The invention relates to a medical image artifact classification method based on a CN-CLIP model, and the method comprises the steps: obtaining a medical image data set containing a plurality of CT images and MR images, and constructing a text label data set in a multi-segment cue word format based on the image type, examination part and artifact type of each image; performing fine tuning on the CN-CLIP pre-training model by using the medical image data set and the text label data set to obtain an artifact classification model; and inputting a medical image to be classified into the artifact classification model, and outputting an artifact classification result of the medical image. According to the medical image artifact classification method based on the CN-CLIP model, the pre-trained Chinese image-text matching model CN-CLIP is utilized, so that the defect that models need to be trained respectively for different image types and examination parts in the prior art is overcome; efficient and accurate artifact classification of CT and MR medical images of different parts is realized through a unified model.

A computer-implemented method and a microscopy system remove image artifacts from artifact-containing microscope images using a machine-learned artifact removal model. This model is trained without acquiring image pairs with and without artifacts. Instead, only microscope images (20-26) containing artifacts (A) are available, from which a set (S) of artifact-containing and / or artifact-free image patches (30-37) is derived. This set is used to train a generative model (Gen, Gen'). Backprojections of image patches (40A-43A) from another set (S2) are calculated into a parameter space of the generative model. Feature vectors (w1, w2) are determined from which the generative model generates image patches (40B-43B) that differ from the image patches (40A-43A) of the further set (S2) in whether they contain artifacts or are artifact-free.These image pairs are used to train the artifact removal model (AM), with an artifact-containing image patch from one of the image pairs serving as input and an artifact-free image patch from that pair as the corresponding target. After training, the artifact removal model generates an artifact-free microscope image (29) from an artifact-containing microscope image (28).

A method includes obtaining emission-tomography functional image data and a corresponding reconstructed anatomical image volume including at least one organ having natural motion; pre-determining a dedicated model for spatial mismatch correction of the at least one organ; performing initial image reconstruction of the emission-tomography functional image data to generate a reconstructed emission-tomography functional image volume utilizing attenuation correction based on the corresponding reconstructed anatomical image volume; and identifying relevant anatomical regions, within both image volumes, where functional image quality may be affected by the natural motion of the at least one organ. The method includes identifying and evaluating potential attenuation-correction image artifacts in the reconstructed emission-tomography functional image volume; estimating model parameters based on confirmed attenuation-correction image artifacts; correcting the corresponding reconstructed anatomical image volume to generate a corrected anatomical image volume; and reconstructing the emission-tomography functional image data utilizing attenuation correction based on the corrected anatomical image volume.