93 results about "Multimodality" patented technology

The invention comprises a system and method for creating medical images of a subject patient using a plurality of imaging devices, such as tomographic imaging scanners. The imaging devices each have a bore through which a patient is translated during scanning. The imaging devices can be moved apart to allow greater access to a patient between the bores.

A Multimodality Brain Mapping System (MBMS), comprising one or more scopes (e.g., microscopes or endoscopes) coupled to one or more processors, wherein the one or more processors obtain training data from one or more first images and / or first data, wherein one or more abnormal regions and one or more normal regions are identified; receive a second image captured by one or more of the scopes at a later time than the one or more first images and / or first data and / or captured using a different imaging technique; and generate, using machine learning trained using the training data, one or more viewable indicators identifying one or abnormalities in the second image, wherein the one or more viewable indicators are generated in real time as the second image is formed. One or more of the scopes display the one or more viewable indicators on the second image.

A mattress system is provided that is optimized for the hospital setting and includes a guiderail system that accepts a variety of accessories for attachment thereto. The guiderail system may have integrated data lines, power lines, gas lines, and / or fluid lines. Also provided are radioabsorbant shields, trays and other components designed for optimal use with the mattress system.

A left atrial appendage occlusion device is provided that acts in conjunction with a wireless transponder unit. The occlusion device provides a seal of the left atrial appendage opening, while the transponder is inserted into the left atrial appendage to sense one or more physiological conditions and relay the sensed information over wireless communication. Further, all or part of the left atrial appendage may be filled using a biocompatible inert filling material injected into the left atrial appendage as part of deployment of the transponder unit.

The present invention provides the multimodality filtration surveillance comprising of a plurality of filtration stages executed at the backend server to confirm nature of anomaly in an event, the filtration stages comprising: a first filter of a video anomalies detection in the event for a specified time-place value, a second filter of a city soundscape adapted to provide a localized decibel maps of a city, a third filter of a geocoded social network adapted to semantically read and analyze data from one or more social media corresponding to the specified time-place value, and a fourth filter of an event triggered or proactive local participatory surveillance adapted to provide augmented information on the detected anomalies.

The embodiment of the invention provides a model training method, device and system and a storage medium. The network training method comprises the steps that a training image and a training image mask are acquired; the training image is input into a front-end model structure in an instance segmentation model to obtain a target region alignment feature map, wherein the target region alignment feature map is a feature map which corresponds to a first target region used for indicating the position of a target object in the training image and is subjected to alignment operation; the target regionalignment feature map is input into a mask generator in the instance segmentation model to obtain a generated segmentation mask corresponding to the target region alignment feature map; a real segmentation mask corresponding to the target region alignment feature map is determined based on the training image mask; and the target region alignment feature map, the generated segmentation mask and the real segmentation mask are utilized to perform adversarial training on the mask generator and a discriminator. Through the method, the problem that the mask generator is influenced by image multimodality can be effectively solved.

The invention discloses a modeling and on-line monitoring method based on multimodality collaboration time frame automatic division, which takes variation of process characteristics in batch shaft and time direction as well as time sequence of time frame running into consideration, and includes the steps of diving all the modalities through collaboration time frame, obtaining a unified time frame division result among different modalities, and building a uniform time frame model for similar process characteristics in each modality to simplify the modeling complexity. According to the invention, based on the result of collaboration time frame division, the relative change among all the modalities is analyzed, a multimodality statistic model based on different fluctuation types is built and applied in on-line monitoring, and the on-line monitoring performance is improved; the method is easy to implement, is successfully applied during the injection molding, not only facilitates the understanding of process characteristic, but also enhances the reliability and confidence level of actual on-line process monitoring, facilitates judging the running state of the industrial process, and timely discovers faults, thereby guaranteeing the safe and reliable running of actual production and the pursuit of high-quality products.

A system and method for specificity-based multimodality three-dimensional optical tomography imaging comprises steps of: optical imaging to obtain a light intensity of body surface optical signal of an imaging target; CT imaging to obtain structure volume data; establishing an equation representing a linear relationship between the distribution of the obtained light intensity of body surface optical signal of the imaging target, the obtained CT discrete mesh data and the distribution of unknown internal self-luminescence light sources; establishing a dynamic sparse regularization target function in every iteration for the equation; and reconstructing a tomography image. The present invention well considers the optical specificity of tissue, in which there is a non-uniform optical characteristic parameter distribution within the same tissue when finite element modeling is used, which is closer to the real situation, so that an accurate imaging effect is achieved.

A method of using an integrated intraluminal imaging system includes an optical coherence tomography interferometer (OCT), an ultrasound subsystem (US) and a phase resolved acoustic radiation force optical coherence elastography subsystem (PR-RAF-OCE). The steps include performing OCT to generate a returned optical signal, performing US imaging to generate a returned ultrasound signal, performing PR-ARF-OCE to generate a returned PR-ARF-OCE signal by generating a amplitude modulated ultrasound beam or chirped amplitude modulated ultrasound beam to frequency sweep the acoustic radiation force, measuring the ARF induced tissue displacement using phase resolved OCT method, and the frequency dependence of the PR-ARF-OCE signal, processing the returned optical signal, the returned ultrasound signal and the measured frequency dependence of the returned PR-ARF-OCE optical coherence elastographic signal to quantitatively measure the mechanical properties of the identified tissues with both spectral and spatial resolution using enhanced materials response at mechanically resonant frequencies to distinguish tissues with varying stiffness, to identify tissues with different biomechanical properties and to measure structural and mechanical properties simultaneously.

The invention relates to a method for three-dimensional registration and brain tissue extraction of individual human brain multimodality medical images. The method comprises the following steps: reading DICOM medical image data, and converting DICOM format data into NIfTI format data; layering images adopting a nuclear magnetic resonance structure; establishing a mixture gaussian model through an east Asia brain structure template and an east Asia brain tissue probability graph of ICBM, and dividing nuclear magnetic data into a grey matter part, a white matter part and a cerebrospinal fluid part; enabling the registration methods of other modality data and nuclear magnetic structure images to be the same; according to a layering and registration result, removing a skull and other parts outside the skull of each modality, and reserving the structure of parts inside the skull; adding weighting of three tissue probability graphs of the grey matter, the white matter and the cerebrospinal fluid obtained through layering of structure images so as to obtain a brain tissue probability graph, and performing Gaussian kernel smoothness; setting a threshold, applying the threshold to each modality image data after registration and resampling, and removing the cranium and parts outside the cranium; outputting a save result in an NIfTI format. According to the method disclosed by the invention, the registration of various structure images and multiplanar reconstruction images of a tested person can be completed at the same time.

An implantable tissue marker incorporates a contrast agent sealed within a chamber in a container formed from a solid material. The contrast agent is selected to produce a change, such as an increase, in signal intensity under magnetic resonance imaging (MRI). An additional contrast agent may also be sealed within the chamber to provide visibility under another imaging modality, such as computed tomographic (CT) imaging or ultrasound imaging.

The invention relates to a multimodality bionic body model applied to ultrasonic or nuclear magnetic resonance detection. The multimodality bionic body model comprises a tissue organ body model, a fixed base and a fluid control system, wherein the tissue organ body model comprises a plurality of body model units imitating human body tissue organs, the plurality of body model units are fixed on the fixed base conforming human anatomy structure according to the tissue organ positions of the human anatomy structure, the tissue organ body model and the fixed base are prepared from a non-metal material, the tissue organ body model is composed of an ultrasonic and nuclear-magnetic bionic material, and the fluid control system is used for analog control of the blood circulation and respiratory movement of the human body. The multimodality bionic body model integrates the body model units imitating a plurality of main tissue organs on a human body trunk position, and is simple in structure; and the body model units are fixed on the fixed base by adopting the anatomic position relation, so as to achieve the actual imitation effect.

The invention relates to a computer aided newsmaker retrieval method based on multimedia analysis. The method comprises the following steps: data preprocessing is performed on a news picture; the multimodality fusion figure relation is initialized; event relation is initialized, a multi-relation probability matrix decomposition model is provided, the potential relations are mined, the correlations between the newsmakers and news events and the query keyword are sorted according to the query keyword submitted by a user and the reconstructed relations; and a result browsing interface is retrieved, namely the name of a person which is submitted to a computer by the user, is used as the retrieval keyword, a relation view using the query person as the center and a related news event list view are provided, and the retrieval result is fed back to the user.

A left atrial appendage occlusion device is provided that acts in conjunction with a wireless transponder unit. The occlusion device provides a seal of the left atrial appendage opening, while the transponder is inserted into the left atrial appendage to sense one or more physiological conditions and relay the sensed information over wireless communication. Further, all or part of the left atrial appendage may be filled using a biocompatible inert filling material injected into the left atrial appendage as part of deployment of the transponder unit.

The invention belongs to the technical field of information processing and particularly relates to a multimodality image fusion method combining multi-scale bilateral filtering and direction filtering. The invention is used to fuse the images of different sensors of the same scene or the same target. The method comprises the following steps: firstly, the multi-scale bilateral filtering is utilized to decompose each source image and obtain a low-pass image and a series of high-pass images; secondly, direction filtering is performed to the high-pass images to the direction indications of the images, then the low-pass images and the directional sub-band images are separtely fused according to a certain fusion rule to obtain a fused low-pass image and a fused directional sub-band image; and finally, the fused image is obtained through direction filtering reconstruction and inverse multi-scale bilateral filtering. The method of the invention has better fusion effect and is better than the traditional multi-scale geometric analysis method; and the quality of the fused image is greatly increased.

An apparatus and method for expanding the FOV of a truncated computed tomography (CT) scan. An iterative calculation is performed on the original CT image to produce an estimate of the image. The calculated estimate of the reconstructed image includes the original image center and a estimate of the truncated portion outside the image center. The calculation uses an image mask with the image center as one boundary.

An apparatus and method for expanding the FOV of a truncated computed tomography (CT) scan. An iterative calculation is performed on the original CT image to produce an estimate of the image. The calculated estimate of the reconstructed image includes the original image center and a estimate of the truncated portion outside the image center. The calculation uses an image mask with the image center as one boundary.

The invention discloses an interaction output method and system for an intelligent robot. The method comprises the steps of obtaining multimodality input data of a user; analyzing the multimodality input data to obtain an analysis result; determining a current interaction requirement according to the analysis result, and calling set output characters matched with the interaction requirement, wherein the characters are borne by images of a virtual robot; generating and outputting interaction response data aiming at the analysis result based on the set output characters. By means of the interaction output method and system for the intelligent robot, the individualized characteristics shown by the robot are matched with a current man-machine interaction progress to the greatest extent while the intelligent robot has the individualized characteristics, the anthropopathic level of the intelligent robot is increased, and the user experience of the intelligent robot is also greatly improved.

The invention provides a multimodality medical image fusion method based on multiscale anisotropic decomposition and low rank analysis. The method comprises the following steps that (1) an image pyramid is established for input images, the images on each layer are subjected to meshing, an anisotropic heat kernel related to data is established, and multiscale representation of the images is achieved; (2) the images in different scales are grouped, low rank analysis is established for each group, low rank parts are extracted, meanwhile, noise is effectively filtered out, and a multiscale space is established by extracted obvious information; (3) in each layer of the image pyramid, low-frequency information is fused by a S-type function, high-frequency information is fused by a maximum selection strategy, and interlayer sampling weights of the pyramid are fused. According to the multimodality medical image fusion method, good robustness is achieved for fusion of noise images.

Systems and methods directed to adaptive radiotherapy planning are provided. In some aspects, provided system and method include producing synthetic images from magnetic resonance data using relaxometry maps. The method includes applying corrections to the data and generating relaxometry maps therefrom. In other aspects, a method for adapting a radiotherapy plan is provided. The method includes determining an objective function based on dose gradients from an initial dose distribution, and generating an optimized plan based on updated images, using aperture morphing and gradient maintenance algorithms without need for organ-at-risk contouring. In yet other aspects, a method for obtaining 4D MR imaging using a temporal reshuffling of data acquired during normal breathing, a method for deformable image registration using a sequentially applied semi-physical model regularization method for multimodality images, and a method to generate 4D plans using an aperture morphing algorithm based on 4D CT or 4D MR imaging are provided.

Methods and devices are disclosed for the imaging of a biological sample from all rotational perspectives in three-dimensional space and with multiple imaging modalities. A biological sample is positioned on an imaging stage that is capable of full 360-degree rotation in at least one of two orthogonal axes. Positioned about the stage are imaging modules enabling the recording of a series of images in multiple modalities, including reflected visible light, fluorescence, X-ray, ultrasound, and optical coherence tomography. A computer can use the images to construct three-dimensional models of the sample and to render images of the sample conveying information from one or more imaging channels. The rendered images can be displayed for an operator who can manipulate the images to present additional information or viewing angles of the sample. The image manipulation can be with touch gestures entered using a sterilizable or disposable touch pen.

The invention discloses an embryo pregnancy result prediction device based on multimodality, and belongs to the field of medical artificial intelligence. Firstly, images of embryos developed to blastocyst stage after in vitro fertilization and corresponding pregnancy results are obtained, three pictures of blastocyst, inner cell mass and trophoblast cells of embryos are obtained, and the pregnancyresults are labeled as labels, and data are labeled as raw data. Then the image is smoothed with Gaussian kernel function to remove part of the noise, and then the image is normalized. The image is then data-augmented as input data. Multimodal method is used to fuse the images of the three images so that the input image contains three evaluation features. the fused image is passed to ResNet-50 for training, that network is optimized according to the target tag, and and is iterated until the training is complete. With the model, three images can be taken before embryo transfer to predict the pregnancy outcome, and the embryo with high success rate can be selected according to the output results, which can improve the final pregnancy success rate.

A multimodality imaging system, comprising: a first imaging system for forming a first image; a second imaging system for forming a second image; and a rotating device on which the first imaging system and the second imaging system are fixed so that the first imaging system and the second imaging system are selectively rotated to a scanning position.

Reference images from one or more OCT scanners are correlated with associated OCT scan data, which is in turn registered and correlated to a wide field image so as to present the OCT scan data registered and aligned to the correct location on the wide field image so as to permit displaying OCT scan data taken at different times or on different machines on a single screen all registered to the wide field image.

An apparatus for providing an integrated tri-modality system includes a fluorescence tomography subsystem (FT), a diffuse optical tomography subsystem (DOT), and an x-ray tomography subsystem (XCT), where each subsystem is combined in the integrated tri-modality system to perform quantitative fluorescence tomography with the fluorescence tomography subsystem (FT) using multimodality imaging with the x-ray tomography subsystem (XCT) providing XCT anatomical information as structural a priori data to the integrated tri-modality system, while the diffuse optical tomography subsystem (DOT) provides optical background heterogeneity information from DOT measurements to the integrated tri-modality system as functional a priori data. A method includes using FT, DOT, and XCT in an integrated fashion wherein DOT data is acquired to recover the optical property of the whole medium to accurately describe photon propagation in tissue, where structural limitations are derived from XCT, and accurate fluorescence concentration and lifetime parameters are recovered to form an accurate image.

A multimodality imaging system including ultrasound, optical coherence tomography (OCT), photoacoustic (PA) imaging, florescence imaging and endoscopic catheter for imaging inside the gastrointestinal tract with real-time automatic image co-registration capability, including: an ultrasound subsystem for imaging; an optical coherence tomography (OCT) subsystem for imaging, a PA microscopy or tomography subsystem for imaging and a florescence imaging subsystem for imaging. An invasive interventional imaging device is included with an instrumentality to take a tissue biopsy from a location visible on the ultrasound subsystem for imaging, on the optical coherence tomography (OCT) subsystem for imaging, photoacoustic (PA) subsystem for imaging and florescence subsystem for imaging. The instrumentality takes a tissue biopsy from a visible location simultaneously with the visualization of the tissue about to be biopsied so that the tissue biopsy location is visualized before, during and after the biopsy.

A multimodality imaging system including a plurality of imaging systems, and at least one rail upon which at least one of the imaging systems is slidingly mounted.

The invention discloses a multimodality automatic updating and replacing background modeling method which comprises the following steps: firstly, carrying out modeling of a main background and an auxiliary background, wherein the modeling of the main background is carried out by the following steps: initializing a main background model, modifying the main background model, and updating threshold; and the modeling of the auxiliary background is carried out by the following steps: establishing an alternate auxiliary background sequence, counting classified data, and updating the threshold of the auxiliary background model; and then computing the background to be updated, and determining the background to replace the auxiliary background according to the occurring frequency of the background to be updated. The method of the invention adopts a multimodality updating and replacing design concept, adopts various modalities to form a vector to carry out the modeling of the background, and finishes background adaptation to the change of ambient lighting through continuous updating and replacing among the modalities. The background modeling method of the invention is suitable for an intelligent monitoring system, and adopts a background differential method for detecting a moving target.

A multimodality imaging phantom is disclosed which is useful for calibrating devices for imaging vascular conduits. The phantom is compatible with X-ray, ultrasound and magnetic resonance imaging techniques. It allows testing, calibration, and inter-modality comparative study of imaging devices, in static or dynamic flow conditions. It also provides a geometric reference for evaluation of accuracy of imaging devices. The tissue-mimicking material is preferably an agar-based solidified gel. A vessel of known desired geometry runs throughout the gel and is connected to an inlet and outlet at its extremities for generating a flow circulation in the vessel. Said phantom also contains fiducial markers detectable in the above-mentioned modalities. The markers are preferably made of glass and are embedded in a layer of agar gel containing a fat component. The markers are implanted at precise known locations to allow identification and orientation of plane views, and they can be used for calibration, resealing and fusion of 3D images obtained from different modalities, and 3D image reconstruction from angiographic plane views. Also disclosed is a process for manufacturing said phantom.

A device for monitoring brain parameters in a patient includes at least one central nervous system function sensor, at least one brain oxygen sensor, at least one blood flow velocity sensor, a video monitor and a computational circuit. The nervous system function sensor is configured to sense a nervous system function of the patient. The brain oxygen sensor is configured to sense a brain oxygen concentration of the patient. The brain blood flow velocity sensor is configured to sense the blood flow velocity of the patient. The computational circuit is in data communication with the nervous system function sensor and the brain oxygen sensor. The computational circuit is configured to generate a graphic representation, for display on the video monitor, of the nervous system function of the patient and the brain oxygen concentration of the patient.