47 results about "Mri scan" patented technology

An exemplary AI system and method are disclosed for reconstructing high-fidelity motion-corrected MRI scans from low-field, motion-corrupted MRI scans (e.g., neonatal MRI data) using a neural network (NN) model in combination with a physics-based motion model. The exemplary AI system and method can enhance image quality and remove motion artifacts which can allow for scans to be performed with significantly reduced scan time, a particular benefit for neonatal subjects as well as all patients when employing low-field MRI.

The invention relates to an apparatus (10) for monitoring a patient undergoing a magnetic resonance image (MRI) scan. The apparatus comprises an input unit (20), a processing unit (30) and an output unit (40). The input unit is configured to provide the processing unit with at least one sensor data of a patient undergoing an MRI scan of an MRI scanner. The input unit is configured to provide the processing unit with at least one scan parameter of the MRI scanner for the MRI scan. The input unit is configured to provide the processing unit with at least one characteristic of the patient. The processing unit is configured to predict a stress level of the patient and / or a predicted motion state of the patient, one or more predictions comprising utilizing the at least one sensor data of the patient, the at least one scan parameter of the MRI scanner and the at least one characteristic of the patient. The output unit is configured to output information related to the predicted stress level of the patient and / or the predicted motion state of the patient.

This invention discloses a coherent electrical stimulation method for idiopathic scoliosis combined with exercise therapy, belonging to the field of electrical stimulation methods for idiopathic scoliosis. It aims to address the problem of how to dynamically adjust stimulation parameters based on individual differences to improve treatment efficacy. The method includes acquiring raw image sequences of the patient's spine through MRI scans, preprocessing the raw image sequences to construct a three-dimensional geometric model of the spine, configuring simulated electrical property parameters for the tissue structures, and then adding coherent electrical surface electrodes to the model. The electrode placement area on the three-dimensional geometric model of the spine is initially defined, and a coherent electrical stimulation signal is generated using a function generator. A comprehensive evaluation index value is calculated through finite element analysis to dynamically adjust the coherent electrical stimulation signal. Based on the coherent electrical stimulation signal parameters and its comprehensive evaluation index value, a coherent electrical stimulation scheme is determined, and ultrasound-guided technology is used to locate the electrode positions and implement coherent electrical stimulation therapy.

Device (1) for obtaining a spatial instrument image (60) of a medical instrument (50) and an anatomical image (62) using a magnetic resonance imaging (MRI) device (10), wherein the device (1) comprises a medical instrument (50), a MRI device (10), and a computing and control unit (70), wherein the medical instrument (50) comprises at least one marker material in at least one region (52, 52', 52'') that exhibits a nuclear magnetic resonance outside the proton resonance range, and wherein the computing and control unit (70) for controlling the MRI device (10) is configured such that, by means of the MRI device (10), a nuclear magnetic resonance imaging scan using proton resonance is performed to obtain a spatial anatomical image (62), and a nuclear magnetic resonance imaging scan using the nuclear magnetic resonance of the at least one marker material is performed. Acquisition of a spatial instrument image (60) is carried out,wherein the computing and control means (70) is designed to receive the anatomy image (62) and the instrument image (60) and to superimpose the anatomy image (62) and the instrument image (60) in the correct position and orientation, characterized in that the computing and control means (70) comprises an image model (56) of the medical instrument (50) and is designed to determine the position and orientation of the medical instrument (50) by means of the instrument image (60) and to superimpose the image model (56) of the medical instrument (50) onto the anatomy image (62) in the correct position and orientation.

A multi-task deep learning system for the detection of Alzheimer's and Parkinson's disease using MRI, consisting of: a ResNet18-based Convolutional Neural Network (CNN) module configured to extract spatial features from preprocessed T1-weighted MRI scans; a first classification head coupled to the CNN module and configured to predict the disease type from a group consisting of Alzheimer's disease (AD), Parkinson's disease (PD) and a healthy control group; a second classification head which is conditionally activated by the first classification head when Alzheimer's disease is predicted and is configured to classify the Alzheimer's stage into one of the following stages: very mild, mild or moderate dementia; a combined loss function module configured to integrate categorical cross-entropy loss for disease classification and weighted cross-entropy loss for Alzheimer stage classification; an interpretability engine configured to provide predictive explanations and including the following: a Grad-CAM module for class-specific spatial activation mapping, a SHAP module for global feature mapping at the voxel level and a LIME module for the local, surrogate-based explanation of individual MRI scan predictions.

The embodiment of the invention provides a high-precision spatial registration method and system based on a total ankle skeleton, and belongs to the technical field of medical image processing, and the method comprises the steps: obtaining tibia and talus three-dimensional data through CT or MRI scanning, and constructing and storing a high-precision skeleton simulation model; positioning trackers containing asymmetrically distributed passive infrared reflection balls are fixed to the tibia and the talus respectively, based on the positioning trackers, double cameras of an optical tracker are used for shooting the reflection balls, three-dimensional coordinates of mark points are obtained through parallax calculation, the real-time space posture of the bone is fitted, a registration matrix is updated, and based on a preoperative model and the tracking posture, the three-dimensional coordinates of the mark points are obtained. A talus coordinate system and a tibia coordinate system are constructed respectively, coarse registration is carried out through coarse registration points based on the coordinate systems, then fine registration points are collected through a probe, fine registration is carried out through a weighted iteration nearest point algorithm, and space registration is completed. According to the invention, through multi-modal data fusion, dynamic pose tracking and a weighted iteration nearest point algorithm, full-ankle bone submillimeter-level high-precision space registration is realized.

This utility model discloses an MRI scan positioning patch containing cod liver oil, belonging to the field of MRI scan auxiliary technology. It includes an upper transparent membrane and a lower transparent membrane, with a cod liver oil layer disposed between the upper and lower transparent membranes. The sides of the upper and lower transparent membranes are sealed together by a heat-sealing layer. This MRI scan positioning patch has a scientific and reasonable design. It uses a patch form to carry the cod liver oil, has a simple and novel structure, is easy to apply to the patient's skin, and is convenient to use, avoiding the discomfort caused by adhesive tape. Furthermore, the adhesive layer ensures the stability of the patch after application, improving the efficiency of clinical operations during MRI scans and demonstrating strong practicality.

A dynamic contrast-enhanced MRI reconstruction method may include: when preparing to inject a contrast agent and during injection thereof, using a DCE-MRI sequence to scan an imaging target, and using a high temporal resolution scanning parameter value pre-inputted by a user to acquire K-space data of each phase with high temporal resolution; based on the acquired K-space data of each phase with high temporal resolution, reconstructing an image of each phase with high temporal resolution; based on a low temporal resolution reconstruction parameter value pre-inputted by the user, subjecting adjacent K-space data of multiple phases with high temporal resolution to summing and averaging in a complex field, and subjecting K-space data obtained after averaging to image reconstruction, to obtain an image of each phase with low temporal resolution. Advantageously, images with high and low temporal resolution can be obtained simultaneously with just a single DCE-MRI scan.

Systems, computer software, and methods are disclosed for generating a relative electron density map (RED) from a magnetic resonance imaging (MRI) scan. This may include acquiring an MRI scan of a portion of a patient and segmenting a first region and a second region in the MRI scan. A RED map may then be generated from the MRI scan by assigning a first RED to the first region, assigning a second RED to the second region, and assigning a RED to unsegmented regions in the MRI scan based on their intensity in the MRI scan.

The invention relates to a method for performing an MRI examination of a patient using an MRI system, the MRI system, a computer-implemented method for providing a media signal using an AI system, the AI ​​system, and an associated computer program product. The inventive method for performing an MRI examination of a patient using an MRI system comprises the following steps: - Adjusting an examination parameter of the MRI examination to the patient using a control unit of the MRI system, - Providing the adapted investigation parameter via the control unit as an input parameter for a generative AI system, wherein the generative AI system is configured to generate a media signal as an output parameter in response to an input of the provided input parameter and to make the generated media signal available for retrieval, wherein the generated media signal depends on the adapted investigation parameter and includes an audio track and / or a video track, - Receiving the generated media signal by means of a playback unit, - Performing the MRI examination of the patient according to the adapted MRI examination parameters using the MRI system in such a way that the received media signal is played back to the patient via the playback unit during the procedure.

Methods and systems for assessing gut barrier function with medical imaging techniques and orally ingested contrast are discussed herein. For example, a method for assessing gut health of a patient includes administering a contrast agent to the patient. The method further includes performing an magnetic resonance imaging (MRI) scan of the patient. The method further includes determining a metric corresponding to the contrast agent in a gut of the patient based on the performed MRI scan. The method further includes assessing health of the gut of the patient based on the metric corresponding to the contrast agent in the gut of the patient.

A method and system for modifying a series of magnetic resonance imaging (MRI) scan sequences for use in a single MRI examination. In one embodiment, a method and system intersperse a set of B1 amplitude measurement sequences within a received series of MRI scan sequences such that an RF parameter value of at least one scan sequence of the received series of MRI scan sequences is altered based on the results of at least one of the interspersed set of B1 amplitude measurement sequences.

This invention relates to the field of ultrasound therapy technology, specifically to an ultrasound localization method based on low-field magnetic resonance imaging (MRI). The method addresses the issues of large equipment size and high cost in existing ultrasound targeting techniques. By introducing a parallel ultrasound scanning process during the initial MRI scan to obtain ultrasound echo data, which is then stitched together with the MRI data. Subsequently, during target area localization, the ultrasound echo data and MRI data are analyzed simultaneously, enabling accurate localization of the target area in the brain and identification of easily penetrable locations on the skull where ultrasound energy can pass through. Based on this, an ultrasound probe with better penetration is selected as the focusing probe, eliminating probes with low emission efficiency, thereby improving the efficiency of ultrasound localization. Furthermore, improvements to the model allow the examination process to be performed using a low-field MRI system, reducing system costs.

This invention provides a device and method for acquiring a three-dimensional model of abdominal organs, comprising: a coil support assembly, an MRI scanner, and an image processing device; the coil support assembly is clamped and fixed to the side of the examination bed to support the abdominal coil and reduce pressure on the abdomen of the user; the MRI scanner is positioned above the abdomen of the user, with the axis of the examination positioning light aligned with the midpoint of the axis of the coil support assembly, and a magnetic resonance imaging (MRI) scan sequence is acquired by scanning with the MRI scanner; the image processing device is communicatively connected to the MRI scanner, acquires the MRI scan sequence, and obtains a three-dimensional model of the abdominal organs based on the MRI scan sequence. This invention achieves precise extraction of abdominal organs at all levels through multi-region seed point strategies and adaptive threshold segmentation, overcoming the inefficiency and subjective limitations of traditional manual segmentation, and ensuring the reliability of the results through automated algorithms, thus providing support for the image analysis of abdominal organs.

The invention relates to the technical field of orthopedic surgery navigation, and discloses an orthopedic surgery navigation system based on an AR technology, and the method comprises the steps: obtaining skeleton structure data of a patient through MRI scanning, carrying out the segmentation and reconstruction of original data through an image processing algorithm, and extracting a three-dimensional model of a skeleton structure; tracking and positioning the key feature region according to the extracted three-dimensional model of the skeletal structure so as to realize real-time tracking of the skeletal structure of the patient; constructing a virtual operation scene according to the skeleton structure data of the patient, and vividly rendering a skeleton model, an operation tool, a tissue and other elements by using a computer graphics technology; performing sensor calibration on the AR equipment and the surgical workstation, determining the position and direction of the AR equipment in the space by using a preset reference point or a marker, and establishing a mapping relation of a camera-world coordinate system; and performing virtual-real fusion on pre-planned navigation information and the actual skeleton structure of the patient according to the skeleton structure tracked in real time and the reconstructed operation scene, and superposing the navigation information in the visual field of a doctor in a virtual form through AR equipment to guide the doctor to perform an operation.

A system and method for controlling rhythmic sensory stimulation provided to a subject with post-stroke depression, PSD, during an MRI scan. A control unit is configured to control a rhythmic sensory stimulation signal such that the signal is rhythmically synchronous to a scanning rhythm of an MRI scanner performing the MRI scan.

The invention relates to a method for performing an MRI examination of a patient using an MRI system, the MRI system, a computer-implemented method for providing a media signal using an AI system, the AI ​​system and an associated computer program product. The inventive method for performing an MRI examination of a patient using an MRI system comprises the following steps: - Adjusting an examination parameter of the MRI examination to the patient using a control unit of the MRI system, - Providing the adapted investigation parameter via the control unit as an input parameter for a generative AI system, wherein the generative AI system is configured to generate a media signal as an output parameter in response to an input of the provided input parameter and to make the generated media signal available for retrieval, wherein the generated media signal depends on the adapted investigation parameter and includes an audio track and / or a video track, - Receiving the generated media signal by means of a playback unit, - Performing the MRI examination of the patient according to the adapted MRI examination parameters using the MRI system in such a way that the received media signal is played back to the patient via the playback unit during the procedure.

This utility model discloses a quick stretcher for magnetic resonance imaging (MRI), belonging to the technical field of MRI-assisted equipment. It includes a support plate made of non-magnetic material; the shape of the support plate matches the scanning bed; two non-magnetic zippers are provided at one end of the support plate along its length, the two zippers being parallel and extending along the length of the support plate; two lifting rods are located on both sides of the support plate along its length; the lifting rods are detachably connected to the support plate; the connection between the lifting rods and the support plate allows for patient transport. After the patient and support plate are placed together on the scanning bed, the lifting rods can be easily removed without affecting the MRI scan, eliminating the need for secondary handling. The structure is simple, easy to manufacture, and inexpensive. Simultaneously, the two non-magnetic zippers at one end of the support plate are opened during MRI head scanning, allowing the scanning bed to enter the gradient coils unimpeded for scanning, without the support plate obstructing the scan, thus facilitating MRI scanning of the patient's head.

The invention relates to an MRI detection system for AIMD. The detection system includes monitoring or detecting a signal from a magnetic field sensitive element. The magnetic field sensitive element may include at least one of an inductor, a reed switch, and a Hall sensor within the IPG. The magnetic field sensitive element may assist the AIMD in detecting MRI to trigger an MRI safe mode in order to prevent adverse effects when performing an MRI scan.

A system and method for MRI-guided radiotherapy may be provided. The method may include obtaining first auxiliary signals and second auxiliary signals collected by an MRI device during an MRI scan of a target subject, wherein the first auxiliary signals are collected by the MRI device at a first time before radiotherapy rays are emitted, and the second auxiliary signals are collected by the MRI device at a second time after the radiotherapy rays are emitted. The method may also include determining whether a first motion amplitude of the target subject from the first time to the second time is greater than a threshold based on the first auxiliary signals and the second auxiliary signals. The method may further include determining whether to stop emitting the radiotherapy rays based on a determination result of whether the first motion amplitude is greater than the threshold.

A control system and method for a magnetic resonance imaging (MRI) system controller is provided to sub-sample k-space for an MRI scan. The method includes, for each radio-frequency excitation pulse in the MRI scan, sub-sampling ky-kz planes using a three-dimensional (3D) echo planar imaging (EPI) sequence by coherently sub-sampling phase encodings in the ky dimension and incoherently sub-sampling phase encodings in the kz dimension. The coherent sub-sampling corresponds to a number of radio-frequency excitation pulses. The ky-kz planes represent a sub-sampling pattern in the ky-kz space, using an incoherent sub-sampling in the kz dimension.

This application relates to a method, apparatus, computer equipment, and storage medium for controlling a magnetic resonance imaging (MRI) bed. The method includes: determining a bed movement strategy based on a target body part of the patient being scanned, wherein the bed movement strategy includes setting a corresponding safe movement speed for each position of the target body part during bed movement; generating bed control commands based on the bed movement strategy; and controlling the bed movement system to adjust the bed movement speed according to the bed control commands, so that the bed movement speed does not exceed the safe movement speed. This method can not only reduce the patient's discomfort during MRI scanning but also ensure the scanning efficiency of the MRI scan.

Methods, computer-readable storage devices, and systems are described for reducing movement of a patient undergoing a magnetic resonance imaging (MRI) scan. One method includes receiving a data frame from the MRI system performing the MRI scan of the patient, comparing the data frame to a reference image to assess motion of a body part of the patient during the MRI scan, generating stimulus to be communicated to the patient during the MRI scan based on a task of the MRI scan and the motion of the body part of the patient during the MRI scan, adjusting the stimulus during the MRI scan to adjust the task and as the motion of the body part of the patient changes, and communicating the stimulus to the patient during the MRI scan, wherein the sensory feedback includes at least one of a game, a movie, a cartoon, a shape, or an auditory signal.

Methods and systems are provided for automatic placement of at least one saturation band on a medical image, which may direct saturation pulses during a MRI scan. A method may include acquiring a localizer image of an imaging subject, determining a plane mask for the localizer image by entering the localizer image as input to a deep neural network trained to output the plane mask based on the localizer image, generating a saturation band based on the plane mask by positioning the saturation band at a position and an angulation of the plane mask, and outputting a graphical prescription for display on a display device, the graphical prescription including the saturation band overlaid on the medical image.

A method for preparing a magnetic resonance imaging (MRI) scan of an examination subject may include performing an adjustment prescan of the examination subject, where the adjustment prescan may be performed using a MRI process. The method may include determining adjusted physical parameter values of the MRI scan based on the adjustment prescan and specifying geometric parameter values of the MRI scan based on the adjustment prescan.

An apparatus for monitoring patients undergoing a Magnetic Resonance Image (MRI) scan provides an input, a processor, and an output. The input provides the processor with at least one sensor data of a patient undergoing an MRI scan by an MRI scanner. The input provides the processor with at least one scan parameter of the MRI scanner for the MRI scan. The input also provides the processor with at least one characteristic of the patient. The processor predicts a stress level of the patient and / or a motion state of the patient, the prediction or predictions utilize at least one sensor data of the patient, the at least one scan parameter of the MRI scanner, and the at least one characteristic of the patient. The output outputs information relating to the predicted stress level of the patient and / or the predicted motion state of the patient.

A system for generating a simulated SWI image of a human brain based on an SNC MR image of the human brain, comprising: an input image module for storing the SNC MR image; a preprocessing module for receiving the SNC MR image, the preprocessing module for preparing and generating the SNC MR image into a standard format for an AI model to extract and classify features of the SNC MR image; a simulated SWI generation model module for receiving the SNC MR images in the stent format and generating simulated SWI images corresponding to each SNC MR image; the deep learning platform is used for operating the AI model, and the AI model is in a connected state; the training module is used for receiving training data and transmitting the training data to the deep learning platform so as to adjust adjustable parameters of the AI model to optimize and generate a simulated SWI image; the test module is used for communicating with the training module and the deep learning platform to receive test data, and the test module is used for verifying the simulated SWI image by using a pre-trained performance standard; and the output storage module is used for receiving and storing the synthesized SWI image.

Methods, systems, and apparatuses are described for analyzing metabolite levels from regions of interest (ROI) of a human brain. An MRI scan of an individual's brain may be received, and may be normalized to produce a Montreal Neurological Institute (MNI)-space MRI scan. A region of interest (ROI) of the individual's brain may be identified on the MNI-space MRI scan. The identified ROI of the individual's brain may- be converted back to the native space and then mapped to a spectroscopic grid. A weighted spectral average method may be applied to determine a spectrum value associated with the ROI of the individual's brain. A metabolite map of the metabolite levels of the ROI of the individual's brain may generated based on the spectrum value.

A frequency offset is selected based on similarity measures of multiple MRI images obtained from frequency scout measurements associated with multiple frequency offsets from a reference frequency of a magnetization excitation pulse. The similarity measure for each respective MRI image of the multiple MRI images is determined based on a comparison between at least one reference image and the respective MRI image. The at least one reference image is determined from the multiple MRI images based on spectrum information of each of the multiple MRI images. Such methods facilitate automatically determining / selecting a more optimal frequency offset for an MRI scan following a frequency scout scan, in particular, for an SSFP or a bSSFP pulse sequence, and thereby banding artifacts and / or flow-related artifacts can be reduced for the MRI scan.

This application provides a multi-level MRI segmentation method for diagnosing tumors. In this application, the tumor type identification process is divided into three stages, from coarse to fine, using different models based on the U-Net framework. For 3D MRI scans of tumor patients, the first stage identifies the first human organ / tissue region using a first segmentation model; the second stage uses a binary segmentation model to identify the tumor region within the first human organ / tissue region; and the third stage uses a multi-class segmentation model to classify different tumors. This three-stage multi-level segmentation improves the accuracy of tumor classification, thereby contributing to the advancement of tumor treatment.