University of Virginia Patent Foundation

Union Strong (beijing) Technology Co. Ltd.

Springbok, Inc.

The United States of America, As Represented by the Secretary, Department of Health and Human Services

Siemens Healthcare Gmbh

Icarus Medical, LLC

Xue Feng

Craig H Meyer

John P Mugler, Iii

Michael Salerno

Samuel W Fielden

Christopher M Kramer

Zhixing Wang

Anudeep Konda

Frederick H Epstein

Ling Song

Lan Qin

Silvia Blemker

Guangming Yang

Josef Pfeuffer

David T Johnson

Li Zhao

Evan Eckersley

Max Wintermark

Kim Butts Pauly

Xiaoying Cai

Adrienne Campbell

Benjamin Scire

Joseph M Hart

Changyu Sun

Wenzhi Wang

Rajiv Ramasawmy

Lara Riem

Mohammad Abdishektaei

Matthew Cousins

Olivia DuCharme

Wilson Miller

Renkun Ni

Charles Rushton

Adrienne E Campbell-Washburn

Quan Dou

Sona Ghadimi

Systems and methods are provided for upper extremity analysis and modeling using medical imaging. The systems and methods may be used to identify and segment both muscle and fatty tissue directly from the standard clinical images, and may be fully automated, thus providing rapid assessments back to the clinician and seamless integration into the clinical decision-making workflow.

Systems and methods for extremity analysis and modeling using medical imaging

A method, an apparatus, and a device for simulating a travel path of a catheter in a blood vessel. The method comprises: determining a preset path for the catheter to travel in a target artery segment based on extending direction of an artery, wherein the target artery segment refers to an artery segment which is subsequently subjected to catheter path simulation and includes an aneurysm (S); simulating the travel path of the catheter in a lumen of the target artery segment (S); and correcting the travel path based on the preset path to obtain a corrected travel path (S): in this way, the resulting simulated and corrected travel path of the catheter may characterize the actual travel path of the catheter in the artery and may also reflect a substantial shape of the catheter indwelling in the lumen of the artery, wherein the corrected travel path highly agrees with the shape of the artery. Based on the corrected travel path, the travel path of the catheter in the blood vessel and the shape and position of the catheter indwelling in the blood vessel may be determined more accurately, such that the operator may determine more intuitively whether the catheter may be inserted to a specified position in the blood vessel, which enhances convenience. The catheter travels spirally along the arterial wall, ensuring stability of the catheter during a surgery process.

Method, apparatus, and device for simulating a travel path of a catheter in a blood vessel

Systems and methods for denoising a magnetic resonance (MR) image utilize an unsupervised deep convolutional neural network (U-DCNN). Magnetic resonance (MR) image data of an area of interest of a subject can be acquired, which can include noisy input images that comprise noise data and noise free image data. For each of the noisy input images, iterations can be run of a converging sequence in an unsupervised deep convolutional neural network. In each iteration, parameter settings are updated; the parameter settings are used in calculating a series of image feature sets with the U-DCNN. The image feature sets predict an output image. The converging sequence of the U-DCNN is terminated before the feature sets predict a respective output image that replicates all of the noise data from the noisy input image. Based on a selected feature set, a denoised MR image of the area of interest of the subject can be output.

Denoising magnetic resonance images using unsupervised deep convolutional neural networks

A computerized system and method of modeling myocardial tissue perfusion can include acquiring a plurality of original frames of magnetic resonance imaging (MRI) data representing images of a heart of a subject and developing a manually segmented set of ground truth frames from the original frames. Applying training augmentation techniques to a training set of the originals frame of MRI data can prepare the data for training at least one convolutional neural network (CNN). The CNN can segment the training set of frames according to the ground truth frames. Applying the respective input test frames to a trained CNN can allow for segmenting an endocardium layer and an epicardium layer within the respective images of the input test frames. The segmented images can be used in calculating myocardial blood flow into the myocardium from segmented images of the input test frames.

System and method for fully automatic LV segmentation of myocardial first-pass perfusion images

A method and a system for measuring morphological parameters of an intracranial aneurysm image, the method comprises: segmenting an intracranial parent artery image from three-dimensional DICOM data of DSA (S); segmenting the intracranial aneurysm image on the intracranial aneurysm image (S); and measuring morphological parameters of the intracranial aneurysm image (S). The method and the system for measuring the morphological parameters of the intracranial aneurysm image as disclosed may implement automated measurement of the intracranial aneurysm image, quickly measure morphological parameters of the intracranial aneurysm image, and guarantee consistency between measurements of morphological parameters of the aneurysm image.

Method and system for measuring morphological parameters of an intracranial aneurysm image

Methods, computing devices, and MRI systems that reduce artifacts produced by Maxwell gradient terms in TSE imaging using non-rectilinear trajectories are disclosed. With this technology, a RF excitation pulse is generated to produce transverse magnetization that generates a NMR signal and a series of RF refocusing pulses to produce a corresponding series of NMR spin-echo signals. An original encoding gradient waveform comprising a non-rectilinear trajectory is modified by adjusting a portion of the original encoding gradient waveform or introducing a zero zeroth-moment waveform segment at end(s) of the original encoding gradient waveform. During an interval adjacent to each of the series of RF refocusing pulses a first gradient pulse is generated. At least one of the first gradient pulses is generated according to the modified gradient waveform. An image is constructed from generated digitized samples of the NMR spin-echo signals obtained.

Methods and systems for Maxwell compensation for spin-echo train imaging

A method of cardiac strain analysis uses displacement encoded magnetic resonance image (MRI) data of a heart of the subject and includes generating a phase image for each frame of the displacement encoded MRI data. Phase images include potentially phase-wrapped measured phase values corresponding to pixels of the frame. A convolutional neural network CNN computes a wrapping label map for the phase image, and the wrapping label map includes a respective number of phase wrap cycles present at each pixel in the phase image. Computing an unwrapped phase image includes adding a respective phase correction to each of the potentially-wrapped measured phase values of the phase image, and the phase correction is based on the number of phase wrap cycles present at each pixel. Computing myocardial strain follows by using the unwrapped phase image for strain analysis of the subject.

Systems and methods for phase unwrapping for dense MRI using deep learning

Training a neural network to correct motion-induced artifacts in magnetic resonance images includes acquiring motion-free magnetic resonance image (MRI) data of a target object and applying a spatial transformation matrix to the motion-free MRI data. Multiple frames of MRI data are produced having respective motion states. A Non-uniform Fast Fourier Transform (NUFFT) can be applied to generate respective k-space data sets corresponding to each of the multiple frames of MRI; the respective k-space data sets can be combined to produce a motion-corrupted k-space data set and an adjoint NUFFT can be applied to the motion-corrupted k-space data set. Updated frames of motion-corrupted MRI data can be formed. Using the updated frames of motion corrupted MRI data, a neural network can be trained that generates output frames of motion free MRI data; and the neural network can be saved.

Motion compensation for MRI imaging

In one aspect the disclosed technology relates to embodiments of a method which, includes acquiring magnetic resonance imaging data, for a plurality of images, of the heart of a subject. The method also includes segmenting, using cascaded convolutional neural networks (CNN), respective portions of the images corresponding to respective epicardium layers and endocardium layers for a left ventricle (LV) and a right ventricle (RV) of the heart. The segmenting is used for extracting biomarker data from segmented portions of the images and, in one embodiment, assessing hypertrophic cardiomyopathy from the biomarker data. The method further includes segmenting processes for T1 MRI data and LGE MRI data.

Automatic quantification of cardiac MRI for hypertrophic cardiomyopathy

Systems and methods for performing ungated magnetic resonance imaging are disclosed herein. A method includes producing magnetic resonance image MRI data by scanning a target in a low magnetic field with a pulse sequence having a spiral trajectory; sampling k-space data from respective scans in the low magnetic field and receiving at least one field map data acquisition and a series of MRI data acquisitions from the respective scans; forming a field map and multiple sensitivity maps in image space from the field map data acquisition; forming target k-space data with the series of MRI data acquisitions; forming initial magnetic resonance images in the image domain by applying a Non-Uniform Fast Fourier Transform to the target k-space data; and forming reconstructed images with a low rank plus sparse (L+S) reconstruction algorithm applied to the initial magnetic resonance images.

Systems and methods for spiral-in-out low field MRI scans

A method and an apparatus for automatic muscle segmentation are provided. The method includes receiving a high-resolution three-dimensional (3D) image obtained by a magnetic resonance imaging (MM) system and splitting the high-resolution 3D image into high-resolution 3D sub-images. Furthermore, the method includes acquiring low-resolution 3D sub-images of the high-resolution 3D sub-images and determining a boundary box within each corresponding low-resolution 3D sub-image. Moreover, the method includes determining a crop box for each boundary box, cropping each high-resolution 3D sub-image based on its corresponding crop box, and segmenting at least one muscle from the cropped box high-resolution 3D sub-image.

System and method for automatic segmentation of muscles from high-resolution MRI using 3D deep convolutional neural network

Suppressing artifacts in MRI image acquisition data includes alternatives to phase cycling by using a Convolutional Neural Network to suppress the artifact-generating echos. A U-NET CNN is trained using phase-cycled artifact-free images for ground truth comparison with received displacement encoded stimulated echo (DENSE) images. The DENSE images include data from a single acquisition with both stimulated (STE) and T1-relaxation echoes. The systems and methods of this disclosure are explained as generating artifact-free images in the ultimate output and avoiding the additional data acquisition needed for phase cycling and shortens the scan time in DENSE MRI.

Method and system for deep convolutional neural net for artifact suppression in dense MRI

An automated method for applying specific geometric constraints to a starter file and considering external specifications outside of fit to achieve an optimized, restorative joint brace or orthotic device. External specifications may include indications of the patient, biometric data, data from prescribing doctors, X-ray data, MRI data, joint geometry to restore optimized function, and envelope of motion. After the fitting process, the starter file undergoes a process of exact commands in order to finish and/or add additional features. With a vertical integration from scanning an object to producing the custom fitted device, the product can be manufactured at scale more rapidly and at lower cost, improving access to superior devices at a reasonable price to the consumer.

Method for automating custom-fitting joint brace

Aspects of the present disclosure relate to magnetic resonance thermometry. In one embodiment, a method includes acquiring undersampled magnetic resonance data associated with an area of interest of a subject receiving focused ultrasound treatment, and reconstructing images corresponding to the area of interest based on the acquired magnetic resonance data, where the reconstructing uses Kalman filtering.

Systems and methods for accelerated MR thermometry

Growing community of inventors

Charlottesville, VA, United States of America

Xue Feng