General Electric Company

Ge Precision Healthcare LLC

Thomas Kwok-Fah Foo

Desmond Teck Beng Yeo

Christopher Judson Hardy

Dattesh Dayanand Shanbhag

Ek Tsoon Tan

Selaka Bandara Bulumulla

Soumya Ghose

Chitresh Bhushan

Jean-Baptiste Mathieu

Jhimli Mitra

Lowell Scott Smith

David Martin Mills

Yanzhe Yang

Luca Marinelli

Seung-Kyun Lee

Radhika Madhavan

Afis Ajala

Mark Ernest Vermilyea

Robert David Darrow

Ravindra Mohan Manjeshwar

Sandeep Narendra Gupta

Florian Wiesinger

Xin Jiang

Arathi Sreekumari

Tingting Song

Saban Kurucay

Yihe Hua

Dominic Michael Graziani

Bo Wang

Matthew Richard Tarasek

Jing Li

Bruno Kristiaan Bernard De Man

Robert Steven Stormont

Minfeng Xu

Charles William Stearns

Rakesh Mullick

Steven Robert Hayashi

Vasile Bogdan Neculaes

Andres M Lozano

Robert Arvin Hedeen

Prabhjot Singh

Anbo Wu

Kai Erik Thomenius

Bruce Allan Hay

Yudong Zhu

Kenneth William Rohling

Warren Lee

Ileana Hancu

Xu Chu

Kevin Warner Flanagan

Paul St Mark Shadforth Thompson

Vincent B Ho

Cynthia Elizabeth Landberg Davis

Prem Venugopal

Sheshadri Thiruvenkadam

Deepa Anand

Saikat Saha

John Karigiannis

Manojkumar Saranathan

Eric William Fiveland

Bruce Courtney Campbell Amm

William Thomas Dixon

Jian Lin

Lorne Wyatt Hofstetter

Laura Irene Sacolick

Daniel Eugene Meyer

Bryan P Bednarz

Glenn Scott Slavin

Michael J MacDonald

Christina Margaret Vasil

Albert Henry Roger Lonn

Anja Christina Sophie Brau

Alexandre Boutet

Martin Andreas Janich

Justin Michael Ricci

Roberta Marie Strigel

James Chapman Ross

Michael Dominic Graziani

Dirk Wim Jos Beque

Teck Beng Desmond Yeo

James Hartman Holmes

Jurgen Germann

Jianwei Qiu

Desmond Teck-Beng Yeo

Kedar Anil Patwardhan

Giang-Chau Ngo

Oguz Akin

Kenneth Paul Zarnock

Manjeshwar Mohan Ravindra

Rekha Venkatesan Tranquebar

Siddharth Vikal

Xing Yang

Jing Wu

Andre De Almeida Maximo

Rebecca Ann Mccann

A system for optimizing DBS parameters for a subject includes automatically performing actions via a processor. The actions include obtaining functional MRI data of a brain of the subject acquired utilizing an MRI system during DBS of the brain utilizing a first set of DBS parameters. The actions include generating functional MRI response maps from the functional MRI data. The actions include extracting, utilizing an unsupervised autoencoder-based neural network, features from the functional MRI response maps. The actions include determining, utilizing a deep learning-based DBS parameter classification model, whether the first set of DBS parameters are optimal DBS parameters for the subject based on the features. The actions include, when the first set of DBS parameters are not the optimal DBS parameters, predicting, utilizing a deep learning-based DBS parameter prediction model, a second set of DBS parameters that are the optimal DBS parameters for the subject based on the features.

Deep learning-based automated parameter optimization and therapy system for deep brain stimulation

A magnetic resonance (MR) system for correcting concomitant field effects is provided. The MR system includes a gradient coil assembly including a plurality of gradient coils configured to apply at least one gradient field to a polarizing magnetic field of the MR system. The MR system also includes a second-order correction coil assembly including a first second-order correction coil configured to correct effects of a first term of second-order concomitant fields generated by the at least one gradient field. The system further includes a second-order correction computing device including at least one processor in communication with at least one memory device. The at least one processor is programmed to control the second-order correction coil assembly by instructing the MR system to apply a compensation field to the second-order correction coil assembly asynchronously with the at least one gradient field.

Systems and methods of correcting effects of second-order concomitant fields in a magnetic resonance system with a second-order correction coil assembly

A computer implemented method is provided. The method includes establishing, via multiple processors, a continuous federated learning framework including a global model at a global site and respective local models derived from the global model at respective local sites. The method also includes retraining or retuning, via the multiple processors, the global model and the respective local models without sharing actual datasets between the global site and the respective local sites but instead sharing synthetic datasets generated from the actual datasets.

System and method for deep learning techniques utilizing continuous federated learning with a distributed data generative model

The present disclosure relates to use of a workflow for automatic prescription of different radiological imaging scan planes across different anatomies and modalities. The automated prescription of such imaging scan planes helps ensure contiguous visualization of the different landmark structures. Unlike prior approaches, the disclosed technique determines the necessary planes using the localizer images itself and does not explicitly segment or delineate the landmark structures to perform plane prescription.

Plane selection using localizer images

A magnetic resonance (MR) system is provided. The MR system includes a gradient coil assembly and a concomitant field correction computing device. The at least one processor of the computing device is programmed to receive MR signals acquired with the MR system using a three-dimensional (3D) pulse sequence, wherein a kx dimension and a ky dimension in k-space are sampled along non-Cartesian trajectories. The at least one processor is further programmed to correct effects of concomitant fields generated by gradient fields applied by the gradient coil assembly by adjusting the MR signals with second-order concomitant phases accumulated from second-order concomitant fields, and reconstructing MR images based on the adjusted MR signals. The second-order concomitant phases vary as functions of time and spatial locations. The at least one processor is also programmed to output the MR images.

Systems and methods of correcting effects of high-order concomitant fields in three-dimensional magnetic resonance imaging

A computer-implemented method of automatically labeling medical images is provided. The method includes clustering training images and training labels into clusters, each cluster including a representative template having a representative image and a representative label. The method also includes training a neural network model with a training dataset that includes the training images and the training labels, and target outputs of the neural network model are labels of the medical images. The method further includes generating a suboptimal label corresponding to an unlabeled test image using the trained neural network model, and generating an optimal label corresponding to the unlabeled test image using the suboptimal label and representative templates. In addition, the method includes updating the training dataset using the test image and the optimal label, retraining the neural network model, generating a label of an unlabeled image using the retrained neural network model, and outputting the generated label.

Systems and methods of automatic medical image labeling

Various methods and systems are provided for stationary CT imaging. In one embodiment, a modular imaging system comprises a plurality of distributed x-ray units releasably coupled to a plurality of detector arrays, with the plurality of distributed x-ray units and the plurality of detector arrays forming a self-supporting structure including a central opening shaped to receive a subject to be imaged. The modular imaging system may image the subject without rotation of the distributed x-ray units or detector arrays around the subject.

Systems and methods for a stationary CT imaging system

A system for minimizing MGI in a superconducting magnet system of an MRI system includes a thermal shield having bi-metal material. The thermal shield is configured to be disposed about a cold mass of the superconducting magnet system, wherein the bi-metal material is configured to minimize MGI.

Thermal shield of magnetic resonance imaging magnet for limiting magnet gradient interaction

A pulse sequence generation computing device for a magnetic resonance imaging (MRI) system includes a processor in communication with a memory device. The processor is programmed to receive a pulse sequence including a plurality of gradient pulses and provide a pulse sequence threshold function corresponding to an acoustic noise reduction level. For each gradient pulse in the pulse sequence, the processor is programmed to determine an amplitude and a slew rate of the gradient pulse, determine a threshold amplitude and slew rate of the gradient pulse, and compare the determined amplitude and slew rate to the threshold amplitude and slew rate. If either the determined amplitude or slew rate exceeds the threshold amplitude or slew rate, the processor adjusts at least one of the amplitude and the slew rate of the gradient pulse to an amplitude and a slew rate as defined by the pulse sequence threshold function.

Pulse sequence generation systems and methods of reducing acoustic noise in magnetic resonance systems

The techniques discussed herein relate to a reduced acoustic noise and vibration magnetic resonance imaging (MRI) acquisition. In certain implementations acoustic noise levels for one or more MRI pulse sequences are characterized and modified by limiting the frequencies and amplitudes of the gradient waveforms so as to produce less noise and vibration when the modified waveform is used during an MRI examination. In this manner, relatively low sound pressure levels can be attained.

Low acoustic noise magnetic resonance image acquisition

The subject matter discussed herein relates to multi-modal image alignment to facilitate biopsy procedures and post-biopsy procedures. In one such example, prostate structures (or other suitable anatomic features or structures) are automatically segmented in pre-biopsy MR and pre-biopsy ultrasound images. Thereafter, pre-biopsy MR and pre-biopsy ultrasound contours are aligned. To account for non-linear deformation of the imaged anatomic structure, a patient-specific transformation model is trained via deep learning based at least in part on the pre-biopsy ultrasound images. The pre-biopsy ultrasound images that are overlaid with the pre-biopsy MR contours and based off the deformable transformation model are then aligned with the biopsy ultrasound images. Such real-time alignment using multi-modality imaging techniques provides guidance during the biopsy and post-biopsy system.

Biopsy workflow using multimodal imaging

The subject matter discussed herein relates to the automatic, real-time registration of pre-operative magnetic resonance imaging (MRI) data to intra-operative ultrasound (US) data (e.g., reconstructed images or unreconstructed data), such as to facilitate surgical guidance or other interventional procedures. In one such example, brain structures (or other suitable anatomic features or structures) are automatically segmented in pre-operative and intra-operative ultrasound data. Thereafter, anatomic structure (e.g., brain structure) guided registration is applied between pre-operative and intra-operative ultrasound data to account for non-linear deformation of the imaged anatomic structure. MR images that are pre-registered to pre-operative ultrasound images are then given the same nonlinear spatial transformation to align the MR images with intra-operative ultrasound images to provide surgical guidance.

Deformable registration for multimodal images

An RF coil array for use in MRI is disclosed, which includes a plurality of transmit coil elements and a plurality of RF power amplifiers. Each RF power amplifier is integrated with at least one transmit coil element for driving the at least one transmit coil element. An MRI transmit array is also disclosed, which includes a plurality of RF transmitters for generating a plurality of RF signals, the RF coil array above-mentioned, and a DC voltage source for providing a DC voltage to the plurality of transmit coil elements. The RF coil array further includes an RF shield for shielding the plurality of transmit coil elements from interacting with magnet cryostat and gradient coil elements. The plurality of RF power amplifiers are connected with respective RF transmitters and configured for power amplification of the RF signals from the respective RF transmitters, and the plurality of transmit coil elements are configured for transmitting respective amplified RF signals.

RF coil array and MRI transmit array

A system and method for providing virtual real-time MRI-guidance for a biopsy outside of a conventional MRI scanner is described. MR images and ultrasound images of a region of a patient's body are simultaneously acquired during a pre-biopsy procedure. Respiratory states that the patient may experience during the biopsy are then determined from the acquired ultrasound images, and each respiratory state is associated with corresponding MR images. The MR images are indexed with their corresponding respiratory state. Ultrasound images are then acquired of the patient during a biopsy procedure. The respiratory state of the patient is determined from the ultrasound images, and the corresponding indexed MR images are displayed.

Image-guided biopsy techniques

The present disclosure provides, in certain implementations, a rule-based or deep learning-based approach capable of assessing diagnostic utility of images in near real time with respect to acquisition. Correspondingly, an automated implementation of such an algorithm on the scanner would, in fact, emulate the doctor himself rating images in real time, and reduce the number of unneeded re-scans and recalls. In one aspect of the present invention it was found that diagnostic utility of an image is not an absolute measure, but instead depends upon the reading radiologist and the scan indication (i.e., the purpose of the scan). Therefore, adapting the threshold (probability of an imaging volume to be deemed good) as a function of reading radiologist and scan indication can result in decreasing the number of re-scans and recalls.

Automated scanning workflow

Growing community of inventors

Clifton Park, NY, United States of America

Thomas Kwok-Fah Foo