Ge Precision Healthcare LLC

Afis Ajala

Thomas Kwok-Fah Foo

Seung-Kyun Lee

Andres M Lozano

Desmond Teck Beng Yeo

John Karigiannis

Radhika Madhavan

Alexandre Boutet

Jianwei Qiu

Jurgen Germann

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 method for measuring concomitant fields in a magnetic resonance (MR) system is provided. The method includes applying a measurement pulse sequence in a plurality of acquisitions. Applying the measurement pulse sequence further includes applying a first bipolar gradient pulse in a first acquisition, applying a second bipolar gradient pulse in reverse polarities from the first bipolar gradient pulse in a second acquisition, and applying the measurement pulse sequence without a bipolar gradient pulse in a third acquisition. The method further includes acquiring MR signals emitted from the subject, and generating phase images based on the MR signals. The method also includes generating volumetric vector field maps based on the phase images, wherein the volumetric vector field maps include concomitant field at each spatial location in a 3D volume, the concomitant field represented as a vector. In addition, the method includes outputting the volumetric vector field maps.

Systems and methods of measuring and correcting effects of concomitant fields in a magnetic resonance system

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.

Growing community of inventors

Schenectady, NY, United States of America

Afis Ajala