公开(公告)号：WO2018187020A1

公开(公告)日：2018-10-11

申请号：PCT/US2018/023074

申请日：2018-03-19

Applicant: GENERAL ELECTRIC COMPANY

Inventor： FU, Lin ,  RAMANI, Sathish ,  DE MAN, Bruno Kristiaan Bernard ,  RUI, Xue ,  AHN, Sangtae

IPC: G06T11/00

Abstract: The present approach relates to the use of machine learning and deep learning systems suitable for solving large-scale, space-variant tomographic reconstruction and/or correction problems. In certain embodiments, a tomographic transform of measured data obtained from a tomography scanner is used as an input to a neural network. In accordance with certain aspects of the present approach, the tomographic transform operation(s) is performed separate from or outside the neural network such that the result of the tomographic transform operation is instead provided as an input to the neural network. In addition, in certain embodiments, one or more layers of the neural network may be provided as wavelet filter banks.

公开(公告)号：WO2019164785A1

公开(公告)日：2019-08-29

申请号：PCT/US2019/018455

申请日：2019-02-19

Applicant: GENERAL ELECTRIC COMPANY

Inventor： RAMANI, Sathish ,  SCHULTE, Rolf ,  HANCU, Ileana ,  ASHE, Jeffrey ,  MCKINNON, Graeme C.

IPC: A61B5/055 ,  A61N1/05 ,  A61N1/36

Abstract: A system and method for localizing a deep brain stimulation electrode (12) in vivo in a subject or object is provided. A magnetic resonance imaging system (36) obtains MR image data from a volume-of-interest by way of a zero echo time (ZTE) or ultrashort echo time (UTE) pulse sequence, with one or more of a phase domain image and a magnitude domain image being analyzed from the MR image data acquired by the ZTE or UTE pulse sequence. One or more electrodes (12) are localized within the volume-of-interest based on an analysis of the phase domain image and/or magnitude domain image. In localizing the electrodes (12), a multi-scale correlation-based analysis of the volume-of-interest is performed to estimate at least one of an electrode center (96) and electrode contact (28) locations of the electrode (12), with the localization being achieved with a fast scan-time and with a high level of accuracy and precision.

公开(公告)号：EP3607529A1

公开(公告)日：2020-02-12

申请号：EP18715880.3

申请日：2018-03-19

Applicant: General Electric Company

Inventor： FU, Lin ,  RAMANI, Sathish ,  DE MAN, Bruno Kristiaan Bernard ,  RUI, Xue ,  AHN, Sangtae

IPC: G06T11/00

公开(公告)号：EP3608877A1

公开(公告)日：2020-02-12

申请号：EP19188957.5

申请日：2019-07-29

Applicant: General Electric Company ,  Rensselaer Polytechnic Institute

Inventor： FU, Lin ,  RAMANI, Sathish ,  TANG, Jie ,  DE MAN, Bruno Kristiaan Bernard ,  PACK, Jed Douglas ,  HSIEH, Jiang ,  WANG, Ge

IPC: G06T11/00

Abstract: The present disclosure relates to image reconstruction with favorable properties in terms of noise reduction, spatial resolution, detail preservation and computational complexity. The disclosed techniques may include some or all of: a first-pass reconstruction, a simplified datafit term, and/or a deep learning denoiser. In various implementations, the disclosed technique is portable to different CT platforms, such as by incorporating a first-pass reconstruction step.