公开(公告)号：US20210031055A1

公开(公告)日：2021-02-04

申请号：US17045978

申请日：2019-04-11

Applicant: Board of Regents of the University of Texas System ,  Rensselaer Polytechnic Institute Office Of Technology Transfer

Inventor： Steve Bin Jiang ,  Xun Jia ,  Ge Wang ,  Hak Choy ,  Nima Hassan-Rezaeian ,  Chenyang Shen

IPC: A61N5/10 ,  G01R33/3815 ,  A61B6/04 ,  A61B5/055 ,  G01R33/38 ,  G01R33/385 ,  G01R33/48 ,  G01R33/3875

Abstract: Various examples of methods, systems, apparatus and devices are provided for MRI adaptation for radiotherapy machines. In one example, a system for MRI-guided radiotherapy can include a mounting ring and superconducting magnets. The mounting ring can be installed on a gantry of a LINAC to rotate about an isocenter of the LINAC moving with the gantry. The first and second superconducting magnet can be positioned substantially parallel to each other at a separation distance with the centers substantially aligned. The first and second superconducting magnets can provide a main magnetic field within a region of interest located between the first and second superconducting magnets. The superconducting magnets can have an aperture positioned at the center of each magnet and can allow a radiotherapy beam emitting from the gantry head to pass through the apertures. In another example, superconducting magnets can be installed at opposite ends of a LINAC gantry.

公开(公告)号：US12175734B2

公开(公告)日：2024-12-24

申请号：US16969072

申请日：2019-02-11

Applicant: RENSSELAER POLYTECHNIC INSTITUTE

Inventor： Ge Wang ,  Daniel David Harrison ,  Xun Jia ,  Klaus Mueller

IPC: G01N33/48 ,  A61B5/00 ,  G06F18/214 ,  G06N3/04 ,  G06N3/08 ,  G06N3/10 ,  G06N20/00 ,  G06T11/00 ,  G06V10/82

Abstract: In some embodiments, a method of machine learning includes identifying, by an auto encoder network, a simulator feature based, at least in part, on a received first simulator data set and an emulator feature based, at least in part, on a received first emulator data set. The method further includes determining, by a synthesis control circuitry, a synthesized feature based, at least in part, on the simulator feature and based, at least in part, on the emulator feature; and generating, by the auto encoder network, an intermediate data set based, at least in part, on a second simulator data set and including the synthesized feature. Some embodiments of the method further include determining, by a generative artificial neural network, a synthesized data set based, at least in part, on the intermediate data set and based, at least in part, on an objective function.

公开(公告)号：US20240036135A1

公开(公告)日：2024-02-01

申请号：US18228064

申请日：2023-07-31

Applicant: Rensselaer Polytechnic Institute

Inventor： Xun Jia ,  Ge Wang ,  Mengzhou Li ,  Weiwen Wu ,  Wenxiang Cong ,  Yuting Peng ,  Jace Grandinetti

IPC: G01R33/48 ,  G01R33/385

CPC classification number: G01R33/4812 ,  G01R33/385

Abstract: In one embodiment, there is provided a magnetic resonance (MR) subsystem for magnetic resonance imaging (MRI). The MR subsystem includes a first magnet-coil assembly and a second magnet-coil assembly. The first magnet-coil assembly includes a first magnet structure and a first gradient coil. The second magnet-coil assembly includes a second magnet structure and a second gradient coil. The first magnet-coil assembly and the second magnet-coil assembly are separated by a gap. The gap is configured to facilitate transmission of an x-ray beam from an x-ray source to an x-ray detector. The x-ray source and the x-ray detector are included in a computed tomography (CT) subsystem.

公开(公告)号：US20210035340A1

公开(公告)日：2021-02-04

申请号：US16969072

申请日：2019-02-11

Applicant: RENSSELAER POLYTECHNIC INSTITUTE

Inventor： Ge Wang ,  Daniel David Harrison ,  Xun Jia ,  Klaus Mueller

IPC: G06T11/00 ,  G06N3/04 ,  G06N3/08 ,  G06K9/62

Abstract: In some embodiments, a method of machine learning includes identifying, by an auto encoder network, a simulator feature based, at least in part, on a received first simulator data set and an emulator feature based, at least in part, on a received first emulator data set. The method further includes determining, by a synthesis control circuitry, a synthesized feature based, at least in part, on the simulator feature and based, at least in part, on the emulator feature; and generating, by the auto encoder network, an intermediate data set based, at least in part, on a second simulator data set and including the synthesized feature. Some embodiments of the method further include determining, by a generative artificial neural network, a synthesized data set based, at least in part, on the intermediate data set and based, at least in part, on an objective function.