公开(公告)号：US12125175B2

公开(公告)日：2024-10-22

申请号：US17718697

申请日：2022-04-12

Applicant: GE Precision Healthcare LLC

Inventor： Xinzeng Wang ,  Daniel Vance Litwiller ,  Sagar Mandava ,  Robert Marc Lebel ,  Graeme Colin Mckinnon ,  Ersin Bayram

IPC: G06T5/70 ,  G06N3/08 ,  G06T7/00 ,  G06V10/82 ,  G16H30/40

CPC classification number: G06T5/70 ,  G06N3/08 ,  G06T7/0012 ,  G06V10/82 ,  G16H30/40 ,  G06T2207/10081 ,  G06T2207/10088 ,  G06T2207/20084 ,  G06T2207/30004

Abstract: Methods and systems are provided for independently removing streak artifacts and noise from medical images, using trained deep neural networks. In one embodiment, streak artifacts and noise may be selectively and independently removed from a medical image by receiving the medical image comprising streak artifacts and noise, mapping the medical image to a streak residual and a noise residual using the trained deep neural network, subtracting the streak residual from the medical image to a first extent, and subtracting the noise residual from the medical image to a second extent, to produce a de-noised medical image, and displaying the de-noised medical image via a display device.

公开(公告)号：US11408954B2

公开(公告)日：2022-08-09

申请号：US16828610

申请日：2020-03-24

Applicant: GE Precision Healthcare LLC

Inventor： Sagar Mandava ,  Ty A. Cashen ,  Daniel Litwiller ,  Ersin Bayram

IPC: G06K9/00 ,  G01R33/56 ,  G06T7/00 ,  G06N3/08 ,  A61B5/055

Abstract: A computer-implemented method of reducing noise and artifacts in medical images is provided. The method includes receiving a series of medical images along a first dimension, wherein the signals in the medical images having a higher correlation in the first dimension than the noise and the artifacts in the medical images. The method further includes, for each of a plurality of pixels in the medical images, deriving a series of data points along the first dimension based on the series of medical images, inputting the series of data points into a neural network model, and outputting the component of signals in the series of data points. The neural network model is configured to separate a component of signals from a component of noise and artifacts in the series of data points. The method further includes generating a series of corrected medical images based on the outputted component of signals.

公开(公告)号：US11341616B2

公开(公告)日：2022-05-24

申请号：US16827422

申请日：2020-03-23

Applicant: GE Precision Healthcare LLC

Inventor： Xinzeng Wang ,  Daniel Vance Litwiller ,  Sagar Mandava ,  Robert Marc Lebel ,  Graeme Colin McKinnon ,  Ersin Bayram

IPC: G06T5/00 ,  G06T7/00 ,  G06N3/08 ,  G16H30/40

Abstract: Methods and systems are provided for independently removing streak artifacts and noise from medical images, using trained deep neural networks. In one embodiment, streak artifacts and noise may be selectively and independently removed from a medical image by receiving the medical image comprising streak artifacts and noise, mapping the medical image to a streak residual and a noise residual using the trained deep neural network, subtracting the streak residual from the medical image to a first extent, and subtracting the noise residual from the medical image to a second extent, to produce a de-noised medical image, and displaying the de-noised medical image via a display device.

公开(公告)号：US20240410966A1

公开(公告)日：2024-12-12

申请号：US18330647

申请日：2023-06-07

Applicant: GE Precision Healthcare LLC

Inventor： Xinzeng Wang ,  Sagar Mandava ,  Xucheng Zhu

IPC: G01R33/56 ,  G06T5/00 ,  G06T5/50 ,  G06T7/00

Abstract: A computer-implemented method of reducing artifacts in multi-channel magnetic resonance (MR) images is provided. The method includes receiving a plurality of sets of MR images acquired by a radio-frequency (RF) coil assembly having a plurality of channels. Each set of MR images includes a plurality of slices of MR images acquired by one of the plurality of channels. The method also includes estimating a plurality of sets of artifacts in the plurality of sets of MR images by inputting the plurality of sets of MR images into a neural network model. Each set of artifacts corresponds to the one of the plurality of channels. The method further includes reducing artifacts in the plurality of sets of MR images based on estimated artifacts, deriving MR images of reduced artifacts by combining the MR images of reduced artifacts, and outputting the MR images of reduced artifacts.

公开(公告)号：US20220237748A1

公开(公告)日：2022-07-28

申请号：US17718697

申请日：2022-04-12

Applicant: GE Precision Healthcare LLC

Inventor： Xinzeng Wang ,  Daniel Vance Litwiller ,  Sagar Mandava ,  Robert Marc Lebel ,  Graeme Colin Mckinnon ,  Ersin Bayram

IPC: G06T5/00 ,  G06T7/00 ,  G06N3/08 ,  G16H30/40

Abstract: Methods and systems are provided for independently removing streak artifacts and noise from medical images, using trained deep neural networks. In one embodiment, streak artifacts and noise may be selectively and independently removed from a medical image by receiving the medical image comprising streak artifacts and noise, mapping the medical image to a streak residual and a noise residual using the trained deep neural network, subtracting the streak residual from the medical image to a first extent, and subtracting the noise residual from the medical image to a second extent, to produce a de-noised medical image, and displaying the de-noised medical image via a display device.

公开(公告)号：US20240257414A1

公开(公告)日：2024-08-01

申请号：US18102834

申请日：2023-01-30

Applicant: GE Precision Healthcare LLC.

Inventor： Sagar Mandava ,  Robert Marc Lebel ,  Michael Carl ,  Florian Wiesinger

IPC: G06T11/00 ,  G01R33/48 ,  G01R33/56 ,  G06N3/08

CPC classification number: G06T11/008 ,  G01R33/4824 ,  G01R33/5608 ,  G06N3/08 ,  G06T2210/41

Abstract: A computer-implemented method for generating a chemical shift artifact corrected reconstructed image from magnetic resonance imaging (MRI) data includes inputting into a trained deep neural network an image generated from the MRI data acquired during a non-Cartesian MRI scan of a subject. The method also includes utilizing the trained deep neural network to generate the chemical shift artifact corrected reconstructed image from the image, wherein the trained deep neural network was trained utilizing a tissue mixing model that models interactions between different tissue types to mitigate chemical shift artifacts. The method further includes outputting from the trained deep neural network the chemical shift artifact corrected reconstructed image.

公开(公告)号：US20210302525A1

公开(公告)日：2021-09-30

申请号：US16828610

申请日：2020-03-24

Applicant: GE Precision Healthcare LLC

Inventor： Sagar Mandava ,  Ty A. Cashen ,  Daniel Litwiller ,  Ersin Bayram

IPC: G01R33/56 ,  G06T7/00 ,  G06N3/08 ,  A61B5/055

Abstract: A computer-implemented method of reducing noise and artifacts in medical images is provided. The method includes receiving a series of medical images along a first dimension, wherein the signals in the medical images having a higher correlation in the first dimension than the noise and the artifacts in the medical images. The method further includes, for each of a plurality of pixels in the medical images, deriving a series of data points along the first dimension based on the series of medical images, inputting the series of data points into a neural network model, and outputting the component of signals in the series of data points. The neural network model is configured to separate a component of signals from a component of noise and artifacts in the series of data points. The method further includes generating a series of corrected medical images based on the outputted component of signals.

公开(公告)号：US20210295474A1

公开(公告)日：2021-09-23

申请号：US16827422

申请日：2020-03-23

Applicant: GE Precision Healthcare LLC

Inventor： Xinzeng Wang ,  Daniel Vance Litwiller ,  Sagar Mandava ,  Robert Marc Lebel ,  Graeme Colin McKinnon ,  Ersin Bayram

IPC: G06T5/00 ,  G06T7/00 ,  G06N3/08 ,  G16H30/40

Abstract: Methods and systems are provided for independently removing streak artifacts and noise from medical images, using trained deep neural networks. In one embodiment, streak artifacts and noise may be selectively and independently removed from a medical image by receiving the medical image comprising streak artifacts and noise, mapping the medical image to a streak residual and a noise residual using the trained deep neural network, subtracting the streak residual from the medical image to a first extent, and subtracting the noise residual from the medical image to a second extent, to produce a de-noised medical image, and displaying the de-noised medical image via a display device.