公开(公告)号：US20200175731A1

公开(公告)日：2020-06-04

申请号：US16206922

申请日：2018-11-30

Applicant: CANON MEDICAL SYSTEMS CORPORATION ,  THE UNIVERSITY OF CENTRAL FLORIDA RESEARCH FOUNDATION, Inc.

Inventor： Alexander KATSEVICH ,  Zhou YU ,  Daxin SHI

IPC: G06T11/00

Abstract: A method and apparatus is provided to reconstruct a computed tomography image using iterative reconstruction (IR) that is accelerated using various combinations of ordered subsets, conjugate gradient, preconditioning, resetting/restarting, and/or gradient approximation techniques. For example, when restarting criteria are satisfied the IR algorithm can be reset by setting conjugate-gradient parameters to initial values and/or by changing the number of ordered subsets. The IR algorithm can be accelerated by approximately calculating the gradients, by using a diagonal or Fourier preconditioner, and by selectively updating the preconditioner based on the regularization function. The update direction and step size can be calculated using the preconditioner and a surrogate function, which is not necessarily separable.

公开(公告)号：US20240338800A1

公开(公告)日：2024-10-10

申请号：US18296840

申请日：2023-04-06

Applicant: CANON MEDICAL SYSTEMS CORPORATION

Inventor： Ting XIA ,  Jian ZHOU ,  Liang CAI ,  Zhou YU ,  Tomohisa IMAMURA ,  Ryosuke IWASAKI ,  Hiroki TAKAHASHI

IPC: G06T5/00 ,  G06T7/00 ,  G06T7/30

CPC classification number: G06T5/70 ,  G06T7/0012 ,  G06T7/30 ,  G06T2207/10132 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/20221 ,  G06T2207/30004

Abstract: An apparatus, method, and computer-readable medium having processing circuitry to receive first ultrasound data including at least one harmonic component, and apply the first ultrasound data to inputs of a trained deep neural network model that outputs enhanced ultrasound image data, the deep neural network model having been trained with training data including input ultrasound data and corresponding target ultrasound data having predetermined target features, and output the enhanced ultrasound image data.

公开(公告)号：US20240062371A1

公开(公告)日：2024-02-22

申请号：US18448773

申请日：2023-08-11

Applicant: CANON MEDICAL SYSTEMS CORPORATION

Inventor： Chih-Chieh LIU ,  Jian ZHOU ,  Qiulin TANG ,  Liang CAI ,  Zhou YU

IPC: G06T7/00 ,  G06T7/11

CPC classification number: G06T7/0012 ,  G06T7/11 ,  G06T2207/20084 ,  G06T2207/30048 ,  G06T2207/30101 ,  G06T2200/04

Abstract: An apparatus is provided with processing circuitry that receives a phase image acquired at a corresponding cardiac phase, determines, from the received phase image, a mask image of a particular cardiac region, applies both the determined mask image and the phase image to inputs of a trained neural network model to obtain, from outputs of the neural network model, a location probability map. The neural network model is trained with a set of input data and a corresponding set of output data. The input data includes a training mask image and a training phase image, and the output data includes a training location probability map. The processing circuitry calculates, for the cardiac phase, from the determined location probability map output from the trained neural network model, a value of a cardiac motion metric. The determined location probability map specifies a probable location of a cardiac vessel.

公开(公告)号：US20220367039A1

公开(公告)日：2022-11-17

申请号：US17730954

申请日：2022-04-27

Applicant: CANON MEDICAL SYSTEMS CORPORATION

Inventor： Liang CAI ,  Jian ZHOU ,  Ting XIA ,  Zhou YU ,  Tomohisa IMAMURA ,  Ryosuke IWASAKI ,  Hiroki TAKAHASHI

IPC: G16H30/40 ,  A61B8/08 ,  G06T5/00 ,  G06N3/08

Abstract: A method and system enable to-be-processed medical image data and its corresponding noise characteristic information to be normalized to resemble noise characteristic information of training data used to train at least one neural network for at least one ultrasound data acquisition mode. After normalizing, this processed medical image data is input into the trained neural network for producing output data used for generating cleaner images. Noise characteristic information can be used directly in training a neural network, generating a trained neural network that can handle medical image data with various noise characteristics.

公开(公告)号：US20220327662A1

公开(公告)日：2022-10-13

申请号：US17705030

申请日：2022-03-25

Applicant: CANON MEDICAL SYSTEMS CORPORATION

Inventor： Masakazu MATSUURA ,  Takuya NEMOTO ,  Hiroki TAGUCHI ,  Tzu-cheng LEE ,  Jian ZHOU ,  Liang CAI ,  Zhou YU

IPC: G06T3/40 ,  G06T5/00 ,  G06T5/50

Abstract: A medical data processing method according to an embodiment includes inputting first medical data relating to a subject imaged with a medical image capture apparatus to a learned model to configured to generate second medical data having lower noise than that of the first medical data and having a super resolution compared with the first medical data based on the first medical data to output the second medical data.

公开(公告)号：US20220130520A1

公开(公告)日：2022-04-28

申请号：US17077413

申请日：2020-10-22

Applicant: CANON MEDICAL SYSTEMS CORPORATION ,  University Health Network

Inventor： Ting XIA ,  Zhou YU ,  Patrik ROGALLA ,  Bernice HOPPEL

IPC: G16H30/20 ,  G06N3/04 ,  G06T7/00 ,  G16H50/20 ,  G16H50/30

Abstract: The present disclosure relates to a method for patient-specific optimization of imaging protocols. According to an embodiment, the present disclosure relates to a method for generating a patient-specific imaging protocol, comprising acquiring scout scan data, the scout scan data including scout scan information and scout scan parameters, generating a simulated image based on the acquired scout scan data, deriving a simulated dose map from the generated simulated image, determining image quality of the generated simulated image by applying machine learning to the generated simulated image, the neural network being trained to generate at least one probabilistic quality representation corresponding to at least one region of the generated simulated image, evaluating the determined image quality relative to a image quality threshold and the derived simulated dose map relative to a dosage threshold, optimizing. based on the evaluating, scan acquisition parameters and image reconstruction parameters, and generating, optimal imaging protocol parameters, wherein the optimal imaging protocol parameters maximize image quality while minimizing radiation exposure.

公开(公告)号：US20210113178A1

公开(公告)日：2021-04-22

申请号：US15929155

申请日：2019-10-18

Applicant: CANON MEDICAL SYSTEMS CORPORATION

Inventor： Jian ZHOU ,  Xiaohui ZHAN ,  Zhou YU

IPC: A61B6/00 ,  A61B6/03 ,  G01T1/24

Abstract: An apparatus and method are described using a forward model to correct pulse pileup in spectrally resolved X-ray projection data from photon-counting detectors (PCDs). The forward model represents pulse pileup effects using an integral in which the integrand includes a term that is a function of a count rate, which term is called a spectrum distortion correction function. This correction function can be represented as superposition of basis energy functions and corresponding polynomials of the count rate, which are defined by the polynomial coefficients. To calibrate the forward model, the polynomial coefficients are adjusted to optimize an objective function, which uses calibration data having known projections lengths for the material components of a material decomposition. To determine projection lengths for projection data from a computed tomography scan, the calibrated polynomial coefficients are held constant and the projection lengths are adjusted to optimize an objective function.

公开(公告)号：US20210012543A1

公开(公告)日：2021-01-14

申请号：US16509408

申请日：2019-07-11

Applicant: Canon Medical Systems Corporation

Inventor： Ilmar HEIN ,  Zhou YU ,  Ting XIA

IPC: G06T11/00 ,  G06T7/00

Abstract: A method and apparatus are provided that use deep learning (DL) networks to reduce noise and artifacts in reconstructed computed tomography (CT), positron emission tomography (PET), and magnetic resonance imaging (MRI) images. DL networks are used in both the sinogram and image domains. In each domain, a detection network is used to (i) determine if particular types of artifacts are exhibited (e.g., beam-hardening artifact, ring, motion, metal, photon-starvation, windmill, zebra, partial-volume, cupping, truncation, streak artifact, and/or shadowing artifacts), (ii) determine whether the detected artifact can be corrected through a changed scan protocol or image-processing techniques, and (iii) determine whether the detected artifacts are fatal, in which case the scan is stopped short of completion. When the artifacts can be corrected, corrective measures are taken through a changed scan protocol or through image processing to reduce the artifacts (e.g., convolutional neural network can be trained to perform the image processing).

公开(公告)号：US20210012541A1

公开(公告)日：2021-01-14

申请号：US16509429

申请日：2019-07-11

Applicant: Canon Medical Systems Corporation

Inventor： Tzu-Cheng LEE ,  Jian ZHOU ,  Zhou YU

IPC: G06T11/00 ,  G06T5/20 ,  G06T5/00 ,  G01N23/046 ,  A61B6/03

Abstract: A method and apparatus is provided to improve the image quality of images generated by analytical reconstruction of a computed tomography (CT) image. This improved image quality results from a deep learning (DL) network that is used to filter a sinogram before back projection but after the sinogram has been filtered using a ramp filter or other reconstruction kernel.