公开(公告)号：US12008689B2

公开(公告)日：2024-06-11

申请号：US17542245

申请日：2021-12-03

Applicant: CANON MEDICAL SYSTEMS CORPORATION

Inventor： Yujie Lu ,  Tzu-Cheng Lee ,  Liang Cai ,  Jian Zhou ,  Zhou Yu

IPC: G06V10/00 ,  G06N3/08 ,  G06T11/00 ,  G16H30/40

CPC classification number: G06T11/005 ,  G06N3/08 ,  G16H30/40 ,  G06T2211/40

Abstract: Devices, systems, and methods obtain first radiographic-image data reconstructed based on a set of projection data acquired in a radiographic scan; apply one or more trained machine-learning models to the set of projection data and the first radiographic-image data to obtain a set of parameters for a scatter kernel; input the set of parameters and the set of projection data into the scatter kernel to obtain scatter-distribution data; and perform scatter correction on the set of projection data using the scatter-distribution data, to obtain a set of corrected projection data.

公开(公告)号：US20230177745A1

公开(公告)日：2023-06-08

申请号：US17542245

申请日：2021-12-03

Applicant: CANON MEDICAL SYSTEMS CORPORATION

Inventor： Yujie Lu ,  Tzu-Cheng Lee ,  Liang Cai ,  Jian Zhou ,  Zhou Yu

IPC: G06T11/00 ,  G16H30/40 ,  G06N3/08

CPC classification number: G06T11/005 ,  G16H30/40 ,  G06N3/08 ,  G06T2211/40

Abstract: Devices, systems, and methods obtain first radiographic-image data reconstructed based on a set of projection data acquired in a radiographic scan; apply one or more trained machine-learning models to the set of projection data and the first radiographic-image data to obtain a set of parameters for a scatter kernel; input the set of parameters and the set of projection data into the scatter kernel to obtain scatter-distribution data; and perform scatter correction on the set of projection data using the scatter-distribution data, to obtain a set of corrected projection data.

公开(公告)号：US11315221B2

公开(公告)日：2022-04-26

申请号：US16372174

申请日：2019-04-01

Applicant: CANON MEDICAL SYSTEMS CORPORATION

Inventor： Masakazu Matsuura ,  Jian Zhou ,  Zhou Yu

IPC: G06K9/00 ,  G06T5/00 ,  G06K9/62 ,  G06T5/50 ,  G06T11/00

Abstract: A method and apparatus is provided to perform medical imaging in which feature-aware reconstruction is performed using a neural network. The neural network is trained to perform feature-aware reconstruction by using a training dataset in which the target data has a spatially-dependent degree of denoising and artifact reduction based on the features represented in the image. For example, a target image can be generated by reconstructing multiple images, each using a respective regularization parameter that is optimized for a different anatomy/organ (e.g., abdomen, lung, bone, etc.). And a target image can be generated using artifact reduction method (e.g. metal artifact reduction, aliasing artifact reduction, etc.). Then respective regions/features (e.g., abdomen, lung, and bone, artifact free, regions/features) can be extracted from the corresponding images and combined into a single combined image, which is used as the target data to train the neural network.

公开(公告)号：US11176428B2

公开(公告)日：2021-11-16

申请号：US16372206

申请日：2019-04-01

Applicant: CANON MEDICAL SYSTEMS CORPORATION

Inventor： Tzu-Cheng Lee ,  Jian Zhou ,  Zhou Yu

IPC: G06K9/66 ,  G06K9/40 ,  G06T7/00 ,  G01T1/161 ,  A61B6/00

Abstract: A method and apparatus is provided to reduce the noise in medical imaging by training a deep learning (DL) network to select the optimal parameters for a convolution kernel of an adaptive filter that is applied in the data domain. For example, in X-ray computed tomography (CT) the adaptive filter applies smoothing to a sinogram, and the optimal amount of the smoothing and orientation of the kernel (e.g., a bivariate Gaussian) can be determined on a pixel-by-pixel basis by applying a noisy sinogram to the DL network, which outputs the parameters of the filter (e.g., the orientation and variances of the Gaussian kernel). The DL network is trained using a training data set including target data (e.g., the gold standard) and input data. The input data can be sinograms generated by a low-dose CT scan, and the target data generated by a high-dose CT scan.

公开(公告)号：US11026642B2

公开(公告)日：2021-06-08

申请号：US16370230

申请日：2019-03-29

Applicant: Canon Medical Systems Corporation

Inventor： Qiulin Tang ,  Jian Zhou ,  Zhou Yu

IPC: A61B6/03 ,  A61B6/00 ,  G06N3/08 ,  G16H50/50 ,  G16H50/20 ,  G06N3/04 ,  G06T11/00

Abstract: A method and apparatuses are provided that use a neural network to correct artifacts in computed tomography (CT) images, especially cone-beam CT (CBCT) artifacts. The neural network is trained using a training dataset of artifact-minimized images paired with respective artifact-exhibiting images. In some embodiments, the artifact-minimized images are acquired using a small cone angle for the X-ray beam, and the artifact-exhibiting images are acquired either by forwarding projecting the artifact-minimized images using a large-cone-angle CBCT configuration or by performing a CBCT scan. In some embodiments, the network is a 2D convolutional neural network, and an artifact-exhibiting image is applied to the neural network as 2D slices taken for the coronal and/or sagittal views. Then the 2D image results from the neural network are reassembled as a 3D imaging having reduced imaging artifacts.

公开(公告)号：US10937206B2

公开(公告)日：2021-03-02

申请号：US16252392

申请日：2019-01-18

Applicant: Canon Medical Systems Corporation

Inventor： Yujie Lu ,  Zhou Yu ,  Jian Zhou ,  Tzu-Cheng Lee ,  Richard Thompson

IPC: G06T11/00 ,  G06T7/11

Abstract: A method and apparatus are provided for using a neural network to estimate scatter in X-ray projection images and then correct for the X-ray scatter. For example, the neural network is a three-dimensional convolutional neural network 3D-CNN to which are applied projection images, at a given view, for respective energy bins and/or material components. The projection images can be obtained by material decomposing spectral projection data, or by segmenting a reconstructed CT image into material-component images, which are then forward projected to generate energy-resolved material-component projections. The result generated by the 3D-CNN is an estimated scatter flux. To train the 3D-CNN, the target scatter flux in the training data can be simulated using a radiative transfer equation method.

公开(公告)号：US20200311878A1

公开(公告)日：2020-10-01

申请号：US16372174

申请日：2019-04-01

Applicant: CANON MEDICAL SYSTEMS CORPORATION

Inventor： Masakazu MATSUURA ,  Jian Zhou ,  Zhou Yu

IPC: G06T5/00 ,  G06K9/62 ,  G06T5/50 ,  G06T11/00

Abstract: A method and apparatus is provided to perform medical imaging in which feature-aware reconstruction is performed using a neural network. The neural network is trained to perform feature-aware reconstruction by using a training dataset in which the target data has a spatially-dependent degree of denoising and artifact reduction based on the features represented in the image. For example, a target image can be generated by reconstructing multiple images, each using a respective regularization parameter that is optimized for a different anatomy/organ (e.g., abdomen, lung, bone, etc.). And a target image can be generated using artifact reduction method (e.g. metal artifact reduction, aliasing artifact reduction, etc.). Then respective regions/features (e.g., abdomen, lung, and bone, artifact free, regions/features) can be extracted from the corresponding images and combined into a single combined image, which is used as the target data to train the neural network.

公开(公告)号：US20200311490A1

公开(公告)日：2020-10-01

申请号：US16372206

申请日：2019-04-01

Applicant: CANON MEDICAL SYSTEMS CORPORATION

Inventor： Tzu-Cheng LEE ,  Jian Zhou ,  Zhou Yu

IPC: G06K9/66 ,  G06K9/40 ,  G06T7/00 ,  G01T1/161 ,  A61B6/00

Abstract: A method and apparatus is provided to reduce the noise in medical imaging by training a deep learning (DL) network to select the optimal parameters for a convolution kernel of an adaptive filter that is applied in the data domain. For example, in X-ray computed tomography (CT) the adaptive filter applies smoothing to a sinogram, and the optimal amount of the smoothing and orientation of the kernel (e.g., a bivariate Gaussian) can be determined on a pixel-by-pixel basis by applying a noisy sinogram to the DL network, which outputs the parameters of the filter (e.g., the orientation and variances of the Gaussian kernel). The DL network is trained using a training data set including target data (e.g., the gold standard) and input data. The input data can be sinograms generated by a low-dose CT scan, and the target data generated by a high-dose CT scan.