公开(公告)号：US12102471B2

公开(公告)日：2024-10-01

申请号：US17720977

申请日：2022-04-14

Applicant: CANON MEDICAL SYSTEMS CORPORATION

Inventor： Xiaohui Zhan ,  Xiaofeng Niu ,  Ruoqiao Zhang

IPC: A61B6/58 ,  A61B6/03 ,  A61B6/42 ,  G01T7/00 ,  G06T7/00 ,  G06T11/00

CPC classification number: A61B6/585 ,  A61B6/032 ,  A61B6/4241 ,  G01T7/005 ,  G06T7/0012 ,  G06T11/005 ,  G06T2207/10081 ,  G06T2207/30004 ,  G06T2207/30168

Abstract: A photon counting computed tomography (CT) method including receiving a first forward model including a set of first parameters and a set of second parameters corresponding to a plurality of materials and path lengths by scanning a slab at plural tube voltages and plural tube currents of an X-ray tube; evaluating an image quality of a material decomposition image reconstructed by the set of first parameters and the set of second parameters; and updating at least one second parameters from the set of second parameters if the image quality of the material decomposition image does not satisfy a predetermined threshold, wherein the updating is achieved by updating the at least one second parameter from the set of second parameters to an energy dependent parameter from a constant value.

公开(公告)号：US11039806B2

公开(公告)日：2021-06-22

申请号：US16227251

申请日：2018-12-20

Applicant: Canon Medical Systems Corporation

Inventor： Jian Zhou ,  Ruoqiao Zhang ,  Zhou Yu ,  Yan Liu

IPC: A61B6/00 ,  G06T11/00 ,  G06T5/20 ,  G06T5/10 ,  G06T5/50 ,  G06N3/08 ,  G06N3/04

Abstract: A deep learning (DL) network corrects/performs sinogram completion in computed tomography (CT) images based on complementary high- and low-kV projection data generated from a sparse (or fast) kilo-voltage (kV)-switching CT scan. The DL network is trained using inputs and targets, which respectively generated with and without kV switching. Another DL network can be trained to correct sinogram-completion errors in the projection data after a basis/material decomposition. A third DL network can be trained to correct sinogram-completion errors in reconstructed images based on the kV-switching projection data. Performance of the DL network can be improved by dividing a 3D convolutional neural network (CNN) into two steps performed by respective 2D CNNs. Further, the projection data and DLL can be divided into high- and low-frequency components to improve performance.

公开(公告)号：US12067651B2

公开(公告)日：2024-08-20

申请号：US17462391

申请日：2021-08-31

Applicant: CANON MEDICAL SYSTEMS CORPORATION

Inventor： Qiulin Tang ,  Ruoqiao Zhang ,  Jian Zhou ,  Zhou Yu

IPC: G06T11/00 ,  G06N3/08 ,  G06T7/00

CPC classification number: G06T11/003 ,  G06N3/08 ,  G06T7/0012 ,  G06T2207/20081 ,  G06T2207/20084

Abstract: Data acquired from a scan of an object can be decomposed into frequency components. The frequency components can be input into a trained model to obtain processed frequency components. These processed frequency components can be composed and used to generate a final image. The trained model can be trained, independently or dependently, using frequency components covering the same frequencies as the to-be-processed frequency components. In addition, organ specific processing can be enabled by training the trained model using image and/or projection datasets of the specific organ.

公开(公告)号：US11864939B2

公开(公告)日：2024-01-09

申请号：US17339093

申请日：2021-06-04

Applicant: CANON MEDICAL SYSTEMS CORPORATION

Inventor： Jian Zhou ,  Ruoqiao Zhang ,  Zhou Yu ,  Yan Liu

IPC: A61B6/00 ,  G06T11/00 ,  G06T5/50 ,  G06T5/20 ,  G06T5/10 ,  G06N3/084 ,  G06N3/045

CPC classification number: A61B6/5258 ,  A61B6/4014 ,  G06N3/045 ,  G06N3/084 ,  G06T5/10 ,  G06T5/20 ,  G06T5/50 ,  G06T11/005 ,  G06T11/006 ,  G06T11/008 ,  A61B6/482 ,  A61B6/5205 ,  G06T2207/10081 ,  G06T2207/20064 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2211/408

Abstract: A deep learning (DL) network corrects/performs sinogram completion in computed tomography (CT) images based on complementary high- and low-kV projection data generated from a sparse (or fast) kilo-voltage (kV)-switching CT scan. The DL network is trained using inputs and targets, which respectively generated with and without kV switching. Another DL network can be trained to correct sinogram-completion errors in the projection data after a basis/material decomposition. A third DL network can be trained to correct sinogram-completion errors in reconstructed images based on the kV-switching projection data. Performance of the DL network can be improved by dividing a 3D convolutional neural network (CNN) into two steps performed by respective 2D CNNs. Further, the projection data and DLL can be divided into high- and low-frequency components to improve performance.