-
公开(公告)号:US20220110600A1
公开(公告)日:2022-04-14
申请号:US17554019
申请日:2021-12-17
Applicant: Canon Medical Systems Corporation
Inventor: Chung CHAN , Jian ZHOU , Evren ASMA
Abstract: A deep learning (DL) convolution neural network (CNN) reduces noise in positron emission tomography (PET) images, and is trained using a range of noise levels for the low-quality images having high noise in the training dataset to produce uniform high-quality images having low noise, independently of the noise level of the input image. The DL-CNN network can be implemented by slicing a three-dimensional (3D) PET image into 2D slices along transaxial, coronal, and sagittal planes, using three separate 2D CNN networks for each respective plane, and averaging the outputs from these three separate 2D CNN networks. Feature-oriented training can be implemented by segmenting each training image into lesion and background regions, and, in the loss function, applying greater weights to voxels in the lesion region. Other medical images (e.g. MRI and CT) can be used to enhance resolution of the PET images and provide partial volume corrections.
-
公开(公告)号:US20240008832A1
公开(公告)日:2024-01-11
申请号:US18371486
申请日:2023-09-22
Applicant: CANON MEDICAL SYSTEMS CORPORATION
Inventor: Chung CHAN , Jian ZHOU , Evren ASMA
CPC classification number: A61B6/5258 , A61B6/032 , A61B6/037 , G06N3/08 , G06T7/0012 , G06T2207/10004 , G06T2207/20081 , G06T2207/20084
Abstract: A deep learning (DL) convolution neural network (CNN) reduces noise in positron emission tomography (PET) images, and is trained using a range of noise levels for the low-quality images having high noise in the training dataset to produce uniform high-quality images having low noise, independently of the noise level of the input image. The DL-CNN network can be implemented by slicing a three-dimensional (3D) PET image into 2D slices along transaxial, coronal, and sagittal planes, using three separate 2D CNN networks for each respective plane, and averaging the outputs from these three separate 2D CNN networks. Feature-oriented training can be implemented by segmenting each training image into lesion and background regions, and, in the loss function, applying greater weights to voxels in the lesion region. Other medical images (e.g. MRI and CT) can be used to enhance resolution of the PET images and provide partial volume corrections.
-
公开(公告)号:US20220104787A1
公开(公告)日:2022-04-07
申请号:US17554032
申请日:2021-12-17
Applicant: Canon Medical Systems Corporation
Inventor: Chung CHAN , Jian ZHOU , Evren ASMA
Abstract: A deep learning (DL) convolution neural network (CNN) reduces noise in positron emission tomography (PET) images, and is trained using a range of noise levels for the low-quality images having high noise in the training dataset to produceuniform high-quality images having low noise, independently of the noise level of the input image. The DL-CNN network can be implemented by slicing a three-dimensional (3D) PET image into 2D slices along transaxial, coronal, and sagittal planes, using three separate 2D CNN networks for each respective plane, and averaging the outputs from these three separate 2D CNN networks. Feature-oriented training can be implemented by segmenting each training image into lesion and background regions, and, in the loss function, applying greater weights to voxels in the lesion region. Other medical images (e.g. MRI and CT) can be used to enhance resolution of the PET images and provide partial volume corrections.
-
公开(公告)号:US20240037814A1
公开(公告)日:2024-02-01
申请号:US17878413
申请日:2022-08-01
Applicant: CANON MEDICAL SYSTEMS CORPORATION
Inventor: Chung CHAN , Li YANG , Xiaoli LI , Wenyuan QI , Evren ASMA , Jeffrey KOLTHAMMER
IPC: G06T11/00
CPC classification number: G06T11/005 , G06T2211/412
Abstract: A dynamic frame reconstruction apparatus and method for medical image processing is disclosed which reduces the computationally expensive reconstruction of images but which retains the accuracy of the image reconstruction. A convolutional neural network is used to cluster the dynamic data into groups of frames, each group sharing similar radiotracer distribution. In one embodiment, groups of frames that have similar reconstruction parameters are determined, and scatter and random estimations are computed once and shared among each of the frames in the same frame group.
-
公开(公告)号:US20220327665A1
公开(公告)日:2022-10-13
申请号:US17225672
申请日:2021-04-08
Applicant: CANON MEDICAL SYSTEMS CORPORATION
Inventor: Chung CHAN , Li YANG , Wenyuan Ql , Evren ASMA , Jeffrey KOLTHAMMER , Yi QIANG
Abstract: Existing, low quality images can be restored using reconstruction or a combination of post-reconstruction techniques to generate a real patient phantom. The real patient phantom (RPP) can then be simulated in Monte Carlo simulations of a higher performance system and a lower performance system. Alternatively, the RPP can be simulated in the higher performance system, and a real scan can be performed by an existing, lower performance system. The higher performance system can be differentiated from the lower performance system in a variety of ways, including a higher resolution time of flight measurement capability, a greater sensitivity, smaller detector crystals, or less scattering. A neural network can be trained using the images produce by the higher performance system as the target, and the images produced by the lower performance system as the input. After training, the trained neural network can be used to output input images taken in a lower performance system with higher performance system characteristics.
-
6.
公开(公告)号:US20230026719A1
公开(公告)日:2023-01-26
申请号:US17469144
申请日:2021-09-08
Applicant: CANON MEDICAL SYSTEMS CORPORATION
Inventor: Chung CHAN , Junyu CHEN , Evren ASMA , Jeffrey KOLTHAMMER
IPC: G06N3/08 , G06N3/04 , G06V10/771 , G06V10/82
Abstract: A neural network is initially trained to remove errors and is later fine tuned to remove less-effective portions (e.g., kernels) from the initially trained network and replace them with further trained portions (e.g., kernels) trained with data after the initial training.
-
公开(公告)号:US20210118098A1
公开(公告)日:2021-04-22
申请号:US17013104
申请日:2020-09-04
Applicant: CANON MEDICAL SYSTEMS CORPORATION
Inventor: Chung CHAN , Jian ZHOU , Evren ASMA
Abstract: A system and method for training a neural network to denoise images. One noise realization is paired to an ensemble of training-ready noise realizations, and fed into a neural network for training. Training datasets can also be retrospectively generated based on existing patient studies to increase the number of training datasets.
-
公开(公告)号:US20230351646A1
公开(公告)日:2023-11-02
申请号:US17965289
申请日:2022-10-13
Inventor: Jinyi QI , Tiantian LI , Zhaoheng XIE , Wenyuan QI , Li YANG , Chung CHAN , Evren ASMA
CPC classification number: G06T11/005 , G06V10/44 , G06V10/7635 , G06V10/82 , G06V20/49 , G06T7/20 , G06T2207/10104 , G06T2207/20081
Abstract: A method, apparatus, and computer instructions stored on a computer-readable medium perform latent image feature extraction by performing the functions of receiving image data acquired during an imaging of a patient, wherein the image data includes motion by the patient during the imaging; segmenting the image data to include M image data segments corresponding to at least N motion phases having shorter durations than a duration of the motion by the patient during the imaging, wherein M is a positive integer greater than or equal to a positive integer N; producing, from the M image data segments, at least N latent feature vectors corresponding to the motion by the patient during the imaging; and performing a gated reconstruction of the N motion phases by reconstructing the image data based on the at least N latent feature vectors.
-
公开(公告)号:US20230206516A1
公开(公告)日:2023-06-29
申请号:US17682738
申请日:2022-02-28
Inventor: Jinyi QI , Tiantian LI , Zhaoheng XIE , Wenyuan QI , Li YANG , Chung CHAN , Evren ASMA
CPC classification number: G06T11/005 , G06T3/40 , G06T7/0014 , A61B6/5282 , A61B6/027 , A61B6/032 , A61B6/037 , G06T2207/20081 , G06T2207/20084 , G06T2207/10104 , G06T2207/10081 , G06T2207/30004 , G06T2210/41 , G06T2211/40
Abstract: A method, system, and computer readable medium to perform nuclear medicine scatter correction estimation, sinogram estimation and image reconstruction from emission and attenuation correction data using deep convolutional neural networks. In one embodiment, a Deep Convolutional Neural network (DCNN) is used, although multiple neural networks can be used (e.g., for angle-specific processing). In one embodiment, a scatter sinogram is directly estimated using a DCNN from emission and attenuation correction data. In another embodiment a DCNN is used to estimate a scatter-corrected image and then the scatter sinogram is computed by a forward projection.
-
10.
公开(公告)号:US20210304457A1
公开(公告)日:2021-09-30
申请号:US17180182
申请日:2021-02-19
Inventor: Jinyi QI , Tiantian LI , Zhaoheng XIE , Wenyuan QI , Li YANG , Chung CHAN , Evren ASMA
Abstract: To reduce the effect(s) caused by patient breathing and movement during PET data acquisition, an unsupervised non-rigid image registration framework using deep learning is used to produce motion vectors for motion correction. In one embodiment, a differentiable spatial transformer layer is used to warp the moving image to the fixed image and use a stacked structure for deformation field refinement. Estimated deformation fields can be incorporated into an iterative image reconstruction process to perform motion compensated PET image reconstruction. The described method and system, using simulation and clinical data, provide reduced error compared to at least one iterative image registration process.
-
-
-
-
-
-
-
-
-