-
公开(公告)号：US20240296521A1
公开(公告)日：2024-09-05
申请号：US18583944
申请日：2024-02-22
CPC分类号： G06T5/60 , G06T5/70 , G06T2207/10088 , G06T2207/20081 , G06T2207/20084 , G06T2207/30004
摘要： The disclosure describes a training method for training a system for de-noising images, which comprises an input-interface and a number of trainable bilateral filters designed and arranged for filtering an image provided by the input interface. The training method includes providing a plurality of training images as input for the system, providing a number of noise maps indicating the standard deviation of the noise for every pixel of a training image, training the number of bilateral filters being based on the training images and the number of noise maps, and calculating analytical gradients of a loss function with respect to filter parameters of the system. At least one of the loss functions is based on Stein's unbiased risk estimator.
-
公开(公告)号：US12118728B2
公开(公告)日：2024-10-15
申请号：US17648686
申请日：2022-01-24
IPC分类号： G06T7/00 , G06V10/36 , G06V10/75 , G06V10/774 , G06V10/82
CPC分类号： G06T7/0016 , G06V10/36 , G06V10/751 , G06V10/7747 , G06V10/82 , G06T2207/20081 , G06T2207/20084 , G06T2207/30004 , G06V2201/03
摘要： A computer implemented method of processing a medical image is disclosed. The method includes receiving a medical image comprising a first plurality of pixels each having an initial pixel value. For each of the first plurality of pixels, a filtering operation is applied to the pixel to generate a filtered pixel value for the pixel based on the initial pixel values of pixels that surround the pixel in the medical image. For each of the first plurality of pixels, a comparison of the initial pixel value with the filtered pixel value is performed. The method comprises, for each of the first plurality of pixels, determining, based on the comparison, whether or not to categorize the pixel as an erroneous pixel; and for each of the first plurality of pixels for which it is determined to categorize the pixel as an erroneous pixel, categorizing the pixel as an erroneous pixel.
-
3.发明公开公开(公告)号：US20240320881A1
公开(公告)日：2024-09-26
申请号：US18610926
申请日：2024-03-20
IPC分类号： G06T11/00 , G06T3/4053 , G06T5/20 , G06T5/70 , G06T5/73
CPC分类号： G06T11/008 , G06T3/4053 , G06T5/20 , G06T5/70 , G06T5/73 , G06T2207/10088 , G06T2207/20084
摘要： Methods and devices for reconstructing Magnetic Resonance Imaging, MRI, images based on MRI data that asymmetrically samples K-space in accordance with a partial Fourier acquisition scheme may us a processing pipeline. The processing pipeline for such reconstruction may be flexibly configured depending on one or more settings of the partial Fourier acquisition scheme. The processing pipeline may include a trained function, e.g., implemented as a neural network, to solve one or more tasks such as deblurring, super-resolution, and/or denoising.
-
公开(公告)号：US12039638B2
公开(公告)日：2024-07-16
申请号：US17443149
申请日：2021-07-21
CPC分类号： G06T11/006 , G06N3/04 , G06N3/08 , G06T2210/41 , G06T2211/424
摘要： Magnetic resonance imaging (MRI) image reconstruction using machine learning is described. A variational or unrolled deep neural network can be used in the context of an iterative optimization. In particular, a regularization operation can be based on a deep neural network. The deep neural network can take, as an input, an aliasing data structure being indicative of aliasing artifacts in one or prior images of the iterative optimization. The deep neural networks can be trained to suppress aliasing artifacts.
-
公开(公告)号：US12106476B2
公开(公告)日：2024-10-01
申请号：US17662088
申请日：2022-05-05
CPC分类号： G06T7/0012 , G06N3/04 , G06T5/92 , G06T7/30 , G06T2207/10088 , G06T2207/20081 , G06T2207/20084 , G06T2207/30096
摘要： DCE MR images are obtained from a MR scanner and under a free-breathing protocol is provided. A neural network assigns a perfusion metric to DCE MR images. The neural network includes an input layer configured to receive at least one DCE MR image representative of a first contrast enhancement state and of a first respiratory motion state and at least one further DCE MR image representative of a second contrast enhancement state and of a second respiratory motion state. The neural network further includes an output layer configured to output at least one perfusion metric based on the at least one DCE MR image and the at least one further DCE MR image. The neural network with interconnections between the input layer and the output layer is trained by a plurality of datasets, each of the datasets having an instance of the at least one DCE MR image and of the at least one further DCE MR image for the input layer and the at least one perfusion metric for the output layer.
-
公开(公告)号：US20240296524A1
公开(公告)日：2024-09-05
申请号：US18591456
申请日：2024-02-29
CPC分类号： G06T5/60 , G06T5/50 , G06T5/70 , G06T2207/10088 , G06T2207/20081 , G06T2207/20216
摘要： A training method for a system with a machine learning model for de-noising images, including: providing numerous image datasets, wherein each image dataset includes a plurality of complex-valued image repetitions; performing a phase correction on the image repetitions, wherein for each provided image repetition of an image dataset a phase-corrected signal image is calculated by amending the phase of the complex-valued image repetition such that the phases of the image repetitions of the image dataset are consistent and such that the signal image comprises signal contribution of the image repetition; calculating a noise map for an image dataset based on the standard deviation between the signal images of this image dataset; and training the machine learning model based on the signal images, the noise map, and a loss function based on Stein's unbiased risk estimator.
-
公开(公告)号：US12039636B2
公开(公告)日：2024-07-16
申请号：US17473206
申请日：2021-09-13
发明人： Simon Arberet , Boris Mailhe , Thomas Benkert , Marcel Dominik Nickel , Mahmoud Mostapha , Mariappan S. Nadar
CPC分类号： G06T11/003 , G06N3/08 , G16H30/20
摘要： For reconstruction in medical imaging using a scan protocol with repetition, a machine learning model is trained for reconstruction of an image for each repetition. Rather than using a loss for that repetition in training, the loss based on an aggregation of images reconstructed from multiple repetitions is used to train the machine learning model. This loss for reconstruction of one repetition based on aggregation of reconstructions for multiple repetitions is based on deep set-based deep learning. The resulting machine-learned model may better reconstruct an image from a given repetition and/or a combined image from multiple repetitions than a model learned from a loss per repetition.
-
8.发明授权公开(公告)号：US12013451B2
公开(公告)日：2024-06-18
申请号：US17929803
申请日：2022-09-06
发明人： Simon Arberet , Boris Mailhe , Marcel Dominik Nickel , Thomas Benkert , Mahmoud Mostapha , Mariappan S. Nadar
IPC分类号： G01R33/48 , G01R33/54 , G01R33/565
CPC分类号： G01R33/4818 , G01R33/546 , G01R33/565
摘要： A computer-implemented method includes, based on scan data defining an input image, determining a reconstructed image using a reconstruction algorithm, and executing a data consistency operation for enforcing consistency between the input image and the reconstructed image. The data consistency operation includes using a norm ball projection that takes into account the available noise level information in order to automatically adjust the balance between the network prediction and the input measurements.
-
公开(公告)号：US20240362835A1
公开(公告)日：2024-10-31
申请号：US18358158
申请日：2023-07-25
CPC分类号： G06T11/006 , A61B5/055 , A61B5/7264 , A61B5/742 , G01R33/4818 , G01R33/5608 , G06T2211/424 , G06T2211/441
摘要： Systems and methods reconstruction for a medical imaging system using a quasi-newton method. An unrolled iterative reconstruction process is used to reconstruct an image from the scan data. The unrolled iterative reconstruction process includes a plurality of cascades that include at least a data-consistency step and a regularization step. The data-consistency step is modified based at least in part on information of already calculated gradients of one or more previous cascades of the plurality of cascades using a quasi-newton computation.
-
-
-
-
-
-
-
-
搜索结果
9 条记录 (耗时 0.015 秒)
