-
公开(公告)号:US20230079353A1
公开(公告)日:2023-03-16
申请号:US17474363
申请日:2021-09-14
摘要: For correction of an image from an imaging system, an inverse solution uses an imaging prior as a regularizer and a physics model of the imaging system. An invertible network is used as the deep-learnt generative model in the regularizer of the inverse solution with the physics model of the degradation behavior of the imaging system. The prior model based on the invertible network provides a closed-form expression of the prior probability, resulting in a more versatile or accurate probability prediction.
-
公开(公告)号:US20220215600A1
公开(公告)日:2022-07-07
申请号:US17457948
申请日:2021-12-07
摘要: A computer-implemented method includes, based on an input dataset 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 determines, for multiple K-space positions at which the input dataset comprises respective source data, a contribution of respective K-space values associated with the input dataset to a K-space representation of the reconstructed image.
-
公开(公告)号:US11288806B2
公开(公告)日:2022-03-29
申请号:US15929430
申请日:2020-05-01
摘要: For medical imaging such as MRI, machine training is used to train a network for segmentation using both the imaging data and protocol data (e.g., meta-data). The network is trained to segment based, in part, on the configuration and/or scanner, not just the imaging data, allowing the trained network to adapt to the way each image is acquired. In one embodiment, the network architecture includes one or more blocks that receive both types of data as input and output both types of data, preserving relevant features for adaptation through at least part of the trained network.
-
公开(公告)号:US11263744B2
公开(公告)日:2022-03-01
申请号:US16707209
申请日:2019-12-09
发明人: Youngjin Yoo , Pascal Ceccaldi , Eli Gibson , Mariappan S. Nadar
摘要: For saliency mapping, a machine-learned classifier is used to classify input data. A perturbation encoder is trained and/or applied for saliency mapping of the machine-learned classifier. The training and/or application (testing) of the perturbation encoder uses less than all feature maps of the machine-learned classifier, such as selecting different feature maps of different hidden layers in a multiscale approach. The subset used is selected based on gradients from back-projection. The training of the perturbation encoder may be unsupervised, such as using an entropy score, or semi-supervised, such as using the entropy score and a difference of a perturbation mask from a ground truth segmentation.
-
公开(公告)号:US20210150783A1
公开(公告)日:2021-05-20
申请号:US16688170
申请日:2019-11-19
发明人: Simon Arberet , Boris Mailhe , Xiao Chen , Mariappan S. Nadar
摘要: For magnetic resonance imaging reconstruction, using a cost function independent of the ground truth and many samples of k-space measurements, machine learning is used to train a model with unsupervised learning. Due to use of the cost function with the many samples in training, ground truth is not needed. The training results in weights or values for learnable variables, which weights or values are fixed for later application. The machine-learned model is applied to k-space measurements from different patients to output magnetic resonance reconstructions for the different patients. The weights and/or values used are the same for different patients.
-
公开(公告)号:US10970837B2
公开(公告)日:2021-04-06
申请号:US16355881
申请日:2019-03-18
发明人: Youngjin Yoo , Mariappan S. Nadar
摘要: Methods and systems are provided for automatically estimating image-level uncertainty for MS lesion segmentation data. A segmentation network is trained to segment MS lesions. The trained segmentation network is then used to estimate voxel level measures of uncertainty by performing Monte-Carlo (MC) dropout. The estimated voxel level uncertainty measures are converted into lesion level uncertainty measures. The information density of the lesion mask, the voxel level measures, and the lesion level measures is increased. A trained network receives input images, the segmented lesion masks, the voxel level uncertainty measures, and the lesion level uncertainty measures and outputs an image level uncertainty measure. The network is trained with a segmentation performance metric to predict an image level uncertainty measure on the segmented lesion mask that is produced by the trained segmentation network.
-
公开(公告)号:US10663549B2
公开(公告)日:2020-05-26
申请号:US14552539
申请日:2014-11-25
发明人: Boris Mailhe , Mariappan S. Nadar , Aurélien Stalder , Qiu Wang , Michael Zenge
IPC分类号: G01R33/56 , G01R33/48 , G01R33/561 , G01R33/483
摘要: A method for acquiring a three-dimensional image volume using a magnetic resonance imaging device includes performing a multi-slice or multi-slab acquisition process to acquire a plurality of slices or three-dimensional slabs corresponding to an imaged object. Each respective slice or three-dimensional slab included in the plurality of slices or three-dimensional slabs comprises k-space data. An iterative compressed-sensing reconstruction process is applied to jointly reconstruct the plurality of three-dimensional slabs as a single consistent volume. The iterative compressed-sensing reconstruction process solves a cost function comprising a summation of individual data fidelity terms corresponding to the plurality of three-dimensional slabs.
-
8.
公开(公告)号:US20190128989A1
公开(公告)日:2019-05-02
申请号:US16008086
申请日:2018-06-14
发明人: Sandro Braun , Boris Mailhe , Xiao Chen , Benjamin L. Odry , Pascal Ceccaldi , Mariappan S. Nadar
IPC分类号: G01R33/565 , G06T5/00 , G06N3/08 , G06N5/04 , G06T7/20
摘要: Systems and methods are provided for correcting motion artifacts in magnetic resonance images. An image-to-image neural network is used to generate motion corrected magnetic resonance data given motion corrupted magnetic resonance data. The image-to-image neural network is coupled within an adversarial network to help refine the generated magnetic resonance data. The adversarial network includes a generator network (the image-to-image neural network) and a discriminator network. The generator network is trained to minimize a loss function based on a Wasserstein distance when generating MR data. The discriminator network is trained to differentiate the motion corrected MR data from motion artifact free MR data.
-
公开(公告)号:US20190046068A1
公开(公告)日:2019-02-14
申请号:US16055546
申请日:2018-08-06
摘要: Systems and methods are provided for generating a protocol independent image. A deep learning generative framework learns to recognize the boundaries and classification of tissues in an MRI image. The deep learning generative framework includes an encoder, a decoder, and a discriminator network. The encoder is trained using the discriminator network to generate a latent space that is invariant to protocol and the decoder is trained to generate the best output possible for brain and/or tissue extraction.
-
公开(公告)号:US10043088B2
公开(公告)日:2018-08-07
申请号:US15606069
申请日:2017-05-26
摘要: For image quality scoring of an image from a medical scanner, a generative model of an expected good quality image may be created using deep machine-learning. The deviation of an input image from the generative model is used as an input feature vector for a discriminative model. The discriminative model may also operate on another input feature vector derived from the input image. Based on these input feature vectors, the discriminative model outputs an image quality score.
-
-
-
-
-
-
-
-
-