Abstract: An apparatus for reconstructing or filtering medical image data is provided. The apparatus includes processing circuitry to receive a first medical image data and meta-parameters related to the first medical image data; apply the received meta-parameters to inputs of a first trained machine-learning (ML) network, e.g., a multilayer perceptron, to obtain, from outputs of the first trained ML network, tuning parameters of a second ML network (e.g., a convolutional neural network) different from the first ML network; apply the received first medical image data to inputs of the second ML network, as tuned by the obtained tuning parameters output from the first ML network, to obtain, from outputs of the second ML network, second medical image data; and output the second medical image data. In one embodiment, the first medical image data is magnetic-resonance k-space data and the second medical data is a magnetic-resonance image.

Abstract: A computer-implemented method for augmenting customer support is disclosed in which a granular taxonomy is formed to classify tickets based on customer issue topic. A dashboard and user interface of performance metrics may be generated for the topics in the taxonomy. Recommendations may also be generated to aid servicing customer support issues for topics in the taxonomy. This may include generating information to aid in determining topics for generating automated responses or generating recommended answers for particular topics. In some implementations, an archive of historic tickets is used to generate training data for a machine learning model to classify tickets.

Abstract: An apparatus for incremental motion correction in medical imaging. The apparatus for motion correction in magnetic resonance imaging includes processing circuitry configured to estimate an intermediate image from a first section of k-space, the first section of the k-space corresponding to acquisition time points within a magnetic resonance scan of a subject, the corresponding acquisition time points within the magnetic resonance scan being associated with shots of the k-space determined to have minimal motion, estimate motion parameters of a second section of the k-space using the estimated intermediate image, combine data from the first section of the k-space with data from the second section of the k-space according to the estimated motion parameters, and reconstruct the combined data of the k-space to generate a final image.

Abstract: Disclosed embodiments provide a framework for processing sets of credentials in real-time using machine learning models to identify requisitions that can be recommended to users. In response to receiving a set of credentials from a user, a system assigns a classification to the set of credentials based on a set of characteristics associated with the set of credentials. A machine learning model is used to assign tags to the text of the set of credentials. These tags correspond to the set of characteristics. Using these tags, a set of open requisitions are identified and provided to the user.

Abstract: The present disclosure relates to a method and apparatus correcting a metal artifact in magnetic resonance imaging (MRI) data. The method and apparatus acquire plural slices along a slice direction of a scanned region associated with a body part, estimate a spatial extent of a signal dispersion of the acquired plural slices along the slice direction, and combine the signal of the acquired plural slices along the slice direction based on the estimated spatial extent of the signal dispersion to generate a reconstructed image of the scanned region.

Abstract: A method for selection of a marker in an augmented reality (AR) environment is provided. The method includes capturing a scene in the augmented reality environment; extracting a set of region of interest from the scene captured; identifying a text in the region of interest or from a document associated to the region of interest; determining a set of phrase-action pairs from the text; generating a representation of a set of region of interest and a representation of a set of phrase-action pairs; calculating inter model similarity using the set of region of interest and the set of phrase-action pairs in common embedding space; computing intra model similarity by comparing the extracted ROI with a generated ROI and the extracted phrase-action with generated phrase actions; and selecting a phrase-action-ROI tuple having the highest intra modal similarity as the marker.

Abstract: An apparatus for incremental motion correction in medical imaging. The apparatus for motion correction in magnetic resonance imaging includes processing circuitry configured to estimate an intermediate image from a first section of k-space, the first section of the k-space corresponding to acquisition time points within a magnetic resonance scan of a subject, the corresponding acquisition time points within the magnetic resonance scan being associated with shots of the k-space determined to have minimal motion, estimate motion parameters of a second section of the k-space using the estimated intermediate image, combine data from the first section of the k-space with data from the second section of the k-space according to the estimated motion parameters, and reconstruct the combined data of the k-space to generate a final image.

Abstract: A magnetic resonance imaging apparatus according to an embodiment includes a processing circuit. The processing circuit acquires a plurality of echo signals not to be encoded corresponding to a plurality of respective shots about acquisition of a plurality of echo signals having been encoded by magnetic resonance imaging for a subject, compares the echo signals not to be encoded with each other about the shots, and identifies a shot to be removed about generation of a magnetic resonance image about the subject out of the shots based on a comparison result of the echo signals not to be encoded.

Abstract: An apparatus for incremental motion correction in medical imaging. The apparatus for motion correction in magnetic resonance imaging includes processing circuitry configured to estimate an intermediate image from a first section of k-space, the first section of the k-space corresponding to acquisition time points within a magnetic resonance scan of a subject, the corresponding acquisition time points within the magnetic resonance scan being associated with shots of the k-space determined to have minimal motion, estimate motion parameters of a second section of the k-space using the estimated intermediate image, combine data from the first section of the k-space with data from the second section of the k-space according to the estimated motion parameters, and reconstruct the combined data of the k-space to generate a final image.

Abstract: An apparatus and method are provided to simultaneously provide good image quality and fast image reconstruction from magnetic resonance imaging (MRI) data by selecting an appropriate value for the regularization parameter used in compressed sensing (CS) image reconstruction. In CS reconstruction a high-resolution image can be reconstructed from randomized undersampled data by imposing sparsity in multi-scale transformation (e.g., wavelet) domain. Further, in the transformation domain, a threshold can be determined between signal and noise levels of the transform coefficients. A regularization parameter based on this threshold scales the regularization term, which imposes sparsity, relative to the data fidelity term in an objective function, thereby balancing the tradeoff between noise and smoothing.

Abstract: Disclosed embodiments provide a framework to facilitate recruitment and processing of applicants. A bot recruiting agent is implemented that engages in a communications session with applicants to solicit responses to questions for a job opening. The responses are scored according to a set of metrics and a fitness score for each applicant is provided. Based on the fitness score, a recommendation for advancing an applicant for the job opening is generated.

Abstract: An apparatus for incremental motion correction in medical imaging. The apparatus for motion correction in magnetic resonance imaging includes processing circuitry configured to estimate an intermediate image from a first section of k-space, the first section of the k-space corresponding to acquisition time points within a magnetic resonance scan of a subject, the corresponding acquisition time points within the magnetic resonance scan being associated with shots of the k-space determined to have minimal motion, estimate motion parameters of a second section of the k-space using the estimated intermediate image, combine data from the first section of the k-space with data from the second section of the k-space according to the estimated motion parameters, and reconstruct the combined data of the k-space to generate a final image.

Abstract: A computing apparatus including a memory storing at least one instruction; and at least one processor configured to execute the at least one instruction to: obtain terminal user property information based on data received from a terminal and a knowledge graph; and compare the terminal user property information with content property information to search for a potential customer.

Abstract: An apparatus and method are provided to simultaneously provide good image quality and fast image reconstruction from magnetic resonance imaging (MRI) data by selecting an appropriate value for the regularization parameter used in compressed sensing (CS) image reconstruction. In CS reconstruction a high-resolution image can be reconstructed from randomized undersampled data by imposing sparsity in multi-scale transformation (e.g., wavelet) domain. Further, in the transformation domain, a threshold can be determined between signal and noise levels of the transform coefficients. A regularization parameter based on this threshold scales the regularization term, which imposes sparsity, relative to the data fidelity term in an objective function, thereby balancing the tradeoff between noise and smoothing.

Abstract: An apparatus and method are provided to simultaneously provide good image quality and fast image reconstruction from magnetic resonance imaging (MRI) data by selecting an appropriate value for the regularization parameter used in compressed sensing (CS) image reconstruction. In CS reconstruction a high-resolution image can be reconstructed from randomized undersampled data by imposing sparsity in multi-scale transformation (e.g., wavelet) domain. Further, in the transformation domain, a threshold can be determined between signal and noise levels of the transform coefficients. A regularization parameter based on this threshold scales the regularization term, which imposes sparsity, relative to the data fidelity term in an objective function, thereby balancing the tradeoff between noise and smoothing.

Abstract: A method and apparatuses are provided to perform chemical species separation in magnetic resonance (MR) imaging (MRI). At least three MR images corresponding respectively to different echo times are obtained and represent signals from multiple chemical species including a first species and a second species in a tissue. A plurality of dual-echo pairs is selected from the at least three MR images. For each pair, a set of dual-echo separated images including a B0 field map, a first image for the first species, and a second image for the second species is estimated. An initial set of combined images including at least one of: an initial combined B0 field map, first, and second image is generated by combining at least one of: two or more of the B0 field maps, two or more of the first images, and two or more of the second images.

Abstract: An apparatus and method are provided to simultaneously provide good image quality and fast image reconstruction from magnetic resonance imaging (MRI) data by selecting an appropriate value for the regularization parameter used in compressed sensing (CS) image reconstruction. In CS reconstruction a high-resolution image can be reconstructed from randomized undersampled data by imposing sparsity in multi-scale transformation (e.g., wavelet) domain. Further, in the transformation domain, a threshold can be determined between signal and noise levels of the transform coefficients. A regularization parameter based on this threshold scales the regularization term, which imposes sparsity, relative to the data fidelity term in an objective function, thereby balancing the tradeoff between noise and smoothing.

Abstract: A method and apparatuses are provided to perform chemical species separation in magnetic resonance (MR) imaging (MRI). At least three MR images corresponding respectively to different echo times are obtained and represent signals from multiple chemical species including a first species and a second species in a tissue. A plurality of dual-echo pairs is selected from the at least three MR images. For each pair, a set of dual-echo separated images including a B0 field map, a first image for the first species, and a second image for the second species is estimated. An initial set of combined images including at least one of: an initial combined B0 field map, first, and second image is generated by combining at least one of: two or more of the B0 field maps, two or more of the first images, and two or more of the second images.