Abstract: Real-time cardiac MRI images may be captured continuously across multiple cardiac phases and multiple slices. Machine learning-based techniques may be used to determine spatial (e.g., slices and/or views) and temporal (e.g., cardiac cycles and/or cardiac phases) properties of the cardiac images such that the images may be arranged into groups based on the spatial and temporal properties of the images and the requirements of a cardiac analysis task. Different groups of the cardiac MRI images may also be aligned with each other based on the timestamps of the images and/or by synthesizing additional images to fill in gaps.

Abstract: A method of preparing cathode particles using a co-precipitation reaction in a reactor is disclosed. A feed stream (a) containing metal cations is fed into the reactor, and a feed stream (b) containing anions is fed into the reactor, wherein a ratio of the metal cations in the feed stream (a) is continuously changed from A1 at time t1 to A2 at time t2. The feed stream (a) and the feed stream (b) are contacted in the reactor to form precipitated precursor particles, and at least one transition metal component in the particle has a non-linear continuous concentration gradient profile over at least a portion along a thickness direction of the particle.

Abstract: A method and apparatus for generating a drivable 3D character, an electronic device and a storage medium are disclosed, which relate to the field of artificial intelligence, such as computer vision, deep learning, or the like, and may be applied to 3D vision and other scenarios. The method may include: acquiring a 3D human body mesh model corresponding to a to-be-processed 2D image; performing a skeleton embedding operation on the 3D human body mesh model; and performing a skin binding operation on the 3D human body mesh model after the skeleton embedding operation to obtain a drivable 3D human body mesh model.

Abstract: Cardiac images such as cardiac magnetic resonance (CMR) images and tissue characterization maps (e.g., T1/T2 maps) may be analyzed automatically using machine learning (ML) techniques, and reports may be generated to summarize the analysis. The ML techniques may include training one or more of an image classification model, a heart segmentation model, or a cardiac pathology detection model to automate the image analysis and/or reporting process. The image classification model may be capable of grouping the cardiac images into different categories, the heart segmentation model may be capable of delineating different anatomical regions of the heart, and the pathology detection model may be capable of detecting a medical abnormality in one or more of the anatomical regions based on tissue patterns or parameters automatically recognized by the detection model. Image registration that compensates for the impact of motions or movements may also be conducted automatically using ML techniques.

Abstract: A computer-implemented method dynamically switches access plans for a query during concurrent query execution. The method includes receiving a first query configured to be processed by a database system. The method also includes generating, for the first query, an access plan for each of identified resource sets. The method includes determining a first set of available resources that represent an available capacity for the database system. The method further includes selecting a first resource set of the one or more resource sets, where the selecting is based on the first set of available resources being closest to the first resource set. The method also includes selecting, based on the first set of available resources, a first access plan of the one or more access plans. The method includes executing the first query and returning results of the first query to a source of the first query.

Abstract: Storage processes are described. For instance, dumping of cache data in a memory table at a source directory table partition in a source container group is stopped in response to receiving a close signal. A notification for creating a target directory table partition is sent to a target container group, the notification including a checkpoint at the source directory table partition. The cache data in the memory table is sent to the target container group, and the source container group is closed in response to a determination that an ownership of the target directory table partition is updated to the target container group. A rescheduling and/or upgrading solution is thus proposed for a source container group, so that the source container group is still in a service state during the rescheduling and/or upgrading solution, which improves the performance of storage services and reduces the data unavailable time.

Abstract: Disclosed herein are systems, methods, and instrumentalities associated with reconstructing magnetic resonance (MR) images based on under-sampled MR data. The MR data include 2D or 3D information, and may encompass multiple contrasts and multiple coils. The MR images are reconstructed using deep learning (DL) methods, which may accelerate the scan and/or image generation process. Challenges imposed by the large quantity of the MR data and hardware limitations are overcome by separately reconstructing MR images based on respective subsets of contrasts, coils, and/or readout segments, and then combining the reconstructed MR images to obtain desired multi-contrast results.

Abstract: In Multiplex MRI image reconstruction, a hardware processor acquires sub-sampled Multiplex MRI data and reconstructs parametric images from the sub-sampled Multiplex MRI data. A machine learning model or deep learning model uses the subsampled Multiplex MRI data as the input and parametric maps calculated from the fully sampled data, or reconstructed fully sample data, as the ground truth. The model learns to reconstruct the parametric maps directly from the subsampled Multiplex MRI data.

Abstract: A neural network system implements a model for generating an output image based on a received input image. The model is learned through a training process during which parameters associated with the model are adjusted so as to maximize a difference between a first image predicted using first parameter values of the model and a second image predicted using second parameter values of the model, and to minimize a difference between the second image and a ground truth image. During a first iteration of the training process the first image is predicted and during a second iteration the second image is predicted. The first parameter values are obtained during the first iteration by minimizing a difference between the first image and the ground truth image, and the second parameter values are obtained during the second iteration by maximizing the difference between the first image and the second image.

Abstract: Described herein are systems, methods, and instrumentalities associated with landmark detection. The detection may be accomplished by determining a graph representation of a plurality of hypothetical landmarks detected in one or more medical images. The graph representation may include nodes that represent the hypothetical landmarks and edges that represent the relationships between paired hypothetical landmarks. The graph representation may be processed using a graph neural network such a message passing graph neural network, by which the landmark detection problem may be converted and solved as a graph node labeling problem.

Abstract: A scheme for modifying an image is disclosed, which includes receiving a source image having a first image configuration; determining a second image configuration for a target image; providing the received source image to an AI engine trained to identify, based on a set of rules related to visual features, candidate regions from the source image; generating proposal images based on the candidate regions, respectively; determining, based on prior aesthetical evaluation data, an aesthetical value of each regional proposal image; and selecting, based on the determined aesthetical value of each regional proposal image, one of the regional proposal images as the target image; extracting, from the AI engine, the target image; and causing the target image to be displayed via a display of a user device.

Abstract: Provided are a backlight module, a preparation method thereof, and a display device. The backlight module includes a substrate, multiple light-emitting elements, a reflection structure and a rubber frame structure, and the multiple light-emitting elements, the reflection structure and the rubber frame structure are located on one side of the substrate. The multiple light-emitting elements and the reflection structure are located within a limited area of the rubber frame structure, and the reflection structure is located between every two adjacent light-emitting elements; and the reflection structure includes a first reflection surface adjacent to a light-emitting element, and the rubber frame structure includes a second reflection surface adjacent to the light-emitting element.

Abstract: The present application relates to a current collector, an electrode plate, a battery cell, a battery, and an electric device. The current collector includes a stainless steel current-collecting portion for collecting a current, where the stainless steel current-collecting portion includes a blank area and a coating area that are arranged adjacent to each other in a preset direction, the coating area is configured to be coated with an active material, and the blank area has a hardness less than that of the coating area.

Abstract: Disclosed are a device and method for detecting defects of a high-voltage cable cross-bonded grounding system. The method comprises: selecting a protective grounding box of a cross-bonded grounding system, respectively connecting a signal excitation coupler to A-phase, B-phase and C-phase coaxial cables of the protective grounding box, selecting a stable signal with a frequency different from a power frequency or a field interference frequency, and testing effective current values and phases responded by the A-phase, B-phase and C-phase coaxial cables when the stable signal with the frequency F1 is injected into the A-phase, B-phase and C-phase coaxial cables of the protective grounding box in a coupled manner; and obtaining resistances and inductances of branch circuits of the cable cross-bonded grounding system by calculation according to measurement data, and determining if the cable cross-bonded grounding system has a connection defect.

Abstract: Motion contaminated magnetic resonance (MR) images for training an artificial neural network to remove motion artifacts from the MR images are difficult to obtain. Described herein are systems, methods, and instrumentalities for injecting motion artifacts into clean MR images and using the artificially contaminated images for machine learning and neural network training. The motion contaminated MR images may be created based on clean source MR images that are associated with multiple physiological cycles of a scanned object, and by deriving MR data segments for the multiple physiological cycles based on the source MR images. The MR data segments thus derived may be combined to obtain a simulated MR data set, from which one or more target MR images may be generated to exhibit a motion artifact. The motion artifact may be created by manipulating the source MR images and/or controlling the manner in which the MR data set or the target MR images are generated.

Abstract: Disclosed is an unmanned aerial vehicle (UAV)-aided over-the-air computing system based on full-duplex relay and a trajectory and power optimization method thereof. The UAV-aided over-the-air computing system adopts the UAV as a full-duplex relay for data fusing and forwarding. The method of the application aims at minimizing an average mean square error of over-the-air computing, and solves an optimization problem under constraints of sensor transmitting power, information transmission rate, UAV trajectory and denoising factor. For an overall joint optimization problem, each optimization variable is determined one by one by an alternative optimization method according to the high coupling of optimization variables.

Abstract: An anatomy-aware contouring editing method includes receiving an image, wherein the image represents an anatomically recognizable structure; identifying a first image segment representing part of the anatomically recognizable structure; annotating the first image segment to generate a label of the part; drawing a contour along a boundary of the part; receiving a first input from a user device indicative of a region of contour failure, wherein the region of contour failure includes a portion of a contour that requires editing; editing the contour for generating an edited contour based on the first input and anatomical information; and updating another contour of another part of the anatomically recognizable structure based on the edited contour, wherein the another part is anatomically related to the part.

Abstract: Methods, computer systems, and apparatus, including computer programs encoded on computer storage media, for processing a perspective view range image generated from sensor measurements of an environment. The perspective view range image includes a plurality of pixels arranged in a two-dimensional grid and including, for each pixel, (i) features of one or more sensor measurements at a location in the environment corresponding to the pixel and (ii) geometry information comprising range features characterizing a range of the location in the environment corresponding to the pixel relative to the one or more sensors. The system processes the perspective view range image using a first neural network to generate an output feature representation. The first neural network comprises a first perspective point-set aggregation layer comprising a geometry-dependent kernel.

Abstract: Disclosed herein are systems, methods, and instrumentalities associated with reconstructing magnetic resonance (MR) images based on multi-slice, under-sampled MRI data (e.g., k-space data). The multi-slice MRI data may be acquired using a simultaneous multi-slice (SMS) technique and MRI information associated with multiple MRI slices may be entangled in the multi-slice MRI data. A neural network may be trained and used to disentangle the MRI information and reconstruct MRI images for the different slices. A data consistency component may be used to estimate k-space data based on estimates made by the neural network, from which respective MRI images associated with multiple MRI slices may be obtained by applying a Fourier transform to the k-space data.

Abstract: A 3D anatomical model of one or more blood vessels of a patient may be obtained using CT angiography, while a 2D image of the blood vessels may be obtained based on fluoroscopy. The 3D model may be registered with the 2D image based on a contrast injection site identified on the 3D model and/or in the 2D image. A fused image may then be created to depict the overlaid 3D model and 2D image, for example, on a monitor or through a virtual reality headset. The injection site may be determined automatically or based on a user input that may include a bounding box drawn around the injection site on the 3D model, a selection of an automatically segmented area in the 3D model, etc.