Abstract: The provided is a magnetic resonance (MR) system and a method for measuring a regional body fat content using same. The method includes: when an object to be measured is a single-substance object: acquiring, by a corresponding radio frequency (RF) pulse sequence, an MR signal of the object to be measured; processing the acquired MR signal, and obtaining a target characteristic parameter value; calibrating, by phantoms with known different fat contents, the characteristic parameter, and establishing a correspondence between the characteristic parameter and the fat contents; and determining a fat content corresponding to the target characteristic parameter value (S1); and when the object to be measured is a mixed-substance object including a fat component and a non-fat component: acquiring an MR signal of the object to be measured; determining undetermined coefficients of the fat component and the non-fat component; and calculating a fat content of the object to be measured.

Abstract: Disclosed herein are systems, devices, and methods for identifying recombinant variants (such as deletion or duplication variants) of genes such as HBA1 gene and HBA2 gene, the copy numbers of HBA1 and/or HBA2, and a copy number variant genotype. Also disclosed herein are systems, devices, and methods for detecting one or more single-nucleotide variants or indels in a HBA1/2 region in a nucleic acid sample.

Abstract: Disclosed herein are systems, methods, and instrumentalities associated with medical image denoising. An apparatus configured to perform the medical image denoising task may be configured to obtain a medical image of an object and separate the medical image into a background layer and a foreground layer. The apparatus may then denoise the background layer using a first neural network pre-trained to suit the characteristics of the background layer, denoise the foreground layer using a second neural network pre-trained to suit the characteristics of the foreground layer, and merge the denoised background layer and the denoised foreground layer back into a clean medical image that depicts the object with improved image quality.

Abstract: Deblurring and denoising a medical image such as X-ray fluoroscopy images may be challenging, and deep-learning based techniques may be employed to meet the challenge. An artificial neural network (ANN) may be trained using training images with synthetic noise and as well as training images with real noise. The parameters of the ANN may be adjusted during the training based on at least a first loss designed to maintain continuity between consecutive medical images generated by the ANN and a second loss designed to maintain similarity of patches inside a medical image generated by the ANN. The parameters of the ANN may be further adjusted based on a third loss that may be calculated from ground truth associated with the synthetic training images. Transfer learning between the synthetic images and the real images may be accomplished using these techniques.

Abstract: A method for coronary road mapping may include receiving a current image associated with a medical scan, determining an image that matches the current image from a sequence of images for which respective blood vessel maps have been determined, and overlaying the current image with the blood vessel map associated with the matching image. The sequence of images may be captured when a contrast agent was present, and the matching image may be identified in response to determining that the physiological phase (e.g., cardiac cycle) and/or view depicted by the image match those depicted by the current image. Motion compensation may be performed as part of the blood vessel overlay, which may enable better visualization of blood vessels and medical device(s) (e.g., a catheter) placed in the blood vessels even when the contrast agent is worn out.

Abstract: Some embodiments of this application provide an electrode assembly, a battery cell, a battery, and an electrical device. The electrode assembly includes a positive electrode, a negative electrode, and a solid electrolyte. The positive electrode contains a lithium supplement material capable of releasing oxygen during first-cycle charging. The solid electrolyte contains a first additive. The first additive is a metal-organic framework compound with a porosity of 65% to 95%. The technical solutions put forward herein not only improve the cycle performance and energy density of the battery, but also improve the safety performance of the battery.

Abstract: The provided is a magnetic resonance (MR) system with spatial selectivity and a working method thereof. The MR system includes a data display and processing module, a spectrometer with at least one transmission channel, at least one power amplifier, a transmit-receive (TR) switch, a preamplifier, multiple sets of coils, and a magnet module, where when a number of transmission channels of the spectrometer is not less than a number of coils, one power amplifier is connected to the TR switch, while other power amplifiers are correspondingly connected to other coils (2, 3, 4) except for a main coil (1); when the number of the transmission channels of the spectrometer is less than the number of the coils, an output terminal of the at least one power amplifier is first connected to at least one power divider and multiple phase shifters and then connected to the coil.

Abstract: Shutdown intervals between nodes of a dependency tree are determined. The dependency tree represents a system to be shut down and the nodes represent system components of the system. The determining the shutdown intervals includes calculating, for a pair of nodes of the dependency tree, a shutdown interval. The calculating is based on a relationship between the pair of nodes. The calculating is repeated for a plurality of pairs of nodes to obtain a plurality of shutdown intervals. The plurality of shutdown intervals is used in a shutdown of the system components. At least one system component represented by at least one node on a higher node level of the dependency tree is to be shut down prior to at least one other system component represented by at least one other node on a lower node level of the dependency tree.

Abstract: Provided are a heat shield and a Josephson junction array chip system, the heat shield includes a cryostat, a sensor group, a radiation shield plate, a clamp assembly, and a vacuum shield cover assembly; the cryostat includes a cold head, a first-stage chassis, and a second-stage chassis; the vacuum shield cover assembly includes a first vacuum shield cover, a second vacuum shield cover, and a heat shield aluminum oxide layer; and the cold head is located in the first vacuum shield cover; and the heat shield aluminum oxide layer is coated on a surface of at least one of the first vacuum shield cover or the second vacuum shield cover; the clamp assembly on the radiation shield plate is configured to fix the Josephson junction array chip; and the sensor group adjacent to the Josephson junction array chip is arranged on the radiation shield plate.

Abstract: A method and an apparatus for establishing a QoS rule are provided. The method includes: A user plane network element obtains first indication information, where the first indication information indicates to trigger, when a first service occurs, establishment of a QoS rule of a QoS flow corresponding to the first service. When the first service meets a first condition, the user plane network element sends flow description information of the first service and an identifier of a first rule to a session management network element, where the first rule corresponds to the first indication information, and the first rule is used to establish the QoS rule.

Abstract: A method and apparatus for equalizing a battery pack, a vehicle, and a storage medium are provided. The method includes: determining whether a current battery pack meets a predetermined offline equalization condition; determining, in response to the current battery pack meeting the predetermined offline equalization condition, a target cell to be equalized in the current battery pack, an equalization time length of the target cell, and a periodic wake-up duration; and equalizing the target cell based on the equalization time length of the target cell, controlling a battery management system to enter a sleep mode, obtaining a duration for which the battery management system is in the sleep mode, waking up the battery management system in response to the duration reaching the periodic wake-up duration, and re-determining whether the current battery pack meets the predetermined offline equalization condition.

Abstract: Disclosed herein are systems, methods, and instrumentalities associated with MRI image reconstruction. According to embodiments of the disclosure, an apparatus configured to perform the MRI image reconstruction task may be configured to obtain an under-sampled MRI image and generate a reconstructed MRI image based on the under-sampled MRI image and a machine-learned (ML) model. The ML model may be trained via contrastive learning, during which randomly selected locations of the reconstructed MRI data generated by the ML model may be replaced with values that are different than the under-sampled MRI data, and the MRI data thus derived may be used as a negative example for the training.

Abstract: A system includes a comparator having a first input, a second input, and an output. The system also includes a first voltage divider having an input and an output, wherein the input of the first voltage divider is coupled to a first power rail, and the output of the first voltage divider is coupled to the first input of the comparator. The system also includes a second voltage divider having an input and an output, wherein the input of the second voltage divider is coupled to a second power rail, and the output of the second voltage divider is coupled to the second input of the comparator. The system further includes a power multiplexer coupled to the first power rail, the second power rail, and a first circuit, and a control circuit coupled to the output of the comparator and the power multiplexer.

Abstract: An integrated circuit is disclosed that includes a power supply multiplexer for selecting between a first power supply voltage and a second power supply voltage to provide a selected power supply voltage to a memory. A controller includes a comparator stage having a comparator with switchable inputs so that the comparator stage may control a binary state of a first output signal responsive to whether the first power supply voltage is greater than the second power supply voltage plus a voltage offset of the comparator. Similarly, the comparator stage may control a binary state of a second output signal responsive to whether the first power supply voltage is greater than the second power supply voltage minus the voltage offset. The controller controls the selection by the power supply multiplexer responsive to the binary states of the first and second output signals.

Abstract: Described herein are systems, methods, and instrumentalities associated with medical image classification and/or sorting. An apparatus may obtain a medical image from a medical image repository and further obtain multiple textual descriptions associated with a set of image classification labels. The apparatus may pair the medical image with one or more of the multiple text descriptions to obtain one or more corresponding image-text pairs, and classify the medical image based on a machine learning (ML) model and the one or more image-text pairs. The ML model may be configured to predict respective similarities between the medical image and the corresponding text descriptions in the one or more image-text pairs, and the apparatus may determine the class of the medical image by comparing the similarities predicted by the ML model. The apparatus may then further process the medical image based on the class of the medical image.

Abstract: Various examples are provided related to hybrid active-passive matrix devices. In one example, an active matrix device includes an array of geometrically shaped VOLET pixels arranged to form an emissive display, where each pixel is visibly discernable to a user; and bus lines routed along edges of the geometrically shaped VOLET pixels. The bus lines include a Vdata line, a Vscan line, and a VDD line. The active matrix device can include a first region formed by the array of geometrically shaped VOLET pixels and a second region including a display panel including pixels that are visibly undiscernible to the user. The active matrix device can include a third region including one or more passive VOLET pixels, which can be larger than the geometrically shaped VOLET pixels.

Abstract: Computer implemented methods, systems, and computer program products include program code executing on a processor(s) that executes a query in the database that includes a SELECT statement that targets a base table. The program code generates an intermediate pending table with a table structure based on the SELECT statement. The program code determines that an INSERT operation inserted a record into the base table behind the fetch on the base table performed based on the SELECT statement. The program code inserts the record into the intermediate pending table in the table structure. The program code performs, based on the SELECT statement, a fetch on the intermediate pending table. The program code generates output for the SELECT statement by merging results of the fetch on the base table and the fetch on the intermediate pending table.

Abstract: Described herein are systems, methods, and instrumentalities associated with segmenting and/or determining the shape of an anatomical structure. An artificial neural network (ANN) is used to perform these tasks based on a statistical shape model of the anatomical structure. The ANN is trained by evaluating and backpropagating multiple losses associated with shape estimation and segmentation mask generation. The model obtained using these techniques may be used for different clinical purposes including, for example, motion estimation and motion tracking.

Abstract: Described herein are systems, methods, and instrumentalities associated with automatically detecting and enhancing multiple objects in medical scan images. The detection and/or enhancement may be accomplished utilizing artificial neural networks such as one or more classification neural networks and/or one or more graph neural networks. The neural networks may be used to detect areas in the medical scan images that may correspond to the objects of interest and cluster the areas belonging to a same object into a respective cluster. These tasks may be accomplished, for example, by representing the areas corresponding to the objects of interest and their interrelationships with a graph and processing the graph through the one or more graph neural networks so that the areas belonging to each object may be properly labeled and clustered. The clusters may then be used to enhance the objects of interests in one or more output scan images.

Abstract: A method and apparatus for protecting non-fungible token (NFT) digital assets, implemented by a terminal device of a user, including: creating, using a third-party application account associated with the user, a private blockchain account for the user; adding NFT information included in a blockchain account associated with the user into an e-wallet corresponding to the third-party application account, wherein the blockchain account is different from the private blockchain account; based on a target NFT being selected by the user in the e-wallet after the user logs into the third-party application account, initiating an off-chain transaction between the blockchain account and the private blockchain account in order to freeze a digital asset corresponding to the target NFT; and canceling the off-chain transaction corresponding to the frozen digital asset in order to unfreeze the frozen digital asset based on the frozen digital asset satisfying a predetermined NFT protection cancellation condition.