Abstract: The present disclosure relates to an image processing method and apparatus. The method comprises: performing face and body feature extraction on an image to be processed to obtain image features including face features and/or body features, and the image to be processed comprises a first image and a second image; performing a face clustering operation, according to the face features extracted from the first image, to obtain a face clustering result; performing a body clustering operation on the second image to obtain a body clustering result, according to the face clustering result and the body features extracted from the first and second images, no face feature has been extracted from the second image; and obtaining, according to the face clustering result and the body clustering result, a clustering result for the image to be processed. The method can improve the recall rate while ensuring the accuracy of the clustering result.

Abstract: A method of processing plaques in magnetic resonance imaging of vessel wall include: step S101, training a generative adversarial network and a capsule neural network to obtain a trained generator network and a trained capsule neural network; and step S102, cascade-connecting the trained generator network with the capsule neural network into a system to recognize and classify plaques in magnetic resonance imaging of vessel wall. In one aspect, the capsule neural network has more abundant vascular plaques characteristic information represented by vector; in another aspect, when the trained generator network and the capsule neural network are cascaded into the system to recognize and classify the plaques in magnetic resonance imaging of vessel wall, an accuracy of recognition and classification may be greatly improved. A device for processing the method as well as a computer for implementing are also disclosed.

Abstract: Provided is a method of producing an oil containing polyunsaturated fatty acids by using Schizochytrium sp. The method comprises: performing fermentation using Schizochytrium sp.; resuspending the resultant cells after fermentation in water, adding cellulase and neutral protease for enzymolysis; mixing the enzymatic hydrolyzate with n-hexane, shaking, extracting, centrifuging, and collecting the n-hexane phase; concentrating the n-hexane phase under reduced pressure to remove the n-hexane, and drying to obtain an oil; performing a first crystallization and a second crystallization, and then performing cold filtration to obtain a liquid oil after the second crystallization; and subjecting the liquid oil to deacidification and decolorization. By regulating fermentation conditions and conducting concentration processing on polyunsaturated fatty acids, the content of eicosapentaenoic acid in the Schizochytrium sp.

Abstract: Disclosed are a method and device for archive application, and a storage medium. The method for archive application includes: acquiring target time and space range information; determining, based on the target time and space range information, at least one target clustered archive in a clustered archive library, wherein the at least one target clustered archive matches the target time and space range information, each of the at least one target clustered archive includes archive information of a respective acquisition object, and the archive information includes activity time and space range information of the respective acquisition object; and performing a predetermined operation based on the at least one target clustered archive.

Abstract: A pixel structure for a vertical cavity surface emitting laser has an emission window. The pixel structure includes a plurality of sub-pixels in the emission window. Bright-area sub-pixels emit light and dark-area sub-pixels having no light emission. The bright-area sub-pixels and the dark-area sub-pixels are arranged in a pattern in the emission window. Various patterns are possible. Different structures for implementing the sub-pixels are described.

Abstract: The present invention discloses a PET image reconstruction method, a computer storage medium, and a computer device. The method includes: step 1, obtaining projection data Y and a system matrix P of a PET image; step 2, constructing an imaging model equation Y=PX, in which X is a reconstructed PET image; step 3, obtaining the initial reconstructed image X, and iteratively updating the initial reconstructed image X according to a first objective function to obtain a first reconstructed image; step 4, iteratively updating the first reconstructed image according to the second objective function to obtain the second reconstructed image; and step 5, determining whether an iteration condition is satisfied, if yes, outputting the current round of iteration to obtain the second reconstructed image as a final PET reconstructed image, and if not, returning to step 3 and using the second reconstructed image in the current round of iteration as an initial reconstructed image in the next round of iteration.

Abstract: There are provided a parallel rapid imaging method and device based on a complex number conjugate symmetry of multi-channel coil data and nonlinear GRAPPA image reconstruction, and a medium. The imaging method includes: obtaining virtual conjugate coil data by expanding the actual multi-channel coil data; combining actual multi-channel coil data and virtual multi-channel coil data to obtain a linear data term and a nonlinear data term; calibrating weighting factors of the linear data term and the nonlinear data term by using combined low-frequency full-sampling data (margins of the low-frequency full-sampling data includes parts of high-frequency data); reconstructing data which is under-sampled in a high-frequency region according to the calibrated weighting factors; fusing the low-frequency full-sampling data and the reconstructed data for the high-frequency region.

Abstract: Disclosed are information transmission method, apparatus, device and medium for medical imaging application. The method includes: an imaging device corresponding to an application authorization request is determined according to the received application authorization request, and an application permission profile of the imaging device is acquired; and a medical imaging application corresponding to the imaging device is determined according to the application permission profile of the imaging device, and medical imaging application information corresponding to the medical imaging application is transmitted to the imaging device.

Abstract: A touch array substrate, a display panel and a display device are provided. The touch array substrate includes a plurality of first electrodes disposed in a row direction and a column direction to form a plurality of electrode rows and a plurality of electrode columns. An edge of the plurality of first electrodes in the column direction includes a convex shape and a concave shape, the convex shape of an edge of one of two adjacent ones of the plurality of electrode columns extends into the concave shape of an edge of the other of the two adjacent ones of the plurality of electrode columns. The touch array substrate can avoid deficiencies such as a vertical line and the like in a macroscopic manner.

Abstract: Disclosed are a magnetic-resonance imaging method, apparatus and system, and a storage medium. The method includes acquiring an initial model of magnetic-resonance imaging and establishing an initial imaging model according to an iterative algorithm used for solving the initial model, where the iterative algorithm includes at least one of an undetermined parameter, an undetermined solving operator or an undetermined structural relationship; training the initial imaging model on the basis of sample data to generate a magnetic-resonance imaging model, where training of the initial imaging model is used for learning the at least one of the undetermined parameter, the undetermined solving operator or the undetermined structural relationship in the iterative algorithm; and acquiring under-sampled K-space data to be processed, inputting the under-sampled K-space data into the magnetic-resonance imaging model, and generating a magnetic-resonance image.

Abstract: Disclosed is a head-mounted display device, including a main body portion with an ocular lens, and further including an adjustment assembly which is connected to the main body portion and is used for adjusting a positional relationship with respect to the main body portion, wherein the adjustment assembly includes a shielding portion; when the adjustment assembly is in a first operating state, the shielding portion is away from the main body portion for realizing a wearing function; and when the adjustment assembly is in a second operating state, the shielding portion is close to the main body portion for shielding the ocular lens, thereby realizing convenient and quick storage and safekeeping, and facilitating the prolonging of the service life of the head-mounted display device.

Abstract: The present disclosure discloses a method and a system for generating a composite PET-CT image based on a non-attenuation-corrected PET image. The method includes: constructing a first generative adversarial network and a second generative adversarial network; obtaining a mapping relationship between a non-attenuation-corrected PET image and an attenuation-corrected PET image by training the first generative adversarial network; obtaining a mapping relationship between the attenuation-corrected PET image and a CT image by training the second generative adversarial network; and generating the composite PET-CT image by utilizing the obtained mapping relationships. According to the present disclosure, a high-quality PET-CT image can be directly composited from a non-attenuation-corrected PET image, and medical costs can be reduced for patients, and radiation doses applied to the patients in examination processes can be minimized.

Abstract: A frequency changer cabinet includes a transformer cabinet to accommodate a transformer, a first air outlet being disposed at a top of the transformer cabinet, and a first air inlet being disposed at a side wall; and a power unit cabinet to accommodate at least one power unit, a second air inlet being disposed at a front side wall, and a rear side of the being connected to the transformer cabinet. In an embodiment, a first air passage baffle and a second air passage baffle are respectively disposed at an upper end and a lower end of a secondary coil, such that air entering from the power unit cabinet to the transformer cabinet can be directly sent to the secondary coil. Further, air entering from the first air inlet can pass through a primary coil and the secondary coil, and then flow out of the transformer cabinet.

Abstract: The disclosure provides a low-dose image reconstruction method and system based on prior anatomical structure difference.

Abstract: A single-shot Fresnel non-coherent correlation digital holographic device based on a polarization-oriented planar lens, comprising: A polarization-oriented planar lens (1) for wavefront modulation and beam splitting, a focusing element (2), a half-wave plate (3) with a small hole and a polarization imaging camera (4). Incident light passes through the polarization-oriented planar lens (1) and the focusing element (2) and is divided into two beams with different polarizations, that is, focused and parallel or focused and divergent beams, wherein the focused beam passes through the small hole of the half-wave plate (3), the parallel or divergent beam passes through the half-wave plate (3), so as to make the polarization of the two beams consistent behind pass through the half-wave plate (3).

Abstract: A scoring system for a billiards game includes a camera, a computer, and an output device. The camera records images of a playing surface of a billiards table and a plurality of billiards balls on the playing surface. The computer analyzes video data to obtain locations of the billiards balls based on a predetermined model, confirms a status of a scene of the billiards game based on the locations of the billiards balls, and records scores and/or obtain data of the current player based on the status of the scene and rules of playing the billiards game. The output device converts information of the scores and the current player into human-readable form.

Abstract: Provided are a method and device for magnetic resonance parameter imaging, medical equipment, and a storage medium. The method comprises: performing acceleration sampling with respect to an image to be reconstructed of an observation target in a preset parameter direction to acquire K-space data corresponding to the image to be reconstructed, calculating, on the basis of the K-space data and of a parameter relaxation model, a parameter value and a compensation coefficient of the image to be reconstructed, generating, on the basis of the compensation coefficient, a compensation image corresponding to the image to be reconstructed, calculating, on the basis of the compensation image, respectively a low-rank part and a sparse part of the image to be reconstructed so as to update the compensation image.

Abstract: The present invention relates to a centrifuge for cleaning a reaction vessel unit, comprising a rotor and a rotor chamber in which the rotor is positioned and supported in rotary fashion. The rotor chamber is delimited by a housing having a drainage channel beneath the rotor. Adjacent to the channel, the inner surface of the housing is embodied in the form of a funnel that feeds into the channel. This centrifuge does not require a suction pump for suctioning liquids from the rotor chamber. In addition, the centrifuge can be provided with an exchangeable module that delimits the rotor chamber and includes the rotor. The exchangeable module can be exchanged after a predetermined amount of use and replaced with another. It is also possible, however, for the module to be removed from the centrifuge, cleaned, and re-inserted.

Abstract: A ground fault locating method for a power distribution network includes: monitoring each phase line of three phase distribution lines, and in the event of occurrence of waves with fault features, performing wave recording to obtain phase line record files; combining the record files corresponding to each of the three phase lines to obtain fault record files; and synthesizing the fault record files to form a transient record file, determining a fault location according to a wave having a maximum change in wave amplitude between two points in the transient record file, and displaying the fault location in a wiring diagram. The ground fault locating method for a power distribution network can significantly improve accuracy of single-phase ground fault detection.