Abstract: A computer device obtains a to-be-annotated image having a first magnification. The device obtains an annotated image from an annotated image set, the annotated image distinct from the to-be-annotated image and having a second magnification that is distinct from with the first magnification. The annotated image set includes at least one annotated image. The device matches the to-be-annotated image with the annotated image to obtain an affine transformation matrix, and generates annotation information of the to-be-annotated image according to the affine transformation matrix and the annotated image. In this way, annotations corresponding to images at different magnifications may be migrated. For example, the annotations may be migrated from the low-magnification images to the high-magnification images, thereby reducing the manual annotation amount and avoiding repeated annotations, and further improving annotation efficiency and reducing labor costs.

Abstract: This application describes a medical image classification method, a model training method, and a server. The medical image classification method includes: obtaining, by a device, a medical image data set. The device includes a memory storing instructions and a processor in communication with the memory. The method includes performing, by the device, quality analysis on the medical image data set, to extract feature information of a medical image in the medical image data set; and classifying, by the device, the medical image data set based on the feature information and by using a pre-trained deep learning network for performing anomaly detection and classification, to obtain a classification result.

Abstract: A method comprises obtaining a pathology image set using a microscope, the pathology image set including at least a to-be-evaluated image and one or more associated images, the associated images and the to-be-evaluated image are consecutive frame images acquired using the microscope. The method comprises determining a first status corresponding to the to-be-evaluated image according to the pathology image set, the first status being used for indicating a motion change of the to-be-evaluated image during the acquisition and the first status includes a plurality of predefined states. The method comprises in accordance with a determination that the first status corresponds to a static state of the plurality of predefined states, determining a second status corresponding to the to-be-evaluated image, the second status indicating a change in image clarity of the to-be-evaluated image. This application further discloses an image status determining apparatus, a device, and a computer storage medium.

Abstract: This invention relates to pharmaceutical compositions and methods for treating (including managing) or preventing metabolic syndrome related conditions using one or more RAR e.g., RAR agonists. Such conditions include, but are not limited to, diseases in pancreas, liver, kidney, testes, muscle, or adipose tissue, as well as other organs that are associated with high fat diet and/or vitamin A deficiency, as well as other conditions associated with abnormal level of triglyceride, cholesterol and/or glucose.

Abstract: This application provides an information transmission method and a communication apparatus. The method includes: A first device sends TWT resource configuration information in a first BSS to a second device. The first device is located in the first BSS, the second device is located in a second BSS, and the first BSS and the second BSS at least partially overlap. According to the information transmission method provided in this application, TWT resource configuration information in a plurality of BSSs is shared among the plurality of BSSs in an OBSS scenario. Therefore, collision can be further avoided during data transmission in different BSSs in the OBSS scenario, thereby improving quality and assurance of data transmission between devices in the plurality of BSSs, and improving efficiency of data transmission in the OBSS scenario.

Abstract: The present disclosure relates to efficient programming and configuring of electronic payment process. An example method includes receiving programming language-based descriptions each describing a distinct functional operation usable to implement the electronic payment process, compiling each programming language-based description into a distinct computer-executable code segment that corresponds to a state of a finite state machine. The method also includes determining transition relationships between states of the finite state machine based on the logic flow of steps of the electronic payment process, generating a state transition table for storing in a cache of a computer-based electronic payment system implementing the finite state machine, and configuring the finite state machine by retrieving the state transition table from the cache at runtime.

Abstract: A statistical learning technique that does not rely upon paired imaging information is described herein. The technique may be computer-implemented and may be used in order to train a statistical learning model to perform image synthesis, such as in support of radiation therapy treatment planning. In an example, a trained statistical learning model may include a convolutional neural network established as a generator convolutional network, and the generator may be trained at least in part using a separate convolutional neural network established as a discriminator convolutional network. The generator convolutional network and the discriminator convolutional network may form an adversarial network architecture for use during training. After training, the generator convolutional network may be provided for use in synthesis of images, such as to receive imaging data corresponding to a first imaging modality type, and to synthesize imaging data corresponding to a different, second imaging modality type.

Abstract: This application provides a beam training method and apparatus. The method includes: generating and sending a set up frame, where the set up frame includes M pieces of time information, each piece of time information corresponds to one receiving device in the M receiving devices, each piece of time information is used to indicate a feedback information sending moment of the corresponding receiving device, each piece of time information is further used to indicate an acknowledgment information receiving moment of the corresponding receiving device, receiving a sector sweep SSW frame, generating feedback information based on the SSW frame, sending the feedback information at a feedback information sending moment indicated by corresponding time information, receiving, at an acknowledgment information receiving moment indicated by the corresponding time information, acknowledgment information. Therefore, a training time can be shortened, and signaling overheads can be reduced.

Abstract: The present disclosure relates to a method for ultrasound imaging and a related equipment, the method for ultrasound imaging comprising: obtaining ultrasound body data of a test object; determining position information of a target anatomical structure from the ultrasound body data; determining an ultrasound image of the target anatomical structure from the ultrasound body data according to the position information of the target anatomical structure; and displaying the ultrasound image.

Abstract: Embodiments of the present disclosure disclose a thin film transistor, a method for manufacturing a thin film transistor, an array substrate, and a display device. The thin film transistor includes a source electrode and a drain electrode, each of the source electrode and the drain electrode including a metal substrate and a conductive layer covering the metal substrate. An adhesion between the conductive layer and a photoresist material is larger than an adhesion between the metal substrate and the photoresist material. The metal substrate and the conductive layer are both formed on a base substrate, an orthographic projection of the conductive layer on the base substrate covers an orthographic projection of the metal substrate on the base substrate, and. an area of the orthographic projection of the conductive layer on the base substrate is larger than an area of the orthographic projection of the metal substrate on the base substrate.

Abstract: Systems and methods include training a deep convolutional neural network (DCNN) to reduce one or more artifacts using a projection space or an image space approach. In a projection space approach, a method can include collecting at least one artifact contaminated cone beam computed tomography (CBCT) projection space image, and at least one corresponding artifact reduced, CBCT projection space image from each patient in a group of patients, and using the artifact contaminated and artifact reduced CBCT projection space images to train a DCNN to reduce artifacts in a projection space image. In an image space approach, a method can include collecting a plurality of CBCT patient anatomical images and corresponding registered computed tomography anatomical images from a group of patients, and using the plurality of CBCT anatomical images and corresponding artifact reduced computed tomography anatomical images to train a DCNN to remove artifacts from a CBCT anatomical image.

Abstract: This application provides a communication method and a communications apparatus. According to the communication method provided in this application, a first device sends, by using a control trailer and to one or more second devices, configuration information used for multiple-input multiple-output MIMO communication between the first device and the second device, so that the MIMO communication can be performed between the first device and the one or more second devices based on the configuration information.

Abstract: Embodiments of this application disclose methods, systems, and devices for medical image analysis and medical video stream processing. In one aspect, a method comprises extracting video frames from a medical image video stream that includes at least two pathological-section-based video frames. The method also comprises identifying single-frame image features in the video frames, mapping the single-frame image features into single-frame diagnostic classification results, and performing a classification mapping based on a video stream feature sequence that comprises the single-frame image features. The classification mapping comprises performing a convolution operation on the video stream feature sequence through a preset convolutional layer, obtaining a convolution result in accordance with the convolution operation, and performing fully connected mapping on the convolution result through a preset fully connected layer.

Abstract: An array substrate includes a base, at least one common electrode, at least one signal line and at least one conductive connecting line. The at least one common electrode is formed on the base, and a signal line arranged correspondingly to each of the at least one common electrode is formed on the base. The signal line includes a light absorbing layer and a metal layer that are stacked in a direction away from the base. Conductivity of the light absorbing layer is less than conductivity of molybdenum. Each of the at least one conductive connecting line is electrically connected to both a common electrode and a metal layer in the corresponding signal line.

Abstract: A method for manufacturing an array substrate, including forming a thin film transistor and a peripheral circuit; forming a passivation layer covering at least the thin film transistor and the peripheral circuit; forming a first via hole penetrating the passivation layer and exposing part of a drain of the thin film transistor, and a second via hole penetrating the passivation layer and exposing part of the peripheral circuit; forming a first conductive layer pattern on the passivation layer, the first conductive layer pattern covering the first via hole and the second via hole; forming a reflective metal layer pattern and a second conductive layer pattern on the first conductive layer pattern, the second conductive layer pattern covering the second via hole.

Abstract: This application provides a beam training method and apparatus. The method includes: A first access point AP determines first information. The first information is used to indicate an association beamforming training A-BFT time period, the A-BFT time period is used to perform A-BFT between a plurality of APs and a station STA within coverage of the plurality of APs, and the plurality of APs include the first AP and at least one second AP. The first AP sends the first information. A first STA receives the first information, and determines, based on the first information, a time period for performing sector sweep. The beam training method and apparatus in embodiments of this application can be used to control the plurality of APs and a plurality of STAs to perform association beamforming training.

Abstract: This disclosure provides an array substrate, a method for fabricating the same, a display panel, and a display device, where a first photo-resist layer is stripped in a changed order in that the first photo-resist layer on a source-drain is stripped through wet etching before a ohm contact layer film and an active layer film are etched in an electrically-conductive channel area (i.e., an electrically-conductive channel of a TFT is etched) to form an ohm contact layer and an active layer.

Abstract: The present invention discloses a method and an apparatus for extracting mountain landscape buildings based on high-resolution remote sensing images. The method comprises: segmenting a remote sensing image, and extracting non-vegetation areas from the remote sensing image by using NDVI; segmenting the non-vegetation areas, and extracting building areas by using NDBI; segmenting the building areas again, and calculating a normalized difference build shadow index NSBI of each patch; calculating NSBI separator of each patch in the non-vegetation areas and setting a separator threshold, and extracting landscape building areas based on the threshold. In the present invention, by introducing a near infrared band in the remote sensing image spectrum, in which there is a significant difference between shadows and non-shadows, the influence of large shadow areas in mountainous shady areas in the remote sensing image on the result of extraction is reduced.