Abstract: Embodiments of this application disclose methods, systems, and devices for image region localization and medical image processing. In one aspect, a method comprises acquiring three-dimensional images of a target body part of a patient. The three-dimensional images comprise a plurality of magnetic resonant imaging (MRI) modalities. The method comprises registering a first image set of a first modality with a second image set of a second modality. After the registering, image features of the three-dimensional images are extracted. The image features are fused to obtain fused features. The method also comprises determining voxel types corresponding to voxels in the three-dimensional images according to the fused features. The method also comprises selecting, from the three-dimensional images, target voxels having a preset voxel type, obtaining position information of the target voxels, and localizing a target region within the target body part based on the position information of the target voxels.

Abstract: A whole slide image (WSI) search method is performed by a computer device, which belong to the field of artificial intelligence. The method includes: acquiring a plurality of tissue images obtained by cropping a WSI; inputting the plurality of tissue images into an image encoder to obtain image feature vectors respectively corresponding to the plurality of tissue images; determining at least one key image from the image feature vectors respectively corresponding to the plurality of tissue images; querying, based on image feature vectors respectively corresponding to the at least one key image, a database for at least one candidate image package respectively corresponding to the at least one key image; and determining at least one screened image package from the at least one candidate image package according to attributes of the at least one candidate image package as search results corresponding to the WSI.

Abstract: This application discloses a method for determining a lesion region, and a model training method and apparatus, and relates to the field of computer vision technologies. The method includes the following steps: sampling a pathological image by a first sampling way to obtain at least two first instance images (310); determining a candidate lesion region in the pathological image, based on feature information extracted from the at least two first instance images (320); sampling the candidate lesion region by a second sampling way to obtain at least two second instance images, where an overlap degree between the second instance images is greater than that between the first instance images (330); and determining lesion indication information of the pathological image, based on feature information extracted from the at least two second instance images, where the lesion indication information is used for indicating the lesion region in the pathological image (340).

Abstract: Provided is a method for searching for a whole slide image performed by a computer device, which relate to the field of artificial intelligence. The method includes: cropping a whole slide image into a plurality of tissue images; generating, through an image encoder, image feature vectors respectively corresponding to the plurality of tissue images; clustering the image feature vectors respectively corresponding to the plurality of tissue images, to determine at least one key image from the plurality of tissue images; querying, based on image feature vectors respectively corresponding to the at least one key image, a database to obtain at least one target image package corresponding to the at least one key image; and determining a whole slide image to which at least one candidate tissue image comprised in the at least one target image package respectively belongs as a final search result.

Abstract: A display panel and a display device are disclosed. The display panel includes a display substrate, a plurality rows of first pixel driving circuits, a plurality rows of second pixel driving circuits, and a plurality of first reset signal lines; the plurality of reset signal lines comprises a plurality of first reset signal lines and a plurality of second reset signal lines, each of the first reset signal lines is only electrically connected to one row of the first pixel driving circuits; each of the second reset signal lines is electrically connected to one row of the first pixel driving circuits and at least one row of the second pixel driving circuits.

Abstract: A liquid discharge head includes a first housing, a sealing member, and a second housing. The first housing includes a nozzle from which a liquid is dischargeable and a liquid chamber communicating with the nozzle. The sealing member openably closes the nozzle. The second housing includes a moving member and a container. The moving member moves a portion of the sealing member between a first position at which the portion of the sealing member contacts the nozzle to close the nozzle and a second position at which the portion of the sealing member is separated from the nozzle to open the nozzle. The container stores and holds the moving member in the container. The sealing member is sandwiched between the first housing and the second housing to partition the liquid chamber and the container.

Abstract: A reliable multi-information entropy PUF for Internet of Things security includes a control circuit, a data register, 128 glitch generation circuits, a 128-to-1 multiplexer, and a Schmidt glitch sampling module. The control circuit controls the data register to generate a square signal, the 128 glitch generation circuits to generate glitch signals to be output and the 128-to-1 multiplexer to select the glitch signals to be output. The Schmidt glitch sampling module samples the glitch signals to obtain PUF response outputs. Each glitch generation circuit generates a glitch signal by means of a fully symmetrical structure. The Schmidt glitch sampling module comprises a first PMOS transistor, a second PMOS transistor, a third PMOS transistor, a fourth PMOS transistor, a first NMOS transistor, a second NMOS transistor, a third NMOS transistor, a fourth NMOS transistor, a buffer module and a D flip-flop.

Abstract: A method for constructing a recognition model of a moisture damage of an asphalt pavement, and a method and system for recognizing the moisture damage of the asphalt pavement are provided. The method includes the following steps: S1, acquiring an initial dataset through a Ground Penetrating Radar (GPR) pavement field survey; S2, acquiring a time-frequency image set; S3, adjusting a resolution of a time-frequency image; and S4, constructing the recognition model and recognizing the moisture damage of the asphalt pavement with the recognition model. —A method and a system for recognizing the moisture damage of the asphalt pavement are further provided. The method for constructing and the method and the system for recognizing solves a technical problem of detecting the moisture damage of the asphalt pavement automatically to not only improving a precision of a moisture damage recognition, but also providing a novel method for analyzing GPR original data.

Abstract: A rotating shaft mechanism, including a mounting base and at least one rotating assembly each of which includes two rotating modules; a rotating module includes a supporting plate, a sliding plate and an elastic pressing mechanism; the supporting plate is rotatably connected to the mounting base; a surface of the supporting plate is provided with a first limiting portion and a second limiting portion; the first limiting portion and the second limiting portion are provided at intervals along the first direction; a portion of the sliding plate is rotatably connected to the mounting base, and another portion of the sliding plate is slidably connected to the supporting plate; and a distance between the end of the sliding plate away from the mounting base and the second limiting portion is proportional to a maximum angle to which the supporting plate is able to rotate.

Abstract: The present invention provides a chain plate flexible finger including a chain plate framework, a pneumatic elastic bellows artificial muscle, and a plastic annular frame. The axial expansion of the elastic bellows artificial muscle is restricted by the chain plate framework to overcome the elastic force of a tension spring to bend, to generate conformal contact between one or more chain plates and an object to be gripped and generate a contact force for a gripping state. With the control of a high-speed on-off valve, the air pressure in an inner cavity of the elastic bellows artificial muscle is accurately controlled to vertically or horizontally grip a cylindrical object, a cuboid object, a spherical object or an ellipsoid object. The flexible finger has adequate flexible adaptability and a simple structure, and is reliable to use, and adapts to differently shaped objects to be gripped and vertically and transversely placed objects.

Abstract: A modular warehouse system and its assembly method are provided. A plurality of storage containers is combined to form a combined storage area, which is provided with a track assembly, a bin gripping robot, and a plurality of bins. An internal space of at least one track-switching container is in communication with the internal space of at least one of the plurality of storage containers. The track-switching container is provided with a track-switching device therein, and the track-track-switching device is configured to switch the bin gripping robot in at least one of the storage containers from a current running track where the bin gripping robot is located to a target running track. An internal space of at least one outbound-inbound container is in communication with the internal space of the track-switching container. The outbound-inbound container is provided with an outbound-inbound device for performing goods outbound-inbound operations.

Abstract: A charging control apparatus and method for an electronic device are provided. During a process of charging, the power adapter first charges the battery with a constant-voltage direct current output, and then after the power adapter receives a quick-charging instruction, the power adapter adjusts an output voltage according to the voltage of the battery fed back by the charging control circuit, and if the output voltage meets a quick-charging voltage condition pre-set by the charging control circuit, the power adapter adjusts an output current and the output voltage respectively according to a preset quick-charging current value and a preset quick-charging voltage value for quick-charging the battery, and meanwhile the charging control circuit introduces direct current from the power adapter for charging the battery; during a process of quick-charging, the power adapter adjusts the output current in real time according to the output voltage thereof and the voltage of the battery.

Abstract: A system generating an electrical signal based on at least one physical quantity, includes sensor units each generating an individual electrical signal in response to the at least one physical quantity, a selecting unit selecting a first number of sensor units from the sensor units and outputting a first combined electrical signal based on the first number of sensor units, and a calibrating unit determining a second number of sensor units to be selected based on the first combined electrical signal.

Abstract: The present invention first develops a novel dualized information theory where both troenpy can quantifying the certainty while entropy can measure the uncertainty. The invention then develops a set of weighting methods for a term using the introduced dual metrics, and these methods makes use of the label information of the documents in the underlying corpus. The invention further proposes a set of class information bias features for each term using the dualized information metric. For various information retrieval and machine learning tasks the invention proposes using these combined features for optimal document representation.

Abstract: An articulation assembly (500) for use with a surgical device includes a drive bar (550), a locking pin (570), a drive gear (560), and a yoke (600). The drive bar (550) includes a base (552) and a stem (590) extending therefrom. The base (552) includes first teeth. The locking pin (570) engages the first teeth of the drive bar (550). The drive gear (560) is operatively coupled to the drive bar (550). The drive gear (560) includes second teeth defining a gap (564) between adjacent second teeth. The gap (564) is configured to receive a portion of the locking pin (570). The yoke (600) is operatively coupled to the drive gear (560) such that rotation of the drive gear (560) causes axial displacement of the yoke (600). Rotation of the drive bar (550) transitions the locking pin (570) from a locked state to an unlocked state and rotates the drive gear (560) when the locking pin (570) is in the unlocked state such that the yoke (600) is axially displaced.

Abstract: A device is described that includes a carrier that has a plurality of light-emitting diode (LED) mounting areas. Each of the LED mounting areas includes a pair of contact pads, which are electrically coupled to the LED mounting area in a first subset of the plurality of LED mounting areas or electrically connected in series with a shunting element in the respective LED mounting area in a second subset of the plurality of LED mounting areas. In some embodiments, LEDs may be placed in the first subset of the plurality of LED mounting areas.

Abstract: This application discloses a physiological image processing method performed by a computer device. The method includes: obtaining a physiological image; determining position information of at least one mutated object in the physiological image based on a physiological image processing model; performing color channel decomposition on the physiological image to obtain staining information corresponding to the physiological image; and making statistics according to the position information and the staining information to obtain a staining counting result of the mutated objects. According to this application, by obtaining the staining counting result of the mutated objects according to the position information of the mutated objects and the staining information, the staining counting result of the mutated objects is quickly obtained.

Abstract: A method for training an image recognition model is performed by a computer device. The method includes: obtaining a sample image and a corresponding sample label; obtaining a sample image patch bag of sample image patches corresponding to the sample image, the sample patch bag having a bag label corresponding to the sample label of the sample image; performing feature analysis on the sample patch bag and the sample image patches in the sample patch bag, respectively, by using an image recognition model; determining a relative entropy loss, a first cross entropy loss corresponding to the sample patch bag and a second cross entropy loss corresponding to the sample image patches based on corresponding bag feature analysis and patch analysis results, respectively; and training the image recognition model based on the relative entropy loss, the first cross entropy loss, and the second cross entropy loss.

Abstract: Provided are a standing coke-making furnace, a coke-making system and a method thereof.

Abstract: Provided is a hinge. The hinge includes: a mounting base, two torsion shafts, a resilient structure, and two rotary arms; wherein the two torsion shafts and the resilient structure are mounted on the mounting base, the resilient structure is disposed between the two torsion shafts, and the two rotary arms are connected to the two torsion shafts respectively; a bump is disposed on a side wall of each of the two torsion shafts, wherein the bump is disposed on a side, close to the resilient structure, of the torsion shaft, and the bumps of the two torsion shafts are in contact with the resilient structure; and the resilient structure is configured to apply a force to the torsion shaft by the bumps, such that the two rotary arms have a tendency to rotate away from each other.