Abstract: Various of the disclosed embodiments relate to systems and methods for processing surgical data to facilitate further downstream operations. For example, some embodiments may include machine learning systems trained to recognize whether video from surgical visualization tools, such as endoscopes, depicts a field of view inside or outside the patient body. The system may excise or whiteout frames of video appearing outside the patient so as to remove potentially compromising personal information, such as the identities of members of the surgical team, the patients identity, configurations of the surgical theater, etc. Appropriate removal of such non-surgical data may facilitate downstream processing, e.g., by complying with regulatory requirements as well as by removing extraneous data potentially inimical to further downstream processing, such as training a downstream classifier.

Abstract: A light detecting system and a light detecting method for a flow cytometer are provided. The light detecting system includes a beam separating device and multiple wavelength division multiplexing devices. The beam separating device is configured to separate a beam to be processed by the flow cytometer into multiple first beams having respective wavelength ranges that either do not overlap with each other or partially overlap with each other. Each of the multiple wavelength division multiplexing devices is configured to receive a respective one of the multiple first beams. The multiple first beams are parallel to each other when received by the multiple wavelength division multiplexing devices. Each of the multiple wavelength division multiplexing devices includes multiple light detecting devices being configured to detect a portion of the respective first beam.

Abstract: The electronic module includes a first circuit board and a second circuit board. The first circuit board includes a first side and a second side opposite to each other. Soldering pads are disposed on the second side. A second circuit board includes a third side and a fourth side opposite to each other. First connection components and second connection components are disposed on the third side, and solder balls are provided on the fourth side. First ends of the first and second connection components are fixed to the third side through a first reflow soldering process. Second ends of the first and second connection components are fixed to the soldering pads through a second reflow soldering process. A first space between adjacent ones of the first connection components is greater than a second space between adjacent ones of the second connection components.

Abstract: The present disclosure provides an apparatus and method for growing high-quality silicon carbide crystals and silicon carbide crystals, and relates to the technical field of the silicon carbide crystals. In the apparatus, a pressure equalizing structure is arranged on the annular guide plate, a pressure difference between a second chamber above the annular guide plate and a first chamber below the annular guide plate can be effectively reduced, and the flow rate of the gaseous-phase crystal growth components at a gap between a top end of the annular guide plate and an edge of the seed crystal can be effectively reduced accordingly, and then the defects such as a “concave interface” on the silicon carbide crystals growing on the seed crystal are avoided, thereby improving the growth quality of the silicon carbide crystals. The silicon carbide crystals prepared by the method have characteristics of fewer defects and high quality.

Abstract: A peristaltic pump includes a frame, a tube, and a rotor, the tube being fitted in the frame. The rotor includes a rotary member and a roller, wherein the rotary member is rotatable relative to the frame, and the roller is movable along the tube for squeezing the tube to pump fluid in the tube, when the rotary member is rotated. The roller is connected to the rotary member in such a manner as to allow the roller to move between a first position that squeezes the tube and a second position that releases, i.e. does not squeeze, the tube, thereby avoiding permanent plastic deformation of the tube.

Abstract: A power module assembly is disposed on a substrate and dissipates heat generated through the substrate. The power module assembly includes a circuit board, a heat-generating device, a first metal block, a first filling material and a second filling material. The circuit board includes at least one plane. The heat-generating device is disposed on the plane. The first metal block includes a first side and a second side. The first side of the first metal block faces the heat-generating device, and the second side of the first metal block faces the substrate. The first filling material is disposed between the first side of the first metal block and the heat-generating device. The second filling material is disposed between the second side of the first metal block and the substrate.

Abstract: Multi-modal data and ontology knowledge fusion machine learning for robotic medical systems is described. One or more processors can generate, using the training dataset and one or more teacher models, classifications of segments of the medical procedures in a first segment type. The one or more processors can map, using an ontology indicating a hierarchy of different segment types of medical procedures, the classifications of the segments in the first segment type to a second segment type. The one or more processors can train, using the mapping based on the classifications generated by the one or more teacher models, one or more student models with a machine learning technique. The one or more processors can execute, using data received from a robotic medical system for a medical procedure, the one or more student models to classify a segment of the medical procedure.

Abstract: A method for predicting movement of a first plurality of keypoints of a first instrument comprises receiving, at a neural network model, a first location of the first plurality of keypoints and a first location of a second plurality of keypoints of a second instrument. The method further comprises determining a trajectory for the first and second pluralities of keypoints by: generating, using an attention model of the neural network model, a first and second tool-level graph indicating a spatial-temporal relationship between the first and second pluralities of keypoints, respectively; and generating a scene-level graph based on the tool-level graphs. The scene-level graph indicates a spatial-temporal relationship between the first and second pluralities of keypoints. The method further comprises generating an output image based on the determined trajectory. The output image includes an output location of the first and second pluralities of keypoints.

Abstract: The present disclosure relates to a kit for detecting a soluble growth stimulation expressed gene 2 protein. In particular, the present disclosure relates to a latex-enhanced turbidimetric immunoassay kit for detecting the concentration and/or content of the sST2 in human samples. The kit can be used in transmission immunoturbidimetry and scattering immunoturbidimetry. The kit comprises a buffer system, an anti-interference component, latex microspheres, an anti-sST2 antibody, etc. The latex-enhanced immunoturbidimetric agent of the present disclosure can detect sST2 proteins within a range of <400 ng/ml in a sample, with a sensitivity of up to 0.1 ng/ml and a high specificity, accuracy and precision. The kit is suitable for a fully automatic biochemical analyzer and a scattering analyzer, and has the advantages of convenient and fast use and low cost, and can be used clinically to detect the sST2 protein.

Abstract: An assembling method of an electronic module is disclosed and includes steps of: (a) providing a first circuit board including a first side and a second side; (b) providing a second circuit board including a third side and a fourth side, and a connection component connected to the third side; (c) providing a solder ball, and stacking the first circuit board, the second circuit board and the solder ball; and (d) performing a reflow soldering process to a stacked structure of the first circuit board, the second circuit board and the solder ball.

Abstract: The present disclosure provides a manufacturing method of a power module, including steps of: (a) providing a substrate, wherein the substrate comprises a first surface, a second surface and at least one working region, the first surface and the second surface are opposite to each other, and the at least one working region is disposed on the first surface or the second surface; (b) providing an electronic component disposed on the substrate; (c) forming an encapsulation layer disposed on the substrate and covering the electronic component, wherein a projection of the encapsulation layer on the first surface of the substrate is not overlapped with a projection of the working region on the first surface of the substrate; and (d) providing a magnetic component disposed on the working region of the substrate, so that the encapsulation layer at least partially surrounds a lateral periphery of the magnetic component, wherein a gap is formed between the encapsulation layer and the lateral periphery of the magnetic c

Abstract: The present disclosure provides a power module including a substrate, a first electronic component, at least one metal component, a first metal connection portion, and a second metal connection portion. The first electronic component and the at least one metal component are disposed at the first side of the substrate. The first metal connection portion and the second metal connection portion are disposed at a second side of the substrate. The first metal connection portion is electrically connected to the first electronic component to form an input and/or output pin of the power module. The second metal connection portion is at least electrically connected to the substrate to form a signal pin of the power module. The first side and the second side are opposite to each other.

Abstract: Systems and methods are presented for training a second machine learning model according to aspects of a trained first machine learning model. Processing features utilized by a training framework to train the first machine learning model are identified, and at least some of the processing features are combined with an initial set of training features to form updated training features. The updated training features are presented to a user for customization, resulting in customized training features. An executable training framework is configured with the customized training features and executed to train the second machine learning model.

Abstract: Systems and methods are presented for training a second machine learning model according to aspects of a trained first machine learning model. Processing features utilized by a training framework to train the first machine learning model are identified, and at least some of the processing features are combined with an initial set of training features to form updated training features. The updated training features are presented to a user for customization, resulting in customized training features. An executable training framework is configured with the customized training features and executed to train the second machine learning model.

Abstract: The present disclosure relates to a kit for detecting a soluble growth stimulation expressed gene 2 protein. In particular, the present disclosure relates to a latex-enhanced turbidimetric immunoassay kit for detecting the concentration and/or content of the sST2 in human samples. The kit can be used in transmission immunoturbidimetry and scattering immunoturbidimetry. The kit comprises a buffer system, an anti-interference component, latex microspheres, an anti-sST2 antibody, etc. The latex-enhanced immunoturbidimetric agent of the present disclosure can detect sST2 proteins within a range of <400 ng/ml in a sample, with a sensitivity of up to 0.1 ng/ml and a high specificity, accuracy and precision. The kit is suitable for a fully automatic biochemical analyzer and a scattering analyzer, and has the advantages of convenient and fast use and low cost, and can be used clinically to detect the sST2 protein.

Abstract: Disclosed is a glucose-6-phosphate dehydrogenase mutant and a use thereof in preparing a detection reagent. Compared with a wild-type glucose-6-phosphate dehydrogenase mutant, the glucose-6-phosphate dehydrogenase mutant contains a combination of the following mutations: 56C, 306C, and 454C. A detection kit prepared by using the glucose-6-phosphate dehydrogenase has strong specificity, high sensitivity, convenient operation, a short detection time, accurate quantification, and is suitable for high-throughput detection.

Abstract: A power module for supplying power to an electrical device includes a first circuit board, a second circuit board, a third circuit board and a heat-conductive element. The first, second and third circuit boards are stacked in sequence, and the heat-conductive element is disposed between the first circuit board and the second circuit board. The heat-conductive element includes a first heat-conductive portion and a second heat-conductive portion. The first heat-conductive portion extends in a direction perpendicular to a plane of the second circuit board and is in contact with a heat-dissipating element on the first circuit board. The second heat-conductive portion extends in a direction parallel to the plane of the second circuit board and is contact with heat-generating components on the second circuit board. The first and the second heat-conductive portions are connected to each other.

Abstract: The present disclosure provides a power module and a manufacturing method thereof. The power module includes a substrate, an electronic component, a magnetic component and an encapsulation layer. The substrate includes a first surface and a second surface opposite to each other, and a working region. The working region is disposed on the first surface or the second surface. The electronic component is disposed on the substrate. The magnetic component is disposed on the working region and includes a lateral periphery. The encapsulation layer is disposed on the substrate, covers the electronic component and at least partially surrounds the lateral periphery of the magnetic component. A projection of the encapsulation layer on the first surface of the substrate is not overlapped with a projection of the working region on the first surface, and a gap is formed between the encapsulation layer and the lateral periphery of the magnetic component.