Abstract: A method includes a step of obtaining plural pieces of training data each of which includes a different radiographic image of a bone and each of which has a label indicating one of an overt fracture, an occult fracture and no fracture, a step of using the plural pieces of training data to pre-train a deep convolutional network (DCN) model to obtain a preliminary DCN model, a step of determining a subset of the plural pieces of training data by at least excluding any piece of training data that has a label indicating occult fracture, and a step of using the subset to train the preliminary DCN model to obtain a first DCN model.

Abstract: The instant disclosure discloses an antibody or antigen-binding fragment thereof binding to Porcine Reproductive and Respiratory Syndrome Virus (PRRSV), and uses of such antibody or antigen-binding fragment thereof to create immunoassay methods or devices for PRRSV detection.

Abstract: The instant disclosure discloses an antibody or antigen-binding fragment thereof binding to Porcine Reproductive and Respiratory Syndrome Virus (PRRSV), and uses of such antibody or antigen-binding fragment thereof to create immunoassay methods or devices for PRRSV detection.

Abstract: The present disclosure provides a method for preparing a biochip. The method includes steps of coating a chip with a first solution of biotin to form a biotin-coated chip, wherein the biotin in the first solution is in a first concentration ranging from 0.1 to 1 ?g/ml; providing the biotin-coated chip with a second solution of avidin to form an avidin/biotin-coated chip, wherein the avidin in the second solution is in a second concentration ranging from 0.1 to 100 ?g/ml; and providing the avidin/biotin-coated chip with a third solution of a biotinylated probe to form the biochip, wherein the biotinylated probed in the third solution is in a third concentration ranging from 1 to 3 ?g/ml.

Abstract: The instant disclosure discloses an antibody or antigen-binding fragment thereof binding to Porcine Reproductive and Respiratory Syndrome Virus (PRRSV), and uses of such antibody or antigen-binding fragment thereof to create immunoassay methods or devices for PRRSV detection.

Abstract: A method for categorizing and adjusting an orientation of a clinical image is implemented using a system that includes a categorization module and a plurality of orientation modules. The method includes: in response to receipt of the clinical image, performing, by the categorization module, a categorization operation so as to categorize the clinical image into one of a plurality of predetermined categories; transmitting the clinical image to a corresponding one of the plurality of orientation modules based on a result of the categorization operation; and performing, by the corresponding one of the plurality of orientation modules, an orientation adjusting operation for adjusting the orientation of the clinical image. For a clinical image that is a facial image and for a clinical image that is an intra-oral image, different orientation adjusting operations may be performed, so as to generate an adjusted image that is properly oriented.

Abstract: A method for establishing a 3D medical imaging model of a subject is to be implemented by an X-ray computed tomography (CT) scanner and a processor. The method includes: emitting X-rays on the subject sequentially from plural angles with respect to the subject to obtain M number of X-ray images of the subject in sequence; obtaining, for each pair of consecutive X-ray images, K number of intermediate image(s) by using the pair of consecutive X-ray images as inputs to a convolutional neural network (CNN) model that has been trained for frame interpolation; and establishing the 3D medical imaging model by using a 3D reconstruction technique based on the M number of X-ray images and the intermediate images obtained for the M number of X-ray images.

Abstract: A method of opportunistic screening of osteoporosis includes obtaining a plain film chest X-ray (CXR); extracting regions of interest (ROIs) from the plain film CXR; and providing individual bone mineral density (BMD) scores corresponding to the extracted ROIs and a joint BMD corresponding to the plain film CXR based on a multi-ROI model by performing: inputting the extracted ROIs into a backbone network to generate individual feature vectors, each individual feature vector corresponding to one of the extracted ROIs; concatenating the individual feature vectors into a joint feature vector; individually decoding the individual feature vectors by a shared fully connected (FC) layer to generate the individual BMDs, each individual BMD corresponding to one of the individual feature vectors; and decoding the joint feature vector by a separate FC layer to generate the joint BMD.

Abstract: A method for establishing a 3D medical imaging model of a subject is to be implemented by an X-ray computed tomography (CT) scanner and a processor. The method includes: emitting X-rays on the subject sequentially from plural angles with respect to the subject to obtain M number of X-ray images of the subject in sequence; obtaining, for each pair of consecutive X-ray images, K number of intermediate image(s) by using the pair of consecutive X-ray images as inputs to a convolutional neural network (CNN) model that has been trained for frame interpolation; and establishing the 3D medical imaging model by using a 3D reconstruction technique based on the M number of X-ray images and the intermediate images obtained for the M number of X-ray images.

Abstract: A method includes a step of obtaining plural pieces of training data each of which includes a different radiographic image of a bone and each of which has a label indicating one of an overt fracture, an occult fracture and no fracture, a step of using the plural pieces of training data to pre-train a deep convolutional network (DCN) model to obtain a preliminary DCN model, a step of determining a subset of the plural pieces of training data by at least excluding any piece of training data that has a label indicating occult fracture, and a step of using the subset to train the preliminary DCN model to obtain a first DCN model.

Abstract: A pattern recognition method of the immunofluorescence images of autoantibody identification is disclosed. The method includes the following steps: inputting a plurality of original cell immunofluorescence images; conducting an operation of a plurality of convolutional neural networks by a processor, the plurality of convolutional neural networks include a convolution layer, a pooling layer and an inception layer for capturing the plurality of convolution features; conducting a judgment process to obtain the proportions of the antinuclear antibodies morphological patterns; and outputting the recognition results.

Abstract: A classification system and a classification method of the autoantibody immunofluorescence image are disclosed. The system includes an input device, a processor and an output device. The plurality of cell immunofluorescence images and the corresponded extractable nuclear antigen results are input through the input device. The processor conducts a plurality of convolution neural network calculation and output the classification based on the extractable nuclear antigen results, so as to obtain an extractable nuclear antigen classification model. When the autoantibody immunofluorescence image is input by the input device, the corresponded classification of the extractable nuclear antigen can be predicted. The classification result is output through the output device.

Abstract: A classification system and a classification method of the autoantibody immunofluorescence image are disclosed. The system includes an input device, a processor and an output device. The plurality of cell immunofluorescence images and the corresponded extractable nuclear antigen results are input through the input device. The processor conducts a plurality of convolution neural network calculation and output the classification based on the extractable nuclear antigen results, so as to obtain an extractable nuclear antigen classification model. When the autoantibody immunofluorescence image is input by the input device, the corresponded classification of the extractable nuclear antigen can be predicted. The classification result is output through the output device.

Abstract: A pattern recognition method of the immunofluorescence images of autoantibody identification is disclosed. The method includes the following steps: inputting a plurality of original cell immunofluorescence images; conducting an operation of a plurality of convolutional neural networks by a processor, the plurality of convolutional neural networks include a convolution layer, a pooling layer and an inception layer for capturing the plurality of convolution features; conducting a judgment process to obtain the proportions of the antinuclear antibodies morphological patterns; and outputting the recognition results.

Abstract: A wireless receiver with automatic gain control and a method for automatic gain control of a receiving circuit utilized in a wireless receiver are provided. The receiving circuit includes a programmable gain amplifier and a low noise amplifier, and the method includes: comparing a gain code of the programmable gain amplifier with a predetermined code range, wherein the gain code is determined by a frequency signal received through the low noise amplifier; and adjusting a gain of the low noise amplifier when the gain code is out of the predetermined code range.

Abstract: An integrated circuit and an apparatus are provided. The integrated circuit comprises a bias circuit, an LC resonator circuit, and a current mode logic (CML) frequency divider. The bias circuit generates first and second bias voltages. The LC resonator circuit generates an oscillation signal having an oscillation frequency. The CML frequency divider, coupled to the bias circuit and the LC resonator circuit, biased by the first and second bias voltages, receives the oscillation signal to generate an output signal having an output frequency with a fractional rate of the oscillation frequency. The oscillation signal comprises AC and DC components, the CML frequency divider receives the AC component to determine an injected frequency and reuses the DC component to provide tail currents to determine a natural frequency of the CML frequency divider. The output frequency is determined by the injected frequency and the natural frequency.

Abstract: A receiver includes a mixer, a poly phase filter, a channel select filter, an analog-to-digital converter and a HI/LO side reject selection unit. The mixer downconverts a signal to generate an in-phase signal and a quadrature signal. The poly phase filter for generates differential IF signals based on the in-phase signal and the quadrature signal. The channel select filter filters out unwanted channel signals from the differential IF signals. The analog-to-digital converter converts the filtered signal into a digital output signal. The HI/LO side reject selection unit is coupled between the mixer and the poly phase filter and capable of rejecting image signals while the mixer is at a high side frequency or at a low side frequency.

Abstract: A Global Positioning System (GPS) receiver integrated with a cellular phone system, comprising a single-balanced mixer, a poly phase filter, a channel select filter, an analog-to-digital converter, a reference frequency source, and a PLL unit is disclosed. The single-balanced mixer downconverts a GPS signal to generate an in-phase signal I and a quadrature signal Q. The poly phase filter generates an IF signal based on the in-phase signal I and the quadrature signal Q. The channel select filter receives the IF signal to filter unwanted channel signals. The analog-to-digital converter converts the signal from the channel select filter to a digital output signal. The reference frequency source provides a reference frequency to the analog-to-digital converter. The PLL unit receives the reference frequency for generating a clock signal to the single-balanced mixer for downconversion.

Abstract: A system capable of limiting a current through a load and a method thereof. The system comprises a current sensor, a determination circuit, and a current mirror circuit. The current sensor, coupled to the load, produces a current indication indicating the current. The determination circuit, coupled to the current sensor, generates a short-circuit signal when the current exceeds a predetermined threshold. The current mirror circuit, coupled to a voltage source, the current sensor and the determination circuit, comprises a current mirror and a bypass path, delivers a mirrored current from the current mirror to the load upon receiving the short-circuit signal, and passes the current from the voltage source through the bypass path to the load in the absence of the short-circuit signal.

Abstract: An integrated circuit and an apparatus are provided. The integrated circuit comprises a bias circuit, an LC resonator circuit, and a current mode logic (CML) frequency divider. The bias circuit generates first and second bias voltages. The LC resonator circuit generates an oscillation signal having an oscillation frequency. The CML frequency divider, coupled to the bias circuit and the LC resonator circuit, biased by the first and second bias voltages, receives the oscillation signal to generate an output signal having an output frequency with a fractional rate of the oscillation frequency. The oscillation signal comprises AC and DC components, the CML frequency divider receives the AC component to determine an injected frequency and reuses the DC component to provide tail currents to determine a natural frequency of the CML frequency divider. The output frequency is determined by the injected frequency and the natural frequency.