The present disclosure relates to a data acquisition device and a configuration method. The device includes a channel, wherein the channel includes a data control panel and a plurality of detection components. At least one of the plurality of detection components is directly connected to the data control panel. The data control panel may be configured to identify the channel and send a configuration command to the plurality of detection components. The plurality of detection components may determine channel location numbers of the plurality of detection components based on the configuration command and send the channel location numbers to the data control panel. The data control panel may determine identification numbers for the plurality of detection components based on the channel location numbers and allocate the identification numbers to the plurality of detection components.

The present disclosure relates to a data acquisition device and a configuration method. The device includes a channel, wherein the channel includes a data control panel and a plurality of detection components. At least one of the plurality of detection components is directly connected to the data control panel. The data control panel may be configured to identify the channel and send a configuration command to the plurality of detection components. The plurality of detection components may determine channel location numbers of the plurality of detection components based on the configuration command and send the channel location numbers to the data control panel. The data control panel may determine identification numbers for the plurality of detection components based on the channel location numbers and allocate the identification numbers to the plurality of detection components.

For machine training and application of a trained complex-valued machine learning model, an activation function of the machine learning model, such as a neural network, includes a learnable parameter that is complex or defined in a complex domain with two dimensions, such as real and imaginary or magnitude and phase dimensions. The complex learnable parameter is trained for any of various applications, such as MR fingerprinting, other medical imaging, or non-medical uses.

A medical system comprises processing circuitry configured to: receive a first trained model, wherein the trained model has been trained using a first data set acquired in a first cohort; receive a second data set acquired in a second cohort; input data included in the second data set and data representative of the first trained model into a second trained model; and receive from the second trained model an affinity-relating value which represents an affinity between the data included in the second data set and the first trained model.

A medical system comprises processing circuitry configured to: receive a first trained model, wherein the trained model has been trained using a first data set acquired in a first cohort; receive a second data set acquired in a second cohort; input data included in the second data set and data representative of the first trained model into a second trained model; and receive from the second trained model an affinity-relating value which represents an affinity between the data included in the second data set and the first trained model.

A medical image segmentation method based on a U-Net, including: sending real segmentation image and original image to a generative adversarial network for data enhancement to generate a composite image with a label; then putting the composite image into original data set to obtain an expanded data set, and sending the expanded data set to improved multi-feature fusion segmentation network for training. A Dilated Convolution Module is added between the shallow and deep feature skip connections of the segmentation network to obtain receptive fields with different sizes, which enhances the fusion of detail information and deep semantics, improves the adaptability to the size of the segmentation target, and improves the medical image segmentation accuracy. The over-fitting problem that occurs when training the segmentation network is alleviated by using the expanded data set of the generative adversarial network.

A medical image segmentation method based on a U-Net, including: sending real segmentation image and original image to a generative adversarial network for data enhancement to generate a composite image with a label; then putting the composite image into original data set to obtain an expanded data set, and sending the expanded data set to improved multi-feature fusion segmentation network for training. A Dilated Convolution Module is added between the shallow and deep feature skip connections of the segmentation network to obtain receptive fields with different sizes, which enhances the fusion of detail information and deep semantics, improves the adaptability to the size of the segmentation target, and improves the medical image segmentation accuracy. The over-fitting problem that occurs when training the segmentation network is alleviated by using the expanded data set of the generative adversarial network.

A method for image analysis of medical test results, comprising receiving, at a server, information from a mobile device regarding test results from a test performed using a testing device, wherein the testing device includes an alignment target disposed on the testing device and a plurality of immunoassay test strips, receiving at the server an image of the testing device from the mobile device, determining by the server RGB values for a plurality of pixels of the image, normalizing by the server the RGB values into a single value, comparing by the server the single value to a control value stored on the server, and providing by the server a risk indicator, wherein the risk indicator indicates a likelihood of a presence of a medical condition.

A method for image analysis of medical test results, comprising receiving, at a server, information from a mobile device regarding test results from a test performed using a testing device, wherein the testing device includes an alignment target disposed on the testing device and a plurality of immunoassay test strips, receiving at the server an image of the testing device from the mobile device, determining by the server RGB values for a plurality of pixels of the image, normalizing by the server the RGB values into a single value, comparing by the server the single value to a control value stored on the server, and providing by the server a risk indicator, wherein the risk indicator indicates a likelihood of a presence of a medical condition.

Rather than rely on variation from physician to physician and limited imaging information for assessing plaque vulnerability of a patient, medical imaging and other information are used by a machine-implemented classifier to predict plaque rupture. Anatomical, morphological, hemodynamic, and biochemical features are used in combination to classify plaque.