Abstract: Methods, devices, and systems for data monitoring are provided. In one aspect, a method of data monitoring, applicable to a magnetic resonance system, includes: obtaining radio frequency (RF) waveform information which is to be sent to an RF transmitting coil of the magnetic resonance system; extracting target waveform information within a current sliding window from the RF waveform information, with a current time point being located within the current sliding window; obtaining, based on the target waveform information, target magnetic flux densities corresponding to the current sliding window; and determining a current real-time specific absorption rate (SAR) based on the target magnetic flux densities.

Abstract: Detector modules, detectors and medical imaging devices are provided. One of the detector modules includes: a support and a plurality of detector sub-modules arranged on the support along an extension direction in which the support extends. Each of the detector sub-modules has a first area and a second area in the extension direction. A detecting device is disposed in the first area, and a functional module is disposed in the second area. The functional module is electrically connected to the detecting device for receiving an electrical signal from the detecting device. The plurality of detector sub-modules includes a first detector sub-module and a second detector sub-module that are arranged adjacent to each other in the extension direction, and the first area of the first detector sub-module at least partially overlaps with the second area of the second detector sub-module.

Abstract: Detector modules, detectors and medical imaging devices are provided. One of the detector modules includes: a support and a plurality of detector sub-modules arranged on the support along an extension direction in which the support extends. Each of the detector sub-modules has a first area and a second area in the extension direction. A detecting device is disposed in the first area, and a functional module is disposed in the second area. The functional module is electrically connected to the detecting device for receiving an electrical signal from the detecting device. The plurality of detector sub-modules includes a first detector sub-module and a second detector sub-module that are arranged adjacent to each other in the extension direction, and the first area of the first detector sub-module at least partially overlaps with the second area of the second detector sub-module.

Abstract: Imaging methods, imaging apparatuses and image processing devices are provided. In one aspect, an imaging method includes: scanning a subject to obtain a photon-counting sequence output by a photon-counting detector of a photon-counting CT system; determining, by using a photon-counting model and the photon-counting sequence, a target material distribution parameter value of the subject, and performing imaging based on the target material distribution parameter value. The photon-counting model is created by at least one of a charge sharing model, an energy resolution model, or a pulse pileup model. The charge sharing model is configured to eliminate energy spectrum distortion and counting loss caused by charge sharing. The energy resolution model is configured to eliminate energy spectrum distortion and counting loss caused by energy resolution. The pulse pileup model is configured to eliminate energy spectrum distortion and counting loss caused by pulse pileup.

Abstract: Medical detectors and medical imaging devices are provided. In one aspect, a medical detector includes: a photoelectric conversion device, a first crystal array layer disposed over the photoelectric conversion device, and a second crystal array layer disposed over the first crystal layer. The first crystal array layer includes a plurality of first scintillation crystals arranged in a first crystal array, and a first coupling medium being filled between every adjacent two of the first scintillation crystals. The second crystal array layer includes a plurality of second scintillation crystals arranged in a second crystal array, and a second coupling medium being filled between every adjacent two of the second scintillation crystals. A light transmittance of the second coupling medium is different from a light transmittance of the first coupling medium.

Abstract: Methods, devices, apparatus and systems for magnetic resonance imaging with deep neural networks are provided. In one aspect, a method of magnetic resonance imaging method combines a deep neural network and an accelerated imaging manner. The method includes: scanning a subject with a first undersampling factor and a first sampling trajectory to obtain first imaging information, processing the first imaging information with the deep neural network to obtain second imaging information corresponding to a second undersampling factor that is smaller than the first undersampling factor, and reconstructing a magnetic resonance image of the subject from the second imaging information.

Abstract: Devices and methods of testing leaking rays are provided. In one aspect, a device includes a first rotary arm configured to rotate around a first rotary axis, a second rotary arm rotatably connected with the first rotary arm and configured to rotate around a second rotary axis, a probe mounted on a rotating end of the second rotary arm and configured to measure a numerical value of leaking rays at each position at which the probe stays, a mounting base rotatably connected with the second rotary arm and configured to mount a ray source component, a first driving unit configured to drive the first rotary arm to rotate around the first rotary axis, and a second driving unit configured to drive the second rotary arm to rotate around the second rotary axis, the first rotary axis being perpendicular to the second rotary axis.

Abstract: Methods, devices, systems, and apparatus for controlling pulse pileup are provided. In one aspect, a method of controlling pulse pileup includes: obtaining scan protocol parameters of a computed tomography (CT) device, the scan protocol parameters including an exposure voltage, an exposure duration for each revolution of a scanning of an object, and a number of views for each revolution, determining an angle of a radioactive source for an i-th view based on the number of views and an initial position of the radioactive source, obtaining an optimal exposure current for the i-th view under the exposure voltage by minimizing an output value of an objective function for the i-th view, and determining a current view based on the exposure duration for each revolution and a current exposure moment to perform the scanning on the object with the optimal exposure current for the current view.

Abstract: A crystal array, a detector, a medical detection device and a method for manufacturing a crystal array are provided. The crystal array includes a plurality of crystals arranged in an array, each of the crystals having a light incident surface, a light exit surface, and a connection surface connecting the light incident surface to the light exit surface, where the connection surface of at least one of two adjacent crystals includes a rough surface and a smooth surface connected to the rough surface, and the rough surface and the smooth surface are arranged along a length direction of the crystal.

Abstract: Methods, devices, systems and apparatus for training image enhancement models and enhancing images are provided. In one aspect, a method of training an image enhancement model includes: for each of one or more constraint features, processing a ground truth image with the constraint feature to obtain a feature image corresponding to the constraint feature, for each of the one or more feature images, using the ground truth image and the feature image to train a convolutional neural network (CNN) structure model corresponding to the feature image, determining a loss function of the image enhancement model based on the one or more CNN structure models corresponding to the one or more feature images, and establishing the image enhancement model based on the loss function. A to-be-enhanced image can be input into the established image enhancement model to obtain an enhanced image.

Abstract: A state space controller includes an integral part configured to integrate a control deviation, wherein the control deviation indicates a difference between a digital value of a gradient coil current and a reference current; a delay compensator configured to generate a digital control amount according to the integrated control deviation by the integral part, and generated a pulse-width modulation drive signal according to the digital control amount, and includes a subtractor of which a non-inverting input terminal is connected to an output terminal of the integral part, a delayer configured to delay the digital control amount by one calculation cycle, and a first feedback loop configured to delay the digital control amount by one calculation cycle and multiply a first compensation coefficient to obtain a first compensation amount, wherein the first compensation amount is input into a first inverting input terminal of the subtractor.

Abstract: Methods, devices, systems and apparatus for magnetic resonance imaging are provided. In an example, a method includes: obtaining M imaging data sets collected by a receiving coil array including N coil channels under M radio-frequency excitations, determining odd echo phase information and even echo phase information for each of the imaging data sets, mapping M odd echo data sets and M even echo data sets of the imaging data sets as a virtual imaging data set for a virtual coil array that includes N×M×2 virtual coil channels, and performing parallel magnetic resonance imaging based on the odd echo phase information and the even echo phase information of each of the imaging data sets, the virtual imaging data set and parallel reconstruction reference data.

Abstract: A magnetic resonance imaging (MRI) method is provided. The method includes: a first echo signal and a second echo signal generated from each of channels of a MRI device are acquired by performing a pre-scanning according to an imaging sequence; a correction displacement with which an imaging phase consistency is maximum is determined by shifting a signal curve of the second echo signal for each of the channels for a plurality of times; a one-order phase correction value and a zero-order phase correction value for the channels are determined under the imaging sequence according to the correction displacement; a formal scanning is performed according to the imaging sequence to obtain scanning data; and a phase correction is performed on the scanning data according to the one-order phase correction value and the zero-order phase correction value to obtain target scanning data for reconstructing an image.

Abstract: Methods, devices and systems for providing a high-precision and fast changing driving current for a gradient coil to generate a gradient magnetic field to acquire a high-quality image in an MRI device are provided. An example gradient amplifier includes a controller, a power amplifying circuit and a filtering circuit. The controller is configured to output pulse signals. The power amplifying circuit includes a first H bridge circuit and a second H bridge circuit and is configured to perform power conversion on an input power supply according to the pulse signals to output a driving current to a gradient coil. The filtering circuit is configured to filter the driving current output by the power amplifying circuit. A phase difference between the pulse signals output by the controller to drive switching tubes on a same position in the first H bridge circuit and the second H bridge circuit is a particular degree.

Abstract: Methods, devices and apparatus for reconstructing a magnetic resonance image are provided. In one aspect, a method includes: determining array coil images according to first data collected by array coils of an MRI device during a prescan, where each coil of the array coils corresponds to a respective one of channels; determining a quadrature body coil image according to at least one of second data collected by a quadrature body coil of the MRI device during the prescan and the first data collected by the array coils; obtaining a corrected quadrature body coil image by correcting an uniformity of the quadrature body coil image; determining coil sensitivity maps according to the array coil images and the corrected quadrature body coil image; and reconstructing a magnetic resonance image with third data collected by the array coils during a normal scan according to the coil sensitivity maps.

Abstract: Methods, apparatus and systems for detecting collision are provided. In one aspect, a method includes: obtaining a first model by performing modelling based on an exterior shape of a first component in the target system, the first component being a movable component, obtaining a second model by performing modelling based on an exterior shape of a second component in the target system, the second component being different from the first component, determining a spatial position of the first model and a spatial position of the second model according to a movement process of the first component at each of detection timings, and for each of the detection timings, determining whether the first component collides with the second component according to the spatial position of the first model, the spatial position of the second model, and a collision condition.

Abstract: Methods, systems, and computer-readable storage mediums for correcting time in a nuclear magnetic resonance device are provided. In one aspect, a method includes obtaining respective transmission time delays of three gradient pulse signals that are generated by a three-dimensional gradient subsystem of the nuclear magnetic resonance device and include a slice-selection gradient signal, a phase-encoding gradient signal, and a frequency-encoding gradient signal, determining a time correction value according to the obtained respective transmission time delays of the three gradient pulse signals, and correcting a respective output time of each of the three gradient pulse signals, an output time of a radio-frequency (RF) pulse signal generated by a RF transmitting subsystem of the nuclear magnetic resonance device, and a reception time of a magnetic resonance signal received by a RF receiving subsystem in a scanning cycle according to the determined time correction value.

Abstract: A crystal array, a detector, a medical detection device and a method for manufacturing a crystal array are provided. The crystal array includes a plurality of crystals arranged in an array, each of the crystals having a light incident surface, a light exit surface, and a connection surface connecting the light incident surface to the light exit surface, where the connection surface of at least one of two adjacent crystals includes a rough surface and a smooth surface connected to the rough surface, and the rough surface and the smooth surface are arranged along a length direction of the crystal.

Abstract: Methods and devices for reconstructing a magnetic resonance image, and a non-transitory machine readable storage medium are provided. In an example, the method includes: obtaining a previous image; for each of channels, collecting k-space data of the channel by a partial sampling technology, generating original k-space data of the channel by mapping the previous image into k-space of the channel, and obtaining residue k-space data of the channel by subtracting the original k-space data of the channel from the k-space data of the channel; reconstructing a residue image with the residue k-space data of each of the channels by taking sparsity of the residue image as a constraint term and a difference between virtual residue k-space data of the channel and the residue k-space data of the channel as a data fidelity term; and obtaining a reconstructed magnetic resonance image by adding the residue image to the previous image.

Abstract: A method and a device for reconstructing magnetic resonance images with different contrasts are provided. According to an example of the method, after collecting magnetic resonance signal data recorded in k-space of N contrasts by N number of magnetic scans, a first image for each of the contrasts may be obtained by performing image reconstruction according to the magnetic resonance signal data corresponding to the contrast; an association coefficient of each of the contrasts may be determined according to the first images for the N contrasts; and a second image shared with the N contrasts may be obtained by performing image reconstruction based on the magnetic resonance signal data of the N contrasts and the association coefficient of each of the N contrasts. In this way, a reconstructed image for each of the contrast may be obtained by combining the association coefficient of the contrast with the second image.