40 results about "Magnetic particle imaging" patented technology

The present application relates to the field of magnetic particle imaging, and particularly relates to a kind of fast calibration method and system of MPI system matrix based on multi-stage wavelet transform and double branch attention network, to solve the problem of time-consuming, complex of existing calibration-based system matrix acquisition method.The method of the present application comprises: obtaining a low-resolution system matrix according to a pre-set undersampling grid;The system matrix is encoded by row RGB to obtain an RGB image;The above-mentioned RGB image is input into the trained MWaveDAN network model to obtain a high-resolution RGB image;The high-resolution RGB image is decoded into complex form to obtain a complex-based system matrix.The present application effectively accelerates the high-resolution acquisition of system matrix in MPI, and provides important support for the future development of MPI technology.

A processor calculates a system function by a first deconvolution operation based on a set of a first detection signal obtained while a calibration sample is disposed in an examination region and a numerical model of a spatial distribution of magnetic particles included in the calibration sample. The processor obtains a spatial distribution of magnetic particles included in an examination sample by a second deconvolution operation based on a set of a second detection signal obtained while the examination sample is disposed in the examination region and the system function.

The invention relates to the technical field of magnetic particle imaging, in particular to a core-shell nanoprobe and a preparation method and application thereof.The core-shell nanoprobe comprises a magnetic core and a nanoshell which is located outside the magnetic core and has a magnetic shielding response function, and the structure of the nanoshell collapses under the tumor microenvironment condition; the saturation magnetization of the magnetic core is greater than or equal to 50 emu / g, and the coercive force is less than or equal to 5 Oe; the saturation magnetization of the nano shell is less than 50 emu / g, and the coercive force is more than 5 Oe. According to the core-shell nanoprobe, through a unique magnetic core-shell structure design and tumor microenvironment response characteristics, a magnetic shielding layer is formed by using a low-signal nano shell with a response magnetic shielding function, and background signal interference is inhibited. In a tumor microenvironment, the shell structure of the core-shell nanoprobe collapses, the magnetic core is exposed, and a high magnetic signal is released and generated, so that the imaging signal-to-noise ratio is remarkably improved. According to the invention, the bottleneck that the traditional MPI probe is lighted in the whole course can be broken through, the tumor specificity is lighted and positioned, and the problems that the external background of the tumor is high, the contrast ratio is poor, and tiny focuses are difficult to detect are solved.

The invention discloses a magnetic particle imaging method based on multi-harmonic energy-full width at half maximum combined weighting, which comprises the following steps: acquiring point spread functions of a plurality of harmonic waves with different frequencies of magnetic nanoparticles, and constructing a corresponding system matrix; measuring a reference sample which does not contain the magnetic nanoparticles, and obtaining a plurality of noise matrixes corresponding to harmonic waves with different frequencies; measuring the sample to be measured, and obtaining magnetization response voltage vectors of a plurality of harmonic waves with different frequencies; respectively calculating an energy two-norm of a system matrix, an energy two-norm of a noise matrix and a full width at half maximum of a point spread function of the system matrix and the noise matrix; splicing the magnetization response voltage signals of each harmonic system matrix to form a total system matrix and a total measurement signal vector; calculating a weight factor of each harmonic wave and forming a weight matrix; and constructing a solution equation of the particle concentration distribution of the sample to be detected, and carrying out iterative solution on the solution equation to obtain a particle concentration distribution image of the sample to be detected. According to the invention, efficient utilization of multi-harmonic information is realized.

A magnetic particle imaging device is provided with: a detection coil (3) for detecting a magnetic change in magnetic particles (1); a compensation coil (4) having a central axis (CA) common to the detection coil (3) and connected to the detection coil (3) with opposite polarity; a first winding tube (21) that holds the detection coil (3); and a second winding tube (22) that holds the compensation coil (4). The distance in the direction of the central axis (CA) of the detection coil (3) and the compensation coil (4) can be changed by increasing or decreasing the contact portion of the first winding tube (21) and the second winding tube (22).

A magnet (100, 300, 400) for a magnetic particle imaging device is provided with a pair of first DC coils (10), a pair of second DC coils (20), and a pair of AC coils (30). The pair of first DC coils are disposed facing each other in a first direction (DR1). The pair of second DC coils are disposed facing each other in a second direction (DR2) perpendicular to the first direction or in a third direction (DR3) perpendicular to the first direction and the second direction. The pair of AC coils is disposed facing each other in a first direction or a second direction. Each of the pair of second DC coils has a pair of first linear portions (22). Each of the pair of first linear portions extends in the same direction as the direction in which the pair of AC coils are disposed facing each other.

The application belongs to the field of magnetic particle imaging, and particularly relates to a rotating gradient magnetic particle imaging device and method based on cross-coil driving, aiming to solve the problems of difficulty in effective coding in the absence of a magnetic field region and low imaging sensitivity in magnetic particle imaging. The application comprises: superimposing the magnetic field generated by two pairs of mutually orthogonal cross-coil pairs and the uniform bias field through a magnetic field generation module to generate an imaging region magnetic field; changing the current direction of any one of the coil pairs in the cross-coil pair or changing the current type of the cross-coil pair to generate a rotating magnetic field under multiple rotating gradients through a gradient rotating module while the uniform bias field remains unchanged; obtaining scanning signals of each point in the imaging region under different magnetic fields through a scanning module; and generating the imaging result of the object to be measured based on the scanning signals under different magnetic fields through an imaging module. The application can realize high-sensitivity and reliable two-dimensional position coding MPI imaging without relying on the traditional magnetic field-free region.

The present application belongs to the technical field of magnetic particle imaging, and particularly relates to an open magnetic particle imaging method and system based on magnetic field rotation coding, aiming to solve the problems of limited imaging resolution, insufficient imaging depth, excessive power consumption and the inability of MPS to image in the prior art single-sided MPI imaging. The present application: uses a bar-shaped permanent magnet or a coil to create a stable and controllable static magnetic field environment, drives the static magnetic field to rotate by means of a mechanical mechanism, changes the distribution form of the spatial static magnetic field and completes the coding operation, increases the number of independent equations to be solved, and then generates a system matrix, constructs a matrix equation capable of accurately solving the magnetic particle concentration distribution, solves the matrix equation, and successfully reconstructs the magnetic particle image of the target object. The present application is applied to a single-sided MPI device, effectively increases the imaging depth, improves the resolution and reduces the power consumption; and is applied to an MPS device, has imaging capability and expands the application range.

The present application belongs to the field of magnetic particle imaging, and particularly relates to a magnetic particle imaging image reconstruction method, system and device based on a max-min concave and total variation constraint, aiming to solve the problem of large error, poor precision and low quality of the MPI image reconstructed by the existing magnetic particle imaging image reconstruction method. The method comprises: acquiring a time domain voltage signal as an input signal; performing Fourier transform on the input signal and constructing a system matrix; based on the system matrix, constructing a mapping equation between the concentration of magnetic particle imaging and the input signal after Fourier transform as a first equation; combining isotropic total variation and max-min concave constraint to reconstruct the first equation to obtain a second equation; and iteratively solving the second equation by an alternating direction multiplier method with a mixed penalty function to obtain the concentration of magnetic particle imaging and perform image reconstruction. The present application reduces the error of the reconstructed MPI image, and improves the precision and quality of the reconstructed MPI image.

The application belongs to the field of magnetic particle imaging, and particularly relates to a magnetic particle imaging method and device based on multi-source noise monitoring and collaborative compensation, aiming to solve the problem that magnetic particle signals are easily interfered by multi-source noise. The method comprises the following steps: during excitation or gradient field operation, a main receiving signal is collected, and multi-path noise monitoring signals are synchronously collected through at least two noise monitoring coils; the multi-path noise monitoring signals are input into a background noise prediction model to obtain predicted background noise, wherein the background noise prediction model is trained based on signals collected by the main receiving coil and the noise monitoring coil under the no-load state of a magnetic particle imaging device; the predicted background noise is eliminated from the main receiving signal to obtain a purified magnetic particle response signal; and a reconstructed image is generated based on the purified magnetic particle response signal. The application can obtain a high signal-to-noise ratio MPI response signal online, and improve the imaging speed and long-term stability without changing the existing scanning architecture.

The application provides a kind of multi-block magnetic particle imaging method and system, which can be applied to medical image processing technical field.The method comprises the following steps: collecting a plurality of magnetic particle system matrices corresponding to a plurality of sub-imaging regions in the region to be imaged respectively; using a trained boundary prediction model to perform extrapolation on the plurality of magnetic particle system matrices to obtain a plurality of matrix extrapolated magnetic particle system matrices, the trained boundary prediction model being trained using simulation-generated magnetic particle system matrix samples and a loss function based on spatial continuity constraints and edge sparsity constraints; using the plurality of matrix extrapolated magnetic particle system matrices to perform image reconstruction on the plurality of sub-imaging regions to obtain a plurality of field-of-view expanded magnetic particle image blocks; performing cropping on the plurality of field-of-view expanded magnetic particle image blocks to obtain a plurality of boundary artifact-eliminated magnetic particle image blocks; and splicing the plurality of boundary artifact-eliminated magnetic particle image blocks to obtain a magnetic particle imaging result of the region to be imaged.

The forward model constrained neural network magnetic particle imaging reconstruction method disclosed by the application obtains a system matrix through calibration, measures voltage data generated by a sample; Fourier transforms the collected data into a frequency domain, uses a signal-to-noise ratio threshold to screen frequency characteristics of the data; uses a Pytorch reconstruction network to realize mapping from one-dimensional voltage data to multi-dimensional magnetic particle concentration distribution; uses the system matrix as a forward model of magnetic particle imaging, generates voltage simulation data from the reconstructed magnetic particle concentration distribution, calculates a difference between the voltage simulation data and input voltage data as a loss function to update network parameters; adds a regularization term in the loss function, and adjusts training parameters and regularization parameters to obtain optimal reconstruction effect. The application uses a forward model constrained neural network to perform magnetic particle imaging reconstruction, and further improves the reconstruction effect by adding a total variation regularization term in the loss function of the network.

A magnetic particle imaging device comprises a detection coil (3) for detecting changes in the magnetism of magnetic particles (1), a compensating coil (4) which has a common central axis (CA) with the detection coil (3) and is connected to the detection coil (3) with opposite polarity, a first winding frame (21) for holding the detection coil (3), and a second winding frame (22) for holding the compensating coil (4). The distance between the detection coil (3) and the compensating coil (4) in one direction of the central axis (CA) is made variable by increasing or decreasing a contact section of the first winding frame (21) and the second winding frame (22).

A pair of first measurement coils is disposed so as to sandwich magnetic particles. A pair of second measurement coils is disposed so as to sandwich magnetic particles and the pair of first measurement coils. A pair of alternate-current magnetic field application coils is disposed so as to sandwich magnetic particles, the pair of first measurement coils, and the pair of second measurement coils. A measurement device outputs a signal representing a difference between a signal measured by the pair of first measurement coils and a signal measured by the pair of second measurement coils.

The application relates to the technical field of magnetic particle imaging, and more particularly to an iron oxide nanoparticle and application of the iron oxide nanoparticle in magnetic particle imaging. The nanoparticle is an octahedral superparamagnetic ferroferric oxide nanoparticle, the nanoparticle is synthesized by adding a surfactant and controlling a reaction rate through a high-temperature thermal decomposition method, the surfactant includes oleic acid and oleylamine, the octahedral superparamagnetic ferroferric oxide nanoparticle is coated with an amphiphilic polymer, the amphiphilic polymer includes polymaleic anhydride-1-octadecenoic acid and polystyrene maleic anhydride copolymer, and the outer layer of the amphiphilic polymer includes biological membranes such as macrophage membranes, red blood cell membranes, neutrophil membranes and tumor cell membranes according to biological application requirements. The surface of the octahedral magnetic particle is a crystal face, the crystal face has low spin disorder and low anisotropy, so that the octahedral magnetic particle has the advantages of low coercivity and high initial magnetic susceptibility, and thus becomes a high-sensitivity magnetic particle imaging tracer.

The present application belongs to the technical field of magnetic particle imaging, and particularly relates to a phase offset calibration method for the instantaneous position of a magnetic field-free point in magnetic particle imaging, aiming to solve the problem that the existing phase offset calibration method for the instantaneous position of a magnetic field-free point requires separate measurement or calculation for each device in the MPI device, resulting in a large workload, a long calibration process time and troublesome adjustment. The method comprises: collecting magnetic particle response signals and current intensity signals as input signals; based on the input signals, cyclically automatically modulating the phase of the instantaneous position of the magnetic field-free point in the imaging process of the MPI device; after the automatic phase modulation is completed, solving the optimal solution of the phase offset; and based on the optimal solution of the phase offset, again automatically modulating the phase of the instantaneous position of the magnetic field-free point in the MPI device to obtain the final instantaneous position and instantaneous speed after phase offset calibration. The present application does not require setting of hardware, greatly reduces the difficulty of phase modulation and facilitates personnel operation.

A magnetic particle imaging (MPI) measurement method includes generating a multi-dimensional image-domain system matrix A using an MPI-sequence with a field free line, using a multi-dimensional sinogram-based system matrixASinogram(t,r,z)∈ℝ[T,Nr,Nz],comprising the following steps:for each time point tc, c∈[1, T]:get a time slice matrix Ac=ASinogram(t=tc, r, z)∈[N<sub2>r< / sub2>,N<sub2>z< / sub2>],replicate the time slice matrix Ac Nr−1 times and copying these replications along a newly added 2nd offset-dimension, resulting in a time volume matrixAc′∈ℝ[Nr,Nr,Nz],rotate the time volume matrixAc′ by the FFL θc=θ(t=tc) at time point t=tc in its 1st and 2nd offset-dimensions, resulting in a rotated matrixAcθ cconcatenate the rotated matricesAcθ c of all time points along a time-dimension and vectorize the spatial dimensions (x, y, z), resulting in a constructed system matrix cSM∈[T,(N<sub2>r< / sub2>×N<sub2>r< / sub2>×N<sub2>z< / sub2>)], andperform a Fourier transformation on the constructed system matrix cSM on its time-dimension resulting in the multi-dimensional image-domain system matrix A.

Electromagnetic device (1) for magnetic particle imaging, comprising the following: - a return yoke (2) with a gap extending in the Y direction and forming a magnetic field space, where the width direction of the magnetic field space is defined as the X direction and the length direction of the magnetic field space is defined as the Y direction; - a gradient magnetic field generation unit (3) formed on the feedback yoke (2) and configured to generate - in the magnetic field space - a gradient magnetic field (HX1) in the X direction and to form - in the magnetic field space - a zero-field region (S1) extending in the Y direction; - an alternating magnetic field generation unit (4) formed on the feedback yoke (2) and configured to generate an alternating magnetic field (HX2) in the magnetic field space; and - a rotation mechanism configured to rotate - when the direction perpendicular to the X-direction and the Y-direction is defined as the Z-direction - the gradient magnetic field (HX1) and the alternating magnetic field (HX2) relative to the subject (6), wherein the Z-direction is the rotation axis (CZ), and wherein the feedback yoke (2) has the following: - an alternating magnetic field yoke (22) configured to correspond to the alternating magnetic field (HX2) and extending in the Y direction; and - a pair of gradient magnetic field yokes (21, 23, 24, 25, 26) which are designed to correspond to the gradient magnetic field (HX1) and which are arranged on the inside of the alternating magnetic field yoke (22) and run in the Y direction so that they are opposite each other.

The invention belongs to the technical field of medical imaging, and relates to a magnetic particle imaging method based on high-low double-frequency magnetic field modulation and multi-group harmonic fusion, which comprises the following steps: determining a magnetic particle imaging area, and dividing the magnetic particle imaging area into a first area and a second area according to the direction of a low-frequency sine scanning magnetic field; placing a magnetic nanoparticle sample of a unit volume in the first area, externally adding a high-low double-frequency magnetic field, extracting harmonic signals of each order in the first area, constructing a system matrix, and calculating a harmonic energy distribution weight matrix corresponding to the system matrix; placing the to-be-measured object in the second area, externally adding a high-low double-frequency magnetic field, extracting harmonic signals of each order in the second area, and obtaining a harmonic signal matrix of the to-be-measured object; and constructing an equation to be solved and carrying out inversion solution to obtain an image of magnetic nanoparticle concentration distribution. The implementation process is convenient and simple, and the application of magnetic particle imaging in biomedicine is expected to be further improved.

This invention relates to a miniature detection system based on magnetic particle imaging, belonging to the field of medical inflammatory imaging technology. This invention is a miniature and simple device for magnetic particle imaging for fingertip detection. It uses a microcontroller as the control terminal, a receiving coil that is closer to the imaging aperture, and low-diameter driving and receiving coils. By improving the signal-to-noise ratio and reducing background interference signals, it effectively improves experimental efficiency and the sensitivity of the detection system, and greatly enhances portability.

The invention belongs to the technical field of magnetic particle imaging, particularly relates to an open type magnetic particle imaging method and system based on magnetic field rotation coding, and aims to solve the problems that existing unilateral MPI imaging resolution is limited, imaging depth is insufficient, power consumption is too high, and MPS cannot perform imaging. According to the method, a stable and controllable static magnetic field environment is created by using a strip-shaped permanent magnet or a coil, the static magnetic field is driven to rotate by means of a mechanical mechanism, the distribution pattern of the space static magnetic field is changed, coding operation is completed, the number of solved independent equations is increased, and then a system matrix is generated; a matrix equation capable of accurately solving magnetic particle concentration distribution is constructed, and a magnetic particle image of a target object is successfully reconstructed by solving the matrix equation. The method is applied to unilateral MPI equipment, the imaging depth is effectively increased, the resolution is improved, and the power consumption is reduced; the method is applied to MPS equipment, has imaging capability, and expands the application range.

The present specification relates to the field of MPI imaging technology, and discloses an open three-dimensional magnetic particle imaging device and method based on a magnetic field free line. The device comprises: a signal detection module configured to provide an open scanning environment by installing a magnetic field free line generating unit composed of two circular permanent magnets arranged in a cross direction of the magnetic poles and a signal receiving unit in two coaxial cylindrical scanning devices symmetrically arranged above and below, emit an initial scanning signal and receive a magnetic particle response signal; an electric control module for controlling the position, intensity and motion trail of the initial scanning signal emitted by the signal detection module; an external signal compensation module for measuring a direct feedthrough signal; and a signal processing and image reconstruction module for processing the magnetic particle response signal and the direct feedthrough signal to obtain a reconstructed image. The present application does not need to consider a high-power power supply module, eliminates the filtering operation on the input current, does not need to consider the heating problem possibly caused by long-time power-on, and simplifies the system.

The application belongs to the field of image reconstruction and multi-modal generative artificial intelligence model of magnetic particle imaging, and particularly relates to a magnetic particle image reconstruction method and system based on a multi-modal diffusion model, aiming to solve the problem that no method can combine a generative model with multi-modal imaging technology to realize accurate quantitative reconstruction of MPI. The application comprises: modeling and discretizing a first excitation signal to obtain a discrete signal, fitting each discrete signal respectively and then superimposing to obtain a first response signal, calculating a loss function, and training a model based on the loss function; using the trained particle response model to process a second time sequence signal to obtain a second response signal; calculating based on the second response signal and a system matrix, gradually adding noise, and constraining to obtain a noise-constrained image; and gradually denoising and restoring the noise-constrained image of the last step to obtain a final reconstructed image. The application makes it possible to realize fast and high-quality MPI image reconstruction.

The invention relates to the field of magnetic particle imaging, in particular to an MPI system matrix rapid calibration method and system based on multistage wavelet transform and a double-branch attention network, and aims to solve the problem that an existing calibration-based system matrix acquisition method is time-consuming and complicated. The method comprises the following steps: acquiring a low-resolution system matrix according to a preset under-sampling grid; carrying out RGB coding on the system matrix according to rows to obtain an RGB image; the RGB image is input into a trained MWaveDAN network model, and a high-resolution RGB image is obtained; a high-resolution RGB image is decoded into a complex number form, and a complex number-based system matrix is obtained. According to the method, high-resolution acquisition of the system matrix in the MPI is effectively accelerated, and important support is provided for future development of the MPI technology.

The invention belongs to the field of magnetic particle imaging, particularly relates to a magnetic particle imaging method and device based on multi-source noise monitoring and cooperative compensation, and aims to solve the problem that magnetic particle signals are easily interfered by multi-source noise. The method comprises the following steps: during the excitation or gradient field working period, acquiring a main receiving signal, and synchronously acquiring multiple paths of noise monitoring signals through at least two noise monitoring coils; the multiple noise monitoring signals are input into a background noise prediction model, predicted background noise is obtained, and the background noise prediction model completes training based on signals collected by a main receiving coil and a noise monitoring coil in the no-load state of the magnetic particle imaging device; the predicted background noise is eliminated from the main receiving signal, and a purified magnetic particle response signal is obtained; and generating a reconstructed image based on the purified magnetic particle response signal. According to the invention, the MPI response signal with a high signal-to-noise ratio can be obtained online, and the imaging speed and long-term stability are improved on the premise of not changing the existing scanning architecture.

The application belongs to the field of magnetic particle imaging, and particularly relates to an MPI acceleration calibration method based on a system matrix super-resolution network, aiming to solve the problems of long calibration time and poor accuracy of reconstructed MPI images of the existing magnetic particle imaging system matrix reconstruction method. The method comprises the following steps: placing a unit MNP sample in the imaging field of view of a magnetic particle imaging device for sparse calibration scanning, and constructing a system matrix as a low-resolution system matrix; inputting the low-resolution system matrix into a system matrix super-resolution network model after pretreatment, to obtain a super-resolved system matrix row set; performing post-processing on the super-resolved system matrix row set to obtain a high-resolution system matrix; and combining the high-resolution system matrix to solve the magnetic particle concentration distribution of a target object to be imaged, and reconstruct an MPI image of the target object to be imaged. The application can greatly reduce the calibration time while accurately reconstructing the MPI image.

The application discloses an imaging method based on magnetization curve fitting of magnetic particle relaxation time, comprising: generating a magnetic field free point (FFP); moving the FFP in a space range where a single magnetic nanoparticle-injected target object is located, generating a pulsed square wave excitation magnetic field at each FFP position, and receiving original signals generated by magnetic nanoparticles in the target object under excitation of the pulsed square wave excitation magnetic field; fitting a target magnetization curve by adjusting relaxation time related parameters in a preset double exponential decay function based on the original signals; taking an adjustment result of the corresponding relaxation time related parameters as a magnetic particle relaxation time detection result of the FFP position; and performing imaging based on at least one same item in the magnetic particle relaxation time detection results obtained based on all FFP positions to obtain a relaxation time imaging graph. The application can separately detect the relaxation time, and combines the FFP scanning to perform multi-color magnetic particle imaging to distinguish plaque, duct and blood vessel regions.

The invention discloses a preparation method of an iron-based magnetic nanocluster with high MPI imaging performance, which comprises the following steps: (1) adding a transition metal salt, an iron salt and a small molecule ligand into a mixed solvent of ethylene glycol / diethylene glycol, and continuously stirring and reacting in an inert gas atmosphere; (2) in the reaction process, adding alkali salt, and continuously reacting at the original reaction temperature; and (3) after the reaction, transferring the reaction liquid into a hydrothermal kettle, reacting at high temperature, cooling to room temperature, standing, washing and drying to obtain the iron-based magnetic nanocluster. According to the method, the iron-based magnetic nanocluster with the particle size of 20-40 nanometers can be prepared, and meanwhile, the water dispersibility, the crystallinity and the magnetic performance of the prepared iron-based magnetic nanocluster can be remarkably improved, so that the iron-based magnetic nanocluster has excellent magnetic particle imaging (MPI) performance.

The invention discloses a preparation method of zinc ferromagnetic nanoparticles for magnetic particle imaging, which comprises the following steps: 1) heating and reacting raw materials containing an organic zinc compound, an organic iron compound, a surfactant and an organic solvent at 280-290 DEG C for 0.4-1 hour to obtain a reaction product; (2) precipitating, centrifugally separating and drying the reaction product to obtain zinc ferromagnetic nanoparticles; 3, the zinc ferromagnetic nano particles react with a hydrophilic modifier, and the zinc ferromagnetic nano particles used for magnetic particle imagines.The octahedral zinc-iron nano magnetic particles are prepared through a high-temperature pyrolysis method, and the MPI performance of the magnetic nano particles is improved by introducing the zinc element into the iron oxide nano particles.

The present application belongs to the field of magnetic particle imaging, and particularly relates to a magnetic particle imaging image denoising method, system and device based on feature fusion, aiming to solve the problem that the existing MPI denoising method is difficult to balance noise removal and image detail preservation. The method comprises: collecting an MPI image to be denoised as an input image; performing denoising processing on the input image based on a pre-trained feature fusion denoising network model to obtain a denoised MPI image; the feature fusion denoising network model comprises a feature extraction module, a feature fusion module and a feature regression module; the feature extraction module comprises a noise feature extractor and a content feature extractor; the feature fusion module comprises two channel attention sub-modules, two convolution layers and a spatial attention sub-module; and the feature regression module is constructed based on the convolution layers. The present application can achieve good denoising effect while preserving the structural details of the MPI image.