7034 results about "Nuclear physics" patented technology

MRI interference with a co-existing ultrasound system may be reduced or avoided by carrying out RF-sensitive operations of the treatment system only when gradient field activity of the MRI system is suppressed.

The invention relates to the field of nuclear fusion, and discloses a fixing device for a nuclear fusion preassembled assembly, and the fixing device comprises a magnet connecting assembly which comprises a first beam body and a magnet connecting part, the first beam body extends in a first direction, and the magnet connecting part is arranged on the first beam body; the vacuum chamber connecting assembly and the magnet connecting assembly are spaced in the second direction, the vacuum chamber connecting assembly comprises a second beam body and a vacuum chamber connecting part, the second beam body extends in the first direction, and the vacuum chamber connecting part is arranged on the second beam body; the beam body connecting assembly is arranged at the two ends of the second beam body in the first direction, is connected with the first beam body and comprises a first connecting piece, a second connecting piece and an elastic energy storage piece, the first connecting piece is movably connected with the second connecting piece and is detachably connected with the first beam body, and the second connecting piece is detachably connected with the second beam body; one end of the elastic energy storage piece is movably connected with the first connecting piece, and the other end is movably connected with the second connecting piece. The gap between the magnet and the vacuum chamber can be restrained, and the position precision between the magnet and the vacuum chamber is guaranteed.

A magnetic resonance image reconstruction device according to an embodiment is a magnetic resonance image reconstruction device that reconstructs magnetic resonance image data in which an artifact due to undersampling is removed or reduced based on undersampled k-space data, and includes a reconstruction unit reconstructing the magnetic resonance image data using a reconstruction network having a correction module. The correction module includes a regularization block generating second image data by performing a regularization process on first image data using a first neural network, and a data consistency block generating third image data by performing a data consistency process so that k-space data corresponding to the second image data approaches the undersampled k-space data. The correction module further includes at least one of a data consistency adjustment block adjusting the data consistency process and a regularization adjustment block adjusting the regularization process.

According to the displacement modulation and optical assistance-based SERF atom magnetometer magnetic imaging method, an SERF atom magnetometer integrated with a magnetic flux guider is used as a magnetic sensor, and low-frequency magnetic field modulation is introduced to the magnetic sensor by controlling a to-be-tested sample to perform periodic infinitesimal displacement in the sensitive direction of the magnetic sensor; the modulation signal is demodulated by combining a phase-locked amplification technology, and a magnetic response signal subjected to phase-locked demodulation at each spatial position is extracted; constructing a magnetic response matrix through two-dimensional track scanning of micron-order step pitch; an image acquisition module and a reflection optical assembly are introduced for spatial registration so as to monitor the relative position in real time, and the visibility and controllability of the magnetic imaging process are guaranteed; the point-by-point detection of fT-level weak magnetic signals can be realized on the premise that an array structure is not needed; the low-frequency noise interference can be effectively inhibited, the stability and definition of direct-current and low-frequency magnetic field imaging are improved, and the method is suitable for high-resolution space imaging application of weak magnetic sources such as magnetic domain structures, nervous tissue slices and ancient rock samples.

The invention provides a magnetic particle imaging resolution improving method and system based on frequency domain information filtering, and relates to the technical field of magnetic particle imaging. Comprising the following steps: inputting original magnetic particle imaging data into a Transform model, and selectively filtering frequency domain information in the magnetic particle imaging data through a fusion frequency domain discrimination feedforward network module in an encoder to obtain the output of the encoder; inputting the output of the encoder into a bottleneck layer, aggregating global and local information through a multi-scale attention mechanism module, and then selectively filtering frequency domain information in the magnetic particle imaging data again to obtain the output of the bottleneck layer; inputting the output of the bottleneck layer into a decoder with the same structure as the bottleneck layer to obtain deep features; inputting the deep features into a convolutional layer to obtain a residual image; and calculating the sum of the original magnetic particle imaging data and the residual image to obtain a reconstructed image. According to the invention, the overall imaging resolution of the MPI image under the low-gradient field acquisition condition is improved.

The invention relates to a multi-contrast magnetic resonance image super-resolution reconstruction method and system. The method comprises the following steps: collecting an image data set, preprocessing the image data set, and dividing the image data set into a training set and a test data set; combining a Hilbert curve, a state space model and a frequency domain enhancement mechanism to construct a multi-contrast magnetic resonance super-resolution reconstruction model based on Hilbert double-domain fusion Mamba; and training a multi-contrast magnetic resonance super-resolution reconstruction model based on Hilbert double-domain fusion Mamba by using the training data set, and then completing the test of the test data set to obtain a super-resolution reconstruction image of the target contrast magnetic resonance image. Frequency domain features are scanned through a Hilbert curve, a cross-modal global frequency dependency relationship is captured, and high-frequency texture details are effectively recovered. And multi-modal local texture information is dynamically fused through a channel attention mechanism, so that neglect of local details by linear scanning is avoided, and the texture reconstruction precision is improved.

The invention relates to the technical field of image processing, in particular to a clinical focus auxiliary segmentation system based on a nuclear magnetic resonance image. The system comprises an MRI image processing module, a lesion auxiliary segmentation module, a probability segmentation correction module and a lesion boundary smoothing module, a corresponding clinical nuclear magnetic resonance image set of a patient can be obtained, image position alignment and gray level adjustment processing can be carried out, and meanwhile a corresponding clinical image lesion segmentation model is constructed to carry out multi-scale fusion auxiliary segmentation. Generating a clinical focus region segmentation fusion image; obtaining a focus confidence probability corresponding to each pixel point in the segmentation image through the clinical focus region segmentation fusion image, and carrying out probability segmentation boundary correction on the clinical focus region segmentation fusion image to obtain a clinical focus region segmentation correction result image; and performing focus edge shape smoothing processing on the clinical focus region segmentation correction result map to generate a clinical focus edge shape segmentation optimization result. According to the invention, high-precision segmentation of the focus in the MRI image can be realized.

The invention discloses a nuclear magnetic T2 spectrum correction method for a shale reservoir, and relates to the field of object detection, and the nuclear magnetic T2 spectrum correction method for the shale reservoir comprises the following steps: 1, determining the gas logging porosity, saturated water porosity and main mineral components of the shale reservoir; compared with the prior art, the method disclosed by the invention has the beneficial effects that a drying-saturated water-centrifugal two-dimensional nuclear magnetic resonance experiment is carried out, and signals of crystal water, clay bound water and hydroxyl in a sample are preliminarily identified; through inversion of organic matter signals in the dry sample, signals of movable water are further determined; the relation between the difference value among the gas logging porosity, the saturated water porosity and the nuclear magnetic porosity and different mineral contents is discussed, and particularly the remarkable influence of iron-containing minerals on the porosity difference value is discussed; by eliminating the influence of diffusion relaxation caused by the magnetic susceptibility difference, the T2 spectrum correction method based on the mineral magnetic susceptibility is established, and the T2 spectrum accuracy obtained through nuclear magnetic resonance measurement is improved.

The invention relates to a double-color magnetic nanoparticle imaging method based on a single-harmonic system matrix, which comprises the following steps: respectively moving two different types of magnetic nanoparticle samples to a central zero magnetic field point, applying a scanning magnetic field to enable the zero magnetic field point to scan the whole imaging field of view, applying an excitation magnetic field to magnetize magnetic nanoparticles, and applying an excitation magnetic field to magnetize the magnetic nanoparticles; acquiring magnetization frequency spectrum signals of the two magnetic nanoparticle samples; the method comprises the following steps: constructing single harmonic system matrixes A1 and A2 based on single harmonic of magnetization spectrum signals of two kinds of magnetic nanoparticle samples; measuring a to-be-measured object formed by the two kinds of magnetic nanoparticles to obtain a measurement magnetization signal U; transversely splicing the single harmonic system matrixes A1 and A2 of the two different types of magnetic nanoparticles to obtain a new single harmonic system matrix A; the concentration distributions c1 and c2 of two different types of magnetic nanoparticles are obtained by combining a new single-harmonic system matrix A with a measurement magnetization signal U, and the concentration distributions of the two different types of magnetic nanoparticles are respectively sent into different color channels to be displayed in different colors. The method has important significance in promoting the application of the magnetic nanoparticle imaging technology in clinical medicine.

The invention discloses an SERF atom magnetometer double-axis magnetic field detection method and device based on pulsed magnetic field modulation, relates to the technical field of magnetic field precision measurement, and compresses the action time of a modulation magnetic field additionally applied in the same unit period on a hot atom ensemble by replacing conventional continuous sinusoidal magnetic field modulation with pulsed magnetic field modulation. The pulse magnetic field with the duty ratio of d can reduce the spin exchange relaxation rate to 2d times of that of a conventional method under the same modulation amplitude and frequency, due to the fact that the spin exchange relaxation rate is effectively restrained, the collected polarizability response signal is obviously improved, and the polarizability response signal can be obtained through the pulse magnetic field with the duty ratio of d and the pulse magnetic field with the duty ratio of d. Low-relaxation-rate sensitivity-enhanced double-axis magnetic field measurement under a pulse modulation scheme is realized, the double-axis measurement sensitivity of a miniaturized SERF atom magnetometer is further improved, and the method has great significance in supporting leap-type development of a future array type extremely-weak magnetic imaging system and medical application thereof.

The invention discloses a BNCT dose calculation method, which comprises the following steps: S1, constructing a voxel model, initializing one or more particles in a simulation system, and respectively acquiring the initial position, energy and movement direction of each particle; s2, adaptively selecting a Monte Carlo particle tracking algorithm and a flux counting mode based on the region where the particles are located and the energy of the particles; s3, repeating the step S2 until the particles leave the simulation system or are killed when meeting a truncation condition; and S4, cumulatively calculating dose distribution. Through the BNCT dose calculation method, the Monte Carlo particle transport simulation time is greatly shortened, the BNCT dose calculation efficiency is optimized, and the method is suitable for rapid and high-precision radiation dose simulation under a BNCT complex tissue structure.

The invention relates to the technical field of Tokamak nuclear fusion, and discloses an assembling method of a pre-assembled assembly of a nuclear fusion device and an installing method of the nuclear fusion device. The pre-assembled assembly comprises a vacuum chamber, a window neck tube in the vacuum chamber, a vacuum chamber cold shield and a TF magnet; the assembling method of the nuclear fusion device preassembled assembly comprises the following steps: supporting between a cold shield inner sector and a vacuum chamber through a first tool; a first tool is supported between the cold shield outer sector and the vacuum chamber; the TF magnet is connected with the middle window position of the vacuum chamber through a second tool, the upper arc-shaped section of the outer fan section of the cold shield is connected with the hoisting tool of the TF magnet through a third tool, and the lower window section of the outer fan section of the cold shield is connected with the second tool; and the middle window section and the annular field magnet supporting seat are connected through a fourth tool. According to the assembling method of the nuclear fusion device pre-assembled assembly, interference among installation of the vacuum chamber, the window neck tube in the vacuum chamber, the vacuum chamber cold shield and the TF magnet can be avoided, and the stability and functionality of the pre-assembled assembly structure are guaranteed.

The invention provides a space measurement and analysis method and system for a neutron diffraction rocking curve of a single crystal material, and the method comprises the steps: S1, building a laboratory coordinate system and a sample coordinate system, and setting a test point grid; s2, collecting a two-dimensional diffraction image of each test point to obtain angle information of the test point; s3, integrating the angle information of the test points based on the test point grid, and preprocessing the two-dimensional diffraction image; s4, extracting key structure parameters of each test point based on the preprocessed two-dimensional diffraction image; s5, constructing a stress field according to the key structure parameters; and S6, constructing a distribution map of crystal internal lattice parameters in a three-dimensional space according to the stress field. The method provided by the invention effectively improves the capability of identifying the non-uniformity and local distortion of the crystal structure, can be widely applied to the fields of residual stress evaluation, defect evolution monitoring, material quality control and the like, and has a remarkable engineering application value.

Disclosed herein is a medical system (100, 400) comprising: a magnetic resonance imaging system (102) configured for providing a respiratory signal. The respiratory signal is descriptive of a respiratory position as well as of inhalation and exhalation of the subject. The execution of machine executable instructions (140) causes the computational system to repeatedly: perform (200) the individual acquisition of k-space data using the magnetic resonance imaging system; receive (202) the respiratory signal; bin (204) the individually acquired k-space data into one of a predetermined number of k-space bins (148) using the respiratory signal and perform outlier rejection. Execution of the machine executable instructions further causes the computational system to reconstruct (208) a magnetic resonance image for each of the predetermined number of k-space bins to provide a respiratory-state resolved magnetic resonance image (150).

A positron emission tomography (PET) scanner includes a plurality of gamma radiation detector modules arranged to form a detector ring. Each detector module includes an array of scintillator detectors. Each scintillator detector comprises a monolithic scintillation crystal and a plurality of photodetector arrays, such as silicon photomultipliers (SiPMs). A photodetector array is positioned on at least two nonparallel faces of each scintillation crystal. In some examples, a photodetector array is positioned on each of three orthogonal faces of each scintillation crystal.

The invention provides a simulation image generation method for simulating a scanning electron microscope and related equipment, and the method comprises the steps: constructing a first imaging feature mapping table and a second imaging feature mapping table based on the scanning electron microscope image data of a real wafer; respectively making a standard imaging script and a defect imaging script based on the two imaging feature mapping tables; obtaining a wafer three-dimensional model and analyzing associated process attribute information in each structural unit; determining a corresponding standard imaging script based on the process attribute information, and performing surface characteristic adjustment on the structural unit to generate a defect-free simulation model; determining a corresponding defect imaging script according to a preset defect introduction condition, and adding a defect on a specified structural unit to generate a simulation model with a defect; and finally, generating a simulation image for simulating the scanning electron microscope. High-simulation scanning electron microscope images are manufactured in batches through a virtual simulation means, and the diversity and coverage of a simulation image data set are improved.

The invention discloses a pulsed neutron generator control system based on LabVIEW, and the system comprises a neutron generator industrial personal computer which operates a virtual human-computer interaction interface developed based on LabVIEW; the console core board carries a DSP main control chip and is embedded into a real-time operating system; the driving sampling board is connected with the console core board and is integrated with a signal conditioning circuit; the neutron generator industrial personal computer communicates with the console core board through a Modbus protocol, and controls and drives the sampling board to output control signals of the three independent power supply ion sources, the storage and the acceleration pole to the neutron tube; wherein the console core board generates three paths of PWM signals with the PWM frequency of 2.5 kHz and the step length of 8191, and the three paths of PWM signals are converted into analog control signals through the driving sampling board. According to the control system, the PWM control precision is greatly improved, the voltage control precision is improved to 0.012% (100% higher than that of a conventional scheme) through the combination of the 8191 step length (13-bit resolution) and the 2.5 kHz frequency, and the neutron yield fluctuation is controlled within + / -1.5%.

The invention belongs to the technical field of shale oil development and research, and discloses a shale oil mobility evaluation method based on a two-dimensional nuclear magnetic resonance experiment, which comprises the following steps: dividing an oil-containing shale sample harvested by a closed coring well into three parts which are respectively marked as a sample 1, a sample 2 and a sample 3; carrying out a TOC determination experiment on the sample 1 to obtain the TOC content of the sample; carrying out a step-by-step pyrolysis experiment on the sample 2 to obtain the contents of the sample S1-1 and the sample S2-2; calculating to obtain a shale oil mobility evaluation factor which is marked as FMO; carrying out a two-dimensional nuclear magnetic resonance experiment on the sample 3 before and after centrifugation to obtain the movable oil content of the sample before and after centrifugation, calculating to obtain the percentage of two-nuclear magnetic resonance movable oil, and recording the percentage as MO2D-NMR; and shale oil mobility evaluation is realized through analysis of the relationship between MO2D-NMR and FMO. According to the method provided by the invention, nondestructive testing of the sample can be realized in the two-dimensional nuclear magnetic resonance experiment process, the loss of light hydrocarbon can be reduced to the greatest extent, and the mobility evaluation precision of shale oil is effectively improved.

The invention discloses a magnetic source positioning method based on a spin-exchange relaxation-free atom magnetometer, and aims to provide a high-precision brand-new solution for magnetic source positioning in a near-zero magnetic environment by performing physical modeling and least square estimation on space magnetic field distribution of a target magnetic source. The magnetometer is enabled to be simultaneously sensitive to a three-axis magnetic field, a light absorption detection method is utilized to ensure that complete three-axis magnetic field information is obtained, and the sensitivity of the three axes reaches fT / Hz1 / 2 (1fT = 10 <-15 > T) magnitude. In the positioning process, the target magnetic source is abstracted into a physical model of the magnetic dipole, and the space magnetic field information generated by the target magnetic source is obtained through the atom magnetometer, so that the long-term stability of the magnetic source positioning process and the high precision of the positioning result can be ensured in the zero magnetic environment; therefore, a high-precision magnetic positioning technical means with great potential is provided for various application scenes such as paleomagnetic sample testing and magnetic source positioning in medical research, and technical progress and application expansion in related fields are expected to be promoted.

The invention discloses an ion source automatic beam adjusting method, a radiotherapy system and related equipment, and relates to the technical field of radiotherapy, and the method comprises the steps: monitoring and adjusting a plurality of control parameters in real time, and obtaining an optimal control parameter combination; under the optimal control parameter combination, the variable quantity of each control parameter before and after adjustment and the performance change of the proton beam are obtained; performing a pulse width charge test according to the variation of each parameter before and after adjustment and the performance change of the proton beam; obtaining an optimal adjustment parameter and an adjustment amount through a pulse width charge test result; and through the optimal adjustment parameter and adjustment amount, automatic beam adjustment is realized, stable and efficient acceleration of the proton beam in the synchrocyclotron system is realized, and the stability and consistency of the proton beam are ensured.

The invention provides a microwave ablation control system and method used based on nuclear magnetic resonance, and belongs to the technical field of ablation control, and the system comprises an MRI rapid temperature measurement module, a temperature prediction module, a microwave ablation power control module, a tissue impedance monitoring module and a data fusion processing module. The microwave ablation instrument, the MRI rapid temperature measurement module and the tissue impedance monitoring module are all connected with the data fusion processing module, the microwave ablation instrument is further connected with a microwave ablation needle inserted in ablation area tissue, and the temperature prediction module and the microwave ablation power control module operate on the data fusion processing module; in combination with the method, the defects that in an existing microwave ablation control method used based on nuclear magnetic resonance, due to the fact that the MRI temperature measurement sequence collection and reconstruction speed is limited, the closed loop control period is too long, the nonlinear change of the heating rate caused by tissue impedance mutation cannot be coped with, and then the overtemperature or undertemperature problem occurs are overcome.

A Rydberg atom television receiver is disclosed. The receiver comprises a probe laser, a source polarizing beam displacer, a Rydberg atom receiver cell, receiver atoms, a detector polarizing beam displacer, a detector polarizing beam cube, a first photodiode, a second photodiode, a differential amplifier, a display, and a coupling laser. The receiver receives a modulated waveform imprinted on a radiofrequency carrier a displays a graphical representation corresponding to a modulation source.

The invention provides a pencil beam dose calculation method. The pencil beam dose calculation method comprises the following steps: acquiring human body image data; determining a plurality of particle types for treatment; calculating initial pencil beam dose distribution corresponding to each particle type; based on the particle types, target action layers, distributed in the human body image data, of all the doses are determined, and the positions of the target action layers corresponding to different particle types are different; based on the target action layer corresponding to each particle type, adjusting each initial dose distribution, and obtaining particle pencil beam dose distribution corresponding to each particle type; superposing the particle pencil beam dose distribution corresponding to each particle type to obtain target pencil beam dose distribution; wherein the dose proportion of the particle pencil beam dose distribution corresponding to the same particle type in the target action layer is greater than the dose proportion of the particle pencil beam dose of the particle type in other parts in the human body image data.

The invention discloses a method for selecting and triggering gamma instant radiation pulse events, and belongs to the technical field of nuclear radiation detection. The method comprises the following steps: carrying out normalization preprocessing on an original gamma pulse radiation time spectrum; s time-frequency transformation is carried out on the preprocessed data, and time-frequency features are extracted; optimizing parameters of the frequency threshold and the amplitude threshold after S time-frequency transformation by adopting a deep reinforcement learning model to obtain an optimal frequency threshold and an optimal amplitude threshold; performing filtering processing on the signal of the S time-frequency conversion result, and separating noise from an effective signal; and searching a pulse radiation event for the filtered signal by applying a morphology-based peak searching method, and positioning the position and the characteristic of a real gamma instant radiation pulse event. According to the method, time-frequency analysis is carried out through S time-frequency transformation, the problem that the frequency of an analysis window cannot be adjusted through short-time window Fourier transformation is solved, the method has better frequency resolution and phase retention characteristics, and gamma pulse signal characteristics can be represented more accurately.

The invention relates to the technical field of medical image auxiliary diagnosis, in particular to a nuclear magnetic resonance image auxiliary diagnosis method and system based on multi-modal fusion. The method comprises the following steps: step 1, synchronously acquiring a three-dimensional T1 weighted structure image, a T2 weighted fluid attenuation inversion recovery image and diffusion weighted imaging data of a subject, carrying out spatial registration by taking the T1 weighted image as a reference, and executing skull stripping and gray scale standardization; 2, individualized brain region segmentation is carried out based on a brain anatomical map, the lesion sensitivity weight of each modal is calculated for each segmented brain region, and the weight is obtained by quantifying the following parameters; step 3, extracting multi-modal image features in each brain region; and 4, inputting the fusion features of the whole brain region into a multi-task classifier. The standardization and alignment of the multi-mode MRI image in the space and gray level are realized, and the problems of space mismatch and feature interference among different modes are effectively solved.

The invention provides a beam control system for BNCT treatment. The system comprises a treatment control module, an accelerator control module and a flux monitoring module. The treatment control module is used for acquiring the delivery dose and the delivery time of the BCNT in real time so as to trigger a beam stopping instruction based on the delivery dose or the delivery time, and transmitting the beam stopping instruction to the accelerator control module so as to terminate neutron beam delivery; the accelerator control module is used for receiving a beam stop instruction to correspondingly close the proton beam so as to terminate neutron beam delivery, and automatically close the proton beam when an abnormal condition occurs; the flux monitoring module is used for monitoring neutron flux in real time and transmitting monitoring data to the treatment control module so that the treatment control module can obtain the delivery dosage in real time based on the monitoring data. According to the application, the delivery of the beam is accurately controlled and the delivery dose and the delivery time are monitored in real time in the BNCT treatment process, so that the accuracy and the safety of the beam delivery of the equipment are ensured.

In various embodiments of the invention, a cooled nuclear magnetic resonance (NMR) probe can utilize a sliding band capacitor which can be moved relative to a parent coil inner conductance tapered skirt to adjust the frequency of the parent coil to allow the parent coil to detect the resonance of at least two nuclei without requiring leads between the parent coil and a lock coil. In this manner a cooled NMR probe can be provided without the disadvantages of prior art cooled NMR probes. In an embodiment of the invention, the sliding band capacitor comprises a diamagnetic insulator with a first volume magnetic susceptibility, at least one paramagnetic metal with a second volume magnetic susceptibility and at least one diamagnetic metal with a third volume magnetic susceptibility, where the sum of the first volume magnetic susceptibility, the second volume magnetic susceptibility and the third volume magnetic susceptibility is approximately zero.

The invention discloses a CO2-EGR visual monitoring method based on nuclear magnetic resonance. The CO2-EGR visual monitoring method aims at solving the problem that dynamic observation of the pore scale gas drive process is insufficient in the traditional technology. Multi-sequence nuclear magnetic resonance monitoring is synchronously executed, a T2 spectrum is obtained through a CPMG sequence to analyze CH4 content changes, a layered T2 spectrum is generated through an SE-SPI sequence to represent axial fluid distribution, a one-dimensional frequency signal is collected based on a GR-HSE sequence to track a displacement leading edge in real time, and fluid migration visualization is achieved in combination with an HSE overall imaging sequence. The system integrates a gas injection unit, a high-pressure-resistant nuclear magnetic holder, a back pressure controller and a data acquisition module, and is hermetically connected through a high-pressure-resistant pipeline to form a closed-loop experiment system. According to the method, displacement front recognition, displacement process in-situ analysis and quantitative characterization of the displacement efficiency in the non-intrusive CO2-EGR process are achieved for the first time, the CO2-EGR visualization bottleneck is broken through, and a scientific basis is provided for optimizing gas injection parameters and improving the natural gas recovery rate and the carbon sequestration efficiency.

The invention discloses a nuclear magnetic resonance free induction decay signal reconstruction method based on a diffusion probability model, and relates to the field of magnetic resonance spectrums.The method comprises the steps that a simulation data set is constructed based on a mathematical model of free induction decay signals, and the simulation data set is divided into a training set, a verification set and a test set; sampling each data set by adopting a Poisson gap non-uniform sampling strategy, and simulating an actual under-sampling condition; constructing a diffusion probability model, gradually adding Gaussian noise through a forward diffusion module to generate a noise-containing sample, and recovering an original signal from a noise signal through a reverse denoising module; and inputting test data into the optimal model for multiple times to obtain a plurality of reconstruction results. According to the method, the reconstruction method based on the diffusion probability model is constructed, training optimization is carried out through Poisson gap non-uniform sampling and simulation signal data sets, and high-precision reconstruction of the under-sampling nuclear magnetic resonance free induction decay signals is achieved.

An apparatus includes an input unit, a processing unit, and an output unit. The input unit is configured to provide the processing unit with at least one diffusion magnetic resonance imaging dMRI image of a patient's brain. The processing unit is configured to: 1) determine an estimate of an orientation of neurons at each voxel in the dMRI image; 2) determine a plurality of fiber tracts in the at least one dMRI image; 3) select a plurality of voxels along at least one fiber tract of the plurality of fiber tracts; and 4) determine a neurological disease classification.