CN115345950A - Image reconstruction method and device, computer equipment and storage medium - Google Patents
Image reconstruction method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN115345950A CN115345950A CN202110528230.5A CN202110528230A CN115345950A CN 115345950 A CN115345950 A CN 115345950A CN 202110528230 A CN202110528230 A CN 202110528230A CN 115345950 A CN115345950 A CN 115345950A
- Authority
- CN
- China
- Prior art keywords
- spatial resolution
- low spatial
- reconstruction
- space data
- space
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 60
- 230000006870 function Effects 0.000 claims description 31
- 238000004590 computer program Methods 0.000 claims description 17
- 238000002360 preparation method Methods 0.000 claims description 9
- 238000003384 imaging method Methods 0.000 abstract description 9
- 238000002595 magnetic resonance imaging Methods 0.000 abstract description 8
- 230000008569 process Effects 0.000 description 17
- 230000000875 corresponding effect Effects 0.000 description 13
- 238000005070 sampling Methods 0.000 description 7
- 230000035945 sensitivity Effects 0.000 description 7
- 238000003062 neural network model Methods 0.000 description 6
- 238000012549 training Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 238000004891 communication Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 210000000056 organ Anatomy 0.000 description 3
- 230000002123 temporal effect Effects 0.000 description 3
- 206010064966 Myocardial oedema Diseases 0.000 description 2
- 238000013184 cardiac magnetic resonance imaging Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 230000002708 enhancing effect Effects 0.000 description 2
- 238000002075 inversion recovery Methods 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 230000002107 myocardial effect Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 206010030113 Oedema Diseases 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 210000004351 coronary vessel Anatomy 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 230000002497 edematous effect Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000005865 ionizing radiation Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000004165 myocardium Anatomy 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000000241 respiratory effect Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T11/00—2D [Two Dimensional] image generation
- G06T11/003—Reconstruction from projections, e.g. tomography
- G06T11/005—Specific pre-processing for tomographic reconstruction, e.g. calibration, source positioning, rebinning, scatter correction, retrospective gating
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
- G06T3/4053—Scaling of whole images or parts thereof, e.g. expanding or contracting based on super-resolution, i.e. the output image resolution being higher than the sensor resolution
- G06T3/4076—Scaling of whole images or parts thereof, e.g. expanding or contracting based on super-resolution, i.e. the output image resolution being higher than the sensor resolution using the original low-resolution images to iteratively correct the high-resolution images
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Magnetic Resonance Imaging Apparatus (AREA)
Abstract
The application relates to an image reconstruction method, an image reconstruction device, computer equipment and a storage medium, wherein a k space data set of a target part is obtained, and the acquisition mode of the k space data set is that the k space center is completely sampled and the k space edge is undersampled; and reconstructing a low spatial resolution T2 parametric map based on the k-space dataset, and then reconstructing a high spatial resolution T2 parametric map according to the k-space dataset and the low spatial resolution T2 parametric map. The method improves the time resolution of the magnetic resonance imaging and ensures the spatial resolution, thereby ensuring the higher time and spatial resolution of the magnetic resonance dynamic imaging.
Description
Technical Field
The present application relates to the field of image processing technologies, and in particular, to an image reconstruction method and apparatus, a computer device, and a storage medium.
Background
Magnetic Resonance Imaging (MRI) is an imaging technique that uses signals generated by the resonance of atomic nuclei within a strong magnetic field to reconstruct images. The technology can obtain high-contrast clear images of the interior of a sample/tissue under the conditions of no damage and no ionizing radiation, and is widely applied to medical diagnosis.
Generally, due to some factors, the imaging speed of magnetic resonance is very slow, and the slow imaging speed causes that the image time resolution of the magnetic resonance imaging is greatly limited in the dynamic imaging of moving organs such as the heart, and at the same time, serious motion artifacts are generated in the images, and the image quality is reduced.
Therefore, how to ensure higher time and space resolution of magnetic resonance dynamic imaging becomes a technical problem to be solved urgently.
Disclosure of Invention
In view of the above, it is necessary to provide an image reconstruction method, an apparatus, a computer device and a storage medium, which can ensure high temporal and spatial resolution of mri.
In a first aspect, an embodiment of the present application provides an image reconstruction method, including:
acquiring a k-space data set of a target part, wherein the acquisition mode of the k-space data set is that the k-space center is completely sampled and the k-space edge is under-sampled;
reconstructing a low spatial resolution T2 parametric map based on the k-space dataset; the low spatial resolution represents a spatial resolution smaller than a first preset value;
reconstructing a high spatial resolution T2 parameter map according to the k-space data set and the low spatial resolution T2 parameter map; the high spatial resolution means a spatial resolution greater than the second preset value.
In one embodiment, reconstructing the high spatial resolution T2 parameter map from the k-space data set and the low spatial resolution T2 parameter map includes:
inputting the k-space data set, the low spatial resolution T2 parameter map and the reconstruction parameters into a preset first reconstruction model to obtain a high spatial resolution T2 parameter map; the first reconstruction model comprises a reconstruction regular constraint term of a low spatial resolution T2 parameter map.
In one embodiment, the obtaining of the first reconstruction model includes:
constructing an objective function of an initial reconstruction model according to the k-space data set, the reconstruction parameters and the sparse parameters; the target function comprises a data fidelity term, a sparse regular constraint term and a reconstruction regular constraint term; reconstructing the canonical constraint term includes a low spatial resolution T2 parameter map;
and minimizing the objective function, and iteratively optimizing the initial reconstruction model until a preset iteration condition is met to obtain a first reconstruction model.
In one embodiment, the k-space data set includes N k-space data having different T2 preparation times, where N is a positive integer.
In one embodiment, reconstructing a low spatial resolution T2 parametric map based on a k-space data set comprises:
reconstructing at least one low spatial resolution T2-weighted image from the k-space dataset;
a low spatial resolution T2 parametric map is reconstructed based on the at least one low spatial resolution T2 weighted image.
In one embodiment, the reconstructing the low spatial resolution T2 parameter map based on at least one low spatial resolution T2 weighted image includes:
fitting the signal intensity value of each pixel point of at least one low spatial resolution T2 weighted image, and determining the obtained fitting value as the T2 value of each pixel point;
and determining an image formed by expressing the pixel points by the T2 value as a low spatial resolution T2 parameter map.
In one embodiment, the reconstructing the low spatial resolution T2 parameter map based on at least one low spatial resolution T2 weighted image includes:
and inputting the k-space data set and the reconstruction parameters into a preset second reconstruction model to obtain a low spatial resolution T2 parameter map.
In a second aspect, an embodiment of the present application provides an image reconstruction apparatus, including:
the data acquisition module is used for acquiring a k-space data set of the target part, wherein the acquisition mode of the k-space data set is that the k-space center is fully sampled and the k-space edge is undersampled;
a first reconstruction module for reconstructing a low spatial resolution T2 parametric map based on the k-space dataset; the low spatial resolution represents a spatial resolution smaller than a first preset value;
the second reconstruction module is used for reconstructing a high spatial resolution T2 parameter map according to the k-space data set and the low spatial resolution T2 parameter map; the high spatial resolution means a spatial resolution greater than the second preset value.
In a third aspect, an embodiment of the present application provides a computer device, including a memory and a processor, where the memory stores a computer program, and the processor implements the method steps of any one of the foregoing first aspects when executing the computer program.
In a fourth aspect, the present application provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the method steps of any one of the embodiments in the first aspect.
The image reconstruction method, the image reconstruction device, the computer equipment and the storage medium provided by the embodiment of the application acquire a k-space data set of a target part, wherein the acquisition mode of the k-space data set is that the k-space center is completely sampled and the k-space edge is undersampled; and reconstructing a low spatial resolution T2 parametric map based on the k-space dataset, and then reconstructing a high spatial resolution T2 parametric map according to the k-space dataset and the low spatial resolution T2 parametric map. In the method, the reconstructed K-space data is a T2 parameter map with low spatial resolution, so the K-space data can be acquired in an undersampling mode, namely, the K-space data is acquired by completely sampling the center of the K-space and undersampling the edge of the K-space, so the data volume of the acquired K-space data is reduced, the scanning time is greatly shortened, the time resolution of magnetic resonance imaging is improved, and after the T2 parameter map with the low spatial resolution is obtained, the T2 parameter map with the high resolution is further reconstructed according to the T2 parameter map with the low spatial resolution, and meanwhile, the spatial resolution is also ensured, so that the higher time and spatial resolution of the magnetic resonance dynamic imaging can be ensured.
Drawings
FIG. 1 is a diagram illustrating an exemplary embodiment of a method for image reconstruction;
FIG. 2 is a schematic flow chart of image reconstruction provided in an embodiment;
FIG. 3 is a schematic flow chart of image reconstruction provided in another embodiment;
FIG. 4 is a schematic flow chart of image reconstruction provided in another embodiment;
FIG. 5 is a schematic flow chart of image reconstruction provided in another embodiment;
FIG. 6 is a flow chart of an image reconstruction process provided in another embodiment;
fig. 7 is a block diagram of an image reconstruction apparatus provided in an embodiment;
FIG. 8 is a diagram illustrating an internal structure of a computer device according to an embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more clearly understood, the present application is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
The image reconstruction method provided by the application can be applied to the application environment shown in fig. 1. Wherein processors in the internal structure of the computer device are used to provide computing and control capabilities. The memory includes a nonvolatile storage medium, an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database is used for storing relevant data of the image reconstruction method process. The network interface is used for communicating with other external devices through network connection. The computer program is executed by a processor to implement an image reconstruction method.
Before specifically describing the technical solution of the embodiment of the present application, a technical background or a technical evolution context on which the embodiment of the present application is based is described. First, a T2 parameter map in the embodiment of the present application is explained: for example, cardiac Magnetic Resonance imaging (CMR) can assess the degree of myocardial edema using T2-weighted sequence images, with the target site being the heart. These images are reconstructed based on the edema-induced extension of transverse relaxation time. Due to the accumulation of water, the proportion of free water increases, myocardial edema appears as high signal intensity on the T2-weighted image, and each pixel on the T2-weighted image shows different signal intensity, particularly different gray scale values displayed by different signal intensities. The T2 weighted image can be qualitatively evaluated, and the T2 quantitative sequence (T2 mapping) is an 'upgraded version' of the T2 weighted image and is used for quantitative determination, and the T2 value of the myocardial tissue is reflected by a numerical value, and if the myocardium is edematous, the T2 value of the myocardial tissue is generally increased. Based on this, an image in which the value at each pixel is a specific T2 value, which is a T2 parameter map, can be acquired as a diagnostic image by the T2 mapping technique.
In practical applications, in order to minimize image blur due to heart motion, the acquisition window must be narrowed, preferably not more than 50ms, but such a narrow acquisition window is not sufficient to cover a sufficient K-space (or K-space) range to achieve a certain spatial resolution, so it is not practical to improve the image quality by the narrow acquisition window. On the other hand, the magnetic resonance imaging process needs to be kept in a static state, the imaging time is too long, discomfort of a patient is increased, the influence of respiratory motion is easily caused, and motion artifacts are generated, so that the k space data cannot be acquired too much, usually 3 k space data are acquired, and when a T2 parameter image is fitted through a T2 weighted image, the final image quality is poor due to the fact that the number of the k space data is small.
In the related art, a T2 parameter map is obtained by independently reconstructing a plurality of acquired k-space data into corresponding T2 weighted images respectively, and then performing image processing on the T2 weighted images to obtain a T2 parameter map, in this method, the T2 parameter map is obtained directly from the T2 weighted images, that is, the spatial resolution of the T2 parameter map is positively correlated with the spatial resolution of the T2 weighted images, and the T2 weighted images are reconstructed from the k-space data, if a T2 weighted image with a high spatial resolution is to be obtained, a sufficient amount of data is required for complete sampling or under-sampling during the acquisition of the k-space data, so as to ensure the high spatial resolution of the reconstructed T2 weighted images. However, when acquiring k-space data, a sufficient amount of data is fully or under sampled, and more data needs to be acquired, which requires longer time and leads to lower time resolution. Vice versa, which in turn leads to a decrease in the spatial resolution of the T2 parameter map. Therefore, how to ensure higher time and space resolution of dynamic magnetic resonance imaging still belongs to the technical problem to be solved. Based on this, the embodiment of the present application provides an image reconstruction method, an apparatus, a computer device, and a storage medium, which can ensure higher time and spatial resolution of magnetic resonance dynamic imaging. In addition, it should be noted that, from the discovery of the above technical defects and the technical solutions described in the following embodiments, the applicant has paid a lot of creative efforts.
The following describes in detail the technical solutions of the present application and how the technical solutions of the present application solve the above technical problems by embodiments and with reference to the drawings. These several specific embodiments may be combined with each other below, and details of the same or similar concepts or processes may not be repeated in some embodiments. In the following description, an execution subject is a computer device when an image reconstruction method provided in an embodiment of the present application is described. In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments.
In one embodiment, as shown in FIG. 2, an image reconstruction method is provided. The embodiment relates to a specific process that computer equipment reconstructs a low spatial resolution T2 parameter map according to k space data of a target part and reconstructs a high spatial resolution T2 parameter map based on the k space data set and the low spatial resolution T2 parameter map; this embodiment comprises the steps of:
s101, acquiring a k-space data set of a target part, wherein the acquisition mode of the k-space data set is that the k-space center is completely sampled and the k-space edge is undersampled.
The data acquired by a magnetic resonance scan is k-space data, i.e., frequency domain data, which is the space used to represent spatial frequencies in a magnetic resonance image. The data of k space is subjected to inverse Fourier transform, and the space positioning coding information in the original data can be decoded to obtain image domain data, namely magnetic resonance image data. Reconstruction is the process of converting k-space data into image domain data. The k-space data points and the image pixel points are in Fourier transform and inverse transform relation, and each data point in the k-space contains the information of the whole image. The reconstruction of the T2 parameter map therefore presupposes that k-space data are acquired first.
The target region in the embodiment of the present application may be a moving organ such as a heart, a coronary artery, or any other applicable organ, which is not limited in the embodiment of the present application. Taking the target site as a heart, it is necessary to acquire a k-space data set of the heart. Optionally, the k-space data set comprises N k-space data, the N k-space data having different T2 preparation times, N being a positive integer. For example, if N is equal to 3, the acquired k-space data set comprises 3 k-space data, and the 3 k-space data have different T2 preparation times. For the heart, one heartbeat cycle includes diastole and systole, so that one acquisition may be performed when acquiring the 3 k-space data of the heart, the first acquisition is performed after the heart recovers, the second acquisition is performed when the heart starts to beat again, the waiting is continued, and the third k-space data is acquired when the heart recovers and beats again. The preparation time is the preparation time in acquiring one k-space data, which is different from the waiting time. The set preparation times for different k-space data are different for a plurality of k-space data. The specific set preparation time can be determined according to actual conditions, and is not limited in the embodiments of the present application.
When acquiring each k-space data in a k-space data set, the acquisition mode is that the k-space center is fully sampled and the k-space edges are undersampled.
When acquiring k-space data, the sampling frequency of the undersampling method does not satisfy the nyquist sampling frequency, which may cause aliasing artifacts. The energy of one image is mainly concentrated in the k-space central region, and if the k-space central region adopts an undersampling mode, aliasing artifacts contain most low-frequency components; whereas k-space edges contain little energy of a map, undersampled edges do not lead to severe aliasing artifacts. Thus, the scan time can be reduced by fully sampling the center of k-space and undersampling the edges of k-space. The range of the completely sampled k-space central region and the degree of undersampling (different degrees, representing different amounts of sampled data) of the edge regions except the central region may be determined according to the requirement of subsequently reconstructing the low spatial resolution T2 parameter map in the embodiment of the present application, which is not limited in the embodiment of the present application. And the edge undersampled data positions of different k-space data are also different, for example, although all the k-space data are undersampled, the first k-space data is acquired by 1, 3 and 7, and the second k-space data is acquired by 2, 4 and 9, which is not limited by the embodiment of the present application.
It should be emphasized that the description of the acquisition mode in the embodiments of the present application merely provides an exemplary acquisition mode. However, in the embodiment of the present application, when the k-space data set is obtained, the obtaining manner may be to obtain stored existing k-space data from a database of the computer device; or downloading required k-space data from other online platforms; alternatively, the heart beat may be simulated by specific software, and the required k-space data may be acquired according to a simulated model, which is not limited in the embodiments of the present application. That is, in the embodiment of the present application, when performing image reconstruction, the acquired k-space data refers to not being acquired in real time, but being acquired by downloading or invoking.
S102, reconstructing a low spatial resolution T2 parametric map based on the k-space data set; the low spatial resolution means a spatial resolution smaller than the first preset value.
After acquiring the k-space dataset of the target site, a low spatial resolution T2 parametric map is reconstructed from the k-space dataset. The spatial resolution refers to the smallest detail which can be displayed in the image when the density resolution is more than 10%; density resolution refers to the minimum density difference between tissues that can be resolved. The two are mutually restricted. Spatial resolution is closely related to pixel size, typically 1.5 times the pixel width. The smaller the number of pixels, the higher the spatial resolution and the sharper the image. Therefore, the degree of low spatial resolution can be determined according to a preset critical value, for example, the preset critical value is a first value equal to 4, and then the spatial resolution less than 4 is the low spatial resolution; of course, the first value is only an example, and the threshold value of the reconstructed low spatial resolution may be determined according to specific situations in practical applications.
For example, the low spatial resolution T2 parameter map may be reconstructed based on the k-space data set by using a pre-trained neural network model and taking the acquired k-space data set as an input, so that a result output by the neural network model is the low spatial resolution T2 parameter map. Alternatively, a corresponding magnetic resonance image may be reconstructed from each k-space data in the k-space data set, and then a low spatial resolution T2 parameter map may be reconstructed from the magnetic resonance image, which is not limited in this embodiment of the present application.
S103, reconstructing a high spatial resolution T2 parameter map according to the k space data set and the low spatial resolution T2 parameter map; a high spatial resolution indicates a spatial resolution greater than the second preset value.
And further reconstructing a high spatial resolution T2 parameter map according to the acquired k-space data set and the reconstructed low spatial resolution T2 parameter map.
Similarly, the degree of high spatial resolution may also be determined according to a preset critical value, for example, if the preset critical value is a second value equal to 8, then the spatial resolution greater than 8 is the high spatial resolution; of course, the second value is just an example, and the reconstructed critical value of high spatial resolution may be determined according to specific situations in practical applications. Moreover, it can be understood that the critical values of the low spatial resolution and the high spatial resolution may be the same value or different values, that is, the first preset value may be equal to the second preset value or may not be equal to the second preset value.
For example, an implementation of reconstructing a high spatial resolution T2 parameter map according to a k-space data set and a low spatial resolution T2 parameter map may be to use a preset algorithm, such as a bilinear difference or a nearest neighbor difference, specifically, may be to perform a simple bilinear difference on the low spatial resolution T2 parameter map, then use a hash algorithm to quickly divide image blocks into different categories (buckets), perform linear filtering on each category by using four pre-trained filters, and then fuse results of different image blocks to obtain a final high spatial resolution T2 parameter map.
Another embodiment may also be that a preset neural network model is trained on a plurality of k-space data sets and low-space resolution T2 parameter maps and corresponding high-space resolution T2 parameter maps, so that the trained neural network model may output a corresponding high-space resolution T2 parameter map according to the k-space data sets and the low-space resolution T2 parameter maps.
The image reconstruction method provided by the embodiment obtains a k-space data set of a target part, wherein the acquisition mode of the k-space data set is that the k-space center is completely sampled and the k-space edge is undersampled; and reconstructing a low spatial resolution T2 parametric map based on the k-space data set, and then reconstructing a high spatial resolution T2 parametric map according to the k-space data set and the low spatial resolution T2 parametric map. In the method, because the low-spatial-resolution T2 parameter map is reconstructed based on the k-space data, the k-space data can be acquired in an undersampled mode, namely, the k-space data is acquired by completely sampling the center of the k-space and undersampling the edge of the k-space, so that the data volume of the acquired k-space data is reduced, the scanning time is greatly shortened, the time resolution of magnetic resonance imaging is improved, and after the low-spatial-resolution T2 parameter map is obtained, the high-resolution T2 parameter map is further reconstructed according to the low-spatial-resolution T2 parameter map, and meanwhile, the spatial resolution is also ensured, so that the higher time and spatial resolution of the dynamic magnetic resonance imaging can be ensured.
On the basis of the above-described embodiment, the following provides an implementable way of reconstructing a high spatial resolution T2 parameter map from a k-space data set and a low spatial resolution T2 parameter map, the embodiment including: inputting the k-space data set, the low spatial resolution T2 parameter map and the reconstruction parameters into a preset first reconstruction model to obtain a high spatial resolution T2 parameter map; the first reconstruction model comprises a reconstruction regular constraint term of a low spatial resolution T2 parameter map.
The first reconstruction model may be the above-mentioned pre-trained neural network model, or may be an algorithm model constructed according to a preset reconstruction algorithm. And taking the algorithm model as an example, the first reconstruction model comprises a reconstruction regular constraint term of the low spatial resolution T2 parameter map, the reconstruction regular constraint term is used for constraining and preventing overfitting from the low spatial resolution T2 parameter map to the high spatial resolution T2 parameter map, and the introduced low spatial resolution T2 parameter map is used as prior knowledge to estimate the actual result of the high spatial resolution T2 parameter. The method enables the T2 parameter map with low spatial resolution to be more accurate.
The reconstruction parameter refers to any parameter required by the reconstruction process, for example, a temporal modulation mode, which is a characteristic that represents the change of the amplitude, frequency and phase of the modulation signal with time, and the temporal modulation mode is a parameter that is preset before the scanning of the acquired k-space data and can be directly acquired and used in the process of reconstructing the image according to the k-space data, that is, the parameter is a known value in the reconstruction process. For another example, the reconstruction parameters include a coil sensitivity map, and the magnetic resonance apparatus uses the electromagnetic wave detected by the receiving coil as the magnetic resonance signal, so the coil sensitivity refers to the degree of response of the receiving coil to the input signal, and the higher the value of the coil sensitivity, the stronger the ability of detecting a weak signal, and a map formed by the coil sensitivity values of the entire coil is the coil sensitivity map. The above two parameters are only examples, and the reconstructed parameters are not limited in the examples of the present application.
For the present embodiment, the k-space data set, the low spatial resolution T2 parameter map, and the reconstruction parameters are all known values, and then these data are input into a preset first reconstruction model, and the output result is the high spatial resolution T2 parameter map. Making it faster from a low spatial resolution T2 parameter map to a high spatial resolution T2 parameter map.
Optionally, as shown in fig. 3, the obtaining process of the first reconstruction model includes the following steps:
s201, constructing an objective function of an initial reconstruction model according to the k-space data set, the reconstruction parameters and the sparse parameters; the target function comprises a data fidelity term, a sparse regular constraint term and a reconstruction regular constraint term; the reconstruction regularization constraint term includes a low spatial resolution T2 parametric map.
The model can be simply understood as a function, so that the above-mentioned first reconstruction model construction process needs to use the objective function as an iteration target. Then, the objective function needs to be constructed by k-space data set, reconstruction parameters and sparse parameters, where the k-space data set and the reconstruction parameters are the same as those in the foregoing embodiments, except that the k-space data set and the reconstruction parameters may be data in a training set, that is, a large amount of diversified training data is acquired as the training set. The sparse parameter refers to a parameter of spatial smoothness, such as a spatial difference or other sparse operator, which is used to measure a parameter of spatial smoothness of an image.
The constructed objective function comprises a data fidelity term, a sparse regular constraint term and a reconstruction regular constraint term, wherein the data fidelity term is used for ensuring that the result conforms to the degradation process. The regular term is used for enhancing the output, namely the sparse regular constraint term and the reconstruction regular constraint term are used for enhancing the output, the difference is that the sparse regular constraint term is used for performing constraint enhancement from the spatial smoothness dimension, and the reconstruction regular constraint term is used for estimating the high spatial resolution T2 parameter and preventing the overfitting dimension from performing constraint enhancement by using the low spatial resolution T2 parameter map as the prior knowledge.
For example, the objective function is:
S202, minimizing the objective function, and iteratively optimizing the initial reconstruction model until a preset iteration condition is met to obtain a first reconstruction model.
After the objective function is constructed, the objective function is minimized, that is, the minimum value of the objective function is solved, for example, a preset iteration condition may be set to reach a preset iteration number T, or an iteration process is converged, then the constructed initial reconstruction model may be iteratively optimized alternately, and the regular term parameters are updated until the preset iteration condition is satisfied, and the training is completed to obtain the first reconstruction model.
From the above objective function, only x is used i And T 2 The other data are known quantities and the T2 weighted image corresponding to each k-space data in the k-space data set and the final high spatial resolution T2 parameter map are output from the first reconstruction model constructed by the objective function. Thereby obtaining a high spatial resolution T2 parameter map.
In the embodiment of the application, the k-space data set, the low spatial resolution T2 parameter map and the reconstruction parameters are input into the preset first reconstruction model to obtain the high spatial resolution T2 parameter map, so that the high spatial resolution T2 parameter map can be quickly and accurately reconstructed from the low spatial resolution T2 parameter map. And the training objective function of the first reconstruction model comprises a data fidelity term, a sparse regular constraint term and a reconstruction regular constraint term, and the error minimization, the sparse constraint and the overfitting constraint are carried out on the data output result in the training process, so that the accuracy of the output result of the finally trained first reconstruction model is ensured.
The above-described process of reconstructing a low spatial resolution T2 parameter map based on a k-space data set is explained below by means of different embodiments.
Then, as shown in fig. 4, in an embodiment, the above-mentioned reconstruction of the low spatial resolution T2 parameter map based on the k-space data set comprises the following steps:
s301, at least one low spatial resolution T2-weighted image is reconstructed from the k-space data set.
The k-space data set comprises a plurality of k-space data, for example 3 k-space data; then, at least one low spatial resolution T2 weighted image may be reconstructed based on each k-space data, and certainly, a low spatial resolution T2 weighted image may be reconstructed corresponding to each k-space data, which is not limited in this embodiment of the present application.
The low spatial resolution T2-weighted image is reconstructed from the k-space dataset in such a way that the image obtained by directly performing inverse fourier transform on the k-space data is the low spatial resolution T2-weighted image. It should be noted that in the embodiment of the present application, the image obtained by performing the inverse fourier transform on the k-space data set is referred to as a low spatial resolution T2 weighted image because the k-space data is acquired in the manner defined in the embodiment of the present application, that is, the k-space central region is fully sampled and the edge region is undersampled, so that the number of acquired k-space data is small, and the spatial resolution of the reconstructed magnetic resonance image (T2 weighted image) is low, so the image is referred to as a low spatial resolution T2 weighted image.
S302, reconstructing a low spatial resolution T2 parameter map based on at least one low spatial resolution T2 weighted image.
After the low spatial resolution T2 weighted image is obtained, a low spatial resolution T2 parametric map is reconstructed according to the low spatial resolution T2 weighted image. This can be understood in connection with the aforementioned differences between the T2-weighted image and the T2 parameter map, i.e. each pixel in the T2-weighted image represents the signal intensity of a different tissue, embodied in a different grey scale. The stronger the tissue signal intensity is, the brighter the part of the corresponding pixel point on the T2 weighted image is; conversely, the weaker the tissue signal strength, the darker the portion of the T2 weighted image corresponding to the pixel. However, each pixel in the T2 parameter map represents a specific T2 value, not signal strength.
Optionally, as shown in fig. 5, reconstructing the low spatial resolution T2 parameter map based on the low spatial resolution T2 weighted image includes:
s401, fitting the signal intensity values of all pixel points of at least one low spatial resolution T2 weighted image, and determining the obtained fitting values as the T2 values of all the pixel points.
Taking the example that the k-space data set includes 3 k-space data and each k-space data corresponds to a reconstructed T2 weighted image, that is, fitting the signal intensity values of the pixel points of the 3 low-spatial-resolution T2 weighted images, and determining the obtained fitting value as the T2 value of each pixel point.
Assuming that 10 × 10 pixel points of one image are equal to 100, and 3 weighted images with low spatial resolution T2 are T21, T22, and T23, respectively, the signal intensities of the pixel points corresponding to the first row and the first column of the three images T21, T22, and T23 are fitted, for example, by a preset fitting function, and a fitting value obtained after fitting is determined to be a T2 value, that is, a T2 value of the pixel point corresponding to the first row and the first column; in this way, the T2 values of other 99 pixels can be obtained, and the T2 values of 100 pixels can be obtained by synthesis.
S402, determining an image formed by expressing the pixel points by the T2 values as a low spatial resolution T2 parameter map.
And after the T2 value of each pixel point is obtained, expressing the pixel points by the T2 value, and forming an image which is the low spatial resolution T2 parameter map.
In the embodiment of the application, after k-space data are reconstructed into a T2 weighted image, a low spatial resolution T2 parametric map is obtained based on the signal intensity value fitting of each pixel point in the T2 weighted image. Because the signal intensity value of each pixel point in the T2 weighted image represents the characteristic of reflecting the T2 characteristic of the target part tissue, the T2 value of the corresponding pixel point is fitted by the signal intensity value of each pixel point, so that the finally obtained low-spatial-resolution T2 parameter map is more accurate.
In a further embodiment, reconstructing the low spatial resolution T2 parametric map based on at least one low spatial resolution T2 weighted image comprises: and inputting the k-space data set and the reconstruction parameters into a preset second reconstruction model to obtain a low spatial resolution T2 parameter map.
Similarly, the second reconstruction model may be the above-mentioned pre-trained neural network model, or may be an algorithm model constructed according to a preset reconstruction algorithm. For the k-space data set and the reconstruction parameters in the second reconstruction model, reference may be made to the description in the foregoing embodiments, which are not repeated herein.
Taking the algorithm model as an example, the process of constructing the second reconstruction model is also required to construct the objective function. For example, the objective function of the second reconstruction model is:
wherein, the objective function
This part is the data fidelity term, where x i Refers to a T2-weighted image reconstructed from any k-space data in the k-space data set, whichever is indicated by the subscript i; t is 2 Refers to a high spatial resolution T2 parameter map; y is i Any k-space data in the k-space data set is referred to as actual data; p is a radical of 1 Refers to the reconstruction parameter time modulation mode; s denotes a reconstructed parametric coil sensitivity map, phi denotes an inversion recovery signal model, where phi (x) i ,T 2 ) Equal to a x Exp (-T/b)) + c, where a is the initial signal amplitude, b is the value of T2, and the offset c is optional. p is a radical of 1 FSΦ(x i ,T 2 ) K-space data which are integrally expressed and reversely estimated according to the reconstruction parameters and the inversion signal model, wherein F refers to Fourier transform; thus, the data fidelity term is minimized by minimizing the difference between the actual k-space data and the predicted k-space data to ensure that the final output T2 parameter map meets the requirements. Wherein,
for sparse regular constraint term, λ i And beta is a regularization coefficient, the error between the regularization term and the data fidelity term is balanced, when the regularization sparsity becomes larger, the solution tends to be smooth, otherwise, the edge of the solution is sharpened. And T is the sparse parameter spatial difference.
And after the objective function of the second reconstruction model is constructed, minimizing the objective function, and iteratively optimizing the initial reconstruction model of the second reconstruction model until a preset iteration condition is met to obtain the second reconstruction model. In the second reconstructed model, there is again only x i And x i The other data are known quantities and are unknown parameters, and a T2 weighted image and a low spatial resolution T2 parameter map corresponding to each k-space data in the k-space data set are output through the second reconstruction model.
In this embodiment, the second reconstruction model is used to obtain the low spatial resolution T2 parameter map from the k-space data set and the reconstruction parameters, and since the model is constructed in advance and error minimization and sparse constraint are performed on the data output result during construction, the constructed model can quickly and accurately reconstruct the low spatial resolution T2 parameter map from the k-space data set.
In addition, an embodiment of the present application further provides an image reconstruction method, as shown in fig. 6, the embodiment includes:
s1, acquiring a k-space data set of a target part, wherein the acquisition mode of the k-space data set is that the k-space center is completely sampled and the k-space edge is undersampled; either S2 or S5 is performed.
S2, reconstructing at least one low spatial resolution T2 weighted image according to the k-space data set; s3 is performed.
S3, fitting the signal intensity value of each pixel point of at least one low spatial resolution T2 weighted image, and determining the obtained fitting value as the T2 value of each pixel point; s4 is performed.
S4, determining an image formed by expressing the pixel points by the T2 values as a low spatial resolution T2 parameter map; s6 is performed.
S5, inputting the k-space data set and the reconstruction parameters into a preset second reconstruction model to obtain a low spatial resolution T2 parameter map; s6 is performed.
S6, constructing an objective function of an initial reconstruction model according to the k-space data set, the reconstruction parameters and the sparse parameters; the target function comprises a data fidelity term, a sparse regular constraint term and a reconstruction regular constraint term; reconstructing the canonical constraint term includes a low spatial resolution T2 parameter map; s7 is performed.
S7, minimizing the objective function, and iteratively optimizing the initial reconstruction model until a preset iteration condition is met to obtain a first reconstruction model; s8 is performed.
S8, inputting the k-space data set, the low spatial resolution T2 parameter map and the reconstruction parameters into a preset first reconstruction model to obtain a high spatial resolution T2 parameter map; the first reconstruction model comprises a reconstruction regular constraint term of a low spatial resolution T2 parameter map.
The image reconstruction method provided in this embodiment has similar implementation principles and technical effects to those of the above method embodiments, and is not described herein again.
It should be understood that, although the steps in the flowcharts of the above embodiments are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least a part of the steps in the flowcharts of the above embodiments may include multiple steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of performing the steps or stages is not necessarily sequential, but may be performed alternately or alternately with other steps or at least a part of the steps or stages in other steps.
In one embodiment, as shown in fig. 7, there is provided an image reconstruction apparatus including: a data acquisition module 10, a first reconstruction module 11 and a second reconstruction module 12, wherein:
the data acquisition module 10 is used for acquiring a k-space data set of a target part, wherein the acquisition mode of the k-space data set is that the k-space center is fully sampled and the k-space edge is under-sampled;
a first reconstruction module 11 for reconstructing a low spatial resolution T2 parametric map based on the k-space dataset; the low spatial resolution represents a spatial resolution smaller than a first preset value;
a second re-modeling block 12 for reconstructing a high spatial resolution T2 parameter map from the k-space data set and the low spatial resolution T2 parameter map; the high spatial resolution means a spatial resolution greater than the second preset value.
In an embodiment, the data obtaining module 10 specifically inputs the k-space data set, the low spatial resolution T2 parameter map, and the reconstruction parameters into a preset first reconstruction model to obtain a high spatial resolution T2 parameter map; the first reconstruction model comprises a reconstruction regular constraint term of a low spatial resolution T2 parameter map.
In one embodiment, the apparatus further comprises:
the building module is used for building an objective function of an initial reconstruction model according to the k-space data set, the reconstruction parameters and the sparse parameters; the target function comprises a data fidelity term, a sparse regular constraint term and a reconstruction regular constraint term; reconstructing the canonical constraint term includes a low spatial resolution T2 parameter map;
and the optimization module is used for minimizing the objective function, and iteratively optimizing the initial reconstruction model until a preset iteration condition is met to obtain a first reconstruction model.
In an embodiment, the k-space data set comprises N k-space data, the N k-space data having different T2 preparation times, N being a positive integer.
In one embodiment, the first reconstruction module 11 includes:
a first reconstruction unit for reconstructing at least one low spatial resolution T2-weighted image from the k-space data set;
a second reconstruction unit for reconstructing a low spatial resolution T2 parametric map based on the at least one low spatial resolution T2 weighted image.
In an embodiment, the second reconstructing unit is specifically configured to fit a signal intensity value of each pixel of at least one low spatial resolution T2 weighted image, and determine an obtained fit value as a T2 value of each pixel; and determining an image formed by expressing the pixel points by the T2 value as a low spatial resolution T2 parameter map.
In one embodiment, the first reconstruction module 11 includes: and the third reconstruction unit is used for inputting the k-space data set and the reconstruction parameters into a preset second reconstruction model to obtain a low spatial resolution T2 parameter map.
For specific limitations of the image reconstruction apparatus, reference may be made to the above limitations of the image reconstruction method, which are not described herein again. The modules in the image reconstruction device can be wholly or partially realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as shown in fig. 8. The computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The communication interface of the computer device is used for communicating with an external terminal in a wired or wireless manner, and the wireless manner can be realized through WIFI, an operator network, NFC (near field communication) or other technologies. The computer program is executed by a processor to implement an image reconstruction method. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, a key, a track ball or a touch pad arranged on the shell of the computer equipment, an external keyboard, a touch pad or a mouse and the like.
Those skilled in the art will appreciate that the architecture shown in fig. 8 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is provided, comprising a memory and a processor, the memory having a computer program stored therein, the processor implementing the following steps when executing the computer program:
acquiring a k-space data set of a target part, wherein the acquisition mode of the k-space data set is that the k-space center is completely sampled and the k-space edge is under-sampled;
reconstructing a low spatial resolution T2 parametric map based on the k-space dataset; the low spatial resolution represents a spatial resolution smaller than a first preset value;
reconstructing a high spatial resolution T2 parameter map according to the k-space data set and the low spatial resolution T2 parameter map; the high spatial resolution means a spatial resolution greater than the second preset value.
The implementation principle and technical effect of the computer device provided by the above embodiment are similar to those of the above method embodiment, and are not described herein again.
In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of:
acquiring a k-space data set of a target part, wherein the acquisition mode of the k-space data set is that the k-space center is completely sampled and the k-space edge is under-sampled;
reconstructing a low spatial resolution T2 parametric map based on the k-space dataset; the low spatial resolution represents a spatial resolution smaller than a first preset value;
reconstructing a high spatial resolution T2 parameter map according to the k-space data set and the low spatial resolution T2 parameter map; the high spatial resolution means a spatial resolution greater than the second preset value.
The implementation principle and technical effect of the computer-readable storage medium provided by the above embodiments are similar to those of the above method embodiments, and are not described herein again.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database or other medium used in the embodiments provided herein can include at least one of non-volatile and volatile memory. Non-volatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical storage, or the like. Volatile Memory can include Random Access Memory (RAM) or external cache Memory. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), among others.
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent application shall be subject to the appended claims.
Claims (10)
1. A method of image reconstruction, the method comprising:
acquiring a k-space data set of a target part, wherein the acquisition mode of the k-space data set is that the k-space center is completely sampled and the k-space edge is undersampled;
reconstructing a low spatial resolution T2 parametric map based on the k-space dataset; the low spatial resolution represents a spatial resolution smaller than a first preset value;
reconstructing a high spatial resolution T2 parameter map according to the k-space data set and the low spatial resolution T2 parameter map; the high spatial resolution represents a spatial resolution greater than a second preset value.
2. The method of claim 1, wherein reconstructing a high spatial resolution T2 parameter map from the k-space data set and the low spatial resolution T2 parameter map comprises:
inputting the k-space data set, the low spatial resolution T2 parameter map and the reconstruction parameters into a preset first reconstruction model to obtain the high spatial resolution T2 parameter map; the first reconstruction model comprises a reconstruction regular constraint term of the low spatial resolution T2 parameter map.
3. The method according to claim 2, wherein the obtaining of the first reconstruction model comprises:
constructing an objective function of an initial reconstruction model according to the k-space data set, the reconstruction parameters and the sparse parameters; the target function comprises a data fidelity term, a sparse regular constraint term and a reconstruction regular constraint term; the reconstruction regularization constraint term comprises a low spatial resolution T2 parameter map;
and minimizing the objective function, and iteratively optimizing the initial reconstruction model until a preset iteration condition is met to obtain the first reconstruction model.
4. A method according to any one of claims 1-3, wherein the k-space data set comprises N k-space data, the N k-space data having different T2 preparation times, the N being a positive integer.
5. The method according to any one of claims 1-3, wherein said reconstructing a low spatial resolution T2 parametric map based on said k-space dataset comprises:
reconstructing at least one low spatial resolution T2-weighted image from the k-space dataset;
reconstructing the low spatial resolution T2 parametric map based on the at least one low spatial resolution T2 weighted image.
6. The method according to claim 5, wherein said reconstructing said low spatial resolution T2 parametric map based on said at least one low spatial resolution T2 weighted image comprises:
fitting the signal intensity value of each pixel point of the at least one low spatial resolution T2 weighted image, and determining the obtained fitting value as the T2 value of each pixel point;
and determining an image formed by all the pixel points after the T2 value is represented as the low spatial resolution T2 parameter map.
7. The method according to claim 5, wherein said reconstructing said low spatial resolution T2 parameter map based on said at least one low spatial resolution T2 weighted image comprises:
and inputting the k-space data set and the reconstruction parameters into a preset second reconstruction model to obtain the low spatial resolution T2 parameter map.
8. An image reconstruction apparatus, characterized in that the apparatus comprises:
the data acquisition module is used for acquiring a k-space data set of a target part, wherein the acquisition mode of the k-space data set is that the k-space center is fully sampled and the k-space edge is under-sampled;
a first reconstruction module for reconstructing a low spatial resolution T2 parametric map based on the k-space dataset;
and the second reconstruction module is used for reconstructing a high spatial resolution T2 parameter map according to the k-space data set and the low spatial resolution T2 parameter map.
9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor, when executing the computer program, implements the steps of the method of any of claims 1 to 7.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110528230.5A CN115345950A (en) | 2021-05-14 | 2021-05-14 | Image reconstruction method and device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110528230.5A CN115345950A (en) | 2021-05-14 | 2021-05-14 | Image reconstruction method and device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115345950A true CN115345950A (en) | 2022-11-15 |
Family
ID=83946471
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110528230.5A Pending CN115345950A (en) | 2021-05-14 | 2021-05-14 | Image reconstruction method and device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115345950A (en) |
-
2021
- 2021-05-14 CN CN202110528230.5A patent/CN115345950A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Tezcan et al. | MR image reconstruction using deep density priors | |
| US20210295474A1 (en) | Methods and system for selective removal of streak artifacts and noise from images using deep neural networks | |
| US8879852B2 (en) | Non-contrast-enhanced 4D MRA using compressed sensing reconstruction | |
| US8823374B2 (en) | System for accelerated MR image reconstruction | |
| CN113344799A (en) | System and method for reducing colored noise in medical images using deep neural networks | |
| US10895622B2 (en) | Noise suppression for wave-CAIPI | |
| WO2020114329A1 (en) | Fast magnetic resonance parametric imaging and device | |
| CN109658468B (en) | Magnetic resonance parameter imaging method, device, equipment and storage medium | |
| Liu et al. | High-performance rapid MR parameter mapping using model-based deep adversarial learning | |
| CN113924503B (en) | Parameter map determination for time domain magnetic resonance | |
| KR102428725B1 (en) | Method and program for imaging quality improving | |
| KR102584166B1 (en) | MAGNETIC RESONANCE IMAGE PROCESSING APPARATUS AND METHOD USING ARTIFICIAL NEURAL NETWORK AND RESCAlING | |
| CN114167334B (en) | Reconstruction method and device of magnetic resonance image and electronic equipment | |
| CN112037298A (en) | Image reconstruction method and device, computer equipment and storage medium | |
| Roy et al. | Fetal XCMR: a numerical phantom for fetal cardiovascular magnetic resonance imaging | |
| CN114529473A (en) | Image reconstruction method, image reconstruction device, electronic apparatus, storage medium, and computer program | |
| Ahn et al. | Quantitative susceptibility map reconstruction using annihilating filter‐based low‐rank Hankel matrix approach | |
| Yi et al. | Fast and Calibrationless low-rank parallel imaging reconstruction through unrolled deep learning estimation of multi-channel spatial support maps | |
| US20160054420A1 (en) | Compensated magnetic resonance imaging system and method for improved magnetic resonance imaging and diffusion imaging | |
| Chang et al. | Group feature selection for enhancing information gain in MRI reconstruction | |
| CN113050009B (en) | Three-dimensional magnetic resonance rapid parameter imaging method and device | |
| Ryu et al. | K-space refinement in deep learning mr reconstruction via regularizing scan specific spirit-based self consistency | |
| CN115345950A (en) | Image reconstruction method and device, computer equipment and storage medium | |
| JP2023069890A (en) | Magnetic resonance imaging device, image processing device, and image processing method | |
| CN111009020B (en) | Image reconstruction method, image reconstruction device, computer equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |