CN117607770B - Magnetic resonance image reconstruction method, device, electronic device and storage medium - Google Patents

Abstract

The present invention provides a magnetic resonance image reconstruction method, device, electronic device and storage medium. The method comprises: obtaining first three-dimensional contour space information and magnetic resonance scanning data of a scanned slice of a scanned object within a first specific field of view; processing the first three-dimensional contour space information to obtain processed first three-dimensional contour space information; inputting the processed first three-dimensional contour space information into a constructed coil sensitivity estimation model to obtain multi-channel coil sensitivity information corresponding to the scanned slice of the scanned object within the first specific field of view; and reconstructing a magnetic resonance image of the scanned object according to the multi-channel coil sensitivity information and the magnetic resonance scanning data.

Description

Magnetic resonance image reconstruction method, device, electronic device and storage medium

Technical Field

The present invention relates to the field of magnetic resonance image reconstruction, and in particular to a magnetic resonance image reconstruction method, device, electronic equipment and storage medium.

Background Art

Magnetic resonance imaging technology is a relatively mature imaging technology at present, especially magnetic resonance parallel imaging technology, which uses multiple receiving coils with unique sensitivity maps to collect information, accelerate data acquisition, and reduce imaging time.

Magnetic resonance parallel imaging technology can generally achieve image reconstruction based on methods such as image domain, K-space domain or hybrid domain. In the image domain-based method, additional scanning or pre-scanning is required to obtain accurate coil sensitivity maps, and then based on the accurate coil sensitivity maps, image reconstruction is flexibly combined with image priors (for example, image sparsity), but this will cause additional scanning time to be included in actual operations; the hybrid domain-based method requires K-space domain center calibration data, uses eigenvalue decomposition to derive coil sensitivity maps from truncated extracted subspaces, and performs mask operations to spatially define the image background area, but this method requires manual adjustment of thresholds to truncate subspaces and select eigenvalues to mask eigenvector maps. Different manually adjusted thresholds result in different derived coil sensitivity maps and different reconstructed image effects; the K-space-based method also requires K-space center calibration data, which limits the acceleration factor and is not conducive to combining prior knowledge of image sparsity.

Summary of the invention

In view of this, the present invention provides a magnetic resonance image reconstruction method, device, electronic device and storage medium.

One aspect of the present invention provides a magnetic resonance image reconstruction method, comprising: obtaining first three-dimensional contour space information and magnetic resonance scanning data of a scanned slice of a scanned object within a first specific field of view; processing the first three-dimensional contour space information to obtain processed first three-dimensional contour space information; inputting the processed first three-dimensional contour space information into a constructed coil sensitivity estimation model to obtain multi-channel coil sensitivity information corresponding to the scanned slice of the scanned object within the first specific field of view; and reconstructing a magnetic resonance image of the scanned object based on the multi-channel coil sensitivity information and the magnetic resonance scanning data.

Optionally, before acquiring first three-dimensional contour space information and magnetic resonance scanning data of scanned slices of the scanned object within the first specific field of view, the method also includes: determining a first transformation matrix between a coordinate system of a second specific field of view and a coordinate system of the first specific field of view, wherein the first transformation matrix is applied to acquiring first three-dimensional contour space information of scanned slices of the scanned object within the first specific field of view.

Optionally, determining a first transformation matrix between a coordinate system of a second specific field of view and a coordinate system of a first specific field of view includes: obtaining first position information of a target object in a registration device within the second specific field of view, where the target object is a marker that can be identified by magnetic resonance scanning; scanning the target object in the registration device within the first specific field of view using a preset gradient scanning direction to obtain a scanned image corresponding to the target object; performing connected domain detection processing on the scanned image to obtain second position information corresponding to the scanned image; and determining a first transformation matrix between a coordinate system of the second specific field of view and a coordinate system of the first specific field of view based on the first position information and the second position information.

Optionally, obtaining first three-dimensional contour space information of scanned slices of the scanned object within a first specific field of view includes: obtaining three-dimensional contour space reference information of the scanned object within a second specific field of view; determining first positioning information of the scanned slices of the scanned object within the first specific field of view; determining second three-dimensional contour space information of the scanned slices of the scanned object within the second specific field of view based on the first positioning information and the three-dimensional contour space reference information; and converting the second three-dimensional contour space information to obtain first three-dimensional contour space information of the scanned slices of the scanned object within the first specific field of view.

Optionally, based on the first positioning information and the three-dimensional contour space reference information, second three-dimensional contour space information of the scanned slices of the scanned object within the second specific field of view is determined, including: based on the first positioning information and the first transformation matrix, second positioning information corresponding to the first positioning information is extracted from the three-dimensional contour space reference information, wherein the first transformation matrix is determined by the coordinate system of the second specific field of view and the coordinate system of the first specific field of view, and the second positioning information is information of the scanned slices of the scanned object within the second specific field of view; based on the second positioning information, second three-dimensional contour space information of the scanned slices of the scanned object within the second specific field of view is determined.

Optionally, the first three-dimensional contour space information is processed to obtain the processed first three-dimensional contour space information, including: determining a second conversion matrix between the first three-dimensional contour space information of the scanned slice and the spatial information of the target scanning range; obtaining third three-dimensional contour space information corresponding to the first three-dimensional contour space information based on the second conversion matrix and the first three-dimensional contour space information, wherein the third three-dimensional contour space information characterizes the uniqueness of the three-dimensional contour space information of the scanned slice of the scanned object within the first specific field of view; and performing data analysis processing on the third three-dimensional contour space information to obtain the processed first three-dimensional contour space information.

Optionally, the processed first three-dimensional contour space information is input into the constructed coil sensitivity estimation model to obtain multi-channel coil sensitivity information corresponding to the scanned slices of the scanned object within a specific field of view, including: obtaining the multi-channel coil sensitivity information corresponding to the scanned slices of the scanned object within a specific field of view based on the first characteristic matrix information, the second characteristic matrix information and the first three-dimensional contour space information, wherein the first characteristic matrix is determined by historical multi-channel sensitivity information, and the second characteristic matrix is determined by historical first three-dimensional contour space information.

Another aspect of the present invention provides a magnetic resonance image reconstruction device, comprising: an acquisition module, used to acquire first three-dimensional contour space information and magnetic resonance scanning data of a scanned slice of a scanned object within a first specific field of view; a processing module, used to process the first three-dimensional contour space information to obtain processed first three-dimensional contour space information; an input module, used to input the processed first three-dimensional contour space information into a constructed coil sensitivity estimation model to obtain multi-channel coil sensitivity information corresponding to the scanned slice of the scanned object within the first specific field of view; and a reconstruction module, used to reconstruct a magnetic resonance image of the scanned object based on the multi-channel coil sensitivity information and the magnetic resonance scanning data.

Another aspect of the present invention provides an electronic device, comprising: one or more processors; and a memory for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors execute the above method.

Another aspect of the present invention provides a computer-readable storage medium storing computer-executable instructions, which are used to implement the above method when executed.

Another aspect of the present invention provides a computer program product, which includes computer executable instructions, and the instructions are used to implement the above method when executed.

By inputting the obtained first three-dimensional contour space information into the constructed coil sensitivity estimation model, the multi-channel coil sensitivity information corresponding to the scan slice of the scanned object within the first specific field of view is obtained; and the magnetic resonance image of the scanned object is reconstructed according to the multi-channel coil sensitivity information and the magnetic resonance scanning data. It is achieved that the multi-channel coil sensitivity information corresponding to the scan slice within the first specific field of view can be quickly obtained by using the constructed coil sensitivity estimation model without the need for a central calibration area, and the image of the scanned object can be quickly reconstructed based on the obtained multi-channel coil sensitivity information, thereby reducing the scanning time in actual operation and improving the reconstruction speed of the non-calibrated magnetic resonance image.

BRIEF DESCRIPTION OF THE DRAWINGS

The above and other objects, features and advantages of the present invention will become more apparent through the following description of the embodiments of the present invention with reference to the accompanying drawings, in which:

FIG1 shows an exemplary system architecture to which a magnetic resonance image reconstruction method and apparatus may be applied according to an embodiment of the present invention;

FIG2 shows a flow chart of a magnetic resonance image reconstruction method according to an embodiment of the present invention;

FIG3 shows a three-dimensional schematic diagram of a scan slice profile according to an embodiment of the present invention;

FIG4( a ) shows a schematic diagram of a VTK coordinate system of a scanned object according to an embodiment of the present invention;

FIG4( b ) is a schematic diagram showing a plane profile of a scanned object according to an embodiment of the present invention;

FIG5 shows a schematic diagram of a registration device according to an embodiment of the present invention;

FIG6 shows a schematic diagram of a process of determining a first conversion matrix according to an embodiment of the present invention;

FIG7 shows a flow chart of a method for obtaining first three-dimensional contour space information according to an embodiment of the present invention;

FIG8 shows a block diagram of a magnetic resonance image reconstruction apparatus according to an embodiment of the present invention; and

FIG. 9 shows a block diagram of an electronic device suitable for implementing a magnetic resonance image reconstruction method according to an embodiment of the present invention.

DETAILED DESCRIPTION

Below, embodiments of the present invention will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the present invention. In the following detailed description, for ease of explanation, many specific details are set forth to provide a comprehensive understanding of embodiments of the present invention. However, it is apparent that one or more embodiments may also be implemented without these specific details. In addition, in the following description, descriptions of known structures and technologies are omitted to avoid unnecessary confusion of concepts of the present invention.

The terms used herein are only for describing specific embodiments and are not intended to limit the present invention. The terms "comprise", "include", etc. used herein indicate the existence of features, steps, operations and/or components, but do not exclude the existence or addition of one or more other features, steps, operations or components.

All terms (including technical and scientific terms) used herein have the meanings commonly understood by those skilled in the art unless otherwise defined. It should be noted that the terms used herein should be interpreted as having a meaning consistent with the context of this specification and should not be interpreted in an idealized or overly rigid manner.

When using expressions such as "at least one of A, B, and C, etc.", they should generally be interpreted according to the meaning of the expression commonly understood by those skilled in the art (for example, "a system having at least one of A, B, and C" should include but is not limited to a system having A alone, B alone, C alone, A and B, A and C, B and C, and/or A, B, C, etc.).

In the embodiments of the present invention, the collection, updating, analysis, processing, use, transmission, provision, invention, storage and other aspects of the data involved (for example, including but not limited to user personal information) are in compliance with the provisions of relevant laws and regulations, are used for legitimate purposes, and do not violate public order and good morals. In particular, necessary measures are taken for user personal information to prevent illegal access to user personal information data and maintain the security of user personal information and network security.

In the embodiment of the present invention, before obtaining or collecting the user's personal information, the user's authorization or consent is obtained.

An embodiment of the present invention provides a magnetic resonance image reconstruction method, comprising: acquiring first three-dimensional contour space information and magnetic resonance scanning data of a scanned slice of a scanned object within a first specific field of view; processing the first three-dimensional contour space information to obtain processed first three-dimensional contour space information; inputting the processed first three-dimensional contour space information into a constructed coil sensitivity estimation model to obtain multi-channel coil sensitivity information corresponding to the scanned slice of the scanned object within the first specific field of view; and reconstructing a magnetic resonance image of the scanned object according to the multi-channel coil sensitivity information and the magnetic resonance scanning data.

FIG1 shows an exemplary system architecture to which the magnetic resonance image reconstruction method and apparatus can be applied according to an embodiment of the present invention. It should be noted that FIG1 is only an example of a system architecture to which the embodiment of the present invention can be applied, to help those skilled in the art understand the technical content of the present invention, but does not mean that the embodiment of the present invention cannot be used in other devices, systems, environments or scenarios.

As shown in Fig. 1, the system architecture according to this embodiment may include a magnetic resonance imaging device 101, a first terminal device 102, a second terminal device 103, a network 104 and a server 105. The network 104 is used to provide a medium for communication links between the magnetic resonance imaging device 101, the first terminal device 102, the second terminal device 103 and the server 105. The network 104 may include various connection types, such as wired and/or wireless communication links, etc.

The magnetic resonance imaging device 101 generates a specific signal for detection, and transmits the specific signal to the first terminal device 102 and the second terminal device 103 through a receiving coil (not shown in the figure) in the magnetic resonance imaging device. The first terminal device 102 and the second terminal device 103 interact with the server 105 through the network 104 to receive or send messages, etc. Various communication client applications may be installed on the first terminal device 102 and the second terminal device 103, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients and/or social platform software, etc. (only as examples).

The first terminal device 102 and the second terminal device 103 may be various electronic devices having display screens and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, desktop computers, and the like.

The server 105 may be a server that provides various services, such as a background management server (only as an example) that provides support for websites browsed by users using the first terminal device 102 and the second terminal device 103. The background management server may analyze and process received data such as user requests, and feed back processing results (such as web pages, information, or data obtained or generated according to user requests) to the terminal device.

It should be noted that the magnetic resonance image reconstruction method provided in the embodiment of the present invention can generally be executed by the server 105. Accordingly, the magnetic resonance image reconstruction device provided in the embodiment of the present invention can generally be set in the server 105. The magnetic resonance image reconstruction method provided in the embodiment of the present invention can also be executed by a server or server cluster that is different from the server 105 and can communicate with the first terminal device 102, the second terminal device 103 and/or the server 105. Accordingly, the magnetic resonance image reconstruction device provided in the embodiment of the present invention can also be set in a server or server cluster that is different from the server 105 and can communicate with the first terminal device 102, the second terminal device 103 and/or the server 105. Alternatively, the magnetic resonance image reconstruction method provided in the embodiment of the present invention can also be executed by the first terminal device 102 or the second terminal device 103, or can also be executed by other terminal devices different from the first terminal device 102 or the second terminal device 103. Accordingly, the magnetic resonance image reconstruction device provided in the embodiment of the present invention can also be set in the first terminal device 102 or the second terminal device 103, or can be set in other terminal devices different from the first terminal device 102 or the second terminal device 103.

It should be understood that the number of terminal devices, networks and servers in Figure 1 is only illustrative. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

FIG. 2 shows a flow chart of a magnetic resonance image reconstruction method according to an embodiment of the present invention.

As shown in FIG. 2 , the method includes operations S210 to S240 .

In operation S210, first three-dimensional contour space information and magnetic resonance scanning data of a scanned slice of a scanned object within a first specific field of view are acquired.

According to an embodiment of the present invention, the scanning object can be a human body, an animal, or a specified area, such as a specific part of the body, for example, the head, chest, abdomen, or any combination thereof, which is not limited in the present invention.

According to an embodiment of the present invention, the scan slice may be obtained by slicing an image corresponding to the scan object through high-speed scanning.

FIG. 3 shows a three-dimensional schematic diagram of a scan slice contour according to an embodiment of the present invention.

As shown in Figure 3, taking the head of a scanned object as an example, a schematic diagram of the three-dimensional data of the scan slice for the head contour is obtained. In different directions, the contour three-dimensional data of multiple scan slices can be obtained respectively. A scanned object can have multiple scan slices.

According to an embodiment of the present invention, the first specific field of view range may be a scanning area selected by an operator where the scanning object needs to be scanned, and may be considered as a FOV (field of view) range selected by the operator.

According to an embodiment of the present invention, the first three-dimensional contour space information may be contour space information of a scan slice of the scan object obtained within the first specific field of view in VTK (The Visualization Toolkit) coordinates.

For example, FIG. 4( a ) shows a schematic diagram of a VTK coordinate system of a scanned object according to an embodiment of the present invention; and FIG. 4( b ) shows a schematic diagram of a plane contour of a scanned object according to an embodiment of the present invention.

Combining Figures 4 (a) and 4 (b), we can see that the center of the scanned object is taken as the origin, the direction of the left side of the scanned object is taken as the positive direction of the X axis, the direction behind the scanned object is taken as the positive direction of the Y axis, and the direction of the head of the scanned object is taken as the positive direction of the Z axis. In the VTK coordinate system, the X-Y plane in Figure 4 (a) corresponds to the L-P plane in Figure 4 (b), the X-Z plane in Figure 4 (a) corresponds to the L-S plane in Figure 4 (b), and the Y-Z plane in Figure 4 (a) corresponds to the P-S plane in Figure 4 (b).

According to an embodiment of the present invention, the magnetic resonance scanning data may be under-sampling data and under-sampling mode data collected when the scanning object is scanned.

In operation S220, the first three-dimensional contour space information is processed to obtain processed first three-dimensional contour space information.

In operation S230, the processed first three-dimensional contour space information is input into the constructed coil sensitivity estimation model to obtain multi-channel coil sensitivity information corresponding to the scan slice of the scanned object within the first specific field of view.

According to an embodiment of the present invention, the first three-dimensional contour space information can be transformed into a maximum scanning range coordinate system, so that contour information of a scanned slice of any scanned object can be represented by the first three-dimensional contour space information in the maximum scanning range coordinate system.

According to an embodiment of the present invention, the first three-dimensional contour space information converted to the maximum scanning range coordinate system is converted into an input signal recognizable by the constructed coil sensitivity estimation model, thereby obtaining the processed first three-dimensional contour space information.

According to an embodiment of the present invention, the coil sensitivity estimation model can quickly obtain multi-channel coil sensitivity information by processing the input first three-dimensional contour space information.

According to an embodiment of the present invention, for each scan slice of the scanned object, a multi-channel coil sensitivity information can be obtained through the coil sensitivity estimation model. The multi-channel coil sensitivity information can characterize the response degree of the receiving coil to the input signal. The higher the value, the stronger the ability to detect weak signals.

In operation S240, a magnetic resonance image is reconstructed for the scanned object according to the multi-channel coil sensitivity information and the magnetic resonance scan data.

According to an embodiment of the present invention, the constructed coil sensitivity estimation model is used to quickly obtain multi-channel coil sensitivity information of a scan slice, and image reconstruction can be performed in combination with magnetic resonance scan data to obtain a final reconstructed image.

According to an embodiment of the present invention, the magnetic resonance scanning data may include undersampling data y , undersampling mode data P , and the multi-channel coil sensitivity information may be expressed as C. The reconstructed image may be determined using the following formula, that is, formula (1):

(1);

Where F is the Fourier transform, Ψ is the sparse transform, and m is the desired reconstructed image.

According to an embodiment of the present invention, the obtained first three-dimensional contour space information is input into the constructed coil sensitivity estimation model to obtain the multi-channel coil sensitivity information corresponding to the scan slice of the scanned object within the first specific field of view; and the magnetic resonance image of the scanned object is reconstructed according to the multi-channel coil sensitivity information and the magnetic resonance scanning data. It is achieved that the multi-channel coil sensitivity information corresponding to the scan slice within the first specific field of view can be quickly obtained by using the constructed coil sensitivity estimation model without the need for a central calibration area, and the image of the scanned object can be quickly reconstructed based on the obtained multi-channel coil sensitivity information, thereby reducing the scanning time in actual operation and improving the reconstruction speed of the non-calibrated magnetic resonance image.

According to an embodiment of the present invention, before acquiring first three-dimensional contour space information and magnetic resonance scanning data of scanned slices of the scanned object within a first specific field of view, the method also includes: determining a first transformation matrix between a coordinate system of a second specific field of view and a coordinate system of the first specific field of view, wherein the first transformation matrix is applied to acquiring first three-dimensional contour space information of scanned slices of the scanned object within the first specific field of view.

According to an embodiment of the present invention, determining a first transformation matrix between a coordinate system of a second specific field of view and a coordinate system of a first specific field of view includes: acquiring first position information of a target object in a registration device within the second specific field of view, where the target object is a marker that can be identified by magnetic resonance scanning; scanning the target object in the registration device within the first specific field of view using a preset gradient scanning direction to acquire a scanned image corresponding to the target object; performing connected domain detection processing on the scanned image to obtain second position information corresponding to the scanned image; and determining a first transformation matrix between the coordinate system of the second specific field of view and the coordinate system of the first specific field of view based on the first position information and the second position information.

According to an embodiment of the present invention, the second specific field of view may be a scanning area of the scanned object under the depth camera device. The coordinate system of the second specific field of view may be a coordinate system of the scanned object under the depth camera device, which may be referred to as the "depth camera device coordinate system" hereinafter.

According to an embodiment of the present invention, the depth camera device may be a magnetically compatible depth camera device, for example, a depth camera, a depth still camera, etc., and the present invention is not limited thereto.

According to an embodiment of the present invention, the first conversion matrix may be a matrix for converting from the depth camera device coordinate system to the VTK coordinate system, so as to achieve registration between the depth camera device coordinate system and the VTK coordinate system.

According to an embodiment of the present invention, the operation may determine the first transformation matrix based on a registration device pre-set on the magnetic resonance imaging device.

For example, FIG5 shows a schematic diagram of a registration device according to an embodiment of the present invention.

As shown in FIG5 , the registration device 500 is composed of a registration object 501, a depth camera device 502 and a marker 503. The depth camera device 502 is embedded in a special registration object 501, and a plurality of markers 503 that can be scanned and identified by a magnetic resonance imaging device 504 are also embedded in the registration object 501, wherein the registration object 501 is used as a reference object, and the relative positions between the depth camera device 502 and the plurality of markers 503 are fixed. The registration device 500 can be fixed in the scanning cavity of the magnetic resonance imaging device 504.

According to an embodiment of the present invention, the registration object may be a device having a specific shape, for example, a device in the shape of a cuboid or a cube, and the marker may be a copper sulfate solution.

According to an embodiment of the present invention, the target object may be a marker in the registration device that can be scanned and identified by a magnetic resonance imaging device. The marker is embedded on the registration object and has a relatively fixed position with the depth camera on the registration object. The coordinates of the target object within the field of view of the depth camera can be obtained in advance, that is, the first position information within the second specific field of view, which can be expressed as MarksInCamera .

According to an embodiment of the present invention, the registration device can be fixed _in the scanning cavity of the magnetic _resonance imaging device, and the target object in the registration device can be scanned within a first specific field of view by using a transceiver-in-one coil through a preset gradient scanning direction ( Gx , Gy , Gz ), _so that a scanned image corresponding to the target object can be obtained.

According to an embodiment of the present invention, the scanned image corresponding to the target object may be a background noise image in which the target object is a bright spot.

According to an embodiment of the present invention, the connected domain detection process may be Blob detection, and the coordinates of the target object in the VTK coordinate system may be obtained by performing Blob detection on the background noise image, that is, the second position information within the first specific field of view, which may be expressed as MarksInVTK .

According to an embodiment of the present invention, a first transformation matrix between a coordinate system of a second specific field of view and a coordinate system of a first specific field of view can be determined based on the first position information MarksInCamera of the target object and the second position information MarksInVTK of the target object. The first transformation matrix can be expressed as CameraToVTK . Specifically, it can be obtained by the following formula (2), that is:

(2);

Here, vtkClassTrf represents a function for solving a first transformation matrix between a coordinate system of the second specific field of view and a coordinate system of the first specific field of view.

FIG. 6 shows a schematic diagram of a process of determining a first conversion matrix according to an embodiment of the present invention.

As shown in combination with FIG. 5 and FIG. 6 , in the registration device, the registration object 601 can be used as a reference object. Based on the relative fixed position of the marker 602 on the registration object and the depth camera 603, the coordinates of the marker within the field of view of the depth camera can be obtained in advance, that is, the first position information 604 within the second specific field of view, which can be expressed as Marks InCamera . The registration device can be fixed in the scanning cavity of the magnetic resonance imaging device, and a specific gradient scanning direction is set by using the transceiver integrated coil to perform FOV scanning on the marker 602, and obtain a background noise image with the marker as a bright spot, that is, a scanned image 605 corresponding to the marker. The scanned image 605 is processed by connected domain detection to obtain the coordinates of the marker in the VTK coordinate system, that is, the second position information 606 within the first specific field of view, which can be expressed as Marks InVTK . According to the first position information 604 and the second position information 606, the first conversion matrix 607 between the coordinate system of the second specific field of view and the coordinate system of the first specific field of view is determined.

FIG. 7 shows a flow chart of a method for acquiring first three-dimensional contour space information according to an embodiment of the present invention.

As shown in FIG. 7 , the method includes operations S710 to S740 .

In operation S710, three-dimensional contour space reference information of a scan object within a second specific field of view is acquired.

In operation S720, first positioning information of a scan slice of the scan object within a first specific field of view is determined.

In operation S730, second three-dimensional contour space information of a scanned slice of the scanned object within a second specific field of view is determined according to the first positioning information and the three-dimensional contour space reference information.

In operation S740, the second three-dimensional contour space information is converted to obtain first three-dimensional contour space information of a scanned slice of the scanned object within a first specific field of view.

According to an embodiment of the present invention, the second specific field of view may be a scannable area under the depth camera device. The three-dimensional contour space reference information may be three-dimensional surface contour space information of the scanned object.

According to an embodiment of the present invention, the three-dimensional contour spatial reference information can be obtained by capturing the scanned object through a registered depth camera installed in a magnetic resonance imaging device.

According to an embodiment of the present invention, the first specific field of view may be a scannable area selected under VTK coordinates. The scanning area for scanning slices under VTK coordinates may be determined according to the detected part of the scanned object, that is, the first positioning information.

According to an embodiment of the present invention, the second three-dimensional contour space information of the scanned slice in the depth camera device coordinate system can be obtained based on the first positioning information of the scanned slice in the VTK coordinate system, which can be expressed as SpatialContourInCamera . The second three-dimensional contour space information represents the cross-sectional space information of the scanned slice in the depth camera device.

According to an embodiment of the present invention, the second three-dimensional contour space information can be transformed based on the first transformation matrix to obtain the first three-dimensional contour information of the scanned slice of the scanned object within the first specific field of view. The first three-round contour information can be expressed as SpatialContour . Specifically, it can be obtained by formula (3), that is:

(3);

Among them, CameraToVTK is the first transformation matrix.

According to an embodiment of the present invention, second three-dimensional contour space information of scanned slices of a scanned object within a second specific field of view is determined based on first positioning information and three-dimensional contour space reference information, including: extracting second positioning information corresponding to the first positioning information from the three-dimensional contour space reference information based on the first positioning information and a first transformation matrix, wherein the first transformation matrix is determined by a coordinate system of the second specific field of view and a coordinate system of the first specific field of view, and the second positioning information is information of scanned slices of the scanned object within the second specific field of view; and determining second three-dimensional contour space information of scanned slices of the scanned object within the second specific field of view based on the second positioning information.

According to an embodiment of the present invention, the scan slice may be a slice having a regular shape, for example, a rectangle. Taking a single scan slice as an example, the first positioning information of the scan slice may include positioning information of the scan slice within a first specific field of view, and the positioning information may include a scan center point ( ScanCenter ), a frequency encoding direction ( FreqDir ) during scanning, a phase encoding direction ( PhaseDir ) during scanning, and a scan length ( FOVLength ), wherein the scan length ( FOVLength ) may include a scan length ( FreqLength ) in a frequency encoding direction and a scan length ( PhaseLength ) in a phase encoding direction.

According to an embodiment of the present invention, the first conversion matrix may be inversely processed to obtain an inverse matrix of the first conversion matrix, which may be expressed as CameraToVTK ⁻¹ .

According to an embodiment of the present invention, the second positioning information may be coordinate information of a cross section of a scan slice within a second specific field of view when the scan object is scanned.

According to an embodiment of the present invention, the inverse matrix of the first transformation matrix can be used to determine the second positioning information of the cross section of the scan slice within the second specific field of view corresponding to the first positioning information, wherein the first positioning information can be the information of the scan slice in the VTK coordinate system when the scan object is scanned. Specifically, it can be obtained by the following formulas (4) to (7), that is:

(4);

(5);

(6);

(7);

Among them, ScanCenterInCamera is the scanning center point converted to the second specific field of view; FreqDirInCamera is the frequency encoding direction converted to the second specific field of view; PhaseDirInCamera is the phase encoding direction converted to the second specific field of view; FOVLength is the scanning length in the second specific field of view.

According to an embodiment of the present invention, the second positioning information may include positioning information of four positions of the scanned slice section within the second specific field of view. For example, the positioning information of the four positions may include upper left corner positioning information, lower left corner positioning information, upper right corner positioning information, and lower right corner positioning information.

According to an embodiment of the present invention, a single scan slice can be taken as an example. For example, the positioning information of the upper left corner of the cut section corresponding to the scan slice within the second specific field of view can be obtained by the following formulas (8) to (10), that is:

(8);

(9);

(10);

Among them, TopLeftCorner [0] is the X-axis coordinate information of the upper left corner; TopLeftCorner [1] is the Y-axis coordinate information of the upper left corner; TopLeftCorner [2] is the Z-axis coordinate information of the upper left corner.

According to an embodiment of the present invention, for example, the positioning information of the lower left corner of the cut section corresponding to the scan slice within the second specific field of view can be obtained by the following formulas (11) to (13), that is:

(11);

(12);

(13);

Among them, BottomLeftCorner [0] is the X-axis coordinate information of the lower left corner; BottomLeftCorner [1] is the Y-axis coordinate information of the lower left corner; BottomLeftCorner [2] is the Z-axis coordinate information of the lower left corner.

According to an embodiment of the present invention, for example, the positioning information of the upper right corner of the cut section corresponding to the scan slice within the second specific field of view can be obtained by the following equations (14) to (16), that is:

(14);

(15);

(16);

Among them, TopRightCorner [0] is the X-axis coordinate information of the upper right corner; TopRightCorner [1] is the Y-axis coordinate information of the upper right corner; TopRightCorner [2] is the Z-axis coordinate information of the upper right corner.

According to an embodiment of the present invention, for example, the positioning information of the lower right corner of the cut section corresponding to the scan slice within the second specific field of view can be obtained by the following equations (17) to (19), that is:

(17);

(18);

(19);

Among them, BottomRightCorner [0] is the X-axis coordinate information of the lower right corner; BottomRightCorner [1] is the Y-axis coordinate information of the lower right corner; BottomRightCorner [2] is the Z-axis coordinate information of the lower right corner.

According to an embodiment of the present invention, the positioning information of the four orientations of the cross section of the scanned slice obtained above can be extracted from the three-dimensional contour space reference information to obtain the second positioning information.

According to an embodiment of the present invention, second three-dimensional contour spatial information of a scan slice of the scanned object within a second specific field of view may be acquired through the second positioning information, which may be represented as SpatialContourInCamera .

According to an embodiment of the present invention, the first three-dimensional contour space information is processed to obtain the processed first three-dimensional contour space information, including: determining a second transformation matrix between the first three-dimensional contour space information of the scanned slice and the spatial information of the target scanning range; obtaining third three-dimensional contour space information corresponding to the first three-dimensional contour space information based on the second transformation matrix and the first three-dimensional contour space information, wherein the third three-dimensional contour space information represents the uniqueness of the three-dimensional contour space information of the scanned slice of the scanned object within the first specific field of view; performing data analysis processing on the third three-dimensional contour space information to obtain the processed first three-dimensional contour space information.

According to an embodiment of the present invention, the target scanning range may be a maximum scanning range that can uniquely represent the first three-dimensional contour space information of any scanned object.

According to an embodiment of the present invention, the second conversion matrix may be a matrix for converting the first three-dimensional contour space information into a coordinate system of the target scanning range, and may be expressed as TrfToLargestRegion .

According to an embodiment of the present invention, based on the second transformation matrix, the first three-dimensional contour space information can be transformed into the maximum scanning range coordinate system by translation, and the third three-dimensional contour space information corresponding to the first three-dimensional contour space information can be obtained, which can be expressed as UniqueSpatialContour . The third three-dimensional contour space information can characterize the uniqueness of the three-dimensional contour space information of the scanned slice of the scanned object within the first specific field of view. The third three-dimensional contour space information can be obtained by the following formula (20), that is:

(20);

According to the embodiment of the present invention, the third three-dimensional contour space information may be gridded and logicized to obtain an input substitute signal suitable for the constructed coil sensitivity estimation model.

According to an embodiment of the present invention, for example, Grid target scanning area (such as ), and compare the third 3D contour space information in the VTK coordinate system with the comparison coordinate system that is the same as the VTK coordinate system, set those that are not null to 1, and the rest to 0, and the first 3D contour space information after gridding and logic processing can be obtained, which can be expressed as S. Specifically, it can be obtained by the following formula (21), that is:

(twenty one);

Among them, Grid means gridding; Logical means logic.

According to an embodiment of the present invention, the processed first three-dimensional contour space information is input into a constructed coil sensitivity estimation model to obtain multi-channel coil sensitivity information corresponding to a scan slice of the scanned object within a specific field of view, including: obtaining multi-channel coil sensitivity information corresponding to a scan slice of the scanned object within a specific field of view based on first characteristic matrix information, second characteristic matrix information and first three-dimensional contour space information, wherein the first characteristic matrix is determined by historical multi-channel sensitivity information, and the second characteristic matrix is determined by historical first three-dimensional contour space information.

According to an embodiment of the present invention, the first characteristic matrix information may be determined in the process of building a coil sensitivity estimation model based on historical multi-channel coil sensitivities, and may be expressed as EC _; the second characteristic matrix information may be determined in the process of building a coil sensitivity estimation model based on historical first three-dimensional contour space information, and may be expressed as E _S.

According to an embodiment of the present invention, the first characteristic matrix information, the second characteristic matrix information and the first three-dimensional contour space information can be used to obtain the multi-channel coil sensitivity information corresponding to the scan slice of the scanned object within a specific field of view. Specifically, it can be obtained by the following formula (22), that is:

(twenty two);

Among them, S is the first three-dimensional contour space information, C is the multi-channel coil sensitivity information _{, EC is the first characteristic matrix information, that is, the characteristic matrix information of the multi-channel coil sensitivity information corresponding to the scan slice; ES} is _the second characteristic matrix information, that is, the characteristic matrix information of the first three-dimensional contour space information corresponding to the scan slice.

According to an embodiment of the present invention, the constructed coil sensitivity estimation model may be constructed by the following method, thereby determining the first characteristic matrix information and the second characteristic matrix information.

According to an embodiment of the present invention, historical multi-channel coil sensitivity information of a scan slice of a scanned object within a first specific field of view is acquired.

According to an embodiment of the present invention, historical first three-dimensional contour space information of a scan slice of a scanned object within a first specific field of view is acquired.

According to an embodiment of the present invention, obtaining the historical first three-dimensional contour space information of the scanned slices of the scanned object within the first specific field of view is the same as the above-mentioned method of obtaining the historical first three-dimensional contour space information of the scanned slices of the scanned object within the first specific field of view, and the present invention will not be repeated here.

According to an embodiment of the present invention, the historical first three-dimensional contour space information of the scanned slices of the scanned object within the first specific field of view is obtained, including: obtaining the historical plane contour image of the scanned slices of the scanned object, performing morphological closing operation on the historical plane contour image to obtain the historical plane contour information of the scanned slices, determining a third conversion matrix from the historical plane contour information to the historical first three-dimensional contour space information under VTK coordinates, and obtaining the historical first three-dimensional contour space information of the scanned slices of the scanned object within the first specific field of view according to the third conversion matrix of the historical first three-dimensional contour space information and the historical plane contour information.

According to an embodiment of the present invention, the third transformation matrix can be obtained according to the historical scanning origin ( Origin ), historical scanning distance ( Spacing ) and historical scanning direction ( Orientation ) in the image standard format information in the historical plane contour image using formula (23), that is:

(twenty three);

Among them, IndexToVTK is a third conversion matrix for converting the historical plane contour information into the historical first three-dimensional contour space information under VTK coordinates.

According to an embodiment of the present invention, the historical first three-dimensional contour space information of the scanned slice of the scanned object within the first specific field of view can be obtained using the following formula (24), that is:

(twenty four);

Among them, SpatialContour¢ is the historical first three-dimensional contour spatial information; Contour is the historical plane contour information.

According to an embodiment of the present invention, the historical first three-dimensional contour space information can be converted to the target scanning range coordinate system to obtain the historical third three-dimensional contour space information, and the historical third three-dimensional contour space information can be gridded and logically processed to obtain the processed historical first three-dimensional contour space information.

According to an embodiment of the present invention, the historical multi-channel coil sensitivity information obtained from the j -th scan slice is For example, historical multi-channel coil sensitivity information It can be expressed by the following formula (25):

(25);

Wherein, j is the jth scan slice, L is the total number of multi-channels corresponding to the jth scan slice; M is the total number of voxels on each channel coil; l is the lth channel corresponding to the jth scan slice; m is the value of the mth voxel on the lth channel; is the value of the mth voxel in the lth channel coil sensitivity information in the multi-channel coil sensitivity information corresponding to the jth scan slice; 1≤ j ≤ J , J represents the total number of scan slices, which is a positive integer greater than or equal to 1 ; 1≤ l ≤ L , 1≤ m ≤ M , L and M are both positive integers greater than or equal to 1.

According to an embodiment of the present invention, the historical first three-dimensional contour space information of the j -th scanning slice is used. For example, the first three-dimensional contour space information It can be expressed by the following formula (26):

(26);

Wherein, N is the total number of voxels in the historical first three-dimensional contour space information corresponding to the j -th scan slice; is the value of the nth voxel in the historical first three-dimensional contour space information corresponding to the jth scan slice; 1≤ n ≤ N; N is a positive integer greater than or equal to 1.

According to an embodiment of the present invention, the matrix corresponding to the j -th scan slice as shown in formula (27) can be constructed by using the above formulas (25) to (26): ,Right now:

(27);

According to an embodiment of the present invention, the total number of scan slices is J as an example, where J is a positive integer greater than or equal to 1. According to the above formula (27), the matrix P for constructing the coil sensitivity estimation model can be obtained as shown in the following formula (28):

(28);

in, ; ; To decentralize the matrix corresponding to the j -th scan slice; is the mean of the matrices corresponding to J scan slices.

According to the embodiment of the present invention, it can be known from the above equations (25) to (28) that the size of the matrix P for constructing the coil sensitivity estimation model can be .

According to an embodiment of the present invention, the covariance matrix can be constructed according to the matrix P. . Covariance matrix is semi-positive definite and its eigenvalues are non-negative. Since the covariance matrix The size is , so the eigenvalue decomposition cannot be performed directly;

According to an embodiment of the present invention, because ,so There are at most J -1 irrelevant eigenvectors.

According to an embodiment of the present invention, it can be assumed that There is an eigenvector X with eigenvalue λ , multiply PX by , we can get , so PX is The characteristic vector of can be expressed as formula (29), that is:

(29);

According to an embodiment of the present invention, the feature matrix E may characterize features of historical multi-channel coil sensitivity information and historical first three-dimensional contour space information corresponding to the scan slice.

According to an embodiment of the present invention, it can be assumed that the matrix corresponding to each scan slice is , you can use The weighted approximation of the eigenvectors corresponding to the first K largest eigenvalues can be expressed as formula (30), that is:

(30);

in, is the weighted value of the kth eigenvector object, is the kth eigenvector, 1≤ k ≤ K; K is a positive integer greater than or equal to 1.

According to an embodiment of the present invention, by combining the above equations (25) to (28) and equation (30), equations (31) to (33) can be obtained:

(31);

(32);

(33);

in, For the matrix Multi-channel coil sensitivity information in the middle forward row; For the matrix The first three-dimensional contour space information of the last N lines.

According to an embodiment of the present invention, based on the above equations (31) to (33), the following equations (34) to (35) can be obtained, namely:

(34);

(35);

Among them, W is the weighted value corresponding to the feature matrix E , which can be expressed as ; EC is the characteristic matrix information of the multi-channel coil _{sensitivity information corresponding to the scan slice; ES is} the characteristic matrix information of the first three-dimensional contour space information corresponding to the scan slice .

According to an embodiment of the _present invention, EC and _ES can be respectively derived from the front of the feature matrix E The coil sensitivity estimation model constructed by using the above equations (34) to (35) can be obtained, that is, as shown in the following equation (36):

(36);

That is, the above formula (22): (twenty two);

Among them, E _C is The inverse of E _S is The matrix of The matrix of .

According to an embodiment of the present invention, the model can be used to quickly obtain multi-channel coil sensitivity information corresponding to the scanned slice based on the first three-dimensional contour space information of the scanned slice of the scanned object within a first specific field of view, thereby quickly realizing image reconstruction.

FIG8 shows a block diagram of a magnetic resonance image reconstruction apparatus according to an embodiment of the present invention.

As shown in FIG. 8 , the apparatus may include: an acquisition module 810 , a processing module 820 , an input module 830 and a reconstruction module 840 .

The acquisition module 810 is used to acquire first three-dimensional contour space information and magnetic resonance scanning data of a scanned slice of a scanned object within a first specific field of view.

The processing module 820 is used to process the first three-dimensional contour space information to obtain processed first three-dimensional contour space information.

The input module 830 is used to input the processed first three-dimensional contour space information into the constructed coil sensitivity estimation model to obtain the multi-channel coil sensitivity information corresponding to the scan slice of the scanned object within the first specific field of view.

The reconstruction module 840 is used to reconstruct the magnetic resonance image of the scanned object according to the multi-channel coil sensitivity information and the magnetic resonance scanning data.

According to an embodiment of the present invention, the device further includes: a determination module.

A determination module is used to determine a first transformation matrix between a coordinate system of a second specific field of view and a coordinate system of a first specific field of view, wherein the first transformation matrix is used to obtain first three-dimensional contour space information of a scanned slice of a scanned object within the first specific field of view.

According to an embodiment of the present invention, the determination module may include: a first acquisition submodule, a scanning submodule, a first processing submodule and a first determination submodule.

The first acquisition submodule is used to acquire first position information of a target object in the registration device within a second specific field of view, where the target object is a marker that can be identified by magnetic resonance scanning.

The scanning submodule is used to scan the target object in the registration device within a first specific field of view using a preset gradient scanning direction to obtain a scanned image corresponding to the target object.

The first processing submodule is used to perform connected domain detection processing on the scanned image to obtain second position information corresponding to the scanned image.

The first determining submodule is used to determine a first conversion matrix between a coordinate system of the second specific visual field and a coordinate system of the first specific visual field according to the first position information and the second position information.

According to an embodiment of the present invention, the acquisition module 810 may include: a second acquisition submodule, a second determination submodule, a third determination submodule and a second processing submodule.

The second acquisition submodule is used to acquire the three-dimensional contour spatial reference information of the scanned object within a second specific field of view.

The second determining submodule is used to determine first positioning information of a scan slice of the scanned object within a first specific field of view.

The third determination submodule is used to determine second three-dimensional contour space information of a scanned slice of the scanned object within a second specific field of view according to the first positioning information and the three-dimensional contour space reference information.

The second processing submodule is used to convert the second three-dimensional contour space information to obtain the first three-dimensional contour space information of the scanned slice of the scanned object within the first specific field of view.

According to an embodiment of the present invention, the third determining submodule may include: an extracting unit and a determining unit.

An extraction unit is used to extract second positioning information corresponding to the first positioning information from the three-dimensional contour space reference information according to the first positioning information and the first transformation matrix, wherein the first transformation matrix is determined by the coordinate system of the second specific field of view and the coordinate system of the first specific field of view, and the second positioning information is information of the scanned slices of the scanned object within the second specific field of view.

The determination unit is used to determine the second three-dimensional contour space information of the scanned slice of the scanned object within the second specific field of view according to the second positioning information.

According to an embodiment of the present invention, the processing module 820 may include: a fourth determining submodule, a first obtaining submodule and a third processing submodule.

The fourth determination submodule is used to determine a second conversion matrix between the first three-dimensional contour space information of the scan slice and the space information of the target scanning range.

The first acquisition submodule is used to obtain third three-dimensional contour space information corresponding to the first three-dimensional contour space information according to the second transformation matrix and the first three-dimensional contour space information, wherein the third three-dimensional contour space information represents the uniqueness of the three-dimensional contour space information of the scanned slices within the first specific field of view of the scanned object.

The third processing submodule is used to perform data analysis and processing on the third three-dimensional contour space information to obtain processed first three-dimensional contour space information.

According to an embodiment of the present invention, the input module 830 may include: a second obtaining submodule.

The second acquisition submodule is used to obtain multi-channel coil sensitivity information corresponding to the scanned slice of the scanned object within a specific field of view based on the first characteristic matrix information, the second characteristic matrix information and the first three-dimensional contour space information, wherein the first characteristic matrix is determined by historical multi-channel sensitivity information, and the second characteristic matrix is determined by historical first three-dimensional contour space information.

According to the embodiments of the present invention, any multiple of the modules, submodules, and units, or at least part of the functions of any multiple of them can be implemented in one module. According to the embodiments of the present invention, any one or more of the modules, submodules, and units can be split into multiple modules for implementation. According to the embodiments of the present invention, any one or more of the modules, submodules, and units can be at least partially implemented as hardware circuits, such as field programmable gate arrays (FPGAs), programmable logic arrays (PLAs), systems on chips, systems on substrates, systems on packages, application specific integrated circuits (ASICs), or can be implemented by hardware or firmware in any other reasonable way of integrating or packaging the circuit, or by any one of the three implementation methods of software, hardware, and firmware, or by a suitable combination of any of them. Alternatively, according to the embodiments of the present invention, one or more of the modules, submodules, and units can be at least partially implemented as computer program modules, and when the computer program modules are run, the corresponding functions can be executed.

For example, any multiple of the acquisition module 810, the processing module 820, the input module 830, and the reconstruction module 840 may be combined in one module/unit/for implementation, or any one of the modules/units/may be split into multiple modules/units/. Alternatively, at least part of the functions of one or more of these modules/units/may be combined with at least part of the functions of other modules/units/and implemented in one module/unit/. According to an embodiment of the present invention, at least one of the acquisition module 810, the processing module 820, the input module 830, and the reconstruction module 840 may be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), a system on a chip, a system on a substrate, a system on a package, an application specific integrated circuit (ASIC), or may be implemented by hardware or firmware such as any other reasonable way of integrating or packaging the circuit, or implemented in any one of the three implementation modes of software, hardware, and firmware, or in a suitable combination of any of them. Alternatively, at least one of the acquisition module 810, the processing module 820, the input module 830 and the reconstruction module 840 may be at least partially implemented as a computer program module, and when the computer program module is executed, the corresponding function may be performed.

It should be noted that the magnetic resonance image reconstruction device part in the embodiment of the present invention corresponds to the magnetic resonance image reconstruction method part in the embodiment of the present invention. The description of the magnetic resonance image reconstruction device part specifically refers to the magnetic resonance image reconstruction method part, which will not be repeated here.

Fig. 9 shows a block diagram of an electronic device suitable for implementing a magnetic resonance image reconstruction method according to an embodiment of the present invention. The electronic device shown in Fig. 9 is only an example and should not bring any limitation to the functions and scope of use of the embodiment of the present invention.

As shown in Figure 9, the electronic device according to an embodiment of the present invention includes a processor 901, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 902 or the program loaded from the storage part 908 to the random access memory (RAM) 903. The processor 901 may include, for example, a general-purpose microprocessor (such as a CPU), an instruction set processor and/or a related chipset and/or a special-purpose microprocessor (for example, an application-specific integrated circuit (ASIC)), etc. The processor 901 may also include an onboard memory for caching purposes. The processor 901 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of the present invention.

In RAM 903, various programs and data required for the operation of the electronic device are stored. Processor 901, ROM 902, and RAM 903 are connected to each other via bus 904. Processor 901 performs various operations of the method flow according to the embodiment of the present invention by executing the program in ROM 902 and/or RAM 903. It should be noted that the program can also be stored in one or more memories other than ROM 902 and RAM 903. Processor 901 can also perform various operations of the method flow according to the embodiment of the present invention by executing the program stored in one or more memories.

According to an embodiment of the present invention, the electronic device may further include an input/output (I/O) interface 905, which is also connected to the bus 904. The system may further include one or more of the following components connected to the I/O interface 905: an input section 906 including a keyboard, a mouse, etc.; an output section 907 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 908 including a hard disk, etc.; and a communication section 909 including a network interface card such as a LAN card, a modem, etc. The communication section 909 performs communication processing via a network such as the Internet. A drive 910 is also connected to the I/O interface 905 as needed. A removable medium 911, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 910 as needed, so that a computer program read therefrom is installed into the storage section 908 as needed.

According to an embodiment of the present invention, the method flow according to an embodiment of the present invention can be implemented as a computer software program. For example, an embodiment of the present invention includes a computer program product, which includes a computer program carried on a computer-readable storage medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 909, and/or installed from the removable medium 911. When the computer program is executed by the processor 901, the above-mentioned functions defined in the system of the embodiment of the present invention are executed. According to an embodiment of the present invention, the system, equipment, device, module, unit, etc. described above can be implemented by a computer program module.

The present invention also provides a computer-readable storage medium, which may be included in the device/apparatus/system described in the above embodiment; or may exist independently without being assembled into the device/apparatus/system. The above computer-readable storage medium carries one or more programs, and when the above one or more programs are executed, the method according to the embodiment of the present invention is implemented.

According to an embodiment of the present invention, the computer-readable storage medium may be a non-volatile computer-readable storage medium. For example, it may include but is not limited to: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present invention, the computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, an apparatus or a device.

For example, according to an embodiment of the present invention, the computer-readable storage medium may include the ROM 902 and/or the RAM 903 described above and/or one or more memories other than the ROM 902 and the RAM 903 .

The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present invention. In this regard, each box in the flowchart or block diagram may represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of the code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box may also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions. It will be understood by those skilled in the art that the features recorded in the various embodiments of the present invention can be combined and/or combined in various ways, even if such a combination or combination is not explicitly recorded in the present invention. In particular, without departing from the spirit and teachings of the present invention, the features recorded in the various embodiments of the present invention can be combined and/or combined in various ways. All such combinations and/or combinations fall within the scope of the present invention.

The embodiments of the present invention are described above. However, these embodiments are only for the purpose of illustration, and are not intended to limit the scope of the present invention. Although the embodiments are described above, this does not mean that the measures in the various embodiments cannot be used in combination. The scope of the present invention is defined by the appended claims and their equivalents. Without departing from the scope of the present invention, those skilled in the art may make various substitutions and modifications, which should all fall within the scope of the present invention.

Claims (8)

1. A magnetic resonance image reconstruction method, characterized in that the method comprises: Acquire first three-dimensional contour space information and magnetic resonance scanning data of a scanned slice of a scanned object within a first specific field of view; Processing the first three-dimensional contour space information to obtain processed first three-dimensional contour space information; Inputting the processed first three-dimensional contour space information into the constructed coil sensitivity estimation model to obtain multi-channel coil sensitivity information corresponding to the scan slice of the scanned object within the first specific field of view; Reconstructing a magnetic resonance image of the scanned object according to the multi-channel coil sensitivity information and the magnetic resonance scan data; The step of processing the first three-dimensional contour space information to obtain the processed first three-dimensional contour space information includes: Determine a second conversion matrix between the first three-dimensional contour space information of the scan slice and the space information of the target scanning range; According to the second conversion matrix and the first three-dimensional contour space information, third three-dimensional contour space information corresponding to the first three-dimensional contour space information is obtained, wherein the third three-dimensional contour space information represents the uniqueness of the three-dimensional contour space information of the scanned slice of the scanned object within the first specific field of view; Performing data analysis on the third three-dimensional contour space information to obtain processed first three-dimensional contour space information; The step of inputting the processed first three-dimensional contour space information into the constructed coil sensitivity estimation model to obtain multi-channel coil sensitivity information corresponding to the scan slice of the scanned object within the first specific field of view includes: Based on the coil sensitivity estimation model, multi-channel coil sensitivity information corresponding to the scan slice of the scanned object within a specific field of view is obtained according to the first characteristic matrix information, the second characteristic matrix information and the first three-dimensional contour space information, wherein the first characteristic matrix is determined by historical multi-channel sensitivity information, the second characteristic matrix is determined by historical first three-dimensional contour space information, and the coil sensitivity estimation model is obtained by the following formula: ; Among them, S is the first three-dimensional contour space information; C is the multi -channel coil sensitivity information; EC is the first characteristic matrix information; _{ES is} the second characteristic matrix information. 2. The method according to claim 1, characterized in that before obtaining the first three-dimensional contour space information and magnetic resonance scanning data of the scanned slice within the first specific field of view of the scanned object, the method further comprises: A first transformation matrix between a coordinate system of a second specific field of view and a coordinate system of the first specific field of view is determined, wherein the first transformation matrix is applied to acquiring first three-dimensional contour space information of a scanned slice of the scanned object within the first specific field of view. 3. The method according to claim 2, characterized in that the step of determining a first transformation matrix between a coordinate system of the second specific field of view and a coordinate system of the first specific field of view comprises: Acquiring first position information of a target object in a registration device within the second specific field of view, wherein the target object is a marker that can be identified by the magnetic resonance scan; Scanning the target object in the registration device within a first specific field of view using a preset gradient scanning direction to obtain a scanned image corresponding to the target object; Performing connected domain detection processing on the scanned image to obtain second position information corresponding to the scanned image; A first conversion matrix between a coordinate system of the second specific field of view and a coordinate system of the first specific field of view is determined according to the first position information and the second position information. 4. The method according to claim 1, characterized in that the step of obtaining first three-dimensional contour space information of a scanned slice of the scanned object within a first specific field of view comprises: Acquire spatial reference information of a three-dimensional contour of the scanned object within a second specific field of view; Determine first positioning information of a scan slice of the scanned object within a first specific field of view; Determine second three-dimensional contour space information of the scan slice of the scanned object within a second specific field of view according to the first positioning information and the three-dimensional contour space reference information; The second three-dimensional contour space information is converted to obtain first three-dimensional contour space information of a scanned slice of the scanned object within a first specific field of view. 5. The method according to claim 4, characterized in that determining the second three-dimensional contour space information of the scanned slice of the scanned object within the second specific field of view according to the first positioning information and the three-dimensional contour space reference information comprises: Extracting second positioning information corresponding to the first positioning information from the three-dimensional contour space reference information according to the first positioning information and the first conversion matrix, wherein the first conversion matrix is determined by a coordinate system of a second specific field of view and a coordinate system of the first specific field of view, and the second positioning information is information of the scanned slice of the scanned object within the second specific field of view; Second three-dimensional contour space information of the scan slice of the scanned object within a second specific field of view is determined according to the second positioning information. 6. A magnetic resonance image reconstruction device, characterized in that the device comprises: An acquisition module, used for acquiring first three-dimensional contour space information and magnetic resonance scanning data of a scanned slice of a scanned object within a first specific field of view; A processing module, used for processing the first three-dimensional contour space information to obtain the processed first three-dimensional contour space information; An input module, used for inputting the processed first three-dimensional contour space information into the constructed coil sensitivity estimation model to obtain multi-channel coil sensitivity information corresponding to the scan slice of the scanned object within the first specific field of view; A reconstruction module, configured to reconstruct a magnetic resonance image of the scanned object according to the multi-channel coil sensitivity information and the magnetic resonance scan data; Wherein, the processing module includes: A fourth determination submodule is used to determine a second conversion matrix between the first three-dimensional contour space information of the scan slice and the space information of the target scanning range; A first obtaining submodule is configured to obtain, according to the second conversion matrix and the first three-dimensional contour space information, third three-dimensional contour space information corresponding to the first three-dimensional contour space information, wherein the third three-dimensional contour space information represents the uniqueness of the three-dimensional contour space information of the scanned slice of the scanned object within the first specific field of view; A third processing submodule is used to perform data analysis and processing on the third three-dimensional contour space information to obtain processed first three-dimensional contour space information; Wherein, the input module includes: The second acquisition submodule is used to obtain the multi-channel coil sensitivity information corresponding to the scan slice of the scanned object within a specific field of view based on the coil sensitivity estimation model according to the first characteristic matrix information, the second characteristic matrix information and the first three-dimensional contour space information, wherein the first characteristic matrix is determined by historical multi-channel sensitivity information, the second characteristic matrix is determined by historical first three-dimensional contour space information, and the coil sensitivity estimation model is obtained by the following formula: ; Among them, S is the first three-dimensional contour space information; C is the multi -channel coil sensitivity information; EC is the first characteristic matrix information; _{ES is} the second characteristic matrix information. 7. An electronic device, characterized in that the electronic device comprises: one or more processors; a memory for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 5. 8. A computer-readable storage medium, characterized in that executable instructions are stored thereon, and when the instructions are executed by a processor, the processor implements the method according to any one of claims 1 to 5.