Magnetic resonance iso-center positioning method, system, and storage medium

Abstract

The application discloses a magnetic resonance ISO center positioning method and system and a storage medium. The method comprises the following steps: collecting a depth image of a patient on a patient examination table; detecting the boundary of a scanning area from the depth image according to the set scanning area information, and constructing a region model covering the boundary of the scanning area; determining the maximum size PX of the X-axis direction and the maximum size PY of the Y-axis direction of the patient on the X-Y plane when the patient enters the magnetic hole based on the depth image; and determining the position of the center point of the region model closest to the electrical center of the magnet according to the principle of not colliding with the magnetic hole, and taking the determined position as the magnetic resonance ISO center for moving the center point of the region model into the magnetic hole. The technical scheme in the application can realize ISO center scanning.

Description

Technical Field

[0001] This invention relates to the field of magnetic resonance imaging, and in particular to a magnetic resonance ISO center localization method, system, and computer-readable storage medium. Background Technology

[0002] Most modern MRI systems used for patient examinations have a magnetic aperture that is a cylinder with a diameter of 60 or 70 centimeters. Limited by the aperture size, the patient stage can only move in one direction within the aperture, typically along the z-axis of the aperture axis. However, movement in one direction restricts isocentric scanning, meaning the scan area needs to be as close as possible to the electrical center of the magnet. With the trend towards developing MR systems with greater aperture openings (such as 80 centimeters or wider), it has become more realistic to allow the patient stage to move in three directions within the aperture. Therefore, by moving the scan area in three directions within the aperture, more isocentric scanning (also known as ISO scanning) can be performed. Summary of the Invention

[0003] In view of this, this invention proposes, on the one hand, a magnetic resonance ISO center localization method, and on the other hand, a magnetic resonance ISO center localization system and a computer-readable storage medium to realize ISO center scanning.

[0004] An embodiment of the present invention proposes a magnetic resonance ISO center localization method, comprising: acquiring a depth image of a patient on a patient examination table; detecting the boundary of the scanning area from the depth image according to the set scanning area information, and constructing a region model covering the boundary of the scanning area; determining, based on the depth image, the maximum dimensions PX and PY of the patient in the XY plane in the X-axis direction when the patient enters the magnetic aperture; determining, according to the principle that the maximum dimensions PX and PY in the X-axis direction do not collide with the magnetic aperture, the position that makes the center point of the region model closest to the electrical center of the magnet, and using the determined position as the center point of the region model to move the magnetic resonance ISO center within the magnetic aperture; wherein, the Z-axis direction is the direction of the patient entering and exiting the magnetic aperture, the X-axis direction is the horizontal direction perpendicular to the Z-axis direction, and the Y-axis direction is the direction perpendicular to the XZ plane.

[0005] In one embodiment, determining the position where the center point of the region model is closest to the electrical center of the magnet, according to the principle of ensuring that the maximum dimensions PX and PY in the X-axis direction do not collide with the magnetic aperture, includes: calculating the vertical distances from the two endpoints of the maximum dimension PX in the X-axis direction to the center point of the region model, and using the larger vertical distance as the anti-collision reference value maxX in the X-axis direction; calculating the vertical distances from the two endpoints of the maximum dimension PY in the Y-axis direction to the center point of the region model, and using the larger vertical distance as the anti-collision reference value maxY in the Y-axis direction; comparing the anti-collision reference value maxX in the X-axis direction with the radius of the magnetic aperture, and determining that the offset value of the X-axis direction from the electrical center of the magnet is 0 when the anti-collision reference value maxX in the X-axis direction is less than or equal to the radius of the magnetic aperture; and determining that the offset value of the X-axis direction from the electrical center of the magnet is 0 when the anti-collision reference value maxX in the X-axis direction is greater than the radius of the magnetic aperture. When determining the radius of the magnetic aperture, the offset value in the X-axis direction from the electrical center of the magnet is determined to be the radius of the magnetic aperture minus the anti-collision reference value maxX in the X-axis direction. The anti-collision reference value maxY in the Y-axis direction is compared with the radius of the magnetic aperture. If the anti-collision reference value maxY in the Y-axis direction is less than or equal to the radius of the magnetic aperture, the offset value in the Y-axis direction from the electrical center of the magnet is determined to be 0. If the anti-collision reference value maxY in the Y-axis direction is greater than the radius of the magnetic aperture, the offset value in the Y-axis direction from the electrical center of the magnet is determined to be the radius of the magnetic aperture minus the anti-collision reference value maxY in the Y-axis direction. The offset value in the Z-axis direction from the electrical center of the magnet is determined to be 0. Based on the offset values ​​in the X-axis, Y-axis, and Z-axis directions from the electrical center of the magnet, the position that makes the center point of the region model closest to the electrical center of the magnet is obtained.

[0006] In one embodiment, determining the maximum dimensions PX and PY of the patient in the XY plane when the patient enters the magnetic aperture based on the depth image includes: calculating the body length of the patient in the Z-axis direction when the center point of the region model is moved to the electrical center of the magnet; and detecting the maximum dimensions PX and PY of the patient in the XY plane from the image region corresponding to the body length in the depth image.

[0007] In one embodiment, determining the maximum dimensions PX and PY of the patient in the XY plane when the patient enters the magnetic aperture based on the depth image includes: detecting the patient's boundary from the depth image and constructing an overall model covering the patient's boundary; and determining the maximum dimensions PX and PY of the patient in the XY plane based on the overall model.

[0008] In one embodiment, determining the position that makes the center point of the region model closest to the electrical center of the magnet based on the offset values ​​of the X-axis, Y-axis, and Z-axis directions from the electrical center of the magnet includes: using the position determined by the offset values ​​of the X-axis, Y-axis, and Z-axis directions from the electrical center of the magnet as the center point position of the region model, and determining the estimated position of the overall model in the magnetic aperture; determining whether the overall model collides with the magnetic aperture at the estimated position, and if there is no collision, then setting the offset values ​​of the X-axis direction from the electrical center of the magnet as the center point position of the region model; determining the estimated position of the overall model in the magnetic aperture; and determining whether the overall model collides with the magnetic aperture at the estimated position. If there is no collision, then setting the offset values ​​of the X-axis direction from the electrical center of the magnet as the center point position of the region model. The position determined by the offset values ​​from the electrical center of the magnet, the offset values ​​in the Y-axis direction, and the offset values ​​in the Z-axis direction are used as the position where the center point of the region model is closest to the electrical center of the magnet. If a collision occurs, the method of traversing the offset values ​​from the electrical center of the magnet along the X-axis and Y-axis respectively is used to find the combination of offset values ​​from the electrical center of the magnet along the X-axis and Y-axis that minimizes the distance from the electrical center of the magnet and prevents the patient from colliding with the magnet hole. The position determined by the combination of the offset values ​​from the electrical center of the magnet along the X-axis and Y-axis and the offset value in the Z-axis direction is used as the position where the center point of the region model is closest to the electrical center of the magnet.

[0009] The magnetic resonance ISO center localization system proposed in this embodiment of the invention includes: a depth camera for acquiring depth images of a patient on a patient examination table; a region model building module for detecting the boundary of the scanning region from the depth image based on set scanning region information, and constructing a region model covering the boundary of the scanning region; a maximum size determination module for determining, based on the depth image, the maximum size PX of the patient in the X-axis direction and the maximum size PY in the Y-axis direction of the patient when entering the magnetic aperture; and a positioning module for determining, according to the principle that the maximum size PX in the X-axis direction and the maximum size PY in the Y-axis direction do not collide with the magnetic aperture, the position that makes the center point of the region model closest to the electrical center of the magnet, and using the determined position as the center point of the region model to be moved to the magnetic resonance ISO center within the magnetic aperture; wherein, the Z-axis direction is the direction in which the patient enters and exits the magnetic aperture, the X-axis direction is the horizontal direction perpendicular to the Z-axis direction, and the Y-axis direction is the direction perpendicular to the XZ plane.

[0010] In one embodiment, the positioning module includes: a first calculation module, configured to calculate the vertical distances from the two endpoints of the maximum dimension PX in the X-axis direction to the center point of the region model, and use the larger vertical distance as the anti-collision reference value maxX in the X-axis direction; a second calculation module, configured to calculate the vertical distances from the two endpoints of the maximum dimension PY in the Y-axis direction to the center point of the region model, and use the larger vertical distance as the anti-collision reference value maxY in the Y-axis direction; and a first processing module, configured to compare the anti-collision reference value maxX in the X-axis direction with the radius of the magnetic hole, and when the anti-collision reference value maxX in the X-axis direction is less than or equal to the radius of the magnetic hole, determine that the offset value of the X-axis direction from the electrical center of the magnet is 0; and when the anti-collision reference value maxX in the X-axis direction is greater than the radius of the magnetic hole, determine that the offset value of the X-axis direction from the electrical center of the magnet is the magnetic hole value. The first processing module subtracts the anti-collision reference value maxX in the X-axis direction from the radius of the magnetic hole; the second processing module compares the anti-collision reference value maxY in the Y-axis direction with the radius of the magnetic hole, and determines that the offset value of the Y-axis direction from the electrical center of the magnet is 0 when the anti-collision reference value maxY in the Y-axis direction is less than or equal to the radius of the magnetic hole; the third processing module determines that the offset value of the Z-axis direction from the electrical center of the magnet is 0; the fourth processing module determines that the offset value of the Z-axis direction from the electrical center of the magnet is 0; and the fifth processing module determines that the position of the center point of the region model is closest to the electrical center of the magnet based on the offset values ​​of the X-axis direction, the Y-axis direction, and the Z-axis direction from the electrical center of the magnet.

[0011] In one embodiment, the maximum size determination module includes: a body length calculation module for calculating the Z-axis body length of the patient entering the magnetic aperture when the center point of the region model is moved to the electrical center of the magnet; and a maximum size detection module for detecting the maximum X-axis size PX and the maximum Y-axis size PY of the patient in the XY plane from the image region corresponding to the body length in the depth image.

[0012] In one embodiment, the maximum size determination module includes: an overall model building module, used to detect the patient's boundary from the depth image and construct an overall model covering the patient's boundary; and a maximum size acquisition module, used to acquire the patient's maximum size PX in the X-axis direction and maximum size PY in the Y-axis direction on the XY plane based on the overall model.

[0013] In one embodiment, the position determination module includes: a first position determination submodule, used to determine the position determined by the offset values ​​in the X-axis direction, the Y-axis direction, and the Z-axis direction from the electrical center of the magnet as the center point position of the region model, and to determine the estimated position of the overall model in the magnetic aperture; and a second position determination submodule, used to determine whether the overall model collides with the magnetic aperture at the estimated position, and if there is no collision, to determine the offset values ​​in the X-axis direction, the Y-axis direction, and the Z-axis direction from the electrical center of the magnet as the center point position of the region model, and to determine the estimated position of the overall model in the magnetic aperture; The position determined by the offset value of the X-axis and the offset value of the Z-axis from the electrical center of the magnet is used as the position where the center point of the region model is closest to the electrical center of the magnet. If a collision occurs, the method of traversing the offset values ​​of the X-axis and Y-axis from the electrical center of the magnet is used to find the combination of offset values ​​of the X-axis and Y-axis from the electrical center of the magnet that minimizes the distance from the electrical center of the magnet and prevents the patient from colliding with the magnet hole. The position determined by the combination of the offset values ​​of the X-axis and Y-axis from the electrical center of the magnet and the offset value of the Z-axis from the electrical center of the magnet is used as the position where the center point of the region model is closest to the electrical center of the magnet.

[0014] The magnetic resonance ISO center localization system proposed in this embodiment of the invention includes: at least one memory and at least one processor, wherein: the at least one memory is used to store a computer program; the at least one processor is used to call the computer program stored in the at least one memory to execute the magnetic resonance ISO center localization method as described in any of the above embodiments.

[0015] The present invention provides a computer-readable storage medium storing a computer program thereon; the computer program can be executed by a processor to implement the magnetic resonance ISO center localization method as described in any of the above embodiments.

[0016] As can be seen from the above scheme, in this embodiment of the invention, a region model of the scanning area is established based on the patient's depth image, and the maximum dimensions PX and PY of the patient in the XY plane when the patient enters the magnetic aperture are determined based on the depth image. Thus, under the premise that the maximum dimensions PX and PY in the XY plane do not collide with the magnetic aperture, the center point of the region model can be moved to a position that can be as close as possible to the electrical center of the magnet, thereby realizing ISO center positioning scanning.

[0017] Furthermore, by calculating the body length of the patient entering the magnetic aperture in the Z-axis direction when the center point of the region model is moved to the electrical center of the magnet, and detecting the maximum dimensions PX and PY of the patient in the X-axis direction and Y-axis direction in the depth image region corresponding to the body length, a more accurate maximum dimension of the body portion entering the magnetic aperture can be obtained.

[0018] In addition, by first establishing an overall model covering the patient's boundary, and then obtaining the patient's maximum size PX in the X-axis direction and maximum size PY in the Y-axis direction on the XY plane based on this overall model, the detection process of the maximum size can be simplified.

[0019] Furthermore, this embodiment provides a simple and easy-to-implement method to move the center point of the region model to a position that can be as close as possible to the electrical center of the magnet, without colliding with the magnetic hole, provided that the maximum size PX in the X-axis direction and the maximum size PY in the Y-axis direction do not collide. Attached Figure Description

[0020] Preferred embodiments of the present invention will now be described in detail with reference to the accompanying drawings, which will make the above and other features and advantages of the present invention more apparent to those skilled in the art. In the drawings:

[0021] Figure 1 This is an exemplary flowchart of a magnetic resonance ISO center localization method according to an embodiment of the present invention.

[0022] Figure 2 This is a schematic diagram of a patient lying on a patient examination table in the original position, as an example of the present invention.

[0023] Figures 3A to 3C This is a schematic diagram of a region model from different angles in an example of the present invention.

[0024] Figure 4 This is a schematic diagram of the overall model in an example of the present invention.

[0025] Figure 5 This is a schematic diagram illustrating the distance between the two endpoints of the maximum dimensions in the X-axis direction and the maximum dimensions in the Y-axis direction, and the center point of the region model, in an example of the present invention.

[0026] Figure 6 This is a schematic diagram of a magnetic resonance ISO center positioning system according to an embodiment of the present invention.

[0027] Figure 7A and Figure 7B for Figure 6 A schematic diagram of the maximum size determination module.

[0028] Figure 7C for Figure 6A schematic diagram of the positioning module.

[0029] Figure 8 This is a schematic diagram of another magnetic resonance ISO center positioning system in an embodiment of the present invention.

[0030] The reference numerals in the attached figures are as follows:

[0031]

[0032] Detailed Implementation

[0033] In this embodiment of the invention, under ideal conditions, the patient's designated scanning area can be moved completely freely to the magnet electrical center within the magnetic aperture, with no mechanical interference between the moving parts (patient examination table surface, patient, coil) and the stationary parts (magnetic aperture, etc.). However, for imaging of body parts that are off-center, such as imaging one shoulder, one knee joint, or the heart region, collisions may occur when the patient examination table is moved to the magnet electrical center due to the limited size of the magnetic aperture. Therefore, to avoid potential collisions, this embodiment of the invention considers acquiring a depth image of the patient (in this embodiment, the patient may include all relevant moving parts such as the coil and examination table surface), constructing a region model covering the scanning area based on this depth image, and detecting the maximum dimensions of the patient's body portion entering the magnetic aperture in the X-axis and Y-axis directions. While ensuring that the maximum dimensions PX in the X-axis direction and PY in the Y-axis direction do not collide with the magnetic aperture, the center point of the region model is moved to a position as close as possible to the magnet electrical center; this position is the determined magnetic resonance ISO center. The patient is then moved to the predetermined ISO center of the magnetic resonance imaging (MRI) by controlling the patient examination table in three directions: X-axis, Y-axis, and Z-axis. The Z-axis is the direction in which the patient enters and exits the magnetic aperture, the X-axis is the horizontal direction perpendicular to the Z-axis, and the Y-axis is the direction perpendicular to the XZ plane.

[0034] To make the objectives, technical solutions, and advantages of the present invention clearer, the following embodiments are provided to further illustrate the present invention in detail.

[0035] Figure 1 This is an exemplary flowchart of a magnetic resonance ISO center localization method according to an embodiment of the present invention. Figure 1 As shown, the method may include the following steps:

[0036] Step 101: Acquire depth images of the patient on the examination table.

[0037] In this embodiment, for ease of description, the term "patient" can be used to refer to the patient himself, as well as the coils and examination table surface associated with him.

[0038] In practical implementation, it can be as follows: Figure 2 As shown, with patient examination table 1 in its original position and patient 2 lying on it, a depth camera (3D camera) is used to acquire the patient's depth image. Specifically, this depth camera can be mounted on the ceiling or wall of the MRI scanning room. Since the position of the depth camera relative to the magnet's electrical center is fixed and known, the camera coordinates can be easily converted to MRI system coordinates. Alternatively, the camera and the MRI system share the same coordinates, hereinafter referred to as global coordinates. In this embodiment, it is assumed that the camera and the MRI system share the same global coordinates, and these global coordinates are coordinates with the magnet's electrical center as the origin (0,0,0). Typically, the magnet's electrical center is located at the center of the magnetohole. In this step, the patient's initial position can be obtained by acquiring the patient's depth image using the depth camera. As long as the patient remains stationary, the positions of all their body parts are fixed and known.

[0039] Furthermore, the patient examination table surface in this embodiment can move within the magnetic hole in three directions: the X-axis direction, the Y-axis direction, and the Z-axis direction.

[0040] Step 102: Based on the set scanning area information, detect the boundary of the scanning area from the depth image and construct a region model covering the boundary of the scanning area.

[0041] In this step, the information for the scanned area can be obtained from the patient's registration information.

[0042] Furthermore, segmentation techniques or AI-based image recognition techniques can be used to detect the boundaries of the scanned region from the depth image, and a region model covering the boundaries of the scanned region can be obtained.

[0043] For example, the planes along the Z-axis in the depth image are segmented to find the scanning region boundaries on each plane. Based on the scanning region boundaries on each plane, a virtual scanning region contour covering all scanning region boundaries is constructed. Alternatively, the planes along the Z-axis are subjected to maximum intensity projection, and the scanning region boundaries are searched on the maximum intensity projection image to obtain a virtual scanning region contour. A region model of a cuboid, cylinder, ellipsoid, or sphere covering the virtual scanning region contour is constructed.

[0044] For example, when searching the depth image along the Z-axis from the positive Z-direction to the negative Z-direction, the first Z-coordinate value z1 of the image plane is recorded when the boundary of the scanned region in the plane is first detected; when searching the depth image along the Z-axis from the negative Z-direction to the positive Z-direction, the second Z-coordinate value z2 of the image plane is recorded when the boundary of the scanned region in the plane is first detected; when searching the depth image along the X-axis from the positive X-direction to the negative X-direction, the first X-coordinate value x1 of the image plane is recorded when the boundary of the scanned region in the plane is first detected; when searching the depth image along the X-axis from the negative X-direction to the positive X-direction... The depth image is searched along the Y-axis from the positive Y direction to the negative Y direction. When the boundary of the scanned region in the plane is first detected, the first Y coordinate value y1 of the image plane is recorded. The depth image is searched along the Y-axis from the negative Y direction to the positive X direction. When the boundary of the scanned region in the plane is first detected, the second Y coordinate value y2 of the image plane is recorded. A cuboid region model with length z1-z2, width x2, and height y1-y2 is constructed.

[0045] In this embodiment, assuming the designated scanning area is the left shoulder, the determined area model 3 can be as follows: Figures 3A to 3C As shown. Figures 3A to 3C A schematic diagram of the region model at different angles is shown. In this embodiment, the center of the scanned region can be defined as the geometric center of the region model. In this embodiment, it is assumed that the global coordinates of the center point of the scanned region are (cx, cy, cz).

[0046] Step 103: Based on the depth image, determine the maximum size PX of the patient in the X-axis direction and the maximum size PY of the patient in the Y-axis direction in the XY plane when the patient enters the magnetic aperture.

[0047] In this step, there are several ways to implement it. Two of them are briefly listed below.

[0048] The first type:

[0049] A1. Calculate the body length of the patient in the Z-axis direction when the center point of the region model is moved to the electrical center of the magnet.

[0050] In this embodiment, it is assumed that the Z-axis distance from the electrical center of the magnet to the magnetic aperture entrance is CZ. Typically, the electrical center of the magnet is located at half the length L of the magnetic aperture, i.e., CZ = L / 2. For an MRI scan with the head-first (or feet-first) orientation, if the distance from the center of the scanning area to the top of the head (or the sole of the foot) is OZ1, and the distance from the center of the scanning area to the sole of the foot (top of the head) is OZ2, if OZ2 is greater than or equal to CZ, then in this step, when the center point of the region model is moved to the electrical center of the magnet, the Z-axis body length Lz of the patient entering the magnetic aperture is Lz = OZ1 + CZ; if OZ2 is less than CZ, then in this step, when the center point of the region model is moved to the electrical center of the magnet, the Z-axis body length Lz of the patient entering the magnetic aperture is Lz = OZ1 + OZ2, i.e., the patient's entire body length.

[0051] A2. Detect the patient's maximum dimension PX in the X-axis direction and maximum dimension PY in the Y-axis direction in the image region corresponding to the body length in the depth image.

[0052] For example, the maximum dimension PX in the X-axis direction may correspond to the shoulder width, or it may correspond to the hip width plus the position of the arms placed flat on both sides, etc.; the maximum dimension PY in the Y-axis direction may correspond to the position from the tip of the nose to the occipital bone, or it may correspond to the position of the thickest part of the chest, or it may correspond to the position where the coil is placed, etc.

[0053] The second type:

[0054] B1. Detect the patient's boundaries from the depth image and construct an overall model covering the patient's boundaries.

[0055] In this step, segmentation techniques or AI-based image recognition techniques can be used to detect the patient's boundaries from the depth image and obtain an overall model covering the patient's boundaries.

[0056] For example, the planes along the Z-axis in the depth image are segmented to find the image contours on each plane. Based on the image contours on each plane, a virtual contour covering all contours is constructed. Alternatively, the planes along the Z-axis are subjected to maximum intensity projection, and contour search is performed on the maximum intensity projection image to obtain a virtual contour. An overall model of a cuboid, cylinder, or elliptical cylinder with a length of z1-z2 covering the virtual contour is constructed, where z1-z2 are two boundary values ​​along the Z-axis.

[0057] For example, the depth image can be searched along the Z-axis from the positive Z-direction to the negative Z-direction. When an object in the plane is first detected, the first Z-coordinate value z3 of the image plane is recorded; the depth image can be searched along the Z-axis from the negative Z-direction to the positive Z-direction. When an object in the plane is first detected, the second Z-coordinate value z4 of the image plane is recorded; the depth image can be searched along the X-axis from the positive X-direction to the negative X-direction. When an object in the plane is first detected, the first X-coordinate value x3 of the image plane is recorded; the depth image can be searched along the X-axis from the negative X-direction to the positive X-direction. When an object in the plane is first detected, the second X-coordinate value x4 of the image plane is recorded; the depth image can be searched along the Y-axis from the positive Y-direction to the negative Y-direction. When an object in the plane is first detected, the first Y-coordinate value y3 of the image plane is recorded; the depth image can be searched along the Y-axis from the negative Y-direction to the positive X-direction. When an object in the plane is first detected, the second Y-coordinate value y4 of the image plane is recorded; a cuboid model with length z3-z4, width x4, and height y3-y4 are constructed.

[0058] Figure 4 A schematic diagram of the overall model 4 in an example of the present invention is shown.

[0059] In this embodiment, step B1 can be executed before step 102, after step 102, or in parallel or interspersed with step 102.

[0060] B2. Based on the overall model, determine the patient's maximum dimension PX in the X-axis direction and maximum dimension PY in the Y-axis direction on the XY plane.

[0061] For example, for the overall model of a cuboid with length z3-z4, width x4, and height y3-y4, the maximum dimension in the X-axis direction is PX = x3-x4, and the maximum dimension in the Y-axis direction is PY = y3-y4.

[0062] As can be seen, the second scenario above simplifies the detection process for the maximum size, while the first scenario provides a more accurate maximum size of the body part of the patient that enters the magnetic aperture.

[0063] Step 104: Based on the principle that the maximum dimension PX in the X-axis direction and the maximum dimension PY in the Y-axis direction do not collide with the magnetic hole, determine the position where the center point of the region model is closest to the electrical center of the magnet, and use the determined position as the center point of the region model to move to the magnetic resonance ISO center inside the magnetic hole.

[0064] In practice, this step can be implemented in several ways; one of them is listed below.

[0065] C1. Calculate the vertical distances from the two endpoints of the maximum dimension PX in the X-axis direction to the center point of the region model, and take the larger vertical distance as the collision avoidance reference value maxX in the X-axis direction.

[0066] In this embodiment, where the scanning area is the left shoulder, the perpendicular distances from the two endpoints of the maximum dimension PX along the X-axis to the center point of the region model can be as follows: Figure 5 As shown, OX1 and PX-OX1 are respectively. Among them, OX1 is greater than PX-OX1, therefore maxX=max(OX1,PX-OX1)=OX1.

[0067] C2. Calculate the vertical distances from the two endpoints of the maximum dimension PY in the Y-axis direction to the center point of the region model, and take the larger vertical distance as the anti-collision reference value maxY in the Y-axis direction.

[0068] In this embodiment, where the scanned area is the left shoulder, the perpendicular distances from the two endpoints of the maximum Y-axis dimension PY to the center point of the region model can be as follows: Figure 5 As shown, OY1 and PY-OY1 are respectively. Among them, OY1 is greater than PY-OY1, therefore maxY=max(OY1,PY-OY1)=OY1.

[0069] C3. Compare the anti-collision reference value maxX in the X-axis direction with the radius of the magnetic hole. When the anti-collision reference value maxX in the X-axis direction is less than or equal to the radius of the magnetic hole, determine that the offset value of the X-axis direction from the electrical center of the magnet is 0. When the anti-collision reference value maxX in the X-axis direction is greater than the radius of the magnetic hole, determine that the offset value of the X-axis direction from the electrical center of the magnet is the radius of the magnetic hole minus the anti-collision reference value maxX in the X-axis direction.

[0070] Assuming the diameter of the magnetic hole is D, then the radius is D / 2. If maxX≤D / 2, the offset value x in the X-axis direction from the electrical center of the magnet is 0. If maxX>D / 2, then x=D / 2-maxX.

[0071] C4. Compare the anti-collision reference value maxY in the Y-axis direction with the radius of the magnetic hole. When the anti-collision reference value maxY in the Y-axis direction is less than or equal to the radius of the magnetic hole, determine that the offset value of the Y-axis direction from the electrical center of the magnet is 0. When the anti-collision reference value maxY in the Y-axis direction is greater than the radius of the magnetic hole, determine that the offset value of the Y-axis direction from the electrical center of the magnet is the radius of the magnetic hole minus the anti-collision reference value maxY in the Y-axis direction.

[0072] If maxY≤D / 2, the offset value y=0 from the electrical center of the magnet in the Y-axis direction; if maxY>D / 2, y=D / 2-maxY.

[0073] C5. Determine that the offset value z of the Z-axis direction from the electrical center of the magnet is 0.

[0074] Generally, the center point of the region model can be aligned with the electrical center of the magnet in the Z-axis direction.

[0075] C6. Based on the offset values ​​of the X-axis direction, Y-axis direction, and Z-axis direction from the electrical center of the magnet, obtain the position that makes the center point of the region model closest to the electrical center of the magnet.

[0076] For example, in the first case in step 103, the positions determined by the offset values ​​of the X-axis direction, the Y-axis direction, and the Z-axis direction from the electrical center of the magnet can be directly used as the positions that make the center point of the region model closest to the electrical center of the magnet, i.e., (x, y, z).

[0077] For the second scenario in step 103, the position determined by the offset values ​​x, y, and z can be used as the center point of the region model, and the estimated position of the overall model in the magnetic aperture can be determined. It is then determined whether the overall model collides with the magnetic aperture at the estimated position. If no collision occurs, (x, y, z) is used as the position that makes the center point of the region model closest to the electrical center of the magnet. If a collision occurs, the method of traversing the offset values ​​of the X-axis and Y-axis from the electrical center of the magnet is used to find the combination of X-axis and Y-axis offset values ​​from the electrical center of the magnet that minimizes the distance from the electrical center of the magnet and prevents the patient from colliding with the magnetic aperture. 2 +y 2 The minimum (x, y) value is used to determine the position where the center point of the region model is closest to the electrical center of the magnet, determined by combining the offset values ​​of the X-axis and Y-axis from the electrical center of the magnet and the offset value of the Z-axis from the electrical center of the magnet.

[0078] Accordingly, the center point of the region model moves from its initial position (cx, cy, cz) to a position (x, y, z) as close as possible to the electrical center of the magnet by a distance of (x-cx, y-cy, z-cz). This allows control over the movement of the inspection table surface along the X, Y, and Z axes, enabling the center point of the region model to move from its initial position (cx, cy, cz) to position (x, y, z).

[0079] The above provides a detailed description of the magnetic resonance ISO center localization method in the embodiments of the present invention. The following provides a detailed description of the magnetic resonance ISO center localization system in the embodiments of the present invention. The magnetic resonance ISO center localization system in the embodiments of the present invention can be used to implement the magnetic resonance ISO center localization method in the embodiments of the present invention. For details not disclosed in detail in the system embodiments of the present invention, please refer to the corresponding descriptions in the method embodiments of the present invention, which will not be repeated here.

[0080] Figure 6 This is an exemplary structural diagram of the magnetic resonance ISO center localization system in an embodiment of the present invention. Figure 6 As shown, the system may include: a depth camera 61, a region model building module 62, a maximum size determination module 63, and a positioning module 64.

[0081] Among them, the depth camera 61 is used to acquire depth images of the patient on the patient examination table.

[0082] The region model building module 62 is used to detect the boundary of the scanned region from the depth image according to the set scanned region information, and construct a region model covering the boundary of the scanned region.

[0083] The maximum size determination module 63 is used to determine, based on the depth image, the maximum size PX of the patient in the X-axis direction and the maximum size PY in the Y-axis direction of the patient when the patient enters the magnetic aperture.

[0084] The positioning module 64 is used to determine the position that makes the center point of the region model closest to the electrical center of the magnet, according to the principle that the maximum size PX in the X-axis direction and the maximum size PY in the Y-axis direction do not collide with the magnetic hole, and to use the determined position as the center point of the region model to move to the magnetic resonance ISO center in the magnetic hole.

[0085] The Z-axis direction is the direction in which the patient enters and exits the magnetic aperture, the X-axis direction is the horizontal direction perpendicular to the Z-axis direction, and the Y-axis direction is the direction perpendicular to the XZ plane.

[0086] In one implementation, the maximum size determination module 63 may be as follows: Figure 7A As shown, it includes: a body length calculation module 631 and a maximum size detection module 632.

[0087] The body length calculation module 631 is used to calculate the body length of the patient in the Z-axis direction when the center point of the region model is moved to the electrical center of the magnet.

[0088] The maximum size detection module 632 is used to detect the patient's maximum size PX in the X-axis direction and maximum size PY in the Y-axis direction in the XY plane from the image region corresponding to the body length in the depth image.

[0089] In another embodiment, the maximum size determination module 63 may be as follows: Figure 7B As shown, it includes: an overall model building module 633 and a maximum size acquisition module 634.

[0090] The overall model building module 633 is used to detect the patient's boundaries from the depth image and construct an overall model covering the patient's boundaries.

[0091] The maximum size acquisition module 634 is used to acquire the patient's maximum size PX in the X-axis direction and maximum size PY in the Y-axis direction on the XY plane based on the overall model.

[0092] In one implementation, the positioning module 64 can be as follows: Figure 7C As shown, it includes: a first calculation module 641, a second calculation module 642, a first processing module 643, a second processing module 644, a third processing module 645, and a position determination module 646.

[0093] The first calculation module 641 is used to calculate the vertical distances from the two endpoints of the maximum dimension PX in the X-axis direction to the center point of the region model, and to use the larger vertical distance as the anti-collision reference value maxX in the X-axis direction.

[0094] The second calculation module 642 is used to calculate the vertical distances from the two endpoints of the maximum dimension PY in the Y-axis direction to the center point of the region model, and to take the larger vertical distance as the anti-collision reference value maxY in the Y-axis direction.

[0095] The first processing module 643 is used to compare the anti-collision reference value maxX in the X-axis direction with the radius of the magnetic hole. When the anti-collision reference value maxX in the X-axis direction is less than or equal to the radius of the magnetic hole, the offset value of the X-axis direction from the electrical center of the magnet is determined to be 0. When the anti-collision reference value maxX in the X-axis direction is greater than the radius of the magnetic hole, the offset value of the X-axis direction from the electrical center of the magnet is determined to be the radius of the magnetic hole minus the anti-collision reference value maxX in the X-axis direction.

[0096] The second processing module 644 is used to compare the anti-collision reference value maxY in the Y-axis direction with the radius of the magnetic hole. When the anti-collision reference value maxY in the Y-axis direction is less than or equal to the radius of the magnetic hole, the offset value of the Y-axis direction from the electrical center of the magnet is determined to be 0. When the anti-collision reference value maxY in the Y-axis direction is greater than the radius of the magnetic hole, the offset value of the Y-axis direction from the electrical center of the magnet is determined to be the radius of the magnetic hole minus the anti-collision reference value maxY in the Y-axis direction.

[0097] The third processing module 645 is used to determine that the offset value of the Z-axis direction from the electrical center of the magnet is 0.

[0098] The position determination module 646 is used to determine the position that makes the center point of the region model closest to the electrical center of the magnet based on the offset values ​​of the X-axis direction, the Y-axis direction, and the Z-axis direction from the electrical center of the magnet.

[0099] For example, targeting Figure 7A The maximum size determination module 63 and the position determination module 646 shown can directly use the offset values ​​of the X-axis direction, the Y-axis direction, and the Z-axis direction from the electrical center of the magnet as the position that makes the center point of the region model closest to the electrical center of the magnet, i.e., (x, y, z).

[0100] against Figure 7B The maximum size determination module 63 and position determination module 646 shown may include a first position determination submodule (not shown in the figure) and a second position determination submodule (not shown in the figure). The first position determination submodule is used to determine the position determined by offset values ​​x, y, and z as the center point of the region model and to determine the estimated position of the overall model within the magnetic aperture. The second position determination submodule is used to determine whether the overall model collides with the magnetic aperture at the estimated position. If there is no collision, (x, y, z) is used as the position that makes the center point of the region model closest to the electrical center of the magnet. If there is a collision, the method of traversing the offset values ​​of the X-axis and Y-axis from the electrical center of the magnet is used to find the combination of X-axis and Y-axis offset values ​​from the electrical center of the magnet that minimizes the distance between the patient and the electrical center of the magnet, i.e., x... 2 +y 2 The minimum (x, y) value is used to determine the position where the center point of the region model is closest to the electrical center of the magnet, determined by combining the offset values ​​of the X-axis and Y-axis from the electrical center of the magnet and the offset value of the Z-axis from the electrical center of the magnet.

[0101] Figure 8 This is a schematic diagram of another magnetic resonance ISO center localization system in the embodiments of this application. This system can be used to implement... Figure 1 The method or implementation shown Figures 6 to 7C The system shown. As... Figure 8 As shown, the system may include at least one memory 81 and at least one processor 82. Additionally, it may include other components, such as communication ports. These components communicate via a bus 83.

[0102] At least one memory 81 is used to store a computer program. In one embodiment, the computer program can be understood to include... Figures 6 to 7C The diagram shows the various modules of the magnetic resonance ISO centering system. In addition, at least one memory 81 can store an operating system, etc. The operating system includes, but is not limited to: Android, Symbian, Windows, Linux, etc.

[0103] At least one processor 82 is used to invoke a computer program stored in at least one memory 81 to execute the magnetic resonance ISO center localization method described in the embodiments of this application. The processor 82 may be a CPU, processing unit / module, ASIC, logic module, or programmable gate array, etc. It can receive and transmit data through the communication port.

[0104] It should be noted that not all steps and modules in the above processes and structural diagrams are mandatory; some steps or modules can be omitted as needed. The execution order of the steps is not fixed and can be adjusted as required. The division of modules is merely for the convenience of description and functional division. In actual implementation, a module can be implemented by multiple modules, and the functions of multiple modules can also be implemented by the same module. These modules can be located in the same device or in different devices.

[0105] It is understood that the hardware modules in the above embodiments can be implemented mechanically or electronically. For example, a hardware module may include specially designed permanent circuits or logic devices (such as dedicated processors, such as FPGAs or ASICs) to perform specific operations. A hardware module may also include programmable logic devices or circuits (such as general-purpose processors or other programmable processors) temporarily configured by software to perform specific operations. The specific method used to implement the hardware module—whether it is mechanical, a dedicated permanent circuit, or a temporarily configured circuit (such as one configured by software)—can be determined based on cost and time considerations.

[0106] Furthermore, this application embodiment also provides a computer-readable storage medium storing a computer program that can be executed by a processor to implement the magnetic resonance ISO center localization method described in this application embodiment. Specifically, a system or device equipped with a storage medium can be provided, on which software program code implementing the functions of any of the above embodiments is stored, and the computer (or CPU or MPU) of the system or device can read and execute the program code stored in the storage medium. In addition, the operating system or the like operating on the computer can be instructed based on the program code to perform some or all of the actual operations. The program code read from the storage medium can also be written to a memory provided in an expansion board inserted into the computer or to a memory provided in an expansion unit connected to the computer, and then the CPU or the like installed on the expansion board or expansion unit can be instructed based on the program code to execute some or all of the actual operations, thereby implementing the functions of any of the above embodiments. The storage medium embodiments for providing program code include floppy disks, hard disks, magneto-optical disks, optical disks (such as CD-ROM, CD-R, CD-RW, DVD-ROM, DVD-RAM, DVD-RW, DVD+RW), magnetic tapes, non-volatile memory cards, and ROMs. Alternatively, program code can be downloaded from a server computer via a communication network.

[0107] As can be seen from the above scheme, in this embodiment of the invention, a region model of the scanning area is established based on the patient's depth image, and the maximum dimensions PX and PY of the patient in the XY plane when the patient enters the magnetic aperture are determined based on the depth image. Thus, under the premise that the maximum dimensions PX and PY in the XY plane do not collide with the magnetic aperture, the center point of the region model can be moved to a position that can be as close as possible to the electrical center of the magnet, thereby realizing ISO center positioning scanning.

[0108] Furthermore, by calculating the body length of the patient entering the magnetic aperture in the Z-axis direction when the center point of the region model is moved to the electrical center of the magnet, and detecting the maximum dimensions PX and PY of the patient in the X-axis direction and Y-axis direction in the depth image region corresponding to the body length, a more accurate maximum dimension of the body portion entering the magnetic aperture can be obtained.

[0109] In addition, by first establishing an overall model covering the patient's boundary, and then obtaining the patient's maximum size PX in the X-axis direction and maximum size PY in the Y-axis direction on the XY plane based on this overall model, the detection process of the maximum size can be simplified.

[0110] Furthermore, this embodiment provides a simple and easy-to-implement method to move the center point of the region model to a position that can be as close as possible to the electrical center of the magnet, without colliding with the magnetic hole, provided that the maximum size PX in the X-axis direction and the maximum size PY in the Y-axis direction do not collide.

[0111] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A magnetic resonance ISO center localization method, characterized in that, include: Acquire depth images of the patient on the examination table; Based on the set scanning area information, the boundary of the scanning area is detected from the depth image, and a region model covering the boundary of the scanning area is constructed. Based on the depth image, determine the maximum size PX of the patient in the X-axis direction and the maximum size PY of the patient in the Y-axis direction in the XY plane when the patient enters the magnetic aperture; Based on the principle of ensuring that the maximum dimensions PX in the X-axis direction and PY in the Y-axis direction do not collide with the magnetic aperture, the position that makes the center point of the region model closest to the center of the magnetic resonance ISO is determined, and the determined position is taken as the center point of the region model and moved to the center of the magnetic resonance ISO inside the magnetic aperture. Wherein, the Z-axis direction is the direction in which the patient enters and exits the magnetic aperture, the X-axis direction is the horizontal direction perpendicular to the Z-axis direction, and the Y-axis direction is the direction perpendicular to the XZ plane. Based on the principle that the maximum dimensions PX and PY in the X-axis direction do not collide with the magnetic aperture, the position that makes the center point of the region model closest to the center of the magnetic resonance imaging (MRI) ISO is determined as follows: Calculate the vertical distances from the two endpoints of the maximum dimension PX in the X-axis direction to the center point of the region model, and take the larger vertical distance as the collision avoidance reference value maxX in the X-axis direction; Calculate the vertical distances from the two endpoints of the maximum dimension PY in the Y-axis direction to the center point of the region model, and take the larger vertical distance as the collision avoidance reference value maxY in the Y-axis direction; The anti-collision reference value maxX in the X-axis direction is compared with the radius of the magnetic aperture. When the anti-collision reference value maxX in the X-axis direction is less than or equal to the radius of the magnetic aperture, the offset value of the X-axis direction from the center of the magnetic resonance ISO is determined to be 0. When the anti-collision reference value maxX in the X-axis direction is greater than the radius of the magnetic aperture, the offset value of the X-axis direction from the center of the magnetic resonance ISO is determined to be the radius of the magnetic aperture minus the anti-collision reference value maxX in the X-axis direction. The anti-collision reference value maxY in the Y-axis direction is compared with the radius of the magnetic aperture. When the anti-collision reference value maxY in the Y-axis direction is less than or equal to the radius of the magnetic aperture, the offset value of the Y-axis direction from the center of the magnetic resonance ISO is determined to be 0. When the anti-collision reference value maxY in the Y-axis direction is greater than the radius of the magnetic aperture, the offset value of the Y-axis direction from the center of the magnetic resonance ISO is determined to be the radius of the magnetic aperture minus the anti-collision reference value maxY in the Y-axis direction. The offset value of the Z-axis direction from the center of the magnetic resonance ISO is determined to be 0; Based on the offset values ​​of the X-axis direction, Y-axis direction, and Z-axis direction from the center of the magnetic resonance ISO, the position that makes the center point of the region model closest to the center of the magnetic resonance ISO is obtained.

2. The magnetic resonance ISO center localization method according to claim 1, characterized in that, The determination of the patient's maximum dimensions PX in the X-axis direction and maximum dimensions PY in the Y-axis direction in the XY plane when the patient enters the magnetic aperture based on the depth image includes: Calculate the Z-axis body length of the patient entering the magnetic aperture when the center point of the region model is moved to the center of the magnetic resonance ISO. The maximum dimensions PX and PY of the patient in the X-axis direction and the maximum dimensions PY in the Y-axis direction of the XY plane are detected from the image region corresponding to the body length in the depth image.

3. The magnetic resonance ISO center localization method according to claim 1, characterized in that, The determination of the patient's maximum dimensions PX in the X-axis direction and maximum dimensions PY in the Y-axis direction in the XY plane when the patient enters the magnetic aperture based on the depth image includes: Detect the patient's boundaries from the depth image and construct an overall model covering the patient's boundaries; Based on the overall model, determine the patient's maximum dimension PX in the X-axis direction and maximum dimension PY in the Y-axis direction on the XY plane.

4. The magnetic resonance ISO center localization method according to claim 3, characterized in that, Based on the offset values ​​from the magnetic resonance ISO center in the X-axis direction, Y-axis direction, and Z-axis direction, the position that makes the center point of the region model closest to the magnetic resonance ISO center is obtained, including: The positions determined by the offset values ​​of the X-axis direction, the Y-axis direction, and the Z-axis direction from the center of the magnetic resonance ISO are used as the center point of the region model, and the estimated position of the overall model in the magnetic aperture is determined. Determine whether the overall model collides with the magnetic aperture at the estimated position. If no collision occurs, the position determined by the offset values ​​of the X-axis, Y-axis, and Z-axis from the center of magnetic resonance imaging (MRI) is taken as the position where the center point of the region model is closest to the center of MRI. If a collision occurs, the method of traversing the offset values ​​of the X-axis and Y-axis from the center of MRI is used to find the combination of X-axis and Y-axis offset values ​​that minimizes the distance from the center of MRI and prevents the patient from colliding with the magnetic aperture. The position determined by the combination of the X-axis and Y-axis offset values ​​and the Z-axis offset value is taken as the position where the center point of the region model is closest to the center of MRI.

5. A magnetic resonance ISO center positioning system, characterized in that, include: A depth camera (61) is used to acquire depth images of the patient on the patient examination table; The region model building module (62) is used to detect the boundary of the scanned region from the depth image according to the set scanned region information, and construct a region model covering the boundary of the scanned region; The maximum size determination module (63) is used to determine, based on the depth image, the maximum size PX of the patient in the X-axis direction and the maximum size PY in the Y-axis direction of the patient when the patient enters the magnetic aperture; The positioning module (64) is used to determine the position that makes the center point of the region model closest to the center of the magnetic resonance ISO according to the principle that the maximum size PX in the X-axis direction and the maximum size PY in the Y-axis direction do not collide with the magnetic hole, and to move the determined position as the center point of the region model to the center of the magnetic resonance ISO inside the magnetic hole. Wherein, the Z-axis direction is the direction in which the patient enters and exits the magnetic aperture, the X-axis direction is the horizontal direction perpendicular to the Z-axis direction, and the Y-axis direction is the direction perpendicular to the XZ plane. The positioning module (64) includes: The first calculation module (641) is used to calculate the vertical distances from the two endpoints of the maximum dimension PX in the X-axis direction to the center point of the region model, and take the larger vertical distance as the anti-collision reference value maxX in the X-axis direction. The second calculation module (642) is used to calculate the vertical distances from the two endpoints of the maximum dimension PY in the Y-axis direction to the center point of the region model, and take the larger vertical distance as the anti-collision reference value maxY in the Y-axis direction. The first processing module (643) is used to compare the anti-collision reference value maxX in the X-axis direction with the radius of the magnetic aperture. When the anti-collision reference value maxX in the X-axis direction is less than or equal to the radius of the magnetic aperture, the offset value of the X-axis direction from the center of the magnetic resonance ISO is determined to be 0. When the anti-collision reference value maxX in the X-axis direction is greater than the radius of the magnetic aperture, the offset value of the X-axis direction from the center of the magnetic resonance ISO is determined to be the radius of the magnetic aperture minus the anti-collision reference value maxX in the X-axis direction. The second processing module (644) is used to compare the anti-collision reference value maxY in the Y-axis direction with the radius of the magnetic aperture. When the anti-collision reference value maxY in the Y-axis direction is less than or equal to the radius of the magnetic aperture, the offset value of the Y-axis direction from the center of the magnetic resonance ISO is determined to be 0. When the anti-collision reference value maxY in the Y-axis direction is greater than the radius of the magnetic aperture, the offset value of the Y-axis direction from the center of the magnetic resonance ISO is determined to be the radius of the magnetic aperture minus the anti-collision reference value maxY in the Y-axis direction. The third processing module (645) is used to determine that the offset value of the Z-axis direction from the center of the magnetic resonance ISO is 0; The position determination module (646) is used to determine the position that makes the center point of the region model closest to the center of the magnetic resonance ISO based on the offset values ​​of the X-axis direction, the Y-axis direction, and the Z-axis direction from the center of the magnetic resonance ISO.

6. The magnetic resonance ISO center positioning system according to claim 5, characterized in that, The maximum size determination module (63) includes: A body length calculation module (631) is used to calculate the body length of the patient in the Z-axis direction when the center point of the region model is moved to the center of the magnetic resonance ISO; The maximum size detection module (632) is used to detect the maximum size PX of the patient in the X-axis direction and the maximum size PY in the Y-axis direction in the XY plane from the image region corresponding to the body length in the depth image.

7. The magnetic resonance ISO center positioning system according to claim 5, characterized in that, The maximum size determination module (63) includes: The overall model building module (633) is used to detect the boundaries of the patient from the depth image and construct an overall model covering the boundaries of the patient; The maximum size acquisition module (634) is used to acquire the maximum size PX of the patient in the X-axis direction and the maximum size PY in the Y-axis direction on the XY plane based on the overall model.

8. The magnetic resonance ISO center positioning system according to claim 7, characterized in that, The location determination module (646) includes: The first position determination submodule is used to determine the position determined by the offset values ​​of the X-axis direction, the Y-axis direction, and the Z-axis direction from the center of the magnetic resonance ISO as the center point position of the region model, and to determine the estimated position of the overall model in the magnetic aperture; The second position determination submodule is used to determine whether the overall model collides with the magnetic aperture at the estimated position. If there is no collision, the position determined by the offset values ​​of the X-axis, Y-axis, and Z-axis directions from the center of magnetic resonance ISO is taken as the position that makes the center point of the region model closest to the center of magnetic resonance ISO. If there is a collision, the method of traversing the offset values ​​of the X-axis and Y-axis from the center of magnetic resonance ISO is used to find the combination of X-axis and Y-axis offset values ​​that minimizes the distance from the center of magnetic resonance ISO and prevents the patient from colliding with the magnetic aperture. The position determined by the combination of the X-axis and Y-axis offset values ​​and the Z-axis offset value is taken as the position that makes the center point of the region model closest to the center of magnetic resonance ISO.

9. A magnetic resonance ISO center positioning system, characterized in that, include: At least one memory (81) and at least one processor (82), wherein: The at least one memory (81) is used to store computer programs; The at least one processor (82) is used to invoke a computer program stored in the at least one memory (81) to perform the magnetic resonance ISO center localization method as described in any one of claims 1 to 4.

10. A computer-readable storage medium having a computer program stored thereon; characterized in that, The computer program can be executed by a processor and implement the magnetic resonance ISO center localization method as described in any one of claims 1 to 4.

Images