Head MRI Registration Method, Navigation Method, System, and Program Product

Abstract

The present application relates to the technical field of transcranial magnetic stimulation target localization, and provides a head MRI registration method, a navigation method, a system and a program product. The patient's face is scanned by a 3D scanner to obtain scan data, and first three-dimensional model data is generated according to the scan data; an optical locator is used to collect the reflective balls attached to the patient's forehead to determine the coordinate positions of the reflective balls in the space of the optical locator; the patient's face is scanned according to the coordinate positions and second three-dimensional model data is generated; rough registration is performed on the MRI three-dimensional data, the first three-dimensional model data and the second three-dimensional model data to obtain a first transformation matrix; the three-dimensional model data and the MRI three-dimensional data are registered according to the first transformation matrix, the MRI three-dimensional data and the three-dimensional model data to obtain a second transformation matrix, and then the movement of the robotic arm is positioned and navigated, and the accuracy and efficiency of head MRI registration and navigation can be improved by the 3D scanner and the optical locator.

Description

Technical Field

[0001] The present application relates to the technical field of transcranial magnetic stimulation therapy, and particularly to a head MRI registration method, navigation method, system, and program product. Background Art

[0002] During the transcranial magnetic stimulation therapy with the assistance of a robotic arm, the magnetic therapy device at the end of the robotic arm needs to be guided to the target position for the patient's treatment by means of an optical locator. During the treatment, due to the possible head offset of the patient, which affects the treatment effect, the optical locator will follow in real time according to the head offset of the patient to improve the treatment effect. Before the guidance, it is necessary to register the magnetic resonance imaging (MRI) data of the patient and the real physical space of the patient. It is necessary to perform three-dimensional reconstruction of the patient's MRI data, and then perform spatial registration of the reconstructed three-dimensional facial data with the real facial data of the patient during the treatment.

[0003] The existing head registration process is to mark the facial feature points in the MRI space, and then use the marked facial feature points to collect the corresponding feature points on the corresponding patient's face with a collection probe. The doctor uses the collection probe to collect the feature points on the patient's face; the coordinate transformation of the MRI space coordinates and the physical space coordinates where the real patient is located is performed through the marked facial feature points and the feature points at the preset positions collected by the collection probe, and the MRI data space coordinates and the real patient space coordinates are unified.

[0004] The disadvantage of this registration process is that when the doctor uses the collection probe to collect the feature points on the patient's head, it is very difficult to accurately collect the corresponding points in the MRI space, and the registration has high requirements for the doctor's collection technique, the registration effect is not ideal, the registration time is long, and the registration efficiency is low. Summary of the Invention

[0005] In order to solve or at least partially solve the above technical problems, the present application provides a head MRI registration method, navigation method, system, and program product, which can avoid the errors caused by manual collection, more accurately achieve registration, and can also improve the head MRI registration speed and navigation speed.

[0006] In a first aspect, the present application provides a head MRI registration method, including:

[0007] Obtain the MRI three-dimensional data of the patient;

[0008] Perform a facial scan on the patient with a 3D scanner to obtain scan data, and generate first three-dimensional model data according to the scan data;

[0009] Use an optical locator to collect the reflective sphere attached to the patient's forehead, and determine the coordinate position of the reflective sphere in the space of the optical locator;

[0010] Scan the patient's face according to the coordinate position of the reflective sphere in the space of the optical locator and generate second three-dimensional model data;

[0011] Perform coordinate transformation on the MRI space coordinates and the space coordinates of the 3D scanner according to the MRI three-dimensional data, the first three-dimensional model data, and the second three-dimensional model data to obtain a first transformation matrix;

[0012] Register the second three-dimensional model data and the MRI three-dimensional data according to the first transformation matrix, the MRI three-dimensional data, and the second three-dimensional model data to obtain a second transformation matrix.

[0013] In a second aspect, the present application provides a method for head MRI navigation, including:

[0014] Obtain the MRI three-dimensional data of the patient;

[0015] Scan the patient's face with a 3D scanner to obtain scan data, and generate first three-dimensional model data according to the scan data;

[0016] Use an optical locator to collect the reflective sphere attached to the patient's forehead, and determine the coordinate position of the reflective sphere in the space of the optical locator;

[0017] Scan the patient's face according to the coordinate position of the reflective sphere in the space of the optical locator and generate second three-dimensional model data;

[0018] Perform coordinate transformation on the MRI space coordinates and the space coordinates of the 3D scanner according to the MRI three-dimensional data, the first three-dimensional model data, and the second three-dimensional model data to obtain a first transformation matrix;

[0019] Register the second three-dimensional model data and the MRI three-dimensional data according to the first transformation matrix, the MRI three-dimensional data, and the second three-dimensional model data to obtain a second transformation matrix;

[0020] Position and navigate the movement of the robotic arm according to the position of the reflective sphere in the space of the optical locator and the second transformation matrix, so as to move the TMS coil to the magnetic stimulation point on the patient's head for treatment.

[0021] In a third aspect, the present application provides a head MRI registration system, including:

[0022] An acquisition module for acquiring the MRI three-dimensional data of the patient;

[0023] The obtaining module is further configured to perform a facial scan on the patient through a 3D scanner to obtain scan data, and generate first three-dimensional model data according to the scan data;

[0024] The acquisition module is configured to use an optical locator to acquire a reflective sphere attached to the patient's forehead, and determine the coordinate position of the reflective sphere in the space of the optical locator;

[0025] The obtaining module is further configured to perform a scan on the patient's face according to the coordinate position of the reflective sphere in the space of the optical locator and generate second three-dimensional model data;

[0026] The registration module is configured to perform coordinate transformation on the MRI space coordinates and the space coordinates of the 3D scanner according to the MRI three-dimensional data, the first three-dimensional model data, and the second three-dimensional model data to obtain a first transformation matrix;

[0027] The registration module is further configured to register the second three-dimensional model data and the MRI three-dimensional data according to the first transformation matrix, the MRI three-dimensional data, and the second three-dimensional model data to obtain a second transformation matrix.

[0028] In a fourth aspect, the present application provides a head MRI navigation system, including:

[0029] An obtaining module, configured to obtain MRI three-dimensional data of a patient;

[0030] The obtaining module is further configured to perform a facial scan on the patient through a 3D scanner to obtain scan data, and generate first three-dimensional model data according to the scan data;

[0031] The acquisition module is configured to use an optical locator to acquire a reflective sphere attached to the patient's forehead, and determine the coordinate position of the reflective sphere in the space of the optical locator;

[0032] The obtaining module is further configured to perform a scan on the patient's face according to the coordinate position of the reflective sphere in the space of the optical locator and generate second three-dimensional model data;

[0033] The registration module is configured to perform coordinate transformation on the MRI space coordinates and the space coordinates of the 3D scanner according to the MRI three-dimensional data, the first three-dimensional model data, and the second three-dimensional model data to obtain a first transformation matrix;

[0034] The registration module is further configured to register the second three-dimensional model data and the MRI three-dimensional data according to the first transformation matrix, the MRI three-dimensional data, and the second three-dimensional model data to obtain a second transformation matrix;

[0035] A navigation module, configured to perform positioning and navigation on the movement of the robotic arm according to the position of the reflective sphere in the space of the optical locator and the second transformation matrix, so as to move the TMS coil to the magnetic stimulation point on the patient's head to perform treatment.

[0036] In a fifth aspect, an embodiment of the present application further provides a head MRI registration system, including a processor and a memory; and one or more programs, the one or more programs are stored in the memory and are configured to be executed by the processor, and the programs include steps for the head MRI registration method as described in the first aspect.

[0037] In a sixth aspect, an embodiment of the present application further provides a head MRI navigation system, including a processor and a memory; and one or more programs, the one or more programs are stored in the memory and are configured to be executed by the processor, and the programs include steps for the head MRI navigation method as described in the second aspect.

[0038] In a seventh aspect, an embodiment of the present application further provides a computer program product, which, when executed by a computer, enables the computer to execute the head MRI registration method of the foregoing first aspect or the head MRI navigation method of the foregoing second aspect.

[0039] For the head MRI registration method of the embodiment of the present application, a 3D scanner is used to scan the patient's face to obtain scan data, and first three-dimensional model data is generated according to the scan data; an optical locator is used to collect the reflective sphere attached to the patient's forehead to determine the coordinate position of the reflective sphere in the space of the optical locator; the patient's face is scanned according to the coordinate position of the reflective sphere in the space of the optical locator and second three-dimensional model data is generated; coordinate transformation is performed on the MRI space coordinates and the space coordinates of the 3D scanner according to the MRI three-dimensional data, the first three-dimensional model data and the second three-dimensional model data to obtain a first transformation matrix; the three-dimensional model data and the MRI three-dimensional data are registered according to the first transformation matrix, the MRI three-dimensional data and the three-dimensional model data to obtain a second transformation matrix. Further, the head MRI navigation method can perform positioning and navigation on the movement of the robotic arm according to the position of the reflective sphere in the space of the optical locator and the second transformation matrix, so as to move the TMS coil to the magnetic stimulation point on the patient's head to perform treatment. Therefore, the accuracy and efficiency of head MRI registration can be improved by using a 3D scanner and an optical locator, and the accuracy and efficiency of transcranial magnetic stimulation treatment can be improved. Description of the Drawings

[0040] To more clearly illustrate the embodiments of the present application, the following will briefly introduce the relevant drawings. It can be understood that the drawings in the following description are only used to illustrate some embodiments of the present application, and those of ordinary skill in the art can also obtain many other technical features and connection relationships not mentioned in this text based on these drawings.

[0041] Figure 1 Structural schematic diagram of a head MRI registration method provided by an embodiment of the present application;

[0042] Figure 2 Demonstration schematic diagram of performing face recognition on MRI three-dimensional data through a preset face recognition model to obtain first face feature points provided by an embodiment of the present application;

[0043] Figure 3 Demonstration schematic diagram of marking first preset feature points on a first three-dimensional model corresponding to first three-dimensional model data provided by an embodiment of the present application;

[0044] Figure 4 Demonstration schematic diagram of collecting a face rectangular area of an RGB image provided by an embodiment of the present application;

[0045] Figure 5 Demonstration schematic diagram of mapping the face rectangular area to a depth map provided by an embodiment of the present application;

[0046] Figure 6 Demonstration schematic diagram of mapping the face rectangular area of an RGB image to MRI three-dimensional data during fine registration provided by an embodiment of the present application;

[0047] Figure 7 Demonstration schematic diagram of performing fine registration on MRI three-dimensional data and second three-dimensional model data provided by an embodiment of the present application;

[0048] Figure 8 Structural schematic diagram of another head MRI registration method provided by an embodiment of the present application;

[0049] Figure 9 Structural schematic diagram of a head MRI registration system provided by an embodiment of the present application;

[0050] Figure 10 Structural schematic diagram of a head MRI registration system provided by an embodiment of the present application. Specific embodiments

[0051] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present application without creative efforts shall fall within the protection scope of the present application.

[0052] The terms "first", "second", "third", "fourth", etc. in the specification and claims of the present application and the accompanying drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units is not limited to the listed steps or units, but optionally further includes steps or units not listed, or optionally further includes other steps or units inherent to these processes, methods, products, or devices.

[0053] Referring to "embodiment" herein means that a specific feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the present application. The phrase is shown at various positions in the specification and does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art will explicitly and implicitly understand that the embodiments described herein can be combined with other embodiments.

[0054] Next, the technical solutions in the embodiments of the present application will be described in detail in conjunction with the accompanying drawings in the embodiments of the present application.

[0055] Embodiment 1

[0056] As Figure 1 shown, Figure 1 is a schematic flowchart of a head MRI registration method provided by an embodiment of the present application. An embodiment of the present application proposes a head MRI registration method, which includes:

[0057] 101. Obtain the three-dimensional MRI data of the patient.

[0058] Among them, a magnetic resonance imaging (MRI) scanner can be used to collect the magnetic resonance brain imaging data of the test subject, and the three-dimensional MRI data can be generated according to the magnetic resonance brain imaging data.

[0059] 102. Scan the face of the patient with a 3D scanner to obtain scan data, and generate first three-dimensional model data according to the scan data.

[0060] The scanned data includes GRB images, depth maps, and point clouds corresponding to the depth maps. Specifically, a 3D scanner can be registered with an optical locator so that the origins of the 3D scanner and the optical locator are in the same coordinate system to determine the relative position relationship between the 3D scanner and the optical locator. The patient's face is scanned with the 3D scanner to obtain scanned data, and first three-dimensional model data is generated based on the scanned data to mark a first preset feature point corresponding to the first three-dimensional model corresponding to the first three-dimensional model data and the MRI three-dimensional data.

[0061] 103. Use an optical locator to collect the reflective sphere attached to the patient's forehead and determine the coordinate position of the reflective sphere in the space of the optical locator.

[0062] Among them, by using an optical locator to collect the reflective sphere attached to the patient's forehead, the coordinate position of the reflective sphere in the space of the optical locator can be known.

[0063] 104. Scan the patient's face according to the coordinate position of the reflective sphere in the space of the optical locator and generate second three-dimensional model data.

[0064] Among them, after using the reflective sphere to determine the coordinate position of the reflective sphere in the space of the optical locator, accurate scanning and generation of second three-dimensional model data can be performed.

[0065] 105. Perform coordinate transformation on the MRI space coordinates and the space coordinates of the 3D scanner according to the MRI three-dimensional data, the first three-dimensional model data, and the second three-dimensional model data to obtain a first transformation matrix.

[0066] Among them, the process of performing coordinate transformation to obtain the first transformation matrix can be understood as rough registration, and the purpose is to improve the coincidence degree of the two sets of data as much as possible through the transformation matrix (rotation and translation).

[0067] Specifically, the first three-dimensional model data is used for feature point marking, and the second three-dimensional model data is used for coordinate transformation with the MRI three-dimensional data. Feature points can be marked at the places with the same features of the two sets of data (the second three-dimensional model data and the MRI three-dimensional data), and then the matrix transformation of the two sets of data is obtained through the transformation of the feature points.

[0068] 106. Register the second three-dimensional model data and the MRI three-dimensional data according to the first transformation matrix, the MRI three-dimensional data, and the second three-dimensional model data to obtain a second transformation matrix.

[0069] Among them, the first transformation matrix is used to determine the initial position for registering the MRI three-dimensional data and the three-dimensional model data of the human face part area; the process of performing registration to obtain the second transformation matrix can be understood as fine registration, such as Figure 7As shown, it is a demonstration schematic diagram for precise registration of MRI three-dimensional data and second three-dimensional model data. In this solution, through rough registration, two groups of data (MRI three-dimensional data and second three-dimensional model data) are initially aligned to find a general matching relationship, providing a better initial position for subsequent precise registration. Further, through precise registration, the optimal transformation matrix is calculated to minimize the distance between corresponding point pairs in two spaces (MRI space and 3D scanner space) to achieve high-precision registration.

[0070] Specifically, the initial position for registering the MRI three-dimensional data and the three-dimensional model data of the facial part region can be determined according to the first transformation matrix; then, the second three-dimensional model data and the MRI three-dimensional data are registered according to the initial position to obtain the second transformation matrix, thereby achieving precise registration.

[0071] In an embodiment of the present application, a head MRI registration method includes: scanning the patient's face by a 3D scanner to obtain scan data, generating first three-dimensional model data according to the scan data; using an optical locator to collect the reflective balls attached to the patient's forehead to determine the coordinate positions of the reflective balls in the optical locator space; scanning the patient's face according to the coordinate positions of the reflective balls in the optical locator space and generating second three-dimensional model data; performing coordinate transformation on the MRI space coordinates and the space coordinates of the 3D scanner according to the MRI three-dimensional data, the first three-dimensional model data, and the second three-dimensional model data to obtain the first transformation matrix; registering the three-dimensional model data and the MRI three-dimensional data according to the first transformation matrix, the MRI three-dimensional data, and the three-dimensional model data to obtain the second transformation matrix. Further, the head MRI navigation method can position and navigate the movement of the robotic arm according to the position of the reflective balls in the optical locator space and the second transformation matrix to move the TMS coil to the magnetic stimulation point on the patient's head for treatment. Thus, the accuracy and efficiency of head MRI registration can be improved by the 3D scanner and the optical locator, and the accuracy and efficiency of transcranial magnetic stimulation treatment can be improved.

[0072] Optionally, the obtaining of the patient's MRI three-dimensional data includes:

[0073] Obtaining the magnetic resonance imaging data of the patient;

[0074] Performing three-dimensional reconstruction on the magnetic resonance imaging data to obtain the MRI three-dimensional data.

[0075] Among them, magnetic resonance brain imaging may include functional magnetic resonance imaging (fMRI) and structural magnetic resonance imaging (sMRI). Three-dimensional reconstruction can be performed based on the functional magnetic resonance image and the structural magnetic resonance image to obtain MRI three-dimensional data.

[0076] Optionally, the coordinate transformation of the MRI spatial coordinates and the spatial coordinates of the 3D scanner according to the MRI three-dimensional data, the first three-dimensional model data, and the second three-dimensional model data to obtain the first transformation matrix includes:

[0077] Mark the first preset feature points corresponding to the MRI three-dimensional data on the first three-dimensional model corresponding to the first three-dimensional model data;

[0078] Mark the second preset feature points corresponding to the first preset feature points on the second three-dimensional model;

[0079] Perform coordinate transformation on the MRI spatial coordinates and the spatial coordinates of the 3D scanner according to the MRI three-dimensional data and the second preset feature points to obtain the first transformation matrix.

[0080] Among them, as Figure 3 shown, it is a demonstration schematic diagram of marking the first preset feature points on the first three-dimensional model corresponding to the first three-dimensional model data. In this solution, by using a face recognition model, the face feature points of the first three-dimensional model scanned by the 3D scanner can be marked to obtain the first preset feature points; through rough registration, the two data sets (MRI three-dimensional data and the second three-dimensional model data) are initially aligned to find a general matching relationship, providing a better initial position for subsequent precise registration.

[0081] Specifically, mark the first preset feature points corresponding to the MRI three-dimensional data on the first three-dimensional model according to the MRI three-dimensional data; then, mark the second preset feature points corresponding to the first preset feature points on the second three-dimensional model, so that the second preset feature points can be used for rough registration to obtain the first transformation matrix.

[0082] Through the transformation matrix (rotation and translation), the coincidence degree of the two data sets is improved as much as possible. The first three-dimensional model data is used for feature point marking, and the second three-dimensional model data is used for coordinate transformation with the MRI three-dimensional data. Feature points can be marked at the same features of the two data sets (the second three-dimensional model data and the MRI three-dimensional data), and then the matrix transformation of the two data sets is obtained through the transformation of the feature points to obtain the first transformation matrix.

[0083] Optionally, the coordinate transformation of the MRI spatial coordinates and the spatial coordinates of the 3D scanner according to the MRI three-dimensional data and the second three-dimensional model data to obtain a first transformation matrix includes:

[0084] Performing face recognition on the MRI three-dimensional data through a preset face recognition model to obtain first face feature points;

[0085] Performing coordinate transformation on the MRI spatial coordinates and the spatial coordinates of the 3D scanner according to the first face feature points and the second preset feature points to obtain a first transformation matrix.

[0086] Among them, as Figure 2 shown, it is a demonstration schematic diagram of performing face recognition on MRI three-dimensional data through a preset face recognition model to obtain first face feature points; specifically, face recognition can be performed on the MRI three-dimensional data through a preset face recognition model to obtain first face feature points. By adopting the face recognition model in this solution, the face feature points of the MRI three-dimensional model can be marked more accurately; the face recognition model can be pre-trained. Specifically, the three-dimensional point cloud sample data of the human face can be obtained through a 3D scanner; the MRI point cloud sample data can be obtained; the three-dimensional point cloud sample data and the MRI point cloud sample data are trained through a PointNet network model to obtain the preset face recognition model.

[0087] In this solution, face feature point recognition can be performed through an AI model. Specifically, face recognition is performed on the MRI three-dimensional data through a preset face recognition model to obtain first face feature points, and then the first face feature points are used for rough registration to obtain a first transformation matrix.

[0088] Optionally, the scan data includes a depth map; the registration of the second three-dimensional model data and the MRI three-dimensional data according to the first transformation matrix, the MRI three-dimensional data and the second three-dimensional model data to obtain a second transformation matrix includes:

[0089] Cropping the face region on the depth map to obtain a partial face region;

[0090] Registering the partial face region and the MRI three-dimensional data according to the first transformation matrix, the MRI three-dimensional data and the three-dimensional model data of the partial face region to obtain a second transformation matrix.

[0091] Among them, by cropping the face region on the depth map to obtain a partial face region and performing fine registration on the partial face region, the registration speed and accuracy can be improved.

[0092] Optionally, registering the face partial region and the MRI three-dimensional data according to the first transformation matrix, the MRI three-dimensional data, and the three-dimensional model data of the face partial region to obtain a second transformation matrix includes:

[0093] Determining an initial position for registering the MRI three-dimensional data and the three-dimensional model data of the face partial region according to the first transformation matrix;

[0094] Performing point cloud set sampling and preprocessing on the MRI three-dimensional data and the three-dimensional model data of the face partial region to obtain a preprocessed target point cloud set and an input point cloud set; the input point cloud set corresponds to the three-dimensional model data of the face partial region, and the target point cloud set corresponds to the MRI three-dimensional data;

[0095] Performing point cloud matching on the target point cloud set and the input point cloud set according to the initial position, wherein the point cloud of the input point cloud set is transformed to the coordinate system corresponding to the target point cloud set by constructing a transformation matrix, and an error function between the source point cloud and the target point cloud after transformation is estimated. When it is determined that the error function converges, a second transformation matrix is obtained.

[0096] Among them, the target point cloud set P = {p1, p2,..., p n} and the input point cloud set X = {x1, x2,..., x n} can be subjected to point cloud matching, a transformation matrix (R, t) is constructed, and the error function is:

[0097] .

[0098] Among them, N is the number of point clouds of the target points.

[0099] Optionally, determining the initial position for registering the MRI three-dimensional data and the three-dimensional model data of the face partial region according to the first transformation matrix includes:

[0100] Performing rotation and translation operations on the MRI three-dimensional data and the three-dimensional model data of the face partial region according to the first transformation matrix to make the MRI three-dimensional data and the three-dimensional model data of the face partial region match successfully, and obtaining the initial position.

[0101] Optionally, the scan data further includes an RGB map. Cropping the face region on the depth map to obtain a face partial region includes:

[0102] Collecting the face rectangular region of the RGB map;

[0103] Mapping the face rectangular region to the depth map to obtain the face partial region of the depth map rectangle.

[0104] As Figure 4 shown, it is a demonstration schematic diagram of collecting the rectangular face area of an RGB image. As Figure 5 shown, it is a demonstration schematic diagram of mapping the rectangular face area to a depth map; As Figure 6 shown, it is a demonstration schematic diagram of mapping the rectangular face area of an RGB image to MRI three-dimensional data during fine registration. By collecting the rectangular face area of the RGB image, mapping the rectangular face area to the depth map, obtaining the partial face area of the depth map rectangle, and performing fine registration on the partial face area, the registration speed and accuracy can be improved.

[0105] Embodiment 2

[0106] As Figure 8 shown, an implementation manner of the present application proposes another head MRI registration method. Figure 8 The flow schematic diagram of another head MRI registration method provided by the implementation manner of the present application. The method includes:

[0107] 201. Obtain the magnetic resonance imaging data of the patient.

[0108] 202. Perform three-dimensional reconstruction on the magnetic resonance imaging data to obtain MRI three-dimensional data.

[0109] 203. Scan the patient's face through a 3D scanner to obtain scan data, and generate first three-dimensional model data according to the scan data.

[0110] 204. Use an optical locator to collect the reflective balls attached to the patient's forehead, and determine the coordinate positions of the reflective balls in the space of the optical locator.

[0111] 205. Scan the patient's face according to the coordinate positions of the reflective balls in the space of the optical locator and generate second three-dimensional model data.

[0112] 206. Mark first preset feature points corresponding to the MRI three-dimensional data on the first three-dimensional model corresponding to the first three-dimensional model data.

[0113] 207. Mark second preset feature points corresponding to the first preset feature points on the second three-dimensional model.

[0114] 208. Perform coordinate transformation on the MRI space coordinates and the space coordinates of the 3D scanner according to the MRI three-dimensional data and the second preset feature points to obtain a first transformation matrix.

[0115] 209. Crop the face area on the depth map to obtain a partial face area.

[0116] 210. Determine the initial position for registering the MRI three-dimensional data and the three-dimensional model data of the partial face region according to the first transformation matrix.

[0117] 211. Perform point cloud set sampling and preprocessing on the MRI three-dimensional data and the three-dimensional model data of the partial face region to obtain a preprocessed target point cloud set and an input point cloud set.

[0118] 212. Perform point cloud matching on the target point cloud set and the input point cloud set according to the initial position. Among them, transform the point cloud of the input point cloud set to the coordinate system corresponding to the target point cloud set by constructing a transformation matrix, estimate the error function between the source point cloud and the target point cloud after transformation, and when it is determined that the error function converges, obtain the second transformation matrix.

[0119] In this embodiment, by marking the first preset feature points corresponding to the MRI three-dimensional data on the first three-dimensional model corresponding to the first three-dimensional model data, marking the second preset feature points corresponding to the first preset feature points on the second three-dimensional model, performing coordinate transformation on the MRI spatial coordinates and the spatial coordinates of the 3D scanner according to the MRI three-dimensional data and the second preset feature points to obtain the first transformation matrix, cropping the face region on the depth map to obtain the partial face region, determining the initial position for registering the MRI three-dimensional data and the three-dimensional model data of the partial face region according to the first transformation matrix, performing point cloud set sampling and preprocessing on the MRI three-dimensional data and the three-dimensional model data of the partial face region to obtain a preprocessed target point cloud set and an input point cloud set, performing point cloud matching on the target point cloud set and the input point cloud set according to the initial position. Among them, transform the point cloud of the input point cloud set to the coordinate system corresponding to the target point cloud set by constructing a transformation matrix, estimate the error function between the source point cloud and the target point cloud after transformation, and when it is determined that the error function converges, obtain the second transformation matrix, mapping the face rectangular region to the depth map, obtaining the partial face region of the depth map rectangle, and performing fine registration on the partial face region can improve the registration speed and accuracy.

[0120] Embodiment Three

[0121] An embodiment of the present application proposes a head MRI navigation method, and this method includes:

[0122] Obtain the MRI three-dimensional data of the patient;

[0123] Perform facial scanning on the patient by a 3D scanner to obtain scanning data, and generate the first three-dimensional model data according to the scanning data;

[0124] Use an optical locator to collect the reflective sphere attached to the patient's forehead, and determine the coordinate position of the reflective sphere in the space of the optical locator;

[0125] Scan the patient's face according to the coordinate position of the reflective sphere in the space of the optical locator and generate second three-dimensional model data;

[0126] Perform coordinate transformation on the MRI spatial coordinates and the spatial coordinates of the 3D scanner according to the MRI three-dimensional data, the first three-dimensional model data, and the second three-dimensional model data to obtain a first transformation matrix;

[0127] Register the second three-dimensional model data and the MRI three-dimensional data according to the first transformation matrix, the MRI three-dimensional data, and the second three-dimensional model data to obtain a second transformation matrix;

[0128] Position and navigate the movement of the robotic arm according to the position of the reflective sphere in the space of the optical locator and the second transformation matrix, so as to move the TMS coil to the magnetic stimulation point on the patient's head for treatment.

[0129] Among them, the steps of the above method can refer to the specific implementation steps of the foregoing head MRI registration method, which will not be elaborated here.

[0130] Scan the patient's face with a 3D scanner to obtain scan data, and generate first three-dimensional model data according to the scan data; use an optical locator to collect the reflective sphere attached to the patient's forehead, and determine the coordinate position of the reflective sphere in the space of the optical locator; scan the patient's face according to the coordinate position of the reflective sphere in the space of the optical locator and generate second three-dimensional model data; perform coordinate transformation on the MRI spatial coordinates and the spatial coordinates of the 3D scanner according to the MRI three-dimensional data, the first three-dimensional model data, and the second three-dimensional model data to obtain a first transformation matrix; register the three-dimensional model data and the MRI three-dimensional data according to the first transformation matrix, the MRI three-dimensional data, and the three-dimensional model data to obtain a second transformation matrix. Further, the head MRI navigation method can position and navigate the movement of the robotic arm according to the position of the reflective sphere in the space of the optical locator and the second transformation matrix, so as to move the TMS coil to the magnetic stimulation point on the patient's head for treatment. By positioning and navigating the movement of the robotic arm, the TMS coil is moved to the magnetic stimulation point on the patient's head for treatment. Thus, the accuracy and efficiency of head MRI registration can be improved by using a 3D scanner and an optical locator, and the accuracy and efficiency of transcranial magnetic stimulation treatment can be improved.

[0131] Example 4

[0132] Such as Figure 9 , Figure 9A head MRI registration system 300 provided by the application implementation method includes:

[0133] An acquisition module 301, configured to acquire three-dimensional MRI data of a patient;

[0134] The acquisition module 301 is further configured to perform a facial scan on the patient through a 3D scanner to obtain scan data, and generate first three-dimensional model data according to the scan data;

[0135] A collection module 302, configured to use an optical locator to collect a reflective sphere attached to the forehead of the patient, and determine the coordinate position of the reflective sphere in the space of the optical locator;

[0136] The acquisition module 301 is further configured to perform a scan on the patient's face according to the coordinate position of the reflective sphere in the space of the optical locator and generate second three-dimensional model data;

[0137] A registration module 303, configured to perform coordinate conversion on the MRI space coordinates and the space coordinates of the 3D scanner according to the MRI three-dimensional data, the first three-dimensional model data, and the second three-dimensional model data to obtain a first conversion matrix;

[0138] The registration module 303 is further configured to register the second three-dimensional model data and the MRI three-dimensional data according to the first conversion matrix, the MRI three-dimensional data, and the second three-dimensional model data to obtain a second conversion matrix.

[0139] Optionally, in terms of acquiring the three-dimensional MRI data of the patient, the acquisition module 301 is specifically configured to:

[0140] Acquire magnetic resonance imaging data of the patient;

[0141] Perform three-dimensional reconstruction on the magnetic resonance imaging data to obtain three-dimensional MRI data.

[0142] Optionally, in terms of performing coordinate conversion on the MRI space coordinates and the space coordinates of the 3D scanner according to the MRI three-dimensional data, the first three-dimensional model data, and the second three-dimensional model data to obtain a first conversion matrix, the registration module 303 is specifically configured to:

[0143] Mark first preset feature points corresponding to the MRI three-dimensional data on a first three-dimensional model corresponding to the first three-dimensional model data;

[0144] Mark second preset feature points corresponding to the first preset feature points on the second three-dimensional model;

[0145] Perform coordinate transformation on the MRI spatial coordinates and the spatial coordinates of the 3D scanner according to the MRI three-dimensional data and the second preset feature points to obtain a first transformation matrix.

[0146] Optionally, in the aspect of performing coordinate transformation on the MRI spatial coordinates and the spatial coordinates of the 3D scanner according to the MRI three-dimensional data and the second preset feature points to obtain a first transformation matrix, the registration module 303 is specifically configured to:

[0147] Perform face recognition on the MRI three-dimensional data through a preset face recognition model to obtain first face feature points;

[0148] Perform coordinate transformation on the MRI spatial coordinates and the spatial coordinates of the 3D scanner according to the first face feature points and the second preset feature points to obtain a first transformation matrix.

[0149] Optionally, the registration module 303 is further configured to:

[0150] Obtain three-dimensional point cloud sample data of a face through a 3D scanner; obtain MRI point cloud sample data;

[0151] Train the three-dimensional point cloud sample data and the MRI point cloud sample data through a PointNet network model to obtain the preset face recognition model.

[0152] Optionally, the scan data includes a depth map; in the aspect of registering the second three-dimensional model data and the MRI three-dimensional data according to the first transformation matrix, the MRI three-dimensional data, and the second three-dimensional model data to obtain a second transformation matrix, the registration module 303 is configured to:

[0153] Crop the face region on the depth map to obtain a partial face region;

[0154] Register the partial face region and the MRI three-dimensional data according to the first transformation matrix, the MRI three-dimensional data, and the three-dimensional model data of the partial face region to obtain a second transformation matrix.

[0155] Optionally, in the aspect of registering the partial face region and the MRI three-dimensional data according to the first transformation matrix, the MRI three-dimensional data, and the three-dimensional model data of the partial face region to obtain a second transformation matrix, the registration module 303 is specifically configured to:

[0156] Determine an initial position for registering the MRI three-dimensional data and the three-dimensional model data of the partial face region according to the first transformation matrix;

[0157] Perform point cloud set sampling and preprocessing on the MRI three-dimensional data and the three-dimensional model data of the partial face region to obtain a preprocessed target point cloud set and an input point cloud set; the input point cloud set corresponds to the three-dimensional model data of the partial face region, and the target point cloud set corresponds to the MRI three-dimensional data;

[0158] Perform point cloud matching on the target point cloud set and the input point cloud set according to the initial position. Specifically, transform the point cloud of the input point cloud set to the coordinate system corresponding to the target point cloud set by constructing a transformation matrix, estimate the error function between the source point cloud and the target point cloud after transformation, and when it is determined that the error function converges, obtain a second transformation matrix.

[0159] Optionally, in terms of determining the initial position for registering the MRI three-dimensional data and the three-dimensional model data of the partial face region according to the first transformation matrix, the registration module 303 is specifically configured to:

[0160] Perform rotation and translation operations on the MRI three-dimensional data and the three-dimensional model data of the partial face region according to the first transformation matrix to successfully match the MRI three-dimensional data and the three-dimensional model data of the partial face region, and obtain the initial position.

[0161] Optionally, the scanned data further includes an RGB image. In terms of cropping the face region on the depth map to obtain the partial face region, the registration module 303 is specifically configured to:

[0162] Collect the rectangular face region of the RGB image;

[0163] Map the rectangular face region to the depth map to obtain the partial face region of the rectangular depth map.

[0164] The head MRI registration method of this embodiment includes obtaining magnetic resonance brain imaging data of a subject individual, where the magnetic resonance brain imaging data includes functional magnetic resonance images and structural magnetic resonance images; preprocessing the magnetic resonance brain imaging data to obtain preprocessed magnetic resonance brain imaging data. By preprocessing the magnetic resonance brain imaging data, noise introduced during signal acquisition is removed, and the true functional activities of the subject's brain are retained, thereby providing a reliable basis for subsequent functional connectivity calculations; then, based on the preprocessed magnetic resonance brain imaging data, superficial brain regions are divided to obtain multiple functional sub-regions; individual target stimulation sites for transcranial magnetic stimulation are determined according to the multiple functional sub-regions. By dividing the superficial brain regions into several functional sub-regions and then using the functional sub-regions as the smallest search unit to find the individualized optimal site one by one, this solution comprehensively considers the spatio-temporal dual characteristics of the superficial cortex of the brain. The spatial arrangement of neurons in the brain is continuous, and neurons with high functional similarity are usually closer in space. The time feature on which the division of functional sub-regions in the superficial brain regions is based is the functional connectivity strength between voxels, which reflects the functional similarity between different voxels, and the spatial feature is the spatial distance between different voxels, aiming to constrain the division of functional sub-regions; by dividing the superficial brain regions into functional sub-regions, the smallest unit of target search can better reflect the functional characteristics of the brain. The voxels within each functional sub-region correspond to similar cognitive functions. This division can reduce the fluctuations in the functional connectivity strength between different voxels and effectively offset the instability of the resting-state functional connectivity within the subject individual. Even if the connectivity strength of some voxels changes over time, the functional characteristics of the entire functional sub-region still remain relatively consistent, thereby improving the robustness of target localization.

[0165] Example Five

[0166] A head MRI navigation system provided by an embodiment of the present application includes:

[0167] An acquisition module for acquiring three-dimensional MRI data of a patient;

[0168] The acquisition module is further configured to scan the face of the patient through a 3D scanner to obtain scan data, and generate first three-dimensional model data according to the scan data;

[0169] A collection module for using an optical locator to collect a reflective sphere attached to the patient's forehead and determining the coordinate position of the reflective sphere in the space of the optical locator;

[0170] The acquisition module is further configured to scan the face of the patient according to the coordinate position of the reflective sphere in the space of the optical locator and generate second three-dimensional model data;

[0171] A registration module, configured to perform coordinate transformation on the MRI spatial coordinates and the spatial coordinates of the 3D scanner according to the MRI three-dimensional data, the first three-dimensional model data, and the second three-dimensional model data, to obtain a first transformation matrix;

[0172] The registration module is further configured to register the second three-dimensional model data and the MRI three-dimensional data according to the first transformation matrix, the MRI three-dimensional data, and the second three-dimensional model data, to obtain a second transformation matrix;

[0173] A navigation module, configured to perform positioning and navigation on the movement of the robotic arm according to the position of the reflective sphere in the space of the optical locator and the second transformation matrix, so as to move the TMS coil to the magnetic stimulation point on the patient's head for treatment.

[0174] Wherein, the specific steps of the above system can refer to the specific implementation steps of the foregoing head MRI registration method, which will not be elaborated here.

[0175] The patient's face is scanned by a 3D scanner to obtain scan data, and a first three-dimensional model data is generated according to the scan data; the reflective sphere attached to the patient's forehead is collected by an optical locator to determine the coordinate position of the reflective sphere in the space of the optical locator; the patient's face is scanned according to the coordinate position of the reflective sphere in the space of the optical locator and a second three-dimensional model data is generated; the MRI spatial coordinates and the spatial coordinates of the 3D scanner are subjected to coordinate transformation according to the MRI three-dimensional data, the first three-dimensional model data, and the second three-dimensional model data to obtain a first transformation matrix; the three-dimensional model data and the MRI three-dimensional data are registered according to the first transformation matrix, the MRI three-dimensional data, and the three-dimensional model data to obtain a second transformation matrix. Further, the head MRI navigation method can perform positioning and navigation on the movement of the robotic arm according to the position of the reflective sphere in the space of the optical locator and the second transformation matrix, so as to move the TMS coil to the magnetic stimulation point on the patient's head for treatment. By performing positioning and navigation on the movement of the robotic arm, the TMS coil is moved to the magnetic stimulation point on the patient's head for treatment. Thus, the accuracy and efficiency of head MRI registration can be improved by using a 3D scanner and an optical locator, and the accuracy and efficiency of transcranial magnetic stimulation treatment can be improved.

[0176] Embodiment Six

[0177] As Figure 10 , Figure 10A head MRI registration system provided by the application implementation method. The head MRI registration system includes a processor 410 and a memory 420; and one or more programs. The one or more programs are stored in the memory. The memory 420 can be a high-speed RAM memory or a non-volatile memory, such as a disk memory. The memory 420 is used to store a set of program codes, and the processor 410 is used to call the program codes stored in the memory 420 to perform the following operations:

[0178] Obtain the three-dimensional MRI data of the patient;

[0179] Perform a facial scan on the patient through a 3D scanner to obtain scan data, and generate first three-dimensional model data according to the scan data;

[0180] Use an optical locator to collect the reflective balls attached to the patient's forehead, and determine the coordinate positions of the reflective balls in the space of the optical locator;

[0181] Scan the patient's face according to the coordinate positions of the reflective balls in the space of the optical locator and generate second three-dimensional model data;

[0182] Perform coordinate transformation on the MRI space coordinates and the space coordinates of the 3D scanner according to the MRI three-dimensional data, the first three-dimensional model data, and the second three-dimensional model data to obtain a first transformation matrix;

[0183] Register the second three-dimensional model data and the MRI three-dimensional data according to the first transformation matrix, the MRI three-dimensional data, and the second three-dimensional model data to obtain a second transformation matrix.

[0184] The head MRI registration system of this embodiment obtains the magnetic resonance brain imaging data of the subject individual, where the magnetic resonance brain imaging data includes functional magnetic resonance images and structural magnetic resonance images; preprocesses the magnetic resonance brain imaging data to obtain the preprocessed magnetic resonance brain imaging data. By preprocessing the magnetic resonance brain imaging data, the noise introduced during signal acquisition is removed, and the true functional activities of the subject's brain are retained, thus providing a reliable basis for subsequent functional connectivity calculation; then, based on the preprocessed magnetic resonance brain imaging data, the superficial brain regions are divided to obtain multiple functional sub-regions; based on the multiple functional sub-regions, the individual target stimulation points of transcranial magnetic stimulation are determined. By dividing the superficial brain regions into several functional sub-regions and then using the functional sub-regions as the smallest search unit to find the individualized optimal stimulation points one by one, this solution comprehensively considers the spatio-temporal dual characteristics of the superficial cortex of the brain. The spatial arrangement of neurons in the brain is continuous, and neurons with high functional similarity are usually closer in space. The time feature on which the division of functional sub-regions in the superficial brain regions is based is the functional connectivity strength between voxels, which reflects the functional similarity between different voxels, and the spatial feature is the spatial distance between different voxels, aiming to constrain the division of functional sub-regions; by dividing the superficial brain regions into functional sub-regions, the smallest unit of target search can better reflect the functional characteristics of the brain. The voxels within each functional sub-region correspond to similar cognitive functions. This division can reduce the fluctuation of the functional connectivity strength between different voxels and effectively offset the instability of the resting-state functional connectivity within the subject individual. Even if the connectivity strength of some voxels changes over time, the functional characteristics of the entire functional sub-region still remain relatively consistent, thereby improving the robustness of target localization.

[0185] Example Seven

[0186] A head MRI navigation system provided by an embodiment of the present application, the head MRI navigation system includes a processor 410 and a memory 420; and one or more programs, the one or more programs are stored in the memory. The above memory 420 can be a high-speed RAM memory or a non-volatile memory, such as a disk memory. The above memory 420 is used to store a set of program codes, and the processor 410 is used to call the program codes stored in the memory 420 to perform the following operations:

[0187] Obtain the three-dimensional MRI data of the patient;

[0188] Scan the face of the patient with a 3D scanner to obtain scan data, and generate first three-dimensional model data according to the scan data;

[0189] Use an optical locator to collect the reflective sphere attached to the patient's forehead and determine the coordinate position of the reflective sphere in the space of the optical locator;

[0190] Scanning the patient's face according to the coordinate position of the reflective sphere in the space of the optical locator and generating second three-dimensional model data;

[0191] Performing coordinate transformation on the MRI space coordinates and the space coordinates of the 3D scanner according to the MRI three-dimensional data, the first three-dimensional model data and the second three-dimensional model data to obtain a first transformation matrix;

[0192] Registering the second three-dimensional model data and the MRI three-dimensional data according to the first transformation matrix, the MRI three-dimensional data and the second three-dimensional model data to obtain a second transformation matrix;

[0193] Positioning and navigating the movement of the robotic arm according to the position of the reflective sphere in the space of the optical locator and the second transformation matrix, so as to move the TMS coil to the magnetic stimulation point on the patient's head to be magnetically stimulated for treatment.

[0194] The head MRI navigation system of this embodiment scans the patient's face through a 3D scanner to obtain scan data, and generates first three-dimensional model data according to the scan data; uses an optical locator to collect the reflective sphere attached to the patient's forehead, and determines the coordinate position of the reflective sphere in the space of the optical locator; scans the patient's face according to the coordinate position of the reflective sphere in the space of the optical locator and generates second three-dimensional model data; performs coordinate transformation on the MRI space coordinates and the space coordinates of the 3D scanner according to the MRI three-dimensional data, the first three-dimensional model data and the second three-dimensional model data to obtain a first transformation matrix; registers the three-dimensional model data and the MRI three-dimensional data according to the first transformation matrix, the MRI three-dimensional data and the three-dimensional model data to obtain a second transformation matrix. Further, the head MRI navigation method can position and navigate the movement of the robotic arm according to the position of the reflective sphere in the space of the optical locator and the second transformation matrix, so as to move the TMS coil to the magnetic stimulation point on the patient's head to be magnetically stimulated for treatment. By positioning and navigating the movement of the robotic arm, the TMS coil is moved to the magnetic stimulation point on the patient's head to be magnetically stimulated for treatment. Thus, the accuracy and efficiency of head MRI registration can be improved through the 3D scanner and the optical locator, and the accuracy and efficiency of transcranial magnetic stimulation treatment can be improved.

[0195] The embodiment of the present application also provides a computer program product, wherein the computer program product includes a non-transitory computer-readable program product storing a computer program, and the computer program is operable to cause a computer to execute some or all of the steps described in any one of the head MRI registration methods or head MRI navigation methods recorded in the embodiment of the present application. This computer program product can be a software installation package.

[0196] Although the present application has been described in connection with various embodiments, those skilled in the art will understand and realize other variations of the disclosed embodiments by referring to the accompanying drawings, the disclosure, and the appended claims when implementing the claimed present application. In the claims, the word "comprising" does not exclude other components or steps, and "a" or "an" does not exclude a plurality. A single processor or other unit may implement several functions recited in the claims. Certain measures are recited in mutually different dependent claims, but this does not mean that these measures cannot be combined to produce a good effect.

[0197] Those skilled in the art should understand that the embodiments of the present application may be provided as a method, an apparatus (device), or a computer program product. Therefore, the present application may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code. The computer program is stored / distributed in a suitable medium, provided together with other hardware or as part of the hardware, or may also be in other distribution forms, such as via the Internet or other wired or wireless telecommunication systems.

[0198] The present application is described with reference to the flowcharts and / or block diagrams of the methods, apparatuses (devices), and computer program products of the embodiments of the present application. It should be understood that each flow and / or block in the flowchart and / or block diagram, and the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable vehicle trajectory analysis devices to produce a machine, such that the instructions executed by the processor of the computer or other programmable vehicle trajectory analysis devices produce a device for implementing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0199] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable vehicle trajectory analysis devices to work in a specific manner, such that the instructions stored in the computer-readable memory produce a manufactured article including an instruction device that implements the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0200] These computer program instructions can also be loaded onto a computer or other programmable vehicle trajectory analysis device, so that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, thereby providing instructions executed on the computer or other programmable device for implementing the process Figure 1 in one process or multiple processes and / or blocks Figure 1 steps for the functions specified in one block or multiple blocks.

[0201] Although the present application has been described in connection with specific features and their embodiments, it is obvious that various modifications and combinations can be made without departing from the spirit and scope of the present application. Accordingly, this specification and the drawings are merely exemplary illustrations of the present application defined by the appended claims, and are considered to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, those skilled in the art can make various changes and variations to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalent technologies, the present application is also intended to include these changes and variations.

Claims

1. A head MRI registration method, characterized in that, Including: Obtaining the three-dimensional MRI data of a patient; Performing a facial scan on the patient by a 3D scanner to obtain scan data, and generating first three-dimensional model data according to the scan data; Collecting a reflective sphere attached to the patient's forehead using an optical locator to determine the coordinate position of the reflective sphere in the space of the optical locator; wherein, the origin of the 3D scanner and the optical locator is in the same coordinate system to determine the relative position relationship between the 3D scanner and the optical locator; Scanning the patient's face according to the coordinate position of the reflective sphere in the space of the optical locator and generating second three-dimensional model data; Performing coordinate transformation on the MRI space coordinates and the space coordinates of the 3D scanner according to the MRI three-dimensional data, the first three-dimensional model data and the second three-dimensional model data to obtain a first transformation matrix; Registering the second three-dimensional model data and the MRI three-dimensional data according to the first transformation matrix, the MRI three-dimensional data and the second three-dimensional model data to obtain a second transformation matrix; The performing coordinate transformation on the MRI space coordinates and the space coordinates of the 3D scanner according to the MRI three-dimensional data, the first three-dimensional model data and the second three-dimensional model data to obtain a first transformation matrix includes: marking first preset feature points corresponding to the MRI three-dimensional data on a first three-dimensional model corresponding to the first three-dimensional model data; marking second preset feature points corresponding to the first preset feature points on the second three-dimensional model; performing coordinate transformation on the MRI space coordinates and the space coordinates of the 3D scanner according to the MRI three-dimensional data and the second preset feature points to obtain a first transformation matrix.

2. The head MRI registration method according to claim 1, wherein The obtaining the three-dimensional MRI data of a patient includes: Obtaining the magnetic resonance imaging data of the patient; Performing three-dimensional reconstruction on the magnetic resonance imaging data to obtain the MRI three-dimensional data.

3. The head MRI registration method according to claim 1, wherein The performing coordinate transformation on the MRI space coordinates and the space coordinates of the 3D scanner according to the MRI three-dimensional data and the second preset feature points to obtain a first transformation matrix includes: Performing face recognition on the MRI three-dimensional data through a preset face recognition model to obtain first face feature points; Performing coordinate transformation on the MRI space coordinates and the space coordinates of the 3D scanner according to the first face feature points and the second preset feature points to obtain a first transformation matrix.

4. The head MRI registration method according to any one of claims 1-3, characterized in that, The scan data includes a depth map; the registering the second three-dimensional model data and the MRI three-dimensional data according to the first transformation matrix, the MRI three-dimensional data and the second three-dimensional model data to obtain a second transformation matrix includes: Cropping the face area on the depth map to obtain a partial face area; Registering the partial face area and the MRI three-dimensional data according to the first transformation matrix, the MRI three-dimensional data and the three-dimensional model data of the partial face area to obtain a second transformation matrix.

5. The head MRI registration method according to claim 4, wherein The registering the partial face area and the MRI three-dimensional data according to the first transformation matrix, the MRI three-dimensional data and the three-dimensional model data of the partial face area to obtain a second transformation matrix includes: Determine the initial position for registering the MRI three-dimensional data and the three-dimensional model data of the partial face region according to the first transformation matrix; Perform point cloud set sampling and preprocessing on the MRI three-dimensional data and the three-dimensional model data of the partial face region to obtain a preprocessed target point cloud set and an input point cloud set; the input point cloud set corresponds to the three-dimensional model data of the partial face region, and the target point cloud set corresponds to the MRI three-dimensional data; Perform point cloud matching on the target point cloud set and the input point cloud set according to the initial position. Among them, transform the point cloud of the input point cloud set to the coordinate system corresponding to the target point cloud set by constructing a transformation matrix, estimate the error function between the source point cloud and the target point cloud after transformation, and when it is determined that the error function converges, obtain the second transformation matrix.

6. The head MRI registration method according to claim 5, wherein The determining the initial position for registering the MRI three-dimensional data and the three-dimensional model data of the partial face region according to the first transformation matrix includes: Perform rotation and translation operations on the MRI three-dimensional data and the three-dimensional model data of the partial face region according to the first transformation matrix to make the MRI three-dimensional data and the three-dimensional model data of the partial face region match successfully, and obtain the initial position.

7. The head MRI registration method according to claim 4, wherein The scanned data further includes an RGB image. The cropping the face region on the depth map to obtain the partial face region includes: Collect the face rectangular region of the RGB image; Map the face rectangular region to the depth map to obtain the partial face region of the depth map rectangle.

8. A head MRI navigation method, characterized in that, Includes: Obtain the MRI three-dimensional data of the patient; Perform facial scanning on the patient by a 3D scanner to obtain scanned data, and generate first three-dimensional model data according to the scanned data; Use an optical locator to collect the reflective balls attached to the patient's forehead, and determine the coordinate positions of the reflective balls in the space of the optical locator; among them, make the origin of the 3D scanner and the optical locator in the same coordinate system to determine the relative position relationship between the 3D scanner and the optical locator; Perform facial scanning on the patient according to the coordinate positions of the reflective balls in the space of the optical locator and generate second three-dimensional model data; Perform coordinate transformation on the MRI space coordinates and the space coordinates of the 3D scanner according to the MRI three-dimensional data, the first three-dimensional model data and the second three-dimensional model data to obtain the first transformation matrix; Register the second three-dimensional model data and the MRI three-dimensional data according to the first transformation matrix, the MRI three-dimensional data and the second three-dimensional model data to obtain the second transformation matrix; According to the position of the reflective balls in the space of the optical locator and the second transformation matrix, perform positioning and navigation on the movement of the robotic arm to move the TMS coil to the magnetic stimulation point on the patient's head for treatment; Performing coordinate transformation on the MRI spatial coordinates and the spatial coordinates of the 3D scanner according to the MRI three-dimensional data, the first three-dimensional model data, and the second three-dimensional model data to obtain a first transformation matrix includes: marking first preset feature points corresponding to the MRI three-dimensional data on a first three-dimensional model corresponding to the first three-dimensional model data; marking second preset feature points corresponding to the first preset feature points on the second three-dimensional model; and performing coordinate transformation on the MRI spatial coordinates and the spatial coordinates of the 3D scanner according to the MRI three-dimensional data and the second preset feature points to obtain a first transformation matrix.

9. A head MRI registration system, characterized in that, including: an acquisition module, configured to acquire three-dimensional MRI data of a patient; The acquisition module is further configured to perform a facial scan on the patient through a 3D scanner to obtain scan data, and generate first three-dimensional model data according to the scan data; a collection module, configured to use an optical locator to collect a reflective sphere attached to the patient's forehead, and determine the coordinate position of the reflective sphere in the space of the optical locator; wherein, the origins of the 3D scanner and the optical locator are in the same coordinate system to determine the relative position relationship between the 3D scanner and the optical locator; The acquisition module is further configured to perform a facial scan on the patient according to the coordinate position of the reflective sphere in the space of the optical locator and generate second three-dimensional model data; a registration module, configured to perform coordinate transformation on the MRI spatial coordinates and the spatial coordinates of the 3D scanner according to the MRI three-dimensional data, the first three-dimensional model data, and the second three-dimensional model data to obtain a first transformation matrix; Performing coordinate transformation on the MRI spatial coordinates and the spatial coordinates of the 3D scanner according to the MRI three-dimensional data, the first three-dimensional model data, and the second three-dimensional model data to obtain a first transformation matrix includes: marking first preset feature points corresponding to the MRI three-dimensional data on a first three-dimensional model corresponding to the first three-dimensional model data; marking second preset feature points corresponding to the first preset feature points on the second three-dimensional model; and performing coordinate transformation on the MRI spatial coordinates and the spatial coordinates of the 3D scanner according to the MRI three-dimensional data and the second preset feature points to obtain a first transformation matrix; The registration module is further configured to register the second three-dimensional model data and the MRI three-dimensional data according to the first transformation matrix, the MRI three-dimensional data, and the second three-dimensional model data to obtain a second transformation matrix.

10. A head MRI navigation system, characterized in that, including: an acquisition module, configured to acquire three-dimensional MRI data of a patient; The acquisition module is further configured to perform a facial scan on the patient through a 3D scanner to obtain scan data, and generate first three-dimensional model data according to the scan data; a collection module, configured to use an optical locator to collect a reflective sphere attached to the patient's forehead, and determine the coordinate position of the reflective sphere in the space of the optical locator; wherein, the origins of the 3D scanner and the optical locator are in the same coordinate system to determine the relative position relationship between the 3D scanner and the optical locator; The acquisition module is further configured to scan the patient's face according to the coordinate position of the reflective sphere in the space of the optical locator and generate second three-dimensional model data; The registration module is configured to perform coordinate transformation on the MRI space coordinates and the space coordinates of the 3D scanner according to the MRI three-dimensional data, the first three-dimensional model data, and the second three-dimensional model data to obtain a first transformation matrix; The performing coordinate transformation on the MRI space coordinates and the space coordinates of the 3D scanner according to the MRI three-dimensional data, the first three-dimensional model data, and the second three-dimensional model data to obtain a first transformation matrix includes: marking first preset feature points corresponding to the MRI three-dimensional data on a first three-dimensional model corresponding to the first three-dimensional model data; marking second preset feature points corresponding to the first preset feature points on the second three-dimensional model; performing coordinate transformation on the MRI space coordinates and the space coordinates of the 3D scanner according to the MRI three-dimensional data and the second preset feature points to obtain a first transformation matrix; The registration module is further configured to register the second three-dimensional model data and the MRI three-dimensional data according to the first transformation matrix, the MRI three-dimensional data, and the second three-dimensional model data to obtain a second transformation matrix; The navigation module is configured to perform positioning and navigation on the movement of the robotic arm according to the position of the reflective sphere in the space of the optical locator and the second transformation matrix, so as to move the TMS coil to the magnetic stimulation point on the patient's head for treatment.

11. A head MRI registration system, characterized in that, Comprising a processor and a memory; and one or more programs, the one or more programs are stored in the memory and configured to be executed by the processor, the programs including the steps for the head MRI registration method according to any one of claims 1 to 7.

12. A head MRI navigation system, characterized in that, Comprising a processor and a memory; and one or more programs, the one or more programs are stored in the memory and configured to be executed by the processor, the programs including the steps for the head MRI navigation method according to claim 8.

13. A computer program product, characterized in that, When the computer program of the computer program product is executed by a processor, it can implement the steps of the head MRI navigation method according to claim 8.

Images