Positioning system and positioning method for nerve regulation target area

Abstract

The invention discloses a positioning system for a nerve regulation and control target region, which comprises a central processing module, a regulation and control target region module, a target region regulation and control module, a feature point identification module, a data comparison module and a profile map positioning module, and is characterized in that the central processing module is used for carrying out algorithm calculation on positioning of the nerve regulation and control target region. According to the invention, the position of the target area can be accurately positioned, the position positioning is faster and more accurate, the positioned position of the target area can be visually observed, and an operator can conveniently and accurately observe the position of the target area; the position of the target area can be narrowed by setting the target area, the range of the position of the target area can be narrowed, so that the required position can be positioned more quickly, and the head contour map of the patient and the generated three-color plane graph can be compared with the generated accurate coordinate position according to the head contour map of the patient. Therefore, the head coordinate can be quickly obtained according to the head profile diagram of the patient, and accurate positioning is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of computer image processing, and in particular to a positioning system and method for a neural regulation target area. Background Art

[0002] For a long time, there has been a lack of effective devices for locating brain target areas for neuromodulation. In recent years, optical navigation devices have been used clinically to calibrate the control device to the brain structure image using a traceable light ball. However, this technology is expensive (imported optical navigation cameras are generally used), cumbersome to operate (calibration requires pointing to characteristic structural points on the head with a calibration indicator), and cannot adapt to head movement, resulting in a low usage rate in clinical applications. In addition, existing equipment is very prone to errors in the process of locating the control target area, and because the scanning range is too large, the efficiency of brain area positioning is reduced. Therefore, in order to solve the shortcomings of existing positioning devices, we propose a positioning system and positioning method for neuromodulation target areas. Summary of the Invention

[0003] The purpose of the present invention is to provide a system and method for locating a target area for neuromodulation to solve the problems in the background art and to provide support for the further development of devices for efficiently and accurately locating brain target areas.

[0004] To achieve the above objectives, the present invention provides the following technical solutions: a system for positioning a target area for neural regulation, comprising:

[0005] Central processing module: The central processing module is used to perform algorithm calculations on the positioning of the neural regulation target area;

[0006] Target area control module: obtains target area control through patient imaging data;

[0007] Feature point recognition module: The feature point recognition module is used to set the patient's head contour map and three-color plane map, and process the feature points through the central processing module to generate a coordinate schematic diagram;

[0008] Data comparison module: The data comparison module is used to compare the precise coordinate data with the patient's head contour map;

[0009] Contour map positioning module: used to display the data compared by the data comparison module.

[0010] For a long time, there has been a lack of effective devices for locating brain target areas for neuromodulation. In recent years, optical navigation devices have been used to calibrate the control device to the brain structure image using a traceable light ball. However, due to the high cost (commonly using imported optical navigation cameras from abroad) and cumbersome operation (calibration requires pointing to characteristic structural points on the head with a calibration indicator), it cannot adapt to head movement and cannot accurately display the target area. Therefore, it is rarely used in clinical applications. In addition, existing equipment is inaccurate in locating the control target area during positioning, which is prone to positioning errors. In addition, the position of the non-control target area needs to be scanned in all directions during the scanning process, which may result in a large position range of the control target area, thereby affecting the positioning efficiency. The present invention can accurately locate the target area position, and the positioning is faster and more accurate. The located target area position can be intuitively observed, which facilitates the operator to accurately observe the target area position; and by setting the target target area, the target area position can be narrowed, and the target area position can be narrowed, so that the desired position can be located more quickly; and the patient's head contour map and the generated three-color plane map can be compared with the generated precise coordinate position, so that the head coordinates can be quickly obtained according to the patient's head contour map, achieving precise positioning.

[0011] Preferably, the input end of the central processing module is electrically connected to the output end of the target area control module; the output end of the central processing module is electrically connected to the input end of the target area control module, the feature point recognition module, the data comparison module and the contour map positioning module; the output end of the target area control module is electrically connected to the input end of the feature point recognition module; the output end of the feature point recognition module is electrically connected to the input end of the data comparison module; the output end of the data comparison module is electrically connected to the input end of the contour map positioning module.

[0012] Preferably, the target area control module is used to obtain the patient's magnetic resonance image and magnetic resonance structural image, and obtain the target area control through the magnetic resonance image and magnetic resonance structural image.

[0013] Preferably, the positioning method of the positioning system for a neural regulation target area comprises the following steps:

[0014] Step 1: Use magnetic resonance imaging to obtain the patient's functional magnetic resonance imaging and magnetic resonance structural imaging, and then obtain the control target area;

[0015] Step 2: using a processing method to match the functional MRI image and the structural MRI image obtained in step 1, thereby obtaining a target area on the structural MRI image;

[0016] Step 3: Use the depth camera to obtain the patient's head outline and the corresponding three-color plane image, use the calculation algorithm to identify the feature points on the plane image, and obtain the coordinate diagram of the patient's body parts based on the patient's head outline;

[0017] Step 4: Obtain the head contour map of the magnetic resonance structure image according to the coordinate diagram in step 3, then substitute the head contour map into the coordinate diagram for precise positioning and obtain accurate coordinate data, and then compare the accurate coordinate data with the patient's head contour map;

[0018] Step 5: Operate the depth camera and image control device to obtain accurate positioning in the patient's head outline image.

[0019] Preferably, the method for acquiring the target area in step 2 includes the following steps:

[0020] A1: Determine the imaging location area based on existing diagnostic images;

[0021] A2: Use multiple images to simulate positioning using CT-Sim and MRI-Sim, and then submit an appointment application;

[0022] A3: After receiving the appointment application, confirm that the CT-Sim simulation and MRI-Sim are scheduled on the same day;

[0023] A4: The mark and the required impact scanning range meet the requirements of CT-Sim simulation positioning and MRI-Sim scanning position. Then the scanning position is expanded, and then the target area position can be acquired.

[0024] Preferably, the feature points on the plane image in step 3 are identified using a SIFT algorithm, and the identification method includes the following steps:

[0025] B1: Set the reference image and the feature points in the reference image;

[0026] B2: Extract feature points from the image to be matched and the reference image respectively, and calculate the feature points using the SIFT algorithm;

[0027] B3: Describe the feature points of the image to be matched and the reference image. The reason is difficult to implement the feature descriptor in the SIFT algorithm.

[0028] B4: Use the nearest neighbor matching method to treat each feature point in the matching image, find the feature point closest to it in the reference image, and use it as the matching result;

[0029] B5: Use the RANSAC algorithm to filter and optimize the matching results, remove mismatched points, and improve the accuracy and robustness of the matching.

[0030] Preferably, in the step B3, in the feature sub-implementation, the pixel values ​​around each feature point are used as input, and the scale and direction of each pixel are calculated using a Gaussian difference pyramid to generate a local vector with 128 dimensions.

[0031] Compared with the prior art, the present invention has the following beneficial effects:

[0032] 1. The present invention can accurately locate the target area, and the positioning is faster and more accurate. The located target area can be observed visually, which is convenient for operators to accurately observe the target area;

[0033] 2. By setting the target area, the position of the target area can be narrowed, and the range of the target area position can be narrowed, so that the desired position can be located more quickly. The patient's head outline map and the generated three-color plane map can be compared with the generated precise coordinate position, so that the head coordinates can be quickly obtained according to the patient's head outline map to achieve precise positioning. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 Schematic diagram of the system principle of the present invention. DETAILED DESCRIPTION

[0035] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0036] Example 1:

[0037] See also Figure 1 The present invention provides a technical solution: a positioning system for a target area of ​​neural regulation, comprising:

[0038] Central processing module: The central processing module is used to perform algorithm calculations on the positioning of the neural regulation target area;

[0039] Target area control module: obtains target area control through patient imaging data;

[0040] Feature point recognition module: The feature point recognition module is used to set the patient's head contour map and three-color plane map, and process the feature points through the central processing module to generate a coordinate schematic diagram;

[0041] Data comparison module: The data comparison module is used to compare the precise coordinate data with the patient's head contour map;

[0042] Contour map positioning module: used to display the data compared by the data comparison module.

[0043] Preferably, the input end of the central processing module is electrically connected to the output end of the target area control module; the output end of the central processing module is electrically connected to the input end of the target area control module, the feature point recognition module, the data comparison module and the contour map positioning module; the output end of the target area control module is electrically connected to the input end of the feature point recognition module; the output end of the feature point recognition module is electrically connected to the input end of the data comparison module; the output end of the data comparison module is electrically connected to the input end of the contour map positioning module, and the central processing module is set up to process the data obtained from the target area control module, the feature point recognition module, the data comparison module and the contour map positioning module, and facilitate the interconnected target area control module, the feature point recognition module, the data comparison module and the contour map positioning module to perform data processing in sequence, so as to facilitate the rapid and convenient positioning of the neural control target area.

[0044] Preferably, the target area control module is used to obtain the patient's magnetic resonance image and magnetic resonance structural image, and obtain the target area control through the magnetic resonance image and magnetic resonance structural image.

[0045] When in use, first of all, the present invention can accurately locate the target area, and the positioning is faster and more accurate. The located target area can be observed visually, which is convenient for the operator to accurately observe the target area; and by setting the target target area, the target area can be narrowed, and the target area can be narrowed, so that the desired position can be located more quickly, and the patient's head outline map and the generated three-color plane map can be compared with the generated precise coordinate position, so that the head coordinates can be quickly obtained according to the patient's head outline map to achieve precise positioning.

[0046] Example 2:

[0047] Preferably, the positioning method of the positioning system for a neural regulation target area comprises the following steps:

[0048] Step 1: Use magnetic resonance imaging to obtain the patient's functional magnetic resonance imaging and magnetic resonance structural imaging, and then obtain the control target area;

[0049] Step 2: using a processing method to match the functional MRI image and the structural MRI image obtained in step 1, thereby obtaining a target area on the structural MRI image;

[0050] Step 3: Use the depth camera to obtain the patient's head outline and the corresponding three-color plane image, use the calculation algorithm to identify the feature points on the plane image, and obtain the coordinate diagram of the patient's body parts based on the patient's head outline;

[0051] Step 4: Obtain the head contour map of the magnetic resonance structure image according to the coordinate diagram in step 3, then substitute the head contour map into the coordinate diagram for precise positioning and obtain accurate coordinate data, and then compare the accurate coordinate data with the patient's head contour map;

[0052] Step 5: Operate the depth camera and image control device to obtain accurate positioning in the patient's head outline image.

[0053] Among them, when locating the neural regulation target area, the regulation target area can be accurately obtained through the magnetic resonance function and magnetic resonance structure influence, and then the corresponding target area can be obtained through data matching, which can narrow the range of the target area to a certain extent. Then, the depth camera can be used to calculate the corresponding feature points through the head contour map and the corresponding three-color plane map, so that an accurate coordinate diagram can be obtained, and then the coordinate data can be compared with the head contour map, so that the neural regulation target area can be accurately located.

[0054] Preferably, the method for acquiring the target area in step 2 includes the following steps:

[0055] A1: Determine the imaging location area based on existing diagnostic images;

[0056] A2: Use multiple images to simulate positioning using CT-Sim and MRI-Sim, and then submit an appointment application;

[0057] A3: After receiving the appointment application, confirm that the CT-Sim simulation and MRI-Sim are scheduled on the same day;

[0058] A4: The mark and the required impact scanning range meet the requirements of CT-Sim simulation positioning and MRI-Sim scanning position. Then the scanning position is expanded, and then the target area position can be acquired.

[0059] Among them, such a target area acquisition method can obtain the corresponding target area more accurately and quickly, and the scanning position can be expanded by using CT-Sim simulation positioning and MRI-Sim scanning position requirements, so that the target area position can be obtained quickly and accurately.

[0060] Preferably, the feature points on the plane image in step 3 are identified using a SIFT algorithm, and the identification method includes the following steps:

[0061] B1: Set the reference image and the feature points in the reference image;

[0062] B2: Extract feature points from the image to be matched and the reference image respectively, and calculate the feature points using the SIFT algorithm;

[0063] B3: Describe the feature points of the image to be matched and the reference image. The reason is difficult to implement the feature descriptor in the SIFT algorithm.

[0064] B4: Use the nearest neighbor matching method to treat each feature point in the matching image, find the feature point closest to it in the reference image, and use it as the matching result;

[0065] B5: Use the RANSAC algorithm to filter and optimize the matching results, remove mismatched points, and improve the accuracy and robustness of the matching.

[0066] Among them, the feature point extraction using the SIFT algorithm for feature recognition can make an accurate match comparison between the image to be matched and the reference image, which can improve the matching degree to a certain extent and extract appropriate feature points.

[0067] Preferably, in the step B3, in the feature sub-implementation, the pixel values ​​around each feature point are used as input, and the scale and direction of each pixel are calculated using a Gaussian difference pyramid to generate a local vector with 128 dimensions.

[0068] When in use, first, when locating the neural regulation target area, the magnetic resonance function and magnetic resonance structure influence can be used to accurately obtain the regulation target area, and then the corresponding target area can be obtained through data matching, which can narrow the scope of the target area to a certain extent. Then, the depth camera can be used to calculate the corresponding feature points through the head contour map and the corresponding three-color plane map, so that an accurate coordinate diagram can be obtained, and then the coordinate data can be compared with the head contour map, so that the neural regulation target area can be accurately located.

[0069] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A system for positioning a target area for neural regulation, characterized by: include: Central processing module: The central processing module is used to perform algorithm calculations on the positioning of the neural regulation target area; Target area control module: obtains target area control through patient imaging data; Feature point recognition module: The feature point recognition module is used to set the patient's head contour map and three-color plane map, and process the feature points through the central processing module to generate a coordinate schematic diagram; Data comparison module: The data comparison module is used to compare the precise coordinate data with the patient's head contour map; Contour map positioning module: used to display the data compared by the data comparison module.

2. The neural regulation target area positioning system according to claim 1, characterized in that: The input end of the central processing module is electrically connected to the output end of the target area control module; the output end of the central processing module is electrically connected to the input ends of the target area control module, the feature point recognition module, the data comparison module and the contour map positioning module; the output end of the target area control module is electrically connected to the input end of the feature point recognition module; the output end of the feature point recognition module is electrically connected to the input end of the data comparison module; the output end of the data comparison module is electrically connected to the input end of the contour map positioning module.

3. The neural regulation target area positioning system according to claim 2, characterized in that: The control target area module is used to obtain the patient's magnetic resonance image and magnetic resonance structural image, and obtain the control target area through the magnetic resonance image and magnetic resonance structural image.

4. A neural regulation target area positioning system according to claims 1-3, characterized in that: The positioning method of the positioning system of the neural regulation target area comprises the following steps: Step 1: Use magnetic resonance imaging to obtain the patient's functional magnetic resonance imaging and magnetic resonance structural imaging, and then obtain the control target area; Step 2: using a processing method to match the functional MRI image and the structural MRI image obtained in step 1, thereby obtaining a target area on the structural MRI image; Step 3: Use the depth camera to obtain the patient's head outline and the corresponding three-color plane image, use the calculation algorithm to identify the feature points on the plane image, and obtain the coordinate diagram of the patient's body parts based on the patient's head outline; Step 4: Obtain the head outline of the magnetic resonance structure image according to the coordinate diagram in step 3, then substitute the head outline into the coordinate diagram for precise positioning and obtain accurate coordinate data, and then compare the accurate coordinate data with the patient's head outline; Step 5: Operate the depth camera and image control device to obtain accurate positioning in the patient's head outline image.

5. The method for locating a target area for neural regulation according to claim 4, characterized in that: The method for acquiring the target area in step 2 includes the following steps: A1: Determine the imaging location area based on existing diagnostic images; A2: Use multiple images to simulate positioning using CT-Sim and MRI-Sim, and then submit an appointment application; A3: After receiving the appointment application, confirm that the CT-Sim simulation and MRI-Sim are scheduled on the same day; A4: The mark and the required impact scanning range meet the requirements of CT-Sim simulation positioning and MRI-Sim scanning position. Then the scanning position is expanded, and then the target area position can be acquired.

6. The method for locating a target area for neural regulation according to claim 5, characterized in that: In step 3, the feature points on the plane image are identified using the SIFT algorithm, and the identification method includes the following steps: B1: Set the reference image and the feature points in the reference image; B2: Extract feature points from the image to be matched and the reference image respectively, and calculate the feature points using the SIFT algorithm; B3: Describe the feature points of the image to be matched and the reference image. The reason is difficult to implement the feature descriptor in the SIFT algorithm. B4: Use the nearest neighbor matching method to treat each feature point in the matching image, find the feature point closest to it in the reference image, and use it as the matching result; B5: Use the RANSAC algorithm to filter and optimize the matching results, remove mismatched points, and improve the accuracy and robustness of the matching.

7. The method for locating a target area for neural regulation according to claim 6, characterized in that: In the step B3, the pixel values ​​around each feature point are used as input in the feature sub-implementation, and the scale and direction of each pixel are calculated using a Gaussian difference pyramid to generate a local vector with 128 dimensions.

Images