Transcranial direct current stimulation electrode positioning method based on artificial intelligence image recognition and application

Abstract

The application provides a transcranial direct current stimulation electrode positioning method based on artificial intelligence image recognition and application. In order to solve the technical problem that a user is difficult to independently and accurately place a tDCS electrode in a home environment, the application provides: acquiring real-time image data of a user's face through a camera of an intelligent device; recognizing and outputting coordinates of a plurality of key points of the face by using an artificial intelligence model; calculating a target position of the electrode on the head based on geometric relations of the key points by using an algorithm; and generating a visual mark on a display interface to guide the user to adjust the electrode to the target position in real time. The application can further include electrode attachment detection by a sub-electrode and double positioning verification by using an AprilTag two-dimensional code. The method can enable the user to conveniently and quickly complete high-precision electrode positioning, and significantly improves the ease of use, treatment accuracy and safety of the tDCS device in a home scenario.

Description

Technical Field

[0001] This invention relates to the field of medical device technology, specifically to an electrode positioning technology for transcranial direct current stimulation (tDCS), and more particularly to an automatic electrode positioning method and application based on artificial intelligence image recognition and processing. Background Technology

[0002] Transcranial direct current stimulation (tDCS) is a non-invasive neuromodulation technique that uses electrodes placed in specific areas of the scalp to apply a weak, constant direct current to modulate the excitability of the cerebral cortex. It is widely used in the clinical treatment and research of neuropsychiatric disorders such as depression, anxiety, and chronic pain.

[0003] The therapeutic effect of tDCS is highly dependent on the accuracy of electrode placement. For example, in treating depression, the cathode electrode typically needs to be precisely placed on the left dorsolateral prefrontal cortex (L-DLPFC), which corresponds to the F3 point in the international 10-20 electroencephalogram (EEG) system. In a clinical setting, electrode placement is usually performed by specially trained medical personnel who manually determine the electrode positions using tools such as measuring tapes, caps, and markers, based on the 10-20 system measurement method. This process is tedious, time-consuming, and highly dependent on the operator's experience.

[0004] As tDCS devices become more home-based and personalized, enabling non-professional users to independently and accurately perform electrode positioning without external guidance has become a pressing technical challenge. Existing home-use devices typically employ a fixed headband or cap design. However, due to significant differences in head shape, circumference, and facial structure among individuals, this "one-size-fits-all" approach struggles to guarantee positioning accuracy. This can lead to deviation of the stimulation target, affecting treatment outcomes and even causing unexpected side effects.

[0005] Therefore, developing a technical solution that allows users to perform electrode positioning independently, conveniently, and accurately in a home setting is crucial for improving the accessibility and effectiveness of tDCS treatment. Summary of the Invention

[0006] This invention provides a transcranial direct current stimulation electrode positioning method and application based on artificial intelligence image recognition, addressing the problem that existing tDCS electrode positioning technology lacks an accurate and easy-to-operate autonomous positioning method that can adapt to individual differences in home application scenarios.

[0007] The core technology of this invention mainly utilizes the camera of a smart device to collect real-time facial images of the user, identifies multiple key anatomical anchor points on the face through an artificial intelligence model, and calculates personalized and precise two-dimensional coordinates of the tDCS electrode target point on the head based on the geometric relationship of these anchor points through an algorithm, and finally guides the user to complete the positioning in a visual way.

[0008] In a first aspect, the present invention provides a method for locating transcranial direct current stimulation electrodes based on artificial intelligence image recognition, the method comprising the following steps:

[0009] Acquire real-time image data of the user's face;

[0010] An artificial intelligence facial recognition model is used to process real-time image data, identify and output the coordinates of multiple preset key points on the user's face. These preset key points include feature points of the user's jawline, eyebrows, eyes, nose and lips.

[0011] Based on the coordinates of multiple preset key points, the target position coordinates of at least one transcranial direct current stimulation electrode on the user's head are calculated using a preset geometric calculation model.

[0012] On the display interface, visual guidance information is generated based on the target location coordinates to guide the user to place the transcranial direct current stimulation electrode at the target location.

[0013] Furthermore, the steps for calculating the target position coordinates using the geometric calculation model include:

[0014] Calculate head size parameters to characterize the user's head size based on the distance between at least two key points;

[0015] Based on the relative positions of the key points of the user's pupils, determine the head tilt parameters used to characterize the head tilt state;

[0016] Determine the first reference point on the midline of the face based on key points of the eyebrows or nose;

[0017] Based on the first reference point, other key facial points, and head size parameters, the second reference point on the midline of the skull is calculated.

[0018] The target position coordinates are calculated by combining the second reference point, head size parameters, and head tilt parameters.

[0019] Furthermore, the target location is the area corresponding to the left dorsolateral prefrontal cortex or the right dorsolateral prefrontal cortex, which is marked as point F3 or F4 in the international 10-20 EEG system.

[0020] Furthermore, it also includes a dual positioning verification step:

[0021] Real-time spatial pose information of the transcranial direct current stimulation device is obtained by using a machine-readable code set on the casing of the image recognition device.

[0022] The spatial pose information is compared and verified with the target position calculated through facial key points to confirm that the actual placement position of the transcranial direct current stimulation electrode is consistent with the target position.

[0023] Furthermore, the machine-readable code is the April Tag QR code.

[0024] Furthermore, the artificial intelligence facial recognition model is the OpenPose model based on a convolutional neural network.

[0025] Furthermore, before acquiring real-time image data of the user's face, at least one of the following electrical detection steps is included:

[0026] Preliminary electrode patch testing: By detecting the current parameters between the sub-electrodes inside the electrode, it is determined whether the disposable electrode patch is well attached to the transcranial direct current stimulation electrode;

[0027] Overall head fit test: By applying a current of a preset waveform between the cathode and anode electrodes and performing the test, it is determined whether the transcranial direct current stimulation device fits well with the user's head.

[0028] In a second aspect, the present invention provides a transcranial direct current stimulation electrode positioning device based on artificial intelligence image recognition, comprising:

[0029] An electrode assembly includes a cathode and an anode, and sub-electrodes and a conductive medium are disposed on the cathode and the anode;

[0030] The current detection module is used to detect the current between the sub-electrodes and the current between the cathode and the anode to evaluate the patch adhesion and the overall attachment status of the head.

[0031] The image acquisition module is used to acquire real-time image data of the user's face;

[0032] The artificial intelligence processing module is used to identify preset key points of the user's face in real-time image data, and to calculate the target position coordinates of at least one transcranial direct current stimulation electrode on the user's head based on the coordinates of the preset key points using a geometric calculation model. The preset key points include feature points of the user's jawline, eyebrows, eyes, nose and lips.

[0033] The visualization guidance module is used to overlay the target location coordinates onto the video output interface in real time to guide the user to place the transcranial direct current stimulation electrode at the target location;

[0034] The positioning verification module is used to identify positioning marks on the surface of the device, obtain the positional information of the transcranial direct current stimulation device relative to the head, and perform real-time verification with facial key point information.

[0035] Thirdly, the present invention provides an electronic device including a memory and a processor, wherein the memory stores a computer program and the processor is configured to run the computer program to execute the above-described transcranial direct current stimulation electrode positioning method based on artificial intelligence image recognition.

[0036] Fourthly, the present invention provides a readable storage medium storing a computer program, the computer program including program code for controlling a process to execute the process, the process including the transcranial direct current stimulation electrode positioning method based on artificial intelligence image recognition described above.

[0037] The main contributions and innovations of this invention are as follows:

[0038] 1. Breaking the professional dependence in home scenarios: Without the guidance of medical staff, users can complete the self-positioning by simply using a smartphone and wearable tDCS device, which significantly reduces the threshold for use and promotes the popularization of tDCS technology in homes;

[0039] 2. Significantly improved positioning accuracy: Relying on the millimeter-level facial key point recognition capability of the OpenPose model, combined with dynamic geometric calculation based on head size and posture, the electrode positioning error is less than 5% of the head diameter, which can accurately match core target points such as L-DLPFC (F3 point) to ensure treatment efficacy.

[0040] 3. Enhanced safety and reliability: Through a dual current feedback mechanism of "preliminary patch detection" and "overall head attachment detection", problems such as poor contact such as patch not being properly attached or hair obstructing the contact are eliminated in real time, avoiding skin risks caused by abnormal local current; at the same time, the dual verification of April Tag and key facial points further ensures that the actual electrode position is consistent with the theoretical target point, reducing the probability of ineffective stimulation.

[0041] 4. High universality: The technical solution has been validated in a diverse range of subjects (covering different head shapes and facial features), and can dynamically adapt to individual facial features and posture differences without the need to adjust hardware or algorithms for specific groups.

[0042] 5. Convenient and intuitive operation: The device uses a smartphone video interface to overlay virtual markers of electrode targets in real time, visually guiding users to adjust the device position. The operation process is in line with the usage habits of home users and requires no additional professional training.

[0043] Details of one or more embodiments of the present invention are set forth in the following drawings and description, so that other features, objects and advantages of the invention will be more readily understood. Attached Figure Description

[0044] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this invention, illustrate exemplary embodiments of the invention and are used to explain the invention, but do not constitute an undue limitation of the invention. In the drawings:

[0045] Figure 1 This is a flowchart of a transcranial direct current stimulation electrode positioning method based on artificial intelligence image recognition according to an embodiment of the present invention;

[0046] Figure 2 This is an example output diagram of a geometric calculation model according to an embodiment of the present invention;

[0047] Figure 3 This is a schematic diagram of a tDCS device according to an embodiment of the present invention;

[0048] Figure 4 yes Figure 3 Another perspective view;

[0049] Figure 5 This is a schematic diagram of the hardware structure of an electronic device according to an embodiment of the present invention.

[0050] In the diagram, 1. Main body of the outer shell; 2. Electrode shell; 3. Conductive rubber; 4. Headband; 5. Switch; 6. LED indicator; 7. Charging port. Detailed Implementation

[0051] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numerals in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with one or more embodiments of this specification. Rather, they are merely examples of apparatuses and methods consistent with some aspects of one or more embodiments of this specification as detailed in the appended claims.

[0052] It should be noted that the steps of the corresponding methods are not necessarily performed in the order shown and described in this specification in other embodiments. In some other embodiments, the methods may include more or fewer steps than described in this specification. Furthermore, a single step described in this specification may be broken down into multiple steps in other embodiments; and multiple steps described in this specification may be combined into a single step in other embodiments.

[0053] Existing transcranial direct current stimulation (tDCS) technology, when used in home settings, suffers from low accuracy and unstable therapeutic effects due to a lack of professional guidance, effective electrode patches and head attachment effectiveness testing methods, and the inability to dynamically adapt to individual head shape and posture differences. It also poses safety risks such as skin irritation.

[0054] Based on this, the present invention addresses the problems existing in the prior art by using artificial intelligence image recognition.

[0055] Example 1

[0056] This invention aims to propose a method for positioning transcranial direct current stimulation electrodes based on artificial intelligence image recognition. Specifically, refer to... Figure 1 The method includes the following technical steps:

[0057] Step 1: Preliminary testing stage of electrode patches

[0058] To ensure treatment comfort, safety, and the durability and waterproofing of the device, the DC pathway of this transcranial direct current stimulation (tDCS) device is as follows: metal electrode - conductive rubber electrode - disposable conductive gel electrode patch - user's skin. To detect whether the disposable electrode patch adheres well to the conductive rubber electrode, sub-electrodes arranged in a semi-circular or concentric circle are provided on both the cathode and anode of this invention. The system (the control system mounted on the tDCS device, which can be simply referred to as the EEG system or system, which carries the method of this invention, and the application (APP) installed on the smart terminal also carries the method of this invention; the two can communicate and work collaboratively) first applies a weak current between the two sub-electrodes within a single electrode (cathode or anode) and detects its current amplitude and waveform stability. When the detected current reaches a stable preset threshold and the waveform is stable, the system determines that the electrode patch has adhered correctly and prompts the user to proceed to the next step.

[0059] In this embodiment, the electrode patch surface of the tDCS device is provided with one cathode and one anode (both circular, 30mm in diameter). Two semi-circular sub-electrodes (inner diameter 5mm, outer diameter 8mm, spacing 2mm, made of medical conductive silver paste) are fixed on the cathode and anode surfaces. The device shell is made of ABS plastic and has two April Tag QR codes (15mm×15mm in size, 0.1mm in depth, located 5mm outside the cathode and anode, respectively) laser-etched for device pose recognition.

[0060] The current path adopts the following structure: "metal electrode (medical stainless steel) → conductive rubber electrode (silicone-based conductive rubber, 2mm thick, resistivity ≤10Ω)". cm) → Disposable conductive gel electrode patch (thickness 0.3mm, water content 80%, conductivity ≥1S / m) → Patient's skin "structure, taking into account both comfort and conductivity.

[0061] Current detection utilizes a current sensor (0.01mA detection accuracy) and signal processing unit integrated within the tDCS device. Its functions are twofold: first, detecting the current between two sub-electrodes within a single electrode (cathode or anode); second, detecting the current between the cathode and anode. The detection data is transmitted in real-time via Bluetooth to a smartphone, or smart terminal. This smart terminal is a common smartphone, such as the iPhone 15 series or Huawei Mate 70 series. After installing an application, the camera can be used to perform image recognition using the application's built-in algorithms—the complete stage of subsequent step three. Higher-end smartphone configurations result in better performance. This system is backward compatible, but the computing power of the terminal device directly affects the latency of the image recognition stage.

[0062] Preferably, such as Figures 3-4 As shown, the outer shell 1 of the tDCS device has electrode shells 2 at both ends, electrode patches are installed on the electrode shells 2, and conductive rubber 3 is provided on the electrode patches. It is worn on the user's head through the headband 4. The outer shell 1 also has a switch 5, an LED indicator 6, a charging port 7, etc., which are all existing technologies. The present invention does not improve the basic structure, but makes some structural improvements and incorporates the method of the present invention.

[0063] Step 2: Overall Head Attachment Testing Stage

[0064] Once both electrode patches pass the detection, the system will prompt the user to wear the tDCS device on their head. To prevent the electrodes from being obstructed by hair or other debris, thus reducing the effective contact area, the system will perform an overall attachment detection. At this time, the system outputs a specific detection waveform between the cathode and anode and monitors the current change trend between them in real time. When the current shows a stable upward trend and eventually maintains a stable DC signal within a certain fluctuation range, the system determines that the device has been successfully attached to the user's scalp and can proceed to the visual positioning stage.

[0065] Step 3: AI Visual Intelligent Positioning Calibration Phase

[0066] 1. Video data acquisition

[0067] Users launch the accompanying application on their smart devices and use the front-facing camera to capture a real-time video stream of their facial images. Each frame of the video stream is transmitted in real-time to the application's built-in image recognition algorithm module.

[0068] 2. Keypoint Annotation in OpenPose Model

[0069] This embodiment preferably uses the open-source OpenPose AI model to process video frames. Based on a convolutional neural network (CNN) and pose estimation algorithm, this model can automatically and accurately identify and label 68 key points on the user's face and the positions of both pupils. These key points precisely define important anatomical landmarks such as the user's jawline (Jaw_0 to Jaw_16), eyebrows, eyes, nose, and lips. The use of this model ensures the accuracy of subsequent calculations and robustness to different user facial features.

[0070] Preferably, the facial key point annotation is performed by the OpenPose model on each frame of the image, automatically identifying and annotating 68 facial key points (coordinates in pixels), including:

[0071] Jawline: Jaw_0 (left endpoint of mandible) to Jaw_16 (right endpoint of mandible);

[0072] Eyebrows: Eyebrow_Left_0 (left end point of left eyebrow) to Eyebrow_Left_4 (inner end point of left eyebrow), Eyebrow_Right_0 (inner end point of right eyebrow) to Eyebrow_Right_4 (right end point of right eyebrow);

[0073] Eyes: Eye_Left_0 to Eye_Left_6 (left eye outline), Eye_Right_0 to Eye_Right_6 (right eye outline), where Eye_Left_2 is the outer point of the left pupil and Eye_Right_2 is the outer point of the right pupil;

[0074] Nose: Nose_0 to Nose_9 (nose outline);

[0075] Lips: Lip_Outer_0 to Lip_Outer_11 (outer side of the lips), Lip_Inner_0 to Lip_Inner_7 (inner side of the lips), where Lip_Inner_6 is the midpoint of the upper lip;

[0076] The positions of both pupils are also marked (Pupil_Left_0 is the center of the left pupil, and Pupil_Right_0 is the center of the right pupil).

[0077] 3. Algorithm to calculate head electrode position

[0078] Based on real-time acquired two-dimensional coordinate data of key points, the system calculates the target stimulation location of the tDCS electrodes using a geometric calculation model. This corresponds to the coordinates of points F3 (left dorsolateral prefrontal cortex L-DLPFC) and F4 (right dorsolateral prefrontal cortex R-DLPFC) in the international 10-20 EEG system. The specific calculation steps are as follows:

[0079] (1) Calculate the head size parameters (call the coordinate points output by the model, calculate the head size and set it as a parameter):

[0080] jaw_0 = [keypoints_data.Jaw_0.X, keypoints_data.Jaw_0.Y];

[0081] jaw_16 = [keypoints_data.Jaw_16.X, keypoints_data.Jaw_16.Y];

[0082] eye_right_2 = [keypoints_data.Eye_Right_2.X, keypoints_data.Eye_Right_2.Y];

[0083] eye_left_2 = [keypoints_data.Eye_Left_2.X, keypoints_data.Eye_Left_2.Y];

[0084] jaw_distance = norm(jaw_0 - jaw_16);

[0085] eye_distance = norm(eye_right_2 - eye_left_2);

[0086] head_size_index = jaw_distance + eye_distance;

[0087] This step, to adapt the algorithm to different users' head sizes, first requires calculating a head size parameter. For example, this is done by calculating the distance between the two furthest points on the jawline, jaw_0 and jaw_16:

[0088] The head size index is calculated by adding the jaw_distance and the distance between the outer corners of the left and right eyes, eye_left_2 and eye_right_2, to obtain a comprehensive head size index, head_size_index.

[0089] (2) Calculate the head tilt angle (determine the head tilt angle by the inclination of both pupils):

[0090] pupil_left = [keypoints_data.Pupil_Left_0.X, keypoints_data.Pupil_Left_0.Y];

[0091] pupil_right = [keypoints_data.Pupil_Right_0.X, keypoints_data.Pupil_Right_0.Y];

[0092] head_tilt_slope = (pupil_right(2) - pupil_left(2)) / (pupil_right(1)- pupil_left(1));

[0093] In order to correct the tilt of the user's head in the video, this step calculates the slope of the line connecting the left pupil (pupil_left) and the right pupil (pupil_right) as the parameter for head tilt.

[0094] (3) Determine the location of the nasal root point (the nasal root point is determined by the midpoint of the inner eyebrow roots on both sides, which is the location of AFz in the system. This location represents the midpoint of the anterior border of the brain):

[0095] eyebrow_left_4 = [keypoints_data.Eyebrow_Left_4.X, keypoints_data.Eyebrow_Left_4.Y];

[0096] eyebrow_right_0 = [keypoints_data.Eyebrow_Right_0.X, keypoints_data.Eyebrow_Right_0.Y];

[0097] nasion_position = (eyebrow_left_4 + eyebrow_right_0) / 2;

[0098] In this step, the system takes the midpoint between the inner points of the left eyebrow (eyebrow_left_4) and the right eyebrow (eyebrow_right_0) as a stable reference point on the facial midline, namely the nasal root point (nasion_position). This position approximates the AFz point in the electroencephalogram (EEG) system.

[0099] (4) Determine the position of the frontal midline Fz (the position of the frontal midline is determined by extending the line connecting the midpoint of the upper lip and the root of the nose (corrected by head size parameters), which is located at the midpoint of F3 and F4):

[0100] lip_inner_6 = [keypoints_data.Lip_Inner_6.X, keypoints_data.Lip_Inner_6.Y];

[0101] direction_vector = nasion_position - lip_inner_6;

[0102] direction_vector = direction_vector / norm(direction_vector);

[0103] Fz_distance = head_size_index * head_size_multiplier;

[0104] Fz_position = nasion_position + direction_vector * Fz_distance;

[0105] In this step, the system determines the direction vector of the facial midline using the upper lip midpoint lip_inner_6 and the nasal root point nasion_position. Then, it extends upwards from the nasal root point nasion_position along this direction vector by a distance Fz_distance positively correlated with the head size index head_size_index, thereby determining the position Fz_position of the key point Fz on the forehead midline. Point Fz is the midpoint between F3 and F4.

[0106] (5) Based on the position of Fz, the L-DLPFC and R-DLPFC (i.e., the F3 and F4 positions in the EEG system) are calculated using head size parameters and head tilt parameters, respectively, to determine the positions of anodic and cathodic stimulation:

[0107] distance_F3_F4 = head_size_index * head_size_multiplier * 0.8;

[0108] direction_vector = [1, head_tilt_slope];

[0109] direction_vector = direction_vector / norm(direction_vector);

[0110] F3_position = Fz_position + distance_F3_F4 * direction_vector;

[0111] F4_position = Fz_position - distance_F3_F4 * direction_vector;

[0112] Based on the determined position of point Fz, this step involves constructing a direction vector related to the head tilt parameter head_tilt_slope, which is roughly parallel to the line connecting the two pupils. From point Fz_position, the system moves along the positive and negative directions of this vector by a distance also related to the head size index head_size_index, thus calculating the coordinates F3_position of the left target point F3 and F4_position of the right target point F4.

[0113] The above steps comprehensively utilize the geometric relationship of facial key points and head shape parameter model to achieve robust adaptation to individual user differences (after testing, the difference between the algorithm's predicted point position and the actual measured point position is less than 5% of the head diameter), and have been verified on experimental participants with diverse characteristics (covering different head shapes and facial features). Example output is shown in Figure 2 (this does not represent the final UI effect, but is only an example of an embodiment of the present invention).

[0114] 4. Visualized real-time guidance

[0115] The system calculates the target position coordinates of F3 and F4 and displays them in real-time on the video output interface of the smart terminal as virtual markers (such as circles or crosses). Users can visually see the deviation between the marked positions and the actual electrodes of the worn tDCS device, and manually fine-tune the position of the tDCS device according to the on-screen instructions until the device electrodes perfectly align with the virtual markers. (See attached image) Figure 2 As shown, the algorithm demonstrated good localization performance on subjects of different ethnicities and facial features.

[0116] Step 4: Dual Positioning Verification Stage

[0117] To further ensure absolute positioning accuracy, this embodiment also includes a dual positioning verification step. Two April Tag QR codes are pre-set (engraved using laser ablation) on the casing of the tDCS device. After the user completes the basic positioning according to the visual guidance, the smart terminal's camera recognizes these two QR codes and uses algorithms to calculate the precise physical position and rotation angle of the tDCS device in three-dimensional space. The system compares and verifies this physical pose information in real time with the target position calculated based on facial key points, ensuring that the actual center of the electrode patch accurately matches the target position calculated by the system, thereby achieving dual verification and guaranteeing optimal treatment results. For example:

[0118] Position deviation ≤ 2mm, rotation angle deviation ≤ 5°; if these conditions are met, the APP will prompt "Positioning successful, treatment can be started"; if the deviation exceeds the threshold, the APP will prompt "Please fine-tune the device to align with the virtual marker" until the verification is successful.

[0119] Preferably, the present invention can also directly replace OpenPose with Google's MediaPipe Face Mesh model. This lightweight model, optimized for mobile devices and based on a CNN architecture, can output 468 3D facial key points in real time (far exceeding the 68 basic points, including detailed structures such as pupils, brow bones, and nose wings), with a positioning accuracy of ±0.8mm. It is robust to head tilt (±45°) and partial occlusion (such as glasses or bangs), adapting to non-standard user postures in home settings. It supports direct output of the 3D coordinates (x, y, z) of key points. Alternatively, the existing open-source Dlib Face Landmark Predictor model can be used. This is a classic facial key point detection model based on HOG features and Support Vector Machine (SVM), stably outputting 68 2D facial key points with a positioning accuracy of ±0.6mm. Its training data covers multiple skin tones and age groups, and only requires supplementing the pupil detection location (e.g., using the MediaPipe Face Mesh model) to seamlessly replace OpenPose. The choice can be made based on the specific circumstances.

[0120] In existing technologies, AI vision models (such as OpenPose and MediaPipe) are mainly used in general scenarios such as face recognition and motion capture, current detection technology is mostly used for circuit fault diagnosis, and tDCS electrode positioning relies on manual operation in medical scenarios. These technologies have developed independently in their respective fields, and there is no inspiration in existing technologies to integrate the three for "home tDCS electrode positioning".

[0121] The core innovation of this invention lies in:

[0122] 1. Precisely anchoring AI vision technology to medical anatomical needs: Instead of simply using facial key point detection, it specifically selects anatomical landmarks (such as the inner eyebrow root point, pupil, and jawline) that are strongly correlated with EEG leads (F3 / F4 / Fz), and designs a geometric calculation model based on these key points to achieve a precise mapping of "facial features → brain region targets" (this mapping relationship is not publicly recorded in existing technologies).

[0123] 2. Progressive synergy between current feedback and visual positioning: First, the basic error of "the patch is not firmly attached" is eliminated by detecting the current of the sub-electrode. Then, the "overall attachment effectiveness of the head" is judged by the current trend of the anode and cathode. Finally, AI visual positioning is used. This logic of "hardware detection lays the foundation for visual positioning" solves the problem of "invalid positioning caused by the device not being attached" when AI vision is used alone. It is a creative combination of the two technologies.

[0124] 3. Scenario-based design of dual verification mechanism: The April Tag QR code is introduced to compare with facial key points, and the "device pose" is associated with the "head anatomical benchmark". This makes up for the defect that AI vision can only locate target points but cannot verify the actual position of the device, forming a "positioning-verification" closed loop. This mechanism has not appeared in the existing tDCS or AI vision field.

[0125] In summary, the tDCS electrode intelligent positioning method based on AI visual recognition and current feedback proposed in this invention uses OpenPose to accurately annotate head feature points in real time. Combined with rigorous algorithm reasoning and a visual user-guided interface, it constructs a complete technical closed loop from "patch detection → head attachment → target point positioning → real-time verification". This solves the long-standing problem of balancing "accuracy-safety-ease of use" in existing technologies. It enables high-precision, adaptive automatic positioning and attachment of electrode patches in home settings, significantly improving the accuracy and convenience of using transcranial direct current stimulation devices.

[0126] Example 2

[0127] Based on the same concept, this invention also proposes a transcranial direct current stimulation electrode positioning device based on artificial intelligence image recognition, comprising:

[0128] An electrode assembly includes a cathode and an anode, and sub-electrodes and a conductive medium are disposed on the cathode and the anode;

[0129] The current detection module is used to detect the current between the sub-electrodes and the current between the cathode and the anode to evaluate the patch adhesion and the overall attachment status of the head.

[0130] The image acquisition module is used to acquire real-time image data of the user's face;

[0131] The artificial intelligence processing module is used to identify preset key points of the user's face in real-time image data, and to calculate the target position coordinates of at least one transcranial direct current stimulation electrode on the user's head based on the coordinates of the preset key points using a geometric calculation model. The preset key points include feature points of the user's jawline, eyebrows, eyes, nose and lips.

[0132] The visualization guidance module is used to overlay the target location coordinates onto the video output interface in real time to guide the user to place the transcranial direct current stimulation electrode at the target location;

[0133] The positioning verification module is used to identify the positioning marks on the surface of the device, obtain the positional information of the transcranial direct current stimulation electrode device relative to the head, and perform real-time verification with the facial key point information.

[0134] Example 3

[0135] This embodiment also provides an electronic device, see reference. Figure 5 It includes a memory 404 and a processor 402, wherein the memory 404 stores a computer program and the processor 402 is configured to run the computer program to perform the steps in any of the above method embodiments.

[0136] Specifically, the processor 402 may include a central processing unit (CPU), or an application-specific integrated circuit (ASIC), or one or more integrated circuits that can be configured to implement embodiments of the present invention.

[0137] Memory 404 may include a mass storage device for data or instructions. For example, and not limitingly, memory 404 may include a hard disk drive (HDD), a floppy disk drive, a solid-state drive (SSD), flash memory, an optical disk drive, a magneto-optical disk drive, magnetic tape, or a Universal Serial Bus (USB) drive, or a combination of two or more of these. Where appropriate, memory 404 may include removable or non-removable (or fixed) media. Where appropriate, memory 404 may be internal or external to a data processing device. In a particular embodiment, memory 404 is non-volatile memory. In a particular embodiment, memory 404 includes read-only memory (ROM) and random access memory (RAM). Where appropriate, the ROM may be a mask-programmed ROM, a programmable read-only memory (PROM), an erasable read-only memory (EPROM), an electrically erasable read-only memory (EEPROM), an electrically alterable read-only memory (EAROM), or flash memory, or a combination of two or more of these. Where appropriate, the RAM can be Static Random-Access Memory (SRAM) or Dynamic Random-Access Memory (DRAM). DRAM can be Fast Page Mode Dynamic Random-Access Memory (FPMDRAM), Extended Data Out Dynamic Random-Access Memory (EDODRAM), Synchronous Dynamic Random-Access Memory (SDRAM), etc.

[0138] The memory 404 can be used to store or cache various data files that need to be processed and / or communicated, as well as possible computer program instructions executed by the processor 402.

[0139] The processor 402 reads and executes computer program instructions stored in the memory 404 to implement any of the transcranial direct current stimulation electrode positioning methods based on artificial intelligence image recognition in the above embodiments.

[0140] Optionally, the electronic device may further include a transmission device 406 and an input / output device 408, wherein the transmission device 406 is connected to the processor 402, and the input / output device 408 is connected to the processor 402.

[0141] The transmission device 406 can be used to receive or send data via a network. Specific examples of the network described above may include wired or wireless networks provided by the communication provider of the electronic device. In one example, the transmission device includes a Network Interface Controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission device 406 may be a Radio Frequency (RF) module used for wireless communication with the Internet.

[0142] Input / output device 408 is used to input or output information.

[0143] Example 4

[0144] This embodiment also provides a readable storage medium storing a computer program, the computer program including program code for controlling a process to execute the process, the process including the transcranial direct current stimulation electrode positioning method based on artificial intelligence image recognition according to Embodiment 1.

[0145] It should be noted that the specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementations, and will not be repeated here.

[0146] Generally, various embodiments can be implemented in hardware or dedicated circuitry, software, logic, or any combination thereof. Some aspects of the invention can be implemented in hardware, while others can be implemented by firmware or software executed by a controller, microprocessor, or other computing device, but the invention is not limited thereto. Although various aspects of the invention may be shown and described as block diagrams, flowcharts, or using some other graphical representation, it should be understood that, by way of non-limiting example, these blocks, apparatuses, systems, techniques, or methods described herein can be implemented in hardware, software, firmware, dedicated circuitry or logic, general-purpose hardware or controllers or other computing devices, or some combination thereof.

[0147] Embodiments of the present invention can be implemented by computer software, which may be executable by a data processor of a mobile device, such as a processor entity, or by hardware, or by a combination of software and hardware. Computer software or programs (also referred to as program products), including software routines, applets, and / or macros, can be stored in any device-readable data storage medium, and they include program instructions for performing specific tasks. A computer program product may include one or more computer-executable components configured to perform embodiments when the program is run. One or more computer-executable components may be at least one piece of software code or a portion thereof. Additionally, it should be noted that any block in the logical flow of the figures may represent a program step, or interconnected logical circuitry, blocks and functions, or a combination of program steps and logical circuitry, blocks and functions. The software may be stored on physical media such as memory chips or blocks of storage implemented within a processor, magnetic media such as hard disks or floppy disks, and optical media such as, for example, DVDs and their data variants, CDs, etc. The physical medium is a non-transient medium.

[0148] Those skilled in the art should understand that the technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments have been described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0149] The above embodiments are merely illustrative of several implementations of the present invention, and their descriptions are relatively specific and detailed, but they should not be construed as limiting the scope of the present invention. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these all fall within the protection scope of the present invention. Therefore, the protection scope of the present invention should be determined by the appended claims.

Claims

1. A method for positioning transcranial direct current stimulation electrodes based on artificial intelligence image recognition, employing a transcranial direct current stimulation device, characterized in that, Includes the following steps: Acquire real-time image data of the user's face; An artificial intelligence facial recognition model is used to process the real-time image data, identify and output the coordinates of multiple preset key points on the user's face. These preset key points include feature points of the user's jawline, eyebrows, eyes, nose and lips. Based on the coordinates of the multiple preset key points, and through a preset geometric calculation model, the target position coordinates of at least one transcranial direct current stimulation electrode on the user's head are calculated, including: Calculate head size parameters to characterize the user's head size based on the distance between at least two key points; Based on the relative positions of the key points of the user's pupils, determine the head tilt parameters used to characterize the head tilt state; Determine the first reference point on the midline of the face based on key points of the eyebrows or nose; Based on the first reference point, other key facial points, and the head size parameters, a second reference point on the midline of the skull is calculated. The target position coordinates are calculated by combining the second reference point, the head size parameters, and the head tilt parameters; On the display interface, visual guidance information is generated based on the target location coordinates to guide the user to place the transcranial direct current stimulation electrode at the target location.

2. The transcranial direct current stimulation electrode positioning method based on artificial intelligence image recognition as described in claim 1, characterized in that, The target location is the area corresponding to the left dorsolateral prefrontal cortex or the right dorsolateral prefrontal cortex.

3. The transcranial direct current stimulation electrode positioning method based on artificial intelligence image recognition as described in claim 1, characterized in that, It also includes a dual location verification step: Real-time spatial pose information of the transcranial direct current stimulation device is obtained by using a machine-readable code set on the casing of the image recognition device. The spatial pose information is compared and verified with the target position calculated from facial key points to confirm that the actual placement position of the transcranial direct current stimulation electrode is consistent with the target position.

4. The transcranial direct current stimulation electrode positioning method based on artificial intelligence image recognition as described in claim 3, characterized in that, The machine-readable code is the April Tag QR code.

5. The transcranial direct current stimulation electrode positioning method based on artificial intelligence image recognition as described in claim 1, characterized in that, The artificial intelligence facial recognition model is the OpenPose model based on a convolutional neural network.

6. A transcranial direct current stimulation electrode positioning method based on artificial intelligence image recognition as described in any one of claims 1 to 5, characterized in that, Before acquiring real-time image data of the user's face, at least one of the following electrical detection steps is included: Preliminary electrode patch inspection: By detecting the current parameters between the sub-electrodes inside the electrode, it is determined whether the disposable electrode patch is well attached to the transcranial direct current stimulation electrode; Overall head fit test: By applying a current of a preset waveform between the cathode and anode electrodes and performing the test, it is determined whether the transcranial direct current stimulation device fits well with the user's head.

7. A transcranial direct current stimulation electrode positioning device based on artificial intelligence image recognition, characterized in that, include: An electrode assembly includes a cathode and an anode, wherein sub-electrodes and a conductive medium are disposed on the cathode and the anode; The current detection module is used to detect the current between the sub-electrodes and the current between the cathode and the anode to evaluate the patch adhesion and the overall attachment status of the head. The image acquisition module is used to acquire real-time image data of the user's face; An artificial intelligence processing module is used to identify preset key points on the user's face in real-time image data. These preset key points include feature points of the user's jawline, eyebrows, eyes, nose, and lips. Based on the coordinates of these preset key points, a geometric calculation model is used to calculate the target position coordinates of at least one transcranial direct current stimulation electrode on the user's head, including: Calculate head size parameters to characterize the user's head size based on the distance between at least two key points; Based on the relative positions of the key points of the user's pupils, determine the head tilt parameters used to characterize the head tilt state; Determine the first reference point on the midline of the face based on key points of the eyebrows or nose; Based on the first reference point, other key facial points, and the head size parameters, a second reference point on the midline of the skull is calculated. The target position coordinates are calculated by combining the second reference point, the head size parameters, and the head tilt parameters; The visualization guidance module is used to overlay the target location coordinates onto the video output interface in real time to guide the user to place the transcranial direct current stimulation electrode at the target location; The positioning verification module is used to identify positioning marks on the surface of the device, obtain the positional information of the transcranial direct current stimulation device relative to the head, and perform real-time verification with facial key point information.

8. An electronic device comprising a memory and a processor, characterized in that, The memory stores a computer program, and the processor is configured to run the computer program to perform the transcranial direct current stimulation electrode positioning method based on artificial intelligence image recognition as described in any one of claims 1 to 6.

9. A readable storage medium, characterized in that, The readable storage medium stores a computer program, the computer program including program code for controlling a process to execute the process, the process including the transcranial direct current stimulation electrode positioning method based on artificial intelligence image recognition according to any one of claims 1 to 6.

Images