Pain dynamic assessment and treatment linkage system based on three-dimensional somatosensory interaction

Abstract

The application relates to the technical field of medical devices and particularly discloses a pain dynamic evaluation and treatment linkage system based on three-dimensional somatosensory interaction, which comprises the following modules: a human body modeling module for constructing a three-dimensional human body dissection model; a somatosensory interaction module for receiving pain area marking instructions and pain intensity scores; an infrared sensing module for monitoring human body infrared thermal imaging data of a patient in real time; a physiological monitoring module for monitoring heart rate variability indexes and skin electric reaction indexes of the patient based on wearable devices; a region marking module for obtaining a calibrated pain area of the patient based on the pain area marking instructions and abnormal temperature zones in the human body infrared thermal imaging data; a pain prediction module for predicting a pain intensity prediction curve in a future period based on the pain intensity scores, the heart rate variability indexes, the skin electric reaction indexes and the calibrated pain area of the patient; and a treatment linkage module for generating treatment parameter control instructions based on the pain trend prediction curve and a multi-dimensional pain characteristic vector, so that precise and dynamic treatment intervention is realized.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of medical devices, in particular to a pain dynamic assessment and treatment linkage system based on three-dimensional somatosensory interaction. BACKGROUND

[0002] In the medical field, the effective management of chronic pain has always been a key research direction. Pain not only brings physical suffering to patients, but also has a negative impact on their psychology and quality of life. For various chronic pains such as post-herpetic neuralgia, cancer pain, etc., accurate pain assessment and timely and effective treatment are crucial. With the development of technology, traditional pain assessment and treatment methods gradually fail to meet the growing demand for precision medicine. The pain dynamic assessment and treatment linkage system based on three-dimensional somatosensory interaction has emerged as the times require, and has important practical significance. In the future, as people's demand for the quality of medical services continues to improve, and technology continues to advance, this system has broad application prospects and can play an important role in more chronic pain treatment scenarios, promoting the development of intelligent and precise pain treatment.

[0003] However, the existing pain assessment and treatment technology simply uses a VAS score scale, which causes communication barriers and understanding difficulties for special groups such as the elderly, resulting in a longer time-consuming and less accurate pain assessment. Moreover, the traditional method cannot intuitively mark the specific pain location for the patient, cannot fully obtain the spatial information of the pain, cannot accurately predict the pain trend, and cannot adjust the treatment parameters in real time according to the real-time pain characteristics, leading to treatment delay and affecting the treatment effect. In addition, the existing assessment and treatment processes are relatively independent, and lack an integrated system to achieve efficient linkage of pain dynamic assessment and treatment, which cannot meet the comprehensive needs of precision medicine for pain management.

[0004] Therefore, the present application proposes a pain dynamic assessment and treatment linkage system based on three-dimensional somatosensory interaction. SUMMARY

[0005] The present application provides a pain dynamic assessment and treatment linkage system based on three-dimensional somatosensory interaction, which can provide a more intuitive and convenient pain assessment method for patients with the help of advanced three-dimensional somatosensory interaction technology, changing the relatively single and subjective assessment mode of the past. At the same time, through linkage with the treatment equipment, the organic combination of pain assessment and treatment is realized, providing strong support for doctors to develop personalized treatment plans, and is expected to improve the effect and efficiency of chronic pain treatment.

[0006] The present application provides a pain dynamic assessment and treatment linkage system based on three-dimensional somatosensory interaction, comprising:

[0007] The human modeling module is used to construct a three-dimensional human anatomical model that includes the patient's bone, nerves and organs in a layered structure and with pain-sensitive area markers associated with each anatomical part.

[0008] The somatosensory interaction module is used to receive user input commands for marking pain areas and pain intensity scores;

[0009] Infrared sensing module, used to monitor the patient's human infrared thermal imaging data in real time;

[0010] A physiological monitoring module is used to monitor patients' heart rate variability and skin conductance indicators based on wearable devices;

[0011] The region marking module is used to obtain the patient's calibrated pain region based on the pain region marking instructions and abnormal temperature areas in human infrared thermal imaging data;

[0012] The pain prediction module is used to predict the pain intensity prediction curve for future cycles based on the patient's pain intensity score, heart rate variability index, skin conductance index, and calibrated pain area.

[0013] The treatment linkage module is used to generate treatment parameter control instructions based on pain trend prediction curves and multidimensional pain feature vectors.

[0014] Optionally, the human body modeling module includes:

[0015] The CT image data acquisition submodule is used to acquire standard human CT image data of patients and generate a basic model containing the patient's bones, major nerve trunks and internal organs through a three-dimensional reconstruction algorithm.

[0016] The pain-sensitive area annotation submodule is used to annotate the pain-sensitive areas of the base model to obtain a three-dimensional human anatomical model of the patient.

[0017] Optionally, the motion-sensing interaction module includes:

[0018] A touchscreen display is used to show a three-dimensional human anatomical model and receive the patient's input of a first pain area marking instruction;

[0019] A depth camera is used to capture the patient's hand gestures and translate them into instructions for marking the second pain area;

[0020] The instruction fusion submodule is used to determine the pain area marking instruction input by the user based on the first pain area marking instruction and / or the second pain area marking instruction;

[0021] The rating receiving submodule is used to receive the pain intensity rating input by the user via an integrated VAS / NRS rating slider.

[0022] Optionally, the region marking module includes:

[0023] The region marking submodule is used to determine the pain region marked by the patient based on the pain region marking instructions;

[0024] The fusion calibration submodule is used to fuse and calibrate the patient's marked pain area and the abnormal temperature area in the human infrared thermal imaging data to obtain the patient's calibrated pain area.

[0025] Optionally, the integrated calibration submodule includes:

[0026] The coordinate matrix transformation unit is used to convert the outline of the pain area marked by the patient into a three-dimensional coordinate matrix to obtain a manually annotated three-dimensional coordinate matrix, and at the same time, convert the outline of the abnormal temperature area in the human infrared thermal imaging data into a three-dimensional coordinate matrix to obtain a thermal imaging three-dimensional coordinate matrix.

[0027] The intersection matrix determination unit is used to calculate the spatial intersection matrix between the manually labeled 3D coordinate matrix and the thermal imaging 3D coordinate matrix.

[0028] The core region determination unit is used to extract the first singular vector of the spatial intersection matrix through singular value decomposition, and to determine the core pain region based on the first singular vector.

[0029] The calibration unit for the region to be calibrated is used to perform first-order difference operations on the manually annotated three-dimensional coordinate matrix to obtain the gradient change matrix of the contour of the pain region annotated by the patient, and to select all boundary points whose gradient change rate exceeds the preset gradient change rate threshold as contour points of the edge region to be calibrated based on the gradient change matrix, and to determine the edge region to be calibrated based on all the contour points of the edge region to be calibrated.

[0030] The temperature inflection point identification unit is used to map the edge region to be calibrated onto the temperature gradient field in the human infrared thermal imaging data, and to determine all temperature change inflection points by fitting the temperature distribution curve with a two-dimensional Gaussian function and calculating the second derivative of the temperature distribution curve.

[0031] The calibration unit for the area to be calibrated is used to correct the edge area to be calibrated based on all temperature change inflection points to obtain the calibration edge area.

[0032] Two-dimensional region fusion unit is used to fuse the core pain region with the calibration edge region to obtain a three-dimensional mesh model of the calibration pain region as the patient's calibration pain region.

[0033] Optionally, the intersection matrix determining unit includes:

[0034] The distance threshold determination subunit is used to set the maximum and minimum distance thresholds based on the accuracy requirements corresponding to the pain intensity score input by the user.

[0035] The Euclidean distance determination sub-unit is used to calculate the three-dimensional Euclidean distance between each boundary point in the manually labeled three-dimensional coordinate matrix and each boundary point in the thermal imaging three-dimensional coordinate matrix.

[0036] The dense point set determination sub-unit is used to summarize all boundary point pairs whose corresponding three-dimensional Euclidean distance does not exceed the maximum distance threshold to obtain the initial intersection point set, and to determine whether there are boundary point pairs in the initial intersection point set whose corresponding three-dimensional Euclidean distance does not exceed the minimum distance threshold. If so, the boundary point pairs in the initial intersection point set whose corresponding three-dimensional Euclidean distance does not exceed the minimum distance threshold are summarized to obtain the dense point set.

[0037] The intersection point set determines the sub-unit, which is used to gather all dense points. Dense point sets whose spatial density exceeds the corresponding density threshold are regarded as true dense point sets. True dense regions are determined based on each true dense point set. All boundary points in all true dense point sets except the boundary point closest to the geometric center of the corresponding true dense region are removed from the initial intersection point set to obtain the final intersection point set.

[0038] The intersection matrix determines the sub-units, which are used to generate the spatial intersection matrix of manually labeled 3D coordinate matrices and thermal imaging 3D coordinate matrices based on the 3D coordinates of each boundary point in the final intersection point set.

[0039] Optionally, the core area defining unit includes:

[0040] The distance-to-it sub-unit is used to calculate the three-dimensional Euclidean distance between each boundary point in the spatial intersection matrix and all remaining boundary points in the spatial intersection matrix except for the current boundary point, based on the spatial intersection matrix, and to serve as all distances to it for the current boundary point;

[0041] The interior point set determines the sub-unit, which is used to select all boundary points in the spatial intersection matrix that are at a distance greater than a distance threshold from the boundary points and summarize them to obtain the interior point set;

[0042] The principal direction vector determines the sub-unit, which is used to extract the first singular vector of the spatial intersection matrix through singular value decomposition, and serves as the principal direction vector of the core pain region.

[0043] The main direction interval is determined by the sub-unit, which is used to extend along the direction of the main direction vector of the core pain area and the corresponding opposite direction, starting from the three-dimensional average coordinates of the inner point set, to obtain the extension line, determine all the intersection points of the extension line with the inner point set and summarize them as the main direction intersection point set, and determine the main direction interval based on the main direction intersection point set.

[0044] The core pain region determination sub-unit is used to determine the standard body of pain direction in the current limb region. Using the main direction interval as the axis, and combining the distribution range of the inner point set on the plane perpendicular to the main direction vector of the core pain region, the core pain region in the shape of the standard body of pain direction is constructed.

[0045] Optionally, a calibration area unit needs to be calibrated, including:

[0046] The first-order difference operation subunit is used to perform first-order difference operations on the manually annotated 3D coordinate matrix to obtain the gradient change matrix of the contour of the pain area annotated by the patient.

[0047] The gradient change rate calculation sub-unit is used to take the ratio of the magnitude of the gradient vector in each row of the gradient change matrix to the temperature difference between the corresponding two boundary points as the gradient change rate.

[0048] The calibration region subunit is used to select all boundary points in the pain region contour marked by the patient as the edge region contour points that have a gradient change rate exceeding a preset gradient change rate threshold, and to determine the edge region to be calibrated based on all the edge region contour points to be calibrated.

[0049] Optionally, the pain prediction module includes:

[0050] The feature construction submodule is used to perform time-series alignment of the patient's pain intensity score, heart rate variability index, and skin conductance index, and to construct a multidimensional pain feature vector by combining the patient's calibrated pain area.

[0051] The pain prediction submodule is used to process multidimensional pain feature vectors using a trained LSTM neural network model to obtain a pain intensity prediction curve for future periods.

[0052] Optionally, the treatment linkage module includes:

[0053] The instruction determination submodule is used to generate treatment parameter control instructions based on the pain trend prediction curve and multidimensional pain feature vector.

[0054] The linkage therapy submodule is used to control the spinal cord stimulator and the intrathecal morphine pump based on the Bluetooth wireless connection established with the spinal cord stimulator and the intrathecal morphine pump and the control commands for treatment parameters.

[0055] The treatment parameters of the spinal cord stimulator include stimulation frequency, pulse width, and stimulation intensity.

[0056] The therapeutic parameters of an intrathecal morphine pump are the drug infusion rate.

[0057] The beneficial effects of this invention compared to existing technologies are as follows: It constructs a three-dimensional human anatomical model that includes a layered structure of bones, nerves, and organs, and marks pain-sensitive areas, providing an intuitive and accurate reference for subsequent pain assessment. It receives user-input pain area marking instructions and intensity scores, allowing patients to directly express their pain sensations. Real-time monitoring of human infrared thermal imaging data helps determine pain areas from the perspective of temperature changes. Heart rate variability and skin conductance indicators are obtained through wearable devices, reflecting the patient's pain state from a physiological perspective. Combining pain area marking instructions with abnormal temperature areas in infrared thermal imaging calibrates pain areas, improving the accuracy of pain area determination. Based on multiple data sources, it predicts pain intensity curves for future periods, enabling a forward-looking understanding of pain development trends. Based on the pain trend prediction curve and multi-dimensional pain feature vectors, it generates treatment parameter control instructions, closely linking pain assessment and treatment, achieving precise and dynamic treatment intervention, and comprehensively improving the scientific rigor and effectiveness of pain assessment and treatment.

[0058] Other features and advantages of the invention will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in this application.

[0059] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0060] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings:

[0061] Figure 1 This is a schematic diagram of a pain dynamic assessment and treatment linkage system based on three-dimensional somatosensory interaction in an embodiment of the present invention;

[0062] Figure 2 This is a flowchart illustrating the sub-modules of the human body modeling module in an embodiment of the present invention.

[0063] Figure 3 This is a flowchart illustrating the sub-modules of the motion-sensing interaction module in an embodiment of the present invention. Detailed Implementation

[0064] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are for illustration and explanation only and are not intended to limit the present invention.

[0065] like Figure 1As shown, this invention provides an implementation method for a three-dimensional somatosensory interactive pain dynamic assessment and treatment linkage system, including:

[0066] The human modeling module is used to construct a three-dimensional human anatomical model that includes the patient's bone, nerves and organs in a layered structure and with pain-sensitive area markers associated with each anatomical part.

[0067] The somatosensory interaction module is used to receive user input commands for marking pain areas and pain intensity scores;

[0068] Infrared sensing module, used to monitor the patient's human infrared thermal imaging data in real time;

[0069] A physiological monitoring module is used to monitor patients' heart rate variability and skin conductance indicators based on wearable devices;

[0070] The region marking module is used to obtain the patient's calibrated pain region based on the pain region marking instructions and abnormal temperature areas in human infrared thermal imaging data;

[0071] The pain prediction module is used to predict the pain intensity prediction curve for future cycles based on the patient's pain intensity score, heart rate variability index, skin conductance index, and calibrated pain area.

[0072] The treatment linkage module is used to generate treatment parameter control instructions based on pain trend prediction curves and multidimensional pain feature vectors.

[0073] In this embodiment, each anatomical location is associated with a corresponding pain-sensitive area marker: when constructing a three-dimensional human anatomical model, different anatomical locations within the model, such as bones, nerves, and organs, are marked with areas prone to pain. For example, neuralgia-sensitive areas are marked with a red semi-transparent layer, musculoskeletal pain-sensitive areas with a blue semi-transparent layer, and visceral pain-sensitive areas with a yellow semi-transparent layer. This way, when a patient marks a painful area on the model, these pre-defined sensitive area markers can be used to more accurately reflect the source of the pain. For instance, if a patient marks pain in the back area, and that area is a musculoskeletal pain-sensitive area, combined with the blue marker, the doctor can initially determine that the pain may be related to the musculoskeletal system.

[0074] In this embodiment, pain intensity scoring is performed by the patient inputting a value from 0 to 10 using the VAS / NRS scoring slider integrated into the somatosensory interaction module. This value represents the level of pain they perceive. 0 represents no pain, and 10 represents extreme pain. For example, if a patient feels their pain level is 5, they slide the slider to the corresponding position. This score is used to assess the patient's current pain intensity.

[0075] In this embodiment, the patient's infrared thermal imaging data is monitored in real time: an infrared sensing module is used to continuously monitor the patient's body and acquire thermal imaging data of the temperature distribution on the body surface. Because the temperature of certain parts of the body may change abnormally when there is pain, real-time monitoring can capture this temperature change information to aid in pain assessment. For example, if a patient has inflammation causing pain in a certain area, that area may show an elevated temperature on the infrared thermal image.

[0076] In this embodiment, heart rate variability (HRV) and skin conductance (GSR) indicators are monitored using wearable devices. HRV reflects changes in the interval between heartbeats; for example, by calculating the time difference between the R waves of adjacent heartbeats and statistically analyzing the patterns of change in heartbeat intervals over a period of time, it can assess the dynamic changes in the autonomic nervous system's regulation of the heart, indirectly reflecting the body's stress response to pain. GSR measures skin conductivity to reflect the activity of sweat glands. For instance, when a patient experiences tension due to pain, sweat gland activity increases, skin conductivity rises, and the GSR value increases, thus reflecting the patient's pain state from a physiological perspective.

[0077] In this embodiment, abnormal temperature zones in human infrared thermal imaging data are defined as areas where the temperature deviates from the normal range within a certain degree. For example, if the normal body temperature range is set to 36.0-37.2℃, and the thermal imaging data shows that the temperature of a certain area is higher than 37.7℃ or lower than 35.5℃ (deviating from the normal range by more than ±0.5℃; the specific threshold can be adjusted according to the actual situation), then that area is marked as an abnormal temperature zone. These areas may be related to the patient's pain area and are used to assist in calibrating the patient's marked pain area.

[0078] In this embodiment, the future period refers to the future time period in which the pain prediction module predicts the intensity of the patient's pain, which is usually the next 24 hours in this embodiment.

[0079] In this embodiment, the pain intensity prediction curve is obtained by the pain prediction module using a trained LSTM neural network model to process the constructed multidimensional pain feature vector. This curve shows the predicted pain intensity change trend for each hour in the next 24 hours.

[0080] In this embodiment, the treatment parameter control instructions are generated by the treatment linkage module based on the pain trend prediction curve and multidimensional pain feature vector, and are used to control the treatment parameters of the spinal cord stimulator and the intrathecal morphine pump. For example, when the current VAS / NRS score is >7 and is predicted to continue to rise within the next hour, an emergency adjustment mode is triggered, increasing the stimulation frequency of the spinal cord stimulator by 20% and the stimulation intensity by 15% (not exceeding the safety threshold); and increasing the infusion rate of the intrathecal morphine pump by 10% (each adjustment not exceeding 0.1 ml / h). When the VAS / NRS score is <3 and persists for more than 2 hours, a maintenance adjustment mode is triggered, reducing the stimulation frequency of the spinal cord stimulator by 10% and the infusion rate of the intrathecal morphine pump by 5%. After all parameter adjustment instructions are generated, they must be confirmed by medical staff via a mobile terminal before execution. In emergency situations, a 30-second automatic execution timeout can be set.

[0081] like Figure 2 As shown, a human body modeling module is proposed to construct an accurate and realistic three-dimensional human anatomical model of the patient, including:

[0082] The CT image data acquisition submodule is used to acquire standard human CT image data of patients and generate a basic model containing the patient's bones, major nerve trunks and internal organs through a three-dimensional reconstruction algorithm.

[0083] The pain-sensitive area annotation submodule is used to annotate the pain-sensitive areas of the base model to obtain a three-dimensional human anatomical model of the patient.

[0084] In this embodiment, standard human CT image data of the patient is acquired: a professional CT scanning device is used to scan the patient's whole body or specific areas. During the scan, X-rays penetrate the patient's body from multiple angles, and a detector receives the attenuation information of the rays after they pass through the body. This attenuation information varies depending on the degree of X-ray absorption by different tissues. For example, bones absorb more X-rays, resulting in a weaker signal on the detector, while soft tissues absorb less and have a relatively stronger signal. The device converts these received signals into digital data, which constitutes the patient's standard human CT image data.

[0085] In this embodiment, a basic model containing the patient's skeleton, major nerve trunks, and internal organs is generated using a 3D reconstruction algorithm. Based on standard human CT image data of the patient, the data is first preprocessed to remove noise interference and enhance image clarity and contrast. Then, a segmentation algorithm is used to separate and identify different tissues in the CT image data, such as bones, nerve trunks, and internal organs. For example, based on the differences in grayscale values ​​of different tissues in the CT image, an appropriate grayscale threshold is set to segment bone tissue from other tissues. For nerve trunks and internal organs, more complex machine learning or deep learning algorithms may be required for identification and segmentation. After segmentation, based on the spatial relationships of each tissue, 3D reconstruction methods such as surface reconstruction or volume rendering are used to reconstruct the segmented tissues in 3D space, generating a basic model containing the patient's skeleton, major nerve trunks, and internal organs. For example, a 3D skeleton model is constructed based on the segmented bone tissue according to its actual spatial location in the body, and combined with the similarly reconstructed nerve trunk and internal organ models to form a complete basic model.

[0086] In this embodiment, pain-sensitive areas are labeled on the base model to obtain a three-dimensional anatomical model of the patient. Based on medical knowledge and clinical experience, pain-sensitive areas are labeled on the generated base model. For neuralgia-sensitive areas, a red semi-transparent layer is used to cover the corresponding nerve distribution area in the base model; musculoskeletal pain-sensitive areas are marked with a blue semi-transparent layer on the relevant bone and muscle parts; and visceral pain-sensitive areas are marked with a yellow semi-transparent layer on the corresponding location of the internal organs. For example, the sciatic nerve distribution area in the base model is covered with a red semi-transparent layer to indicate that this area is a neuralgia-sensitive area; the lumbar spine and surrounding muscles are marked with a blue semi-transparent layer to represent a musculoskeletal pain-sensitive area; and the stomach area is marked with a yellow semi-transparent layer to indicate that this is a visceral pain-sensitive area. Through such labeling, a three-dimensional anatomical model of the patient with pain-sensitive area markings is finally obtained.

[0087] like Figure 3 As shown, to achieve multi-mode and convenient motion-sensing interaction, a motion-sensing interaction module is proposed, including:

[0088] A touchscreen display is used to show a three-dimensional human anatomical model and receive the patient's input of a first pain area marking instruction;

[0089] A depth camera is used to capture the patient's hand gestures and translate them into instructions for marking the second pain area;

[0090] The instruction fusion submodule is used to determine the pain area marking instruction input by the user based on the first pain area marking instruction and / or the second pain area marking instruction;

[0091] The rating receiving submodule is used to receive the pain intensity rating input by the user via an integrated VAS / NRS rating slider.

[0092] In this embodiment, a three-dimensional human anatomical model is displayed, and the system receives a first pain area marking instruction input by the patient. Within the motion-sensing interaction module, a 1:1 scale three-dimensional human anatomical model is presented on the touchscreen, which includes the layered structure of bones, nerves, and organs. The patient can directly use their finger to click or circle the body parts they feel pain on the touchscreen; these actions constitute the first pain area marking instruction. For example, if the patient clicks on the chest area on the touchscreen, this click conveys information to the system that there may be a painful area in the chest.

[0093] In this embodiment, the patient's hand gestures are captured and translated into a second pain area marking instruction: a depth camera tracks the patient's hand gestures in front of a three-dimensional human anatomical model in real time. For example, the patient might draw a circle in the air with their finger to indicate a pain area. After the depth camera captures this gesture, a specific image recognition and conversion algorithm (similar to matching the coordinates, shape, and other features of the gesture with a predefined action template) is used to convert the gesture into a second pain area marking instruction that the system can understand, allowing the system to clearly identify the pain area the patient is pointing to.

[0094] In this embodiment, the pain area marking instruction input by the user is determined based on the first pain area marking instruction and / or the second pain area marking instruction. The instruction fusion submodule analyzes and processes the first pain area marking instruction (from touch operation) and the second pain area marking instruction (from gesture translation). If the patient performs both touch operation and gesture action, and the areas indicated by the two are close, the system may combine the information from both and take the overlapping or close area as the final determined pain area marking instruction; if only one instruction exists, the instruction is directly used as the pain area marking instruction input by the user. For example, if the patient clicks on the leg on the touch screen and simultaneously circles the same position on the leg in the air with a gesture, the system will determine that the leg area is the pain area marked by the patient.

[0095] In this embodiment, a pain intensity rating input by the user is received via an integrated VAS / NRS scoring slider: The VAS / NRS scoring slider is integrated into the touchscreen display of the motion-sensing interaction module. Patients select a score from 0 to 10 based on their perceived pain level by sliding the slider. For example, if a patient feels their pain level is 6, they slide the slider to the position corresponding to 6. The system receives this score as the patient's input pain intensity rating, thereby quantifying the patient's current pain level.

[0096] To accurately determine the patient's calibrated pain area, a region marking module is proposed, including:

[0097] The region marking submodule is used to determine the pain region marked by the patient based on the pain region marking instructions;

[0098] The fusion calibration submodule is used to fuse and calibrate the patient's marked pain area and the abnormal temperature area in the human infrared thermal imaging data to obtain the patient's calibrated pain area.

[0099] In this embodiment, the pain area marked by the patient is determined based on the pain area marking instruction: When the patient inputs the pain area marking instruction through the touch screen or depth camera in the motion-sensing interaction module, the system first obtains the coordinate information in the instruction. If it is a first pain area marking instruction generated by touch operation, the system directly reads the coordinates on the three-dimensional human anatomical model corresponding to the finger touching the screen; if it is a second pain area marking instruction translated from a gesture, the instruction captured and translated by the depth camera also contains the coordinate information on the corresponding model.

[0100] Based on this coordinate information, the system uses a spatial mapping algorithm to accurately map the coordinates of the two-dimensional screen coordinates or the coordinates translated from gestures to the spatial coordinate system of the three-dimensional human anatomical model. For example, the system pre-sets the conversion relationship between screen coordinates and three-dimensional model spatial coordinates. According to this relationship, the point of touch on the screen or the virtual point pointed to by the gesture is mapped to the actual position in the three-dimensional model.

[0101] Then, the system determines the specific area on the 3D human anatomical model based on the acquired coordinates. For click operations, the system uses the click coordinates as the center and a preset range (such as a spherical area with a radius of 5mm) to determine the pain area; for selection or smearing operations, the system determines the pain area based on the range enclosed by the operation trajectory. In this way, the pain area marked by the patient is clearly identified based on the pain area marking instructions, providing a foundation for subsequent pain assessment and calibration.

[0102] To achieve high-precision fusion calibration of the pain area, a fusion calibration submodule is proposed, including:

[0103] The coordinate matrix transformation unit is used to convert the outline of the pain area marked by the patient into a three-dimensional coordinate matrix to obtain a manually annotated three-dimensional coordinate matrix, and at the same time, convert the outline of the abnormal temperature area in the human infrared thermal imaging data into a three-dimensional coordinate matrix to obtain a thermal imaging three-dimensional coordinate matrix.

[0104] The intersection matrix determination unit is used to calculate the spatial intersection matrix between the manually labeled 3D coordinate matrix and the thermal imaging 3D coordinate matrix.

[0105] The core region determination unit is used to extract the first singular vector of the spatial intersection matrix through singular value decomposition, and to determine the core pain region based on the first singular vector.

[0106] The calibration unit for the region to be calibrated is used to perform first-order difference operations on the manually annotated three-dimensional coordinate matrix to obtain the gradient change matrix of the contour of the pain region annotated by the patient, and to select all boundary points whose gradient change rate exceeds the preset gradient change rate threshold as contour points of the edge region to be calibrated based on the gradient change matrix, and to determine the edge region to be calibrated based on all the contour points of the edge region to be calibrated.

[0107] The temperature inflection point identification unit is used to map the edge region to be calibrated onto the temperature gradient field in the human infrared thermal imaging data, and to determine all temperature change inflection points by fitting the temperature distribution curve with a two-dimensional Gaussian function and calculating the second derivative of the temperature distribution curve.

[0108] The calibration unit for the area to be calibrated is used to correct the edge area to be calibrated based on all temperature change inflection points to obtain the calibration edge area.

[0109] Two-dimensional region fusion unit is used to fuse the core pain region with the calibration edge region to obtain a three-dimensional mesh model of the calibration pain region as the patient's calibration pain region.

[0110] In this embodiment, the pain area contour marked by the patient is converted into a three-dimensional coordinate matrix to obtain a manually labeled three-dimensional coordinate matrix: The system acquires the pain area contour marked by the patient on a three-dimensional human anatomical model through touch or gesture. For this contour, the coordinate values ​​of each point on the contour in the coordinate system of the three-dimensional human anatomical model are extracted sequentially in a certain order. The coordinates of each point contain three dimensions (x, y, z). These coordinate values ​​are arranged in order to form a matrix, with rows representing the number of contour points and columns of 3, thus obtaining the manually labeled three-dimensional coordinate matrix.

[0111] In this embodiment, the contours of abnormal temperature zones in human infrared thermal imaging data are converted into a three-dimensional coordinate matrix to obtain a thermal imaging three-dimensional coordinate matrix: the contours of abnormal temperature zones are identified from the human infrared thermal imaging data. Similarly, for each point on this contour, its coordinates (x, y, z) in the same spatial coordinate system as the three-dimensional human anatomical model are determined. These coordinate values ​​are then arranged into a matrix, with rows representing the number of contour points and columns of 3, thus obtaining the thermal imaging three-dimensional coordinate matrix.

[0112] In this embodiment, the first singular vector of the spatial intersection matrix is ​​extracted through singular value decomposition (SVD): SVD is performed on the spatial intersection matrix. SVD decomposes the matrix into the product of three matrices, i.e., A = UΣV. TΣ is a diagonal matrix, and the values ​​on the diagonal are singular values, arranged in descending order. The first singular vector is the first column vector of the U matrix, which reflects the main directional characteristics of the region represented by the spatial intersection matrix.

[0113] In this embodiment, a first-order difference operation is performed on the manually annotated 3D coordinate matrix to obtain the gradient change matrix of the pain region contour annotated by the patient: each row of the manually annotated 3D coordinate matrix represents the 3D coordinates of a point on the pain region contour. Performing a first-order difference operation on the matrix, i.e., calculating the difference between the coordinates of adjacent rows, yields a new matrix, which is the gradient change matrix of the pain region contour annotated by the patient. This matrix reflects the changes in coordinates between points on the contour, indicating the steepness and directional changes of the contour.

[0114] In this embodiment, a preset gradient change rate threshold is set: based on the actual needs and experience of pain assessment, a value is set as the threshold for the gradient change rate. The gradient change rate refers to the ratio of the magnitude of the gradient vector in each row of the gradient change matrix to the temperature difference between the corresponding two boundary points. For example, the threshold is set to 0.5.

[0115] In this embodiment, the edge regions to be calibrated are determined based on the contour points of all edge regions to be calibrated: these contour points are connected together, and the edge regions to be calibrated are determined according to their distribution range and shape.

[0116] In this embodiment, the edge region to be calibrated is mapped onto the temperature gradient field in the human infrared thermal imaging data. A two-dimensional Gaussian function is used to fit the temperature distribution curve, and the second derivative of the temperature distribution curve is calculated to determine all temperature change inflection points: the coordinates of the edge region to be calibrated are mapped onto the temperature gradient field corresponding to the human infrared thermal imaging data to obtain the temperature distribution data of that region in the temperature gradient field. Then, a two-dimensional Gaussian function is used to fit these temperature distribution data to obtain a smooth temperature distribution curve. The second derivative of this curve is calculated; when the second derivative is 0 and the first derivative has an extremum at that point, the corresponding point is the temperature change inflection point. All temperature change inflection points are determined in this way; these inflection points represent the locations where the degree of temperature change changes drastically.

[0117] In this embodiment, the calibration edge region is obtained by correcting the calibration edge region based on all temperature change inflection points: the contour of the calibration edge region is adjusted according to the coordinates of the determined temperature change inflection points. For example, if a temperature change inflection point is located near a segment of the contour of the calibration edge region, it indicates that the segment of the contour may need to be corrected according to the temperature change. Possible correction methods include moving the segment of the contour a certain distance in the direction of the temperature change inflection point, or changing the shape of the segment of the contour to better reflect the actual situation reflected by the temperature change, thereby obtaining the calibration edge region.

[0118] In this embodiment, the core pain region and the calibration edge region are fused to obtain a three-dimensional mesh model of the calibration pain region, which serves as the patient's calibration pain region. The calibration edge region and the core pain region are stitched together according to their positional relationship in three-dimensional space. For example, the calibration edge region surrounds the core pain region. After combining the two, a three-dimensional mesh generation algorithm is used to generate a three-dimensional mesh model on this fused region, with the mesh cell side length set to no more than 2mm. This three-dimensional mesh model is the calibration pain region, which more accurately reflects the patient's actual pain area, providing a more precise basis for subsequent pain assessment and treatment.

[0119] To improve the accuracy of pain area calibration, an intersection matrix determination unit is proposed, including:

[0120] The distance threshold determination subunit is used to set the maximum and minimum distance thresholds based on the accuracy requirements corresponding to the pain intensity score input by the user.

[0121] The Euclidean distance determination sub-unit is used to calculate the three-dimensional Euclidean distance between each boundary point in the manually labeled three-dimensional coordinate matrix and each boundary point in the thermal imaging three-dimensional coordinate matrix.

[0122] The dense point set determination sub-unit is used to summarize all boundary point pairs whose corresponding three-dimensional Euclidean distance does not exceed the maximum distance threshold to obtain the initial intersection point set, and to determine whether there are boundary point pairs in the initial intersection point set whose corresponding three-dimensional Euclidean distance does not exceed the minimum distance threshold. If so, the boundary point pairs in the initial intersection point set whose corresponding three-dimensional Euclidean distance does not exceed the minimum distance threshold are summarized to obtain the dense point set.

[0123] The intersection point set determines the sub-unit, which is used to gather all dense points. Dense point sets whose spatial density exceeds the corresponding density threshold are regarded as true dense point sets. True dense regions are determined based on each true dense point set. All boundary points in all true dense point sets except the boundary point closest to the geometric center of the corresponding true dense region are removed from the initial intersection point set to obtain the final intersection point set.

[0124] The intersection matrix determines the sub-units, which are used to generate the spatial intersection matrix of manually labeled 3D coordinate matrices and thermal imaging 3D coordinate matrices based on the 3D coordinates of each boundary point in the final intersection point set.

[0125] In this embodiment, maximum and minimum distance thresholds are set based on the accuracy requirements corresponding to the pain intensity score input by the user: different pain intensity scores input by the user result in different accuracy requirements for pain area localization. Generally speaking, a higher pain intensity score means that the patient's pain perception is more intense, and in this case, more precise pain area localization is desired. For example, when the pain intensity score is between 8 and 10, the maximum distance threshold may be set to 2 mm and the minimum distance threshold to 0.5 mm; if the score is between 3 and 7, the maximum distance threshold may be set to 3 mm and the minimum distance threshold to 1 mm. By adjusting the thresholds according to the pain intensity score, intersection points can be reasonably selected under different pain levels, improving the accuracy of pain area calibration.

[0126] In this embodiment, the three-dimensional Euclidean distance is the square root of the sum of the squares of the differences in coordinates of two points in the same dimension. In this embodiment, this distance is calculated between each boundary point in the manually labeled three-dimensional coordinate matrix and each boundary point in the thermal imaging three-dimensional coordinate matrix to determine the proximity of the two points in three-dimensional space and whether they might be intersection points.

[0127] In this embodiment, spatial density refers to the number of points within a given spatial volume. In this embodiment, for a set of points (such as a subset of points in an initial intersection point set), a spatial volume containing these points is first determined. For example, with a certain point as the center and a radius of... sphere volume Then count the number of points within that volume. spatial density .

[0128] In this embodiment, the density threshold is a spatial density value standard set based on the actual pain area calibration needs and experience. For example, the density threshold is set to 5 points / mm. 3 .

[0129] In this embodiment, a true dense region is determined based on each true dense point set: for each true dense point set that satisfies a spatial density greater than a density threshold, the true dense region is determined based on the distribution of these points in three-dimensional space. For example, by calculating the convex hull of the point set, a convex polygon (a convex polyhedron in three-dimensional space) containing all the points is obtained, and the region enclosed by this convex polyhedron is the true dense region. Alternatively, using the two points farthest apart in the point set as the axis, and combining the distance range of other points from this axis, a region resembling a cylinder or elliptical cylinder is determined as the true dense region, which can better cover the actual area represented by the true dense point set.

[0130] In this embodiment, the geometric center of the truly dense region is calculated as follows: For a given truly dense region, its geometric center is calculated. If the truly dense region is a convex polyhedron composed of a set of points, the sum of the coordinates of all points is first calculated, and then divided by the number of points n to obtain the coordinates of the geometric center.

[0131] In this embodiment, a spatial intersection matrix of the manually labeled 3D coordinate matrix and the thermal imaging 3D coordinate matrix is ​​generated based on the 3D coordinates of each boundary point in the final intersection point set. The final intersection point set contains possible intersection points between the manually labeled pain area and the thermal imaging abnormal temperature area after filtering and removing redundancy. The 3D coordinates of these points are arranged in order to form a matrix, with the rows representing the number of intersection points and the columns being 3. This matrix is ​​the spatial intersection matrix of the manually labeled 3D coordinate matrix and the thermal imaging 3D coordinate matrix.

[0132] To accurately determine the core pain region, a core region determination unit is proposed, including:

[0133] The distance-to-it sub-unit is used to calculate the three-dimensional Euclidean distance between each boundary point in the spatial intersection matrix and all remaining boundary points in the spatial intersection matrix except for the current boundary point, based on the spatial intersection matrix, and to serve as all distances to it for the current boundary point;

[0134] The interior point set determines the sub-unit, which is used to select all boundary points in the spatial intersection matrix that are at a distance greater than a distance threshold from the boundary points and summarize them to obtain the interior point set;

[0135] The principal direction vector determines the sub-unit, which is used to extract the first singular vector of the spatial intersection matrix through singular value decomposition, and serves as the principal direction vector of the core pain region.

[0136] The main direction interval is determined by the sub-unit, which is used to extend along the direction of the main direction vector of the core pain area and the corresponding opposite direction, starting from the three-dimensional average coordinates of the inner point set, to obtain the extension line, determine all the intersection points of the extension line with the inner point set and summarize them as the main direction intersection point set, and determine the main direction interval based on the main direction intersection point set.

[0137] The core pain region determination sub-unit is used to determine the standard body of pain direction in the current limb region. Using the main direction interval as the axis, and combining the distribution range of the inner point set on the plane perpendicular to the main direction vector of the core pain region, the core pain region in the shape of the standard body of pain direction is constructed.

[0138] In this embodiment, the distance threshold is a pre-set distance value used to filter the set of interior points from all boundary points of the spatial intersection matrix. For example, it can be set to 5mm.

[0139] In this embodiment, starting from the three-dimensional average coordinates of the inner point set, straight lines are drawn along the direction of the main direction vector of the core pain region and its corresponding opposite direction. All intersections of these straight lines with the inner point set are identified and summarized as the main direction intersection set. The main direction interval is then determined based on this set: First, the average three-dimensional coordinates of all points in the inner point set are calculated to obtain a three-dimensional average coordinate point. Using this point as the starting point, straight lines are drawn along the direction of the main direction vector v of the core pain region obtained through singular value decomposition and its opposite direction −v. Then, all intersections of these two straight lines with the inner point set are found and collected to form the main direction intersection set. Within this set, the two furthest intersections are identified; the interval formed by the line segment between these two intersections is the main direction interval. For example, if the three-dimensional average coordinates of the inlier set are (10,10,10) and the principal direction vector is (1,0,0), then the intersection points of the straight lines extended along this direction and the opposite direction with the inlier set may be (5,10,10), (15,10,10), etc. The principal direction interval may be the interval defined by the line segment from (5,10,10) to (15,10,10), which reflects the range of the core pain area in the principal direction.

[0140] In this embodiment, a standard pain trajectory model for the current limb region is determined: based on medical knowledge and clinical experience, pain in different limb regions often has specific directional and morphological characteristics, which are summarized as a standard pain trajectory model. For example, neuralgia in the arm usually follows a long strip along the nerve distribution, and the corresponding standard pain trajectory model might be a long strip-shaped model; while visceral pain in the abdomen may tend to have an approximately spherical distribution centered on a certain internal organ, and the corresponding standard pain trajectory model is a near-spherical shape. By determining the limb location of the current pain area and selecting the corresponding standard pain trajectory model, a rough shape reference framework is provided for constructing the core pain area.

[0141] In this embodiment, a core pain region with a standard pain trajectory shape is constructed using the main direction interval as the axis and the distribution range of the inner point set on the plane perpendicular to the main direction vector of the core pain region. The previously determined main direction interval serves as the central axis of the core pain region. Then, the distribution of the inner point set on the plane perpendicular to the main direction vector is considered. For example, the projection of the inner point set onto these planes is calculated to determine the distribution range of the projection points. For instance, the point farthest from the central axis among the projection points is found to determine the radius or size in the vertical direction. Using the main direction interval as the axis and the size in the vertical direction as the basis, combined with the shape of the previously determined standard pain trajectory shape (such as a long strip, a spherical shape, etc.), a model of the core pain region is constructed. For example, if the main direction interval is a line segment along the x-axis, the projection of the inner point set onto the plane perpendicular to the x-axis shows a circular distribution range with a radius of 3mm, and the standard pain trajectory shape of the current limb region is a long strip, then a long strip-shaped core pain region with a radius of 3mm and the main direction interval as the axis is constructed, making it more consistent with the characteristics of the actual pain region.

[0142] To accurately calibrate the area to be calibrated, a calibration unit for the area to be calibrated is proposed, including:

[0143] The first-order difference operation subunit is used to perform first-order difference operations on the manually annotated 3D coordinate matrix to obtain the gradient change matrix of the contour of the pain area annotated by the patient.

[0144] The gradient change rate calculation sub-unit is used to take the ratio of the magnitude of the gradient vector in each row of the gradient change matrix to the temperature difference between the corresponding two boundary points as the gradient change rate.

[0145] The calibration region subunit is used to select all boundary points in the pain region contour marked by the patient as the edge region contour points that have a gradient change rate exceeding a preset gradient change rate threshold, and to determine the edge region to be calibrated based on all the edge region contour points to be calibrated.

[0146] In this embodiment, the ratio of the magnitude of the gradient vector in each row of the gradient transformation matrix to the temperature difference between the corresponding two boundary points is taken as the gradient rate of change: In the gradient transformation matrix G, the (Δx) of each row i ,Δy i ,Δz i This forms a gradient vector. The magnitude of the gradient vector represents the actual distance change between adjacent boundary points in three-dimensional space. Simultaneously, the temperature values ​​corresponding to these two adjacent boundary points in human infrared thermal imaging data are obtained, and their temperature difference is calculated. The gradient rate of change is equal to the ratio of the magnitude to the temperature difference; it reflects the degree of spatial change in the contour of the pain area corresponding to a unit temperature change, and is used to measure the relationship between contour change and temperature change.

[0147] To achieve effective prediction of pain development trends, a pain prediction module is proposed, including:

[0148] The feature construction submodule is used to perform time-series alignment of the patient's pain intensity score, heart rate variability index, and skin conductance index, and to construct a multidimensional pain feature vector by combining the patient's calibrated pain area.

[0149] The pain prediction submodule is used to process multidimensional pain feature vectors using a trained LSTM neural network model to obtain a pain intensity prediction curve for future periods.

[0150] In this embodiment, the patient's pain intensity score, heart rate variability (HRV) index, and skin conductance (GSR) index are time-series aligned, and combined with the patient's calibrated pain region to construct a multidimensional pain feature vector. This involves collecting pain intensity score, HRV index, and GSR index data at different time points. Since these data may differ in their acquisition time, time-series alignment is necessary to ensure that each time point corresponds to data from all three indicators. For example, assuming data is collected hourly, the data for different indicators at each hour is compiled and aligned. For the calibrated pain region, features such as the area of ​​the pain region, the overlap between the pain region and densely nerve-rich areas, and the three-dimensional center coordinates of the pain region are extracted. Then, the time-series aligned pain intensity score, HRV index, GSR index data, and the features of the calibrated pain region are integrated to form a multidimensional pain feature vector. For example, the constructed vector might be in the form of [pain intensity score, HRV time-domain index, GSR peak value, pain region area, overlap between the pain region and densely nerve-rich areas, x-value of the three-dimensional center coordinates of the pain region, y-value of the three-dimensional center coordinates of the pain region, z-value of the three-dimensional center coordinates of the pain region].

[0151] In this embodiment, a trained LSTM neural network model is used to process multidimensional pain feature vectors to obtain a pain intensity prediction curve for future periods. The constructed multidimensional pain feature vectors are sequentially input into the trained LSTM neural network model in chronological order. The model's internal structure processes these input data layer by layer, learning time-series features and patterns through memory units and gating mechanisms, capturing the relationship between pain intensity and other relevant indicators over time. For example, the model may learn the potential link between changes in heart rate variability and future pain intensity changes. After processing, the model outputs the predicted pain intensity value for each time point within the future period (e.g., the next 24 hours). Finally, these predicted values ​​are used to generate a continuous pain intensity prediction curve using a specific curve fitting method (e.g., cubic spline curve fitting), visually demonstrating the trend of future pain intensity changes over time.

[0152] In this embodiment, the trained LSTM neural network model is developed as follows: First, historical data from at least 500 chronic pain patients are collected, including hourly records of pain area, VAS / NRS scores, HRV, GSR, and corresponding treatment parameters. This data is then divided into training and validation sets in a 7:3 ratio. The model's input layer dimension is set to 4 (corresponding to the four parameters in the multidimensional feature vector: pain intensity score, HRV index, GSR index, and calibrated pain area). The hidden layer contains 32 neurons, which perform nonlinear transformations on the input data through complex weighted connections to uncover latent features and relationships within the data. The output layer provides a predicted pain intensity value for the next 24 hours. The Adam optimizer is used to adjust the model's weight parameters, ensuring the model's predictions are as close to the true values ​​as possible. The training cycle is set to 100 rounds, during which the model continuously adjusts its weights based on the training set data. After each training round, the model's performance is evaluated using validation set data, and the mean absolute error of the validation set is calculated. When the mean absolute error of the validation set is less than 1.0, the model training is considered to have achieved good results, and training is stopped to obtain the final trained LSTM neural network model. This model can effectively process the input multidimensional pain feature vector and predict the future pain intensity.

[0153] To achieve precise linkage between pain assessment and treatment, a treatment linkage module is proposed, including:

[0154] The instruction determination submodule is used to generate treatment parameter control instructions based on the pain trend prediction curve and multidimensional pain feature vector.

[0155] The linkage therapy submodule is used to control the spinal cord stimulator and the intrathecal morphine pump based on the Bluetooth wireless connection established with the spinal cord stimulator and the intrathecal morphine pump and the control commands for treatment parameters.

[0156] The treatment parameters of the spinal cord stimulator include stimulation frequency, pulse width, and stimulation intensity.

[0157] The therapeutic parameters of an intrathecal morphine pump are the drug infusion rate.

[0158] In this embodiment, treatment parameter control instructions are generated based on pain trend prediction curves and multidimensional pain feature vectors: the system generates treatment parameter control instructions according to these data and established rules.

[0159] For example, when the pain trend prediction curve shows a sustained increase in pain intensity within the next hour, and the current VAS / NRS score is greater than 7, while the multidimensional pain feature vector indicates corresponding abnormal changes in the patient's physiological indicators (such as heart rate variability and skin conductance response), an emergency adjustment mode is triggered. For spinal cord stimulators, the stimulation frequency is increased by 20% according to the rules; that is, if the current stimulation frequency is f, the adjusted frequency is f×(1+20%). The stimulation intensity is increased by 15% (but not exceeding the safety threshold; assuming the safety threshold is Imax, if the current stimulation intensity is I, the adjusted intensity is I×(1+15%), and I×(1+15%)≤Imax must be satisfied). For intrathecal morphine pumps, the drug infusion rate is increased by 10% (a single adjustment does not exceed 0.1 ml / h; assuming the current infusion rate is v, the adjusted rate is v×(1+10%); if v×(1+10%)−v>0.1 ml / h, the adjusted rate is v+0.1 ml / h).

[0160] For example, when the VAS / NRS score is less than 3 and lasts for more than 2 hours, and the multidimensional pain feature vector reflects that the patient's physiological state is relatively stable, a maintenance mode is triggered. For spinal cord stimulators, the stimulation frequency is reduced by 10%, that is, the adjusted frequency is the current frequency f multiplied by (1−10%); for intrathecal morphine pumps, the drug infusion rate is reduced by 5%, that is, the adjusted rate is the current rate v multiplied by (1−5%).

[0161] By comprehensively analyzing pain trend prediction curves and multidimensional pain feature vectors, and based on these rules, the system generates control instructions for treatment parameters of spinal cord stimulators and intrathecal morphine pumps to achieve precise and dynamic treatment intervention.

[0162] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of this invention and its equivalents, this invention also intends to include these modifications and variations.

Claims

1. A pain dynamic assessment and treatment linkage system based on three-dimensional somatosensory interaction, characterized in that, include: The human modeling module is used to construct a three-dimensional human anatomical model that includes the patient's bone, nerves and organs in a layered structure and with pain-sensitive area markers associated with each anatomical part. The somatosensory interaction module is used to receive user input commands for marking pain areas and pain intensity scores; Infrared sensing module, used to monitor the patient's human infrared thermal imaging data in real time; A physiological monitoring module is used to monitor patients' heart rate variability and skin conductance indicators based on wearable devices; The region marking module is used to obtain the patient's calibrated pain region based on the pain region marking instructions and abnormal temperature areas in human infrared thermal imaging data; The pain prediction module is used to predict the pain intensity prediction curve for future cycles based on the patient's pain intensity score, heart rate variability index, skin conductance index, and calibrated pain area. The treatment linkage module is used to generate treatment parameter control instructions based on pain trend prediction curves and multidimensional pain feature vectors; The region marking module includes: The region marking submodule is used to determine the pain region marked by the patient based on the pain region marking instructions; The fusion calibration submodule is used to fuse and calibrate the patient's marked pain area and the abnormal temperature area in the human infrared thermal imaging data to obtain the patient's calibrated pain area. The integrated calibration submodule includes: The coordinate matrix transformation unit is used to convert the outline of the pain area marked by the patient into a three-dimensional coordinate matrix to obtain a manually annotated three-dimensional coordinate matrix, and at the same time, convert the outline of the abnormal temperature area in the human infrared thermal imaging data into a three-dimensional coordinate matrix to obtain a thermal imaging three-dimensional coordinate matrix. The intersection matrix determination unit is used to calculate the spatial intersection matrix between the manually labeled 3D coordinate matrix and the thermal imaging 3D coordinate matrix. The core region determination unit is used to extract the first singular vector of the spatial intersection matrix through singular value decomposition, and to determine the core pain region based on the first singular vector. The calibration unit for the region to be calibrated is used to perform first-order difference operations on the manually annotated three-dimensional coordinate matrix to obtain the gradient change matrix of the contour of the pain region annotated by the patient, and to select all boundary points whose gradient change rate exceeds the preset gradient change rate threshold as contour points of the edge region to be calibrated based on the gradient change matrix, and to determine the edge region to be calibrated based on all the contour points of the edge region to be calibrated. The temperature inflection point identification unit is used to map the edge region to be calibrated onto the temperature gradient field in the human infrared thermal imaging data, and to determine all temperature change inflection points by fitting the temperature distribution curve with a two-dimensional Gaussian function and calculating the second derivative of the temperature distribution curve. The calibration unit for the area to be calibrated is used to correct the edge area to be calibrated based on all temperature change inflection points to obtain the calibration edge area. Two-dimensional region fusion unit is used to fuse the core pain region with the calibration edge region to obtain a three-dimensional mesh model of the calibration pain region as the patient's calibration pain region; The intersection matrix determination unit includes: The distance threshold determination subunit is used to set the maximum and minimum distance thresholds based on the accuracy requirements corresponding to the pain intensity score input by the user. The Euclidean distance determination sub-unit is used to calculate the three-dimensional Euclidean distance between each boundary point in the manually labeled three-dimensional coordinate matrix and each boundary point in the thermal imaging three-dimensional coordinate matrix. The dense point set determination sub-unit is used to summarize all boundary point pairs whose corresponding three-dimensional Euclidean distance does not exceed the maximum distance threshold to obtain the initial intersection point set, and to determine whether there are boundary point pairs in the initial intersection point set whose corresponding three-dimensional Euclidean distance does not exceed the minimum distance threshold. If so, the boundary point pairs in the initial intersection point set whose corresponding three-dimensional Euclidean distance does not exceed the minimum distance threshold are summarized to obtain the dense point set. The intersection point set determines the sub-unit, which is used to gather all dense points. Dense point sets whose spatial density exceeds the corresponding density threshold are regarded as true dense point sets. True dense regions are determined based on each true dense point set. All boundary points in all true dense point sets except the boundary point closest to the geometric center of the corresponding true dense region are removed from the initial intersection point set to obtain the final intersection point set. The intersection matrix determines the sub-unit, which is used to generate a spatial intersection matrix of manually labeled 3D coordinate matrix and thermal imaging 3D coordinate matrix based on the 3D coordinates of each boundary point in the final intersection point set; The core area is defined by the following units: The distance-to-it sub-unit is used to calculate the three-dimensional Euclidean distance between each boundary point in the spatial intersection matrix and all remaining boundary points in the spatial intersection matrix except for the current boundary point, based on the spatial intersection matrix, and to serve as all distances to it for the current boundary point; The interior point set determines the sub-unit, which is used to select all boundary points in the spatial intersection matrix that are at a distance greater than a distance threshold from the boundary points and summarize them to obtain the interior point set; The principal direction vector determines the sub-unit, which is used to extract the first singular vector of the spatial intersection matrix through singular value decomposition, and serves as the principal direction vector of the core pain region. The main direction interval is determined by the sub-unit, which is used to extend along the direction of the main direction vector of the core pain area and the corresponding opposite direction, starting from the three-dimensional average coordinates of the inner point set, to obtain the extension line, determine all the intersection points of the extension line with the inner point set and summarize them as the main direction intersection point set, and determine the main direction interval based on the main direction intersection point set. The core pain region determination sub-unit is used to determine the standard body of pain direction in the current limb region. Using the main direction interval as the axis, and combining the distribution range of the inner point set on the plane perpendicular to the main direction vector of the core pain region, the core pain region in the shape of the standard body of pain direction is constructed. The calibration unit for the area to be calibrated includes: The first-order difference operation subunit is used to perform first-order difference operations on the manually annotated 3D coordinate matrix to obtain the gradient change matrix of the contour of the pain area annotated by the patient. The gradient change rate calculation sub-unit is used to take the ratio of the magnitude of the gradient vector in each row of the gradient change matrix to the temperature difference between the corresponding two boundary points as the gradient change rate. The calibration region subunit is used to select all boundary points in the pain region contour marked by the patient as the edge region contour points that have a gradient change rate exceeding a preset gradient change rate threshold, and to determine the edge region to be calibrated based on all the edge region contour points to be calibrated.

2. The pain dynamic assessment and treatment linkage system based on three-dimensional somatosensory interaction according to claim 1, characterized in that, The human body modeling module includes: The CT image data acquisition submodule is used to acquire standard human CT image data of patients and generate a basic model containing the patient's bones, major nerve trunks and internal organs through a three-dimensional reconstruction algorithm. The pain-sensitive area annotation submodule is used to annotate the pain-sensitive areas of the base model to obtain a three-dimensional human anatomical model of the patient.

3. The pain dynamic assessment and treatment linkage system based on three-dimensional somatosensory interaction according to claim 1, characterized in that, The motion-sensing interaction module includes: A touchscreen display is used to show a three-dimensional human anatomical model and receive the patient's input of a first pain area marking instruction; A depth camera is used to capture the patient's hand gestures and translate them into instructions for marking the second pain area; The instruction fusion submodule is used to determine the pain area marking instruction input by the user based on the first pain area marking instruction and / or the second pain area marking instruction; The rating receiving submodule is used to receive the pain intensity rating input by the user via an integrated VAS / NRS rating slider.

4. The pain dynamic assessment and treatment linkage system based on three-dimensional somatosensory interaction according to claim 1, characterized in that, The pain prediction module includes: The feature construction submodule is used to perform time-series alignment of the patient's pain intensity score, heart rate variability index, and skin conductance index, and to construct a multidimensional pain feature vector by combining the patient's calibrated pain area. The pain prediction submodule is used to process multidimensional pain feature vectors using a trained LSTM neural network model to obtain a pain intensity prediction curve for future periods.

5. The pain dynamic assessment and treatment linkage system based on three-dimensional somatosensory interaction according to claim 1, characterized in that, The treatment linkage module includes: The instruction determination submodule is used to generate treatment parameter control instructions based on the pain trend prediction curve and multidimensional pain feature vector. The linkage therapy submodule is used to control the spinal cord stimulator and the intrathecal morphine pump based on the Bluetooth wireless connection established with the spinal cord stimulator and the intrathecal morphine pump and the control commands for treatment parameters. The treatment parameters of the spinal cord stimulator include stimulation frequency, pulse width, and stimulation intensity. The therapeutic parameters of an intrathecal morphine pump are the drug infusion rate.

Images