Multi-dimensional physiological data automatic teenager idiopathic scoliosis intelligent screening system

Abstract

The invention discloses an automatic teenager idiopathic scoliosis intelligent screening system based on multi-dimensional physiological data, and relates to the field of scoliosis, the system comprises a camera module, a double shoulder height measurer, a waist stress sensing device, a back curve stress sensing device, a plantar pressure distribution testing device and a scoliosis intelligent analysis module; the camera shooting module is used for shooting the back and the side surfaces when the body is upright and the back when the body bends forwards; the double-shoulder height measurer is used for measuring the heights of double shoulders; the waist stress sensing device applies force to the two side waists and measures the counter-acting force of the side waists; the back curve stress sensing device is used for measuring a back curve; the plantar pressure distribution testing device is used for measuring the pressure of two feet; the scoliosis intelligent analysis module judges the risk degree of scoliosis according to the picture, the height difference of the shoulders, the counter-acting force of the side waist, the back curve and the pressure of the feet, the examination process is rapid and free of radiation, and the accuracy of the examination result is high.

Description

Technical Field

[0001] This application relates to the field of scoliosis, and in particular to an intelligent screening system for adolescent idiopathic scoliosis using multidimensional physiological data. Background Technology

[0002] Currently, the screening for adolescent idiopathic scoliosis is mainly conducted through manual palpation by specialists, scoliosis detection rulers, and clinical X-rays. The accuracy of this method is affected by the doctor's personal experience and technique, which may lead to missed diagnoses. Furthermore, multiple X-ray diagnoses involve radiation, and the disease requires multiple screenings over many years. Screening a single person takes 3 to 5 minutes, which is not suitable for multiple screenings of a large population. Summary of the Invention

[0003] The purpose of this application is to provide an automated intelligent screening system for adolescent idiopathic scoliosis based on multidimensional physiological data, which is fast, radiation-free, and has high accuracy in the examination results.

[0004] To achieve the above objectives, this application provides the following solution: This application provides a multidimensional physiological data-based automatic intelligent screening system for adolescent idiopathic scoliosis, including: a camera module, a shoulder height measuring device, a lumbar stress sensing device, a back curve stress sensing device, a foot pressure distribution testing device, and a scoliosis intelligent analysis module.

[0005] The camera module is used to take pictures of the user's back and side when standing upright, as well as the user's back when bending forward; the shoulder height measuring device is used to measure the height of the user's shoulders; the lumbar stress sensing device is used to apply equal force to both sides of the user's waist and measure the value of the reaction force on both sides of the waist; the back curve stress sensing device is used to measure the curve of the concave area on both sides of the spinous process of the spine to obtain the back curve; the foot pressure distribution testing device is used to measure the pressure of the user's feet.

[0006] The intelligent scoliosis analysis module is used to determine the height difference between the user's shoulders based on the height of the user's shoulders; to determine the key points of the spinous processes of each vertebra based on photos of the user's back when standing and when bending forward; to determine the line connecting the key points of the spinous processes based on the key points of each vertebra; to determine the angle between the user's trunk midline and the horizontal line based on the user's side profile photo; and to determine the degree of scoliosis risk based on the angle between the line connecting the key points of the spinous processes and the vertical line, the angle between the trunk midline and the horizontal line, the height difference between the shoulders, the values ​​of the reaction forces on both sides of the waist, the back curve, and the pressure on the feet.

[0007] According to the specific embodiments provided in this application, this application has the following technical effects: This application provides a multidimensional physiological data automatic intelligent screening system for adolescent idiopathic scoliosis. The entire diagnostic process is performed by the scoliosis intelligent analysis module based on the user's back photos, side photos, shoulder height, the value of the reaction force on both sides of the waist, back curve and pressure on both feet. No manual palpation is required, and it is not affected by the doctor's personal experience and technique. The examination process is fast and the examination results are highly accurate. The entire process does not require CT and is radiation-free. Attached Figure Description

[0008] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0009] Figure 1 This is a schematic diagram of the structure of an intelligent screening system for adolescent idiopathic scoliosis based on multidimensional physiological data, provided as an embodiment of this application.

[0010] Figure 2 The improved HRNet network architecture diagram provided for this application.

[0011] Figure 3 This is a structural diagram of the attention module in a convolutional block.

[0012] Figure reference numerals: Shoulder height measuring device-1, Waist stress sensing device-2, Back curve stress sensing device-3, Foot pressure distribution testing device-4, Display-5, First camera-6, Second camera-7, Door-8. Detailed Implementation

[0013] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0014] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0015] In one exemplary embodiment, such as Figure 1As shown, an automated intelligent screening system for adolescent idiopathic scoliosis based on multidimensional physiological data is provided, including: a camera module, a shoulder height measuring device 1, a lumbar stress sensing device 2, a back curve stress sensing device 3, a foot pressure distribution testing device 4, and a scoliosis intelligent analysis module.

[0016] The camera module is used to take pictures of the user's back and side when standing upright, as well as the user's back when bending forward; the shoulder height measuring device 1 is used to measure the height of the user's shoulders; the lumbar stress sensing device 2 is used to apply equal force to both sides of the user's waist and measure the value of the reaction force on both sides of the waist; the back curve stress sensing device 3 is used to measure the curve of the concave area on both sides of the spinous process of the spine to obtain the back curve; the foot pressure distribution testing device 4 (scoliosis will cause different stress on the two feet) is used to measure the pressure on the user's feet.

[0017] The intelligent scoliosis analysis module is used to determine the height difference between the user's shoulders based on the height of the user's shoulders; to determine the key points of the spinous processes of each vertebra based on photos of the user's back when standing and when bending forward; to determine the line connecting the key points of the spinous processes based on the key points of each vertebra; to determine the angle between the user's trunk midline and the horizontal line based on the user's side profile photo; and to determine the degree of scoliosis risk based on the angle between the line connecting the key points of the spinous processes and the vertical line (the line perpendicular to the horizontal line), the angle between the trunk midline and the horizontal line, the height difference between the shoulders, the values ​​of the reaction forces on both sides of the waist, the back curve, and the pressure on both feet.

[0018] In practical applications, the camera module includes a first camera 6 and a second camera 7. The first camera 6 is used to take side photos, and the second camera 7 is used to take back photos.

[0019] In another exemplary embodiment of this application, the key points of the spinous processes of each vertebra of the user's spine are obtained based on photos of the user's back when standing upright and photos of the user's back when bending forward. Specifically, a spinal key point detection algorithm is used to process the photos of the user's back when standing upright and photos of the user's back when bending forward to obtain a heat map of the spinous process key points, and the key points of the spinous processes of each vertebra of the spine are obtained based on the heat map of the spinous process key points.

[0020] The spinal keypoint detection algorithm proposed in this application uses HRNet as its backbone network, retaining its core advantage of "high-resolution feature flow throughout," and achieves targeted improvements through an embedded attention mechanism. In another exemplary embodiment of this application, the spinal keypoint detection algorithm is an improved HRNet model, such as... Figure 2As shown, it includes an HRNet network, a first CBAM network, a second CBAM network, and a third CBAM network. The second and third stages of the HRNet network are connected through the first CBAM network, the third and fourth stages of the HRNet network are connected through the second CBAM network, and the output of the HRNet network is connected to the third CBAM network.

[0021] The spinal keypoint detection algorithm provided in this application includes a feature extraction layer, a feature fusion layer, and an output layer. The feature extraction layer adopts the multi-branch parallel structure of the HRNet network, progressively constructing feature map branches from high resolution to low resolution through four stages. Each stage contains multiple residual units, extracting low-level features (such as grayscale variations and edge contours) and mid-level features (such as overall vertebral morphology and intervertebral space distribution) through convolution, batch normalization, and ReLU activation functions. Unlike the original HRNet network, this application embeds a Convolutional Block Attention Module (CBAM) after the residual units of each resolution branch starting from the second stage, achieving dynamic feature selection and enhancement. CBAM applies dual weighting to the features of each branch in terms of both channel and spatial dimensions, focusing on enhancing the feature responses of key areas such as vertebral edges, pedicles, and odontoid processes, while suppressing interference from irrelevant information such as soft tissue, noise, and artifacts.

[0022] Feature fusion layer: The HRNet network adopts a cross-resolution fusion strategy. It uses bilinear interpolation upsampling and downsampling to stitch together the feature maps of different resolution branches. This allows the high-resolution branches to retain detailed information (such as the subtle protrusions of the vertebral body edges) and fuse the global semantic information of the low-resolution branches (such as the continuity of the vertebral sequence), ultimately outputting a high-resolution feature map.

[0023] Output layer: The fused feature map is mapped to a heatmap of spike keypoints using a 1×1 convolution. The heatmap size is the same as that of the high-resolution feature map. Figure 1 Each channel corresponds to a key point of the spinous process, and the peak position in the heat map is the coordinate of that key point.

[0024] In another exemplary embodiment of this application, such as Figure 2 As shown, the first CBAM network includes a first CBAM, a second CBAM, and a third CBAM.

[0025] The input of the first CBAM is connected to the output of the first convolutional block of the second stage of the HRNet network; the output of the first CBAM is connected to the input of the first convolutional block of the third stage of the HRNet network.

[0026] The input of the second CBAM is connected to the downsampling output and the upsampling output of the second stage of the HRNet network, respectively; the output of the second CBAM is connected to the upsampling input and the downsampling input of the third stage of the HRNet network, respectively.

[0027] The input of the third CBAM is connected to the output of the second convolutional block of the second stage of the HRNet network; the output of the third CBAM is connected to the input of the second convolutional block of the third stage of the HRNet network.

[0028] In another exemplary embodiment of this application, such as Figure 2 As shown, the second CBAM network includes the fourth CBAM, the fifth CBAM, and the sixth CBAM.

[0029] The input of the fourth CBAM is connected to the output of the third convolutional block of the third stage of the HRNet network; the output of the fourth CBAM is connected to the input of the first convolutional block of the fourth stage of the HRNet network.

[0030] The input of the fifth CBAM is connected to the output of the fourth convolutional block of the third stage of the HRNet network; the output of the fifth CBAM is connected to the input of the second convolutional block of the fourth stage of the HRNet network.

[0031] The input of the sixth CBAM is connected to the output of the fifth convolutional block of the third stage of the HRNet network; the output of the sixth CBAM is connected to the input of the third convolutional block of the fourth stage of the HRNet network.

[0032] In another exemplary embodiment of this application, such as Figure 2 As shown, the third CBAM network includes a seventh CBAM and a sixth convolutional block connected in sequence; the input of the seventh CBAM is connected to the output of the fourth convolutional block of the fourth stage of the HRNet network.

[0033] In practical applications, the convolutional block attention module is a lightweight attention mechanism, with a structure as follows: Figure 3 As shown, through the cascaded collaboration of channel attention and spatial attention, "importance weighting" of feature maps is achieved. This application embeds this into the residual units of each branch of the HRNet network. The specific mechanism is as follows: Channel attention: Focuses on which feature channels are more important. By learning the weights of the channel dimensions, it strengthens channels containing key anatomical information (such as high-contrast channels at the vertebral body edges) and weakens noise or background channels. Implementation process: The input feature map... F(The shape is C×H×W, where C is the number of channels, and H and W are the height and width, respectively.) Global average pooling and global max pooling are performed respectively to obtain two 1×1×C channel descriptors; these two are fed into a shared multilayer perceptron (containing one hidden layer), outputting a channel weight vector; the weights are normalized to the 0-1 interval using the sigmoid activation function, and multiplied by the channel dimension of the original feature map to achieve channel-level feature enhancement. The calculation process can be represented as: .

[0034] in, Represents the result of global average pooling, with dimension . ; Represent real numbers; Represents the result of global max pooling, with dimension . ; This represents the channel attention weight vector, with dimension 1. C represents the number of channels in the feature map; MLP stands for Multilayer Perceptron. This indicates that a global average pooling operation is performed on the feature map F. This indicates that a global max pooling operation is performed on the feature map F. σ Here, ⊙ represents the Sigmoid activation function, and ⊙ represents element-wise multiplication. For broadcast operations (extending channel weights to the spatial dimension), 1 H×W For size H × W A matrix of all 1s F ca This is the feature map after channel attention enhancement.

[0035] Spatial attention focuses on which spatial locations in the feature map are more important. By learning the weights of the spatial dimension, it strengthens the feature responses of key areas such as vertebral edges and intervertebral spaces, while suppressing non-critical areas (such as surrounding soft tissue). Implementation: The feature map processed by channel attention is subjected to average pooling and max pooling along the channel dimension, resulting in two H×W×1 spatial descriptors. These two descriptors are concatenated along the channel dimension (forming H×W×2), and then compressed into an H×W×1 spatial weight map through a 1×1 convolution. After normalization using the sigmoid activation function, it is multiplied in the spatial dimension by the feature map output by the channel attention, achieving spatial-level feature enhancement. The calculation process can be represented as: .

[0036] in, Indicates to F ca The result after channel-dimensional average pooling. The dimension is 1×H×W, reflecting the average response intensity of each spatial location of the feature map across all channels, used to capture global spatial features. Indicates toF ca The result after channel-dimensional max pooling. The dimension is 1×H×W, focusing on the maximum response value across all channels at each spatial location of the feature map, used to highlight key local spatial features. MSa represents the spatial attention weight vector. This indicates that feature concatenation has been performed. AP is channel-level average pooling, MP is channel-level max pooling, Concat is channel-level concatenation, and Conv1×1 is a 1×1 convolution (compressing the number of channels to 1). σ Here, ⊙ represents the Sigmoid activation function, and ⊙ represents element-wise multiplication. For broadcast operations (extending spatial weights to the channel dimension), 1 C For length C A vector of all 1s F sa This is the final feature map after spatial attention enhancement.

[0037] For vertebrae with unique shapes, such as C1 and C2, CBAM can enhance the feature channels of unique structures such as the odontoid process and the anterior arch of the atlas through channel attention, and focus on the spatial position of these structures through spatial attention to reduce morphological confusion with other vertebrae. For intervertebral spaces that are obscured by osteophytes or have blurred edges (such as the C5 and C6 vertebrae), CBAM can dynamically enhance the feature response of the unobscured areas and improve the model's ability to recognize incomplete structures.

[0038] In practical applications, when using the WING loss function for spinous process keypoint detection, the WING loss applies equal weight to all keypoints, failing to specifically optimize for difficult points and thus limiting model performance. Specifically, among the keypoints of the seven vertebrae of the spine, vertebrae like C1 and C2, due to their unique morphology (lacking typical vertebral structures and containing odontoid processes) and high overlap with adjacent vertebrae, present significantly greater difficulty in locating keypoints (such as the tip of the odontoid process and the lower edge of C2) than those of conventional vertebrae like C3 to C7. Furthermore, even within the same vertebra, points easily obscured by osteophytes, such as pedicles and intervertebral spaces, are more difficult to locate than clearly defined areas like the vertebral midpoint. If all points are assigned the same loss weight, the model may tend to optimize easily located points (where the loss decreases quickly) while neglecting difficult points (where the loss decreases slowly), ultimately resulting in low detection accuracy for difficult points and failing to meet clinical needs for locating key anatomical structures. Therefore, this application improves the loss function by automatically assigning higher weights to high-difficulty points, forcing the model to prioritize these difficult-to-localize regions during training, thus increasing their learning priority and balancing the detection accuracy of key points of varying difficulty, adapting to the challenges posed by the unique anatomy of the spine. The specific improved formula is as follows: .

[0039] in, , Let K represent the improved loss function, and e represent the base of the natural logarithm. ( (The prediction error represents the original WING loss, used for each keypoint) k Assigning difficulty weights w k During training, the average prediction error of each key point is calculated in real time. The larger the error, w k The larger ( α , β To adjust the parameters, more attention is paid to points with large errors.

[0040] In another exemplary embodiment of this application, the process for determining the risk level of scoliosis in a user is as follows: the risk level of scoliosis in a user is obtained based on the angle between the line connecting the key points of the spinous processes of the user's spine and the vertical line, a preset angle range, the angle between the midline of the trunk and the horizontal line, a preset normal angle threshold, the height difference between the shoulders, a preset normal threshold for the height difference between the shoulders, the value of the reaction force on both sides of the waist, a preset normal threshold for lateral waist stress, the back curve, a preset back reference curve, the pressure on both feet, and a preset reference pressure on both feet.

[0041] In practical applications, the back curve stress sensing device includes an automatic spinal palpation device and a trajectory-monitored motion capture device. The automatic spinal palpation device measures the curve of the depressions on both sides of the spinous processes of the spine, and is connected to the trajectory-monitored motion capture device to record the motion curve of the automatic spinal palpation device as the back curve. Specifically, the automatic spinal palpation device is similar to the rollers of a massage chair.

[0042] In practical applications, if the angle between the line connecting the key points of the spinous processes of the user's spine and the vertical line is not 0, it is judged as a risk of scoliosis. Less than 10 degrees is low risk, more than 40 degrees is high risk, and in between is moderate risk.

[0043] The angle between the midline of the torso and the horizontal line is compared with a preset normal value threshold. If it is less than or greater than the threshold, the risk of scoliosis is determined.

[0044] The height difference between the two shoulders is compared with a preset normal threshold for the height difference between the two shoulders. If it is greater than the threshold, it is determined that there is a risk of scoliosis.

[0045] The values ​​of the reaction forces on both sides of the waist are compared with the preset normal threshold for lateral waist stress. If the values ​​are greater than or less than the normal threshold and the stress on both sides is asymmetrical, then there is a risk of scoliosis.

[0046] The back curve is compared with a preset back baseline curve. If the curvature exceeds the normal range, a risk of scoliosis is identified.

[0047] If the pressure asymmetry between the two feet exceeds 30%, and the difference from the preset baseline pressure between the two feet is greater than 30%, a risk of scoliosis is identified.

[0048] Finally, based on the above results, it was determined whether there was a risk of scoliosis. In addition, if the pressure difference between the two feet exceeded 50%, a high risk of scoliosis was determined.

[0049] In another exemplary embodiment of this application, the shoulder height measuring device 1 is a shoulder height laser height measuring instrument, similar to an electronic height scale.

[0050] In another exemplary embodiment of this application, the multidimensional physiological data-based automated intelligent screening system for adolescent idiopathic scoliosis further includes: a communication module; the scoliosis intelligent analysis module sends the user's scoliosis risk level to the user's mobile phone via the communication module. The user can view the information through the corresponding app on the mobile terminal.

[0051] In another exemplary embodiment of this application, the multidimensional physiological data automatic adolescent idiopathic scoliosis intelligent screening system further includes: a display 5; the display 5 is used to display the method of using the multidimensional physiological data automatic adolescent idiopathic scoliosis intelligent screening system.

[0052] like Figure 1 As shown, the multidimensional physiological data automatic adolescent idiopathic scoliosis intelligent screening system provided in this application is set up in a room. The specific usage method is as follows: After entering through door 8, the person faces the monitor 5 to watch the usage instructions and uses the second camera 7 for facial recognition. Both the second camera 7 and the monitor 5 are set on the BHDE plane. The person takes off their shirt and faces the monitor 5 with their back to the screen. At this time, the first camera 6 takes a side view photo, and the second camera 7 takes a back view photo in an upright position. The first camera 6 is set on the GFEH plane. The person stands on the foot pressure distribution testing device 4 to measure the pressure of both feet. The foot pressure distribution testing device 4 is set on the ground, i.e., the ABCD plane. The shoulder height is measured by the shoulder height measuring device 1, which is set on the AGCF plane. The lumbar stress sensing device 2 measures the stress on both sides of the waist. There are two lumbar stress sensing devices 2, which are set on the ABCD plane and the GFEH plane respectively. After the measurement is completed, the person bends forward, and the second camera 7 takes a back view photo. Then, the person faces the monitor 5 and places their back against the back curve stress sensing device 3 to measure the back curve. The back curve stress sensing device 3 is set on the AGCF plane. The data is then uploaded to the scoliosis intelligent analysis module.

[0053] The multidimensional physiological data-based automated intelligent screening system for adolescent idiopathic scoliosis provided in this application allows for automatic screening around the clock. Its accuracy can reach the level of senior physicians (with more than 10 years of clinical experience). The single test takes 1-2 minutes. The data is transmitted remotely to a cloud platform for diagnosis, and the results can be sent to the mobile phones of the screened person's parents, specialized hospitals, or local disease control departments. This provides important screening results for further early rehabilitation training or further clinical treatment of high-risk groups.

[0054] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0055] 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 are 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.

[0056] This document uses specific examples to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. Furthermore, those skilled in the art will recognize that, based on the ideas of this application, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A multidimensional physiological data-based automated intelligent screening system for adolescent idiopathic scoliosis, characterized in that, The multidimensional physiological data-based automated intelligent screening system for adolescent idiopathic scoliosis includes: Camera module, shoulder height measuring device, lumbar stress sensing device, back curve stress sensing device, foot pressure distribution testing device, and scoliosis intelligent analysis module. The camera module is used to take pictures of the user's back and side when standing upright, as well as the user's back when bending forward; the shoulder height measuring device is used to measure the height of the user's shoulders; the lumbar stress sensing device is used to apply equal force to both sides of the user's waist and measure the value of the reaction force on both sides of the waist; the back curve stress sensing device is used to measure the curve of the concave area on both sides of the spinous process of the spine to obtain the back curve; the foot pressure distribution testing device is used to measure the pressure of the user's feet. The intelligent scoliosis analysis module is used to determine the height difference between the user's shoulders based on the height of the user's shoulders; to determine the key points of the spinous processes of each vertebra based on photos of the user's back when standing and when bending forward; to determine the line connecting the key points of the spinous processes based on the key points of each vertebra; to determine the angle between the user's trunk midline and the horizontal line based on the user's side profile photo; and to determine the degree of scoliosis risk based on the angle between the line connecting the key points of the spinous processes and the vertical line, the angle between the trunk midline and the horizontal line, the height difference between the shoulders, the values ​​of the reaction forces on both sides of the waist, the back curve, and the pressure on the feet.

2. The multidimensional physiological data-based automatic intelligent screening system for adolescent idiopathic scoliosis according to claim 1, characterized in that, The key points of the spinous processes of each vertebra in the user's spine are obtained by taking photos of the user's back when standing upright and when bending forward. Specifically, the spinal key point detection algorithm is used to process the photos of the user's back when standing upright and when bending forward to obtain a heat map of the spinous process key points. The key points of the spinous processes of each vertebra in the spine are then obtained based on the heat map of the spinous process key points.

3. The multidimensional physiological data-based automatic intelligent screening system for adolescent idiopathic scoliosis according to claim 2, characterized in that, The spinal key point detection algorithm includes an HRNet network, a first CBAM network, a second CBAM network, and a third CBAM network. The second and third stages of the HRNet network are connected through the first CBAM network, the third and fourth stages of the HRNet network are connected through the second CBAM network, and the output of the HRNet network is connected to the third CBAM network.

4. The multidimensional physiological data-based automatic intelligent screening system for adolescent idiopathic scoliosis according to claim 3, characterized in that, The first CBAM network includes the first CBAM, the second CBAM, and the third CBAM; The input of the first CBAM is connected to the output of the first convolutional block of the second stage of the HRNet network; the output of the first CBAM is connected to the input of the first convolutional block of the third stage of the HRNet network. The input of the second CBAM is connected to the downsampling output and the upsampling output of the second stage of the HRNet network, respectively; the output of the second CBAM is connected to the upsampling input and the downsampling input of the third stage of the HRNet network, respectively. The input of the third CBAM is connected to the output of the second convolutional block of the second stage of the HRNet network; the output of the third CBAM is connected to the input of the second convolutional block of the third stage of the HRNet network.

5. The multidimensional physiological data-based automatic intelligent screening system for adolescent idiopathic scoliosis according to claim 3, characterized in that, The second CBAM network includes the fourth CBAM, the fifth CBAM, and the sixth CBAM; The input of the fourth CBAM is connected to the output of the third convolutional block of the third stage of the HRNet network; the output of the fourth CBAM is connected to the input of the first convolutional block of the fourth stage of the HRNet network. The input of the fifth CBAM is connected to the output of the fourth convolutional block of the third stage of the HRNet network; the output of the fifth CBAM is connected to the input of the second convolutional block of the fourth stage of the HRNet network. The input of the sixth CBAM is connected to the output of the fifth convolutional block of the third stage of the HRNet network; the output of the sixth CBAM is connected to the input of the third convolutional block of the fourth stage of the HRNet network.

6. The multidimensional physiological data-based automatic intelligent screening system for adolescent idiopathic scoliosis according to claim 3, characterized in that, The third CBAM network consists of a seventh CBAM and a sixth convolutional block connected in sequence; the input of the seventh CBAM is connected to the output of the fourth convolutional block of the fourth stage of the HRNet network.

7. The multidimensional physiological data-based automatic intelligent screening system for adolescent idiopathic scoliosis according to claim 1, characterized in that, The process of determining the risk level of scoliosis in a user is as follows: the risk level of scoliosis in a user is determined based on the angle between the line connecting the key points of the spinous processes of the user's spine and the vertical line, the preset angle range, the angle between the trunk midline and the horizontal line, the preset normal value angle threshold, the height difference between the shoulders, the preset normal threshold for the height difference between the shoulders, the value of the reaction force on both sides of the waist, the preset normal threshold for lateral waist stress, the back curve, the preset back baseline curve, the pressure on both feet, and the preset baseline pressure on both feet.

8. The multidimensional physiological data-based automatic intelligent screening system for adolescent idiopathic scoliosis according to claim 1, characterized in that, The shoulder height measuring device is a shoulder height laser height measuring instrument.

9. The multidimensional physiological data-based automatic intelligent screening system for adolescent idiopathic scoliosis according to claim 1, characterized in that, The multidimensional physiological data automatic adolescent idiopathic scoliosis intelligent screening system also includes: a communication module; the scoliosis intelligent analysis module sends the user's scoliosis risk level to the user's mobile phone through the communication module.

10. The multidimensional physiological data-based automatic intelligent screening system for adolescent idiopathic scoliosis according to claim 1, characterized in that, The automated intelligent screening system for adolescent idiopathic scoliosis based on multidimensional physiological data also includes: a display; the display is used to show the usage method of the automated intelligent screening system for adolescent idiopathic scoliosis based on multidimensional physiological data.

Images