Scoliosis back image data classification method and system based on unified marble loss

Abstract

The invention discloses a scoliosis back image data classification method and system based on unified marble loss and a medium. The method comprises the following steps: acquiring basic information of the back of a patient and scoliosis back image data; preprocessing the scoliosis back image data to obtain preprocessed data, and extracting back spine image features from the preprocessed data; constructing and training a scoliosis classification model based on unified marble loss according to the preprocessed data, optimizing model parameters, generating a pair of non-parallel separation hyperplanes by the model, and obtaining hyperplane parameters; performing classification decision by adopting the hyperplane parameters and the new back spine image features to obtain a classification result; and outputting the classification result. According to the method, model optimization is performed on the constructed scoliosis classification model based on the unified marble loss function, so that the model can perform classification and prediction more accurately.

Description

Technical Field

[0001] The present invention relates to the technical field of medical image processing and pattern recognition, and in particular to a method, system and medium for classifying scoliosis back image data based on unified pinball loss. Background Art

[0002] Scoliosis is a complex three-dimensional spinal deformity and a common spinal disease. If not intervened and corrected in time, it may lead to serious health problems, including respiratory dysfunction, spinal pain, and limited motor function.

[0003] The cause of scoliosis is unknown. If preventive diagnosis and treatment are not carried out in the early stages, there is a risk of serious complications. As patients grow and develop, they are prone to chronic back pain, which leads to more obvious changes in the back, including asymmetric hips and shoulders, protruding ribs, and lateral tilt of the waist and trunk. More seriously, the ribs may compress the lungs and cause difficulty breathing. Although previous etiology investigations have shown that patients with diseases such as cerebral palsy and muscular dystrophy are more likely to develop scoliosis than other patients, in most cases the cause of adolescent scoliosis is unknown.

[0004] Currently, common scoliosis detection methods include:

[0005] Visual feeling method: The doctor observes the shape of the back to judge whether the shoulders are asymmetrical or whether the spine deviates from the normal axis. This method relies on the doctor's experience, is prone to misjudgment, and is highly subjective.

[0006] X-ray image measurement of Cobb angle method: This is a commonly used diagnostic method in clinical practice. The patient needs to maintain a fixed posture, and the doctor uses X-rays to measure the Cobb angle to determine the severity of scoliosis. Although this method is accurate, long-term and frequent use of X-rays is not good for health and is not suitable for large-scale screening.

[0007] Traditional scoliosis screening methods mainly rely on physical detection methods and X-ray filming. Although these methods can be used routinely in clinical practice, they have many limitations. First, traditional physical detection methods include simple physical examinations and physical measurements. Although such non-invasive methods are safe, the positive predictive value of screening is low, often leading to unnecessary referrals and further imaging examinations; although X-rays are the gold standard, frequent radiation exposure poses potential risks to health and is particularly unsuitable for long-term monitoring. In addition, existing technologies such as the Chinese patent "CN201210441954.9" propose a scoliosis detection method based on X-ray images. The method includes identifying the spinal curvature area in the spinal image through deep learning and calculating the Cobb angle, but the scheme still relies on X-ray imaging and it is difficult to solve the problem of radiation exposure.

[0008] The above screening methods are not only costly and inefficient, but also difficult to be widely used in the preliminary screening of large populations.

[0009] With the rapid development of computer vision, artificial intelligence and machine learning technologies, automated image classification methods have gradually been applied to the diagnosis and screening of scoliosis. Such methods have the advantages of being non-invasive, low-cost, and without the need for radiation exposure, which can reduce human errors and improve screening efficiency. However, existing automated methods still face many challenges when dealing with large-scale data, especially when faced with data containing noise or outliers, the accuracy and robustness of the model may be affected. Therefore, there is an urgent need for an algorithm that can improve the accuracy and efficiency of scoliosis image classification to cope with the challenges of noise and large-scale data. Summary of the invention

[0010] In view of the defects in the prior art, the present invention provides a method and system for classifying scoliosis back image data based on unified pinball loss, which solves the technical problems existing in the prior art.

[0011] In a first aspect, an embodiment of the present invention provides a method for classifying scoliosis back image data based on unified pinball loss, comprising the following steps:

[0012] Obtain basic information of the patient's back and image data of the scoliotic back;

[0013] Preprocessing the scoliosis back image data to obtain preprocessed data, and extracting back spine image features from the preprocessed data;

[0014] According to the preprocessed data, a scoliosis classification model based on unified pinball loss is constructed and trained, and the model parameters are optimized. The model generates a pair of non-parallel separation hyperplanes and obtains the hyperplane parameters.

[0015] Using the hyperplane parameters and the new back spine image features to make a classification decision and obtain a classification result;

[0016] The classification result is output.

[0017] In a second aspect, an embodiment of the present invention provides a scoliosis back image data classification system based on unified pinball loss, comprising: an image acquisition module, a data processing module, a model training module, a classification decision module and an output module, wherein the image acquisition module is used to obtain basic information of the patient's back and scoliosis back image data;

[0018] The data processing module is used to preprocess the scoliosis back image data to obtain preprocessed data, and extract back spine image features from the preprocessed data;

[0019] The model training module is used to construct and train a scoliosis classification model based on unified pinball loss according to the preprocessed data, optimize the model parameters, and the model generates a pair of non-parallel separation hyperplanes to obtain hyperplane parameters;

[0020] The classification decision module uses the hyperplane parameters and the new back spine image features to make classification decisions and obtain classification results;

[0021] The output module is used to output the classification results.

[0022] In a third aspect, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by a processor, the processor executes the method described in the above embodiment.

[0023] Beneficial effects of the present invention:

[0024] The embodiments of the present invention provide a scoliosis back image data classification method, system and medium based on unified pinball loss, which utilize machine learning methods to perform data mapping based on patient back images using a Gaussian kernel function, and ultimately construct a scoliosis classification model based on a unified pinball loss function for classifying the degree of scoliosis. The additional process of minimizing the pinball loss reduces the impact of misclassification, thereby optimizing the model and enabling the model to classify and predict more accurately. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following is a brief introduction to the drawings required for the specific embodiments or the description of the prior art. In all the drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, the elements or parts are not necessarily drawn according to the actual scale.

[0026] Figure 1 The classification flow chart of the traditional machine learning algorithm is shown;

[0027] Figure 2 A flowchart of a method for classifying scoliosis back image data based on unified pinball loss provided by a first embodiment of the present invention is shown;

[0028] Figure 3 A UPTBLDC composition diagram is shown;

[0029] Figure 4 The flowchart of the unified pinball loss scoliosis classification model in the first embodiment of the present invention is shown;

[0030] Figure 5A structural block diagram of a scoliosis back image data classification system based on unified pinball loss provided by another embodiment of the present invention is shown;

[0031] Figure 6 A timing diagram of a scoliosis back image data classification system based on unified pinball loss according to another embodiment of the present invention is shown. DETAILED DESCRIPTION

[0032] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0033] It should be understood that when used in this specification and the appended claims, the terms "include" and "comprises" indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0034] It should also be understood that the terms used in this specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the specification of the present invention and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0035] It should be further understood that the term "and / or" used in the present specification and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0036] like Figure 1 As shown, a classification flow chart of a traditional machine learning algorithm is shown. When the support vector machine performs image classification, the input is not the original image but a feature extraction step is performed first.

[0037] The parameters involved in the method of the embodiment of the present invention are all determined by cross-validation rather than being fixed values.

[0038] like Figure 2 As shown, a method for classifying scoliosis back image data based on unified pinball loss is provided in the first embodiment of the present invention, comprising:

[0039] S1. Obtain basic information of the patient's back and image data of the scoliotic back.

[0040] In this embodiment, the collected scoliosis back image data is the scoliosis back image data publicly available on Kaggle, wherein the test set includes 16 scoliosis images and 20 non-scoliosis images, and the training set includes 120 scoliosis images and 103 non-scoliosis images. In order to improve the accuracy of the test set, the embodiment of the present invention uses the k-fold cross-validation method and conducts multiple experiments to test the prediction accuracy.

[0041] S2, obtaining image data of the back of the scoliosis and performing preprocessing to obtain preprocessed data, and extracting back spine image features from the preprocessed data.

[0042] In this embodiment, the preprocessing process includes: image segmentation, grayscale processing, filtering and denoising processing, size standardization processing, and image normalization. Finally, the image area size is cropped to a 224×224 format to improve the accuracy of subsequent machine learning method processing. The data set is divided into 75% training set and 25% test set.

[0043] Specifically, the back image is segmented and the region of interest (ROI), namely the spine region, is extracted.

[0044] The local binary method (LBP) is used to improve the texture representation. The LBP operator assigns a value to a pixel based on whether it is greater than or equal to the center pixel in the image. If the value of S is greater than or equal to the center pixel at the pixel location, the pixel is set to 1; otherwise, it is set to 0. Subsequently, using P = 8 and R = 1, the LBP code of the neighborhood is created.

[0045] x i represents the position of the i-th neighboring pixel, and Z represents the pixel intensity. i )-Z(X), the pixel allocation principle of the LBP method is

[0046] according to Normalize to eliminate the influence of factors such as brightness.

[0047] S3. Based on the preprocessed data, a scoliosis classification model based on unified pinball loss is established and model training is performed to solve the optimization problem of maximizing the classification interval between samples of different scoliosis degrees and minimizing the unified pinball loss function to reduce the impact of misclassification.

[0048] like Figure 3 As shown, a UPTBLDC composition diagram is shown.

[0049] Initialization of parameters: The parameter σ of the Gaussian kernel function is set using the standard deviation of the sample distance of the data set; the penalty parameter c is initialized to 1; the trade-off parameter λ is initially set to 0.5, and the relaxation variable ξ in the soft margin model is initially selected to be 1 to control the penalty ratio; the parameter τ that determines the penalty ratio is initialized to 0.5. It should be noted that the values ​​of the above parameters need to be adjusted through cross-validation.

[0050] A scoliosis classification model based on unified pinball loss was constructed, including:

[0051] The uniform pinball loss function is defined as:

[0052]

[0053] Where y is the true label of the sample, f(x) is the predicted output of the model, τ is the parameter that controls the smoothness of the pinball loss, τ takes values ​​in the interval [-1,0)∪(0,1], and u=1-yf ω,b (x) represents the distance of the sample point relative to its corresponding category hyperplane.

[0054] Reference to process steps in specific applications Figure 4 , Figure 4 This is a workflow diagram of the scoliosis classification model based on the unified pinball loss. The unified pinball loss is used to solve the problem that the hyperparameters of machine learning are difficult to adjust and affect the classification performance.

[0055] The idea of ​​twins is further introduced to find a pair of non-parallel hyperplane decision functions f based on the unified pinball loss scoliosis classification model + (x) and f - (x),

[0056]

[0057] Among them, f + (x) and f - (x) represent the decision functions of two non-parallel hyperplanes, and is the weight parameter of the classification hyperplane; is a Gaussian kernel function used to map the features of the input scoliosis image data into a high-dimensional space.

[0058] The distance from a single data sample to the hyperplane is calculated as:

[0059]

[0060] in, represents the distance from the i-th positive sample to the hyperplane, represents the distance from the i-th negative sample to the hyperplane, l1 and l2 represent the number of positive and negative samples respectively, and Represents the i-th positive and negative samples, positive samples Belongs to the category of more severe scoliosis, negative samples They belong to the category of mild or normal scoliosis; and Represents the true category label of the i-th sample.

[0061] In the calculation process of the interval mean and interval variance of the unified pinball loss scoliosis classification model, the interval mean and interval variance are divided into positive and negative categories. The calculation refers to the distance to the other type of hyperplane. The relationship between the interval mean and the interval variance is calculated as follows:

[0062]

[0063] Referring to the relative distance between hyperplanes, the distance from a single sample to the hyperplane can be transformed into a matrix form:

[0064]

[0065] and Represents a mapping function in a high-dimensional feature space. This approach can better distinguish different types of scoliosis and improve the performance of the classification model. Q1 and Q2 are symmetric matrices, and the calculation formulas for Q1 and Q2 are as follows:

[0066]

[0067] Based on the unified pinball loss scoliosis classification model, a pair of unknown vectors ω is sought by maximizing the mean of positive and negative intervals and minimizing the variance of positive and negative intervals. + ,ω - , that is, consider the following two optimization problems:

[0068]

[0069] where τ∈[−1,1], λ1,λ2,λ3,λ4 are the trade-off parameters between the interval variance and the interval mean, λ1,λ2,λ3,λ4>0, ‖ω - ‖ 2 is the regularization term, c1 and c2 are the hyperparameters corresponding to the regularization term, c3 and c4 are the parameters that weigh the total error, and is the interval mean, and is the interval variance.

[0070] On this basis, let the slack variable ξi Satisfy i =∑ i L τ (1-y i (ω T φ(x i ))), where L τ is the pinball loss function, and τ is the parameter that determines the penalty ratio.

[0071]

[0072] According to the constraints, the parameters required for optimal classification are solved. The present invention is based on the symmetric characteristics of the unified pinball loss scoliosis classification model, which solves the object of two pairs of small-scale QPP problems. According to the constraints, the optimal hyperplane parameters corresponding to the scoliosis image samples are solved. The optimal solution is further re-expressed as w + =φ(X)η1 and w - =φ(X)η2, considering and The constraints are as follows:

[0073]

[0074] Further derivation and substitution can be obtained

[0075]

[0076] The Lagrangian multiplier vectors α and β are introduced, and combined with the classification requirements of scoliosis image data, the optimization objective of the classifier is converted into the Lagrangian form:

[0077]

[0078] in is the Lagrange multiplier vector, let Can be obtained

[0079] Convert to Wolfe dual form

[0080]

[0081] st-τc3e2≤α1-β1≤c3e2,

[0082]

[0083] st-τc4e1≤α2-β2≤c4e1,,

[0084] in is the Lagrange multiplier vector,

[0085]

[0086] S4. Perform classification decision based on the calculated hyperplane parameters and the feature vector of the new back image data to obtain a classification result. Specifically, classification is performed by calculating the relative position of the hyperplane parameters and the feature vector of the new back image data.

[0087] The Wolfe dual problem and the parameter vectors η1 and η2 associated with the optimal hyperplane are derived. A new input vector Which class it belongs to depends on the distance to the two non-parallel hyperplanes. The class to which the hyperplane with a closer distance belongs is the predicted label value of the input sample.

[0088] The final decision function of the scoliosis classification model based on unified pinball loss is expressed as:

[0089] Among them, the kernel matrix It represents the similarity between the input sample x and the training sample X, which is calculated by the Gaussian kernel function. These kernel values ​​are combined with the dual parameter η for the final classification decision to determine the degree of scoliosis of the patient.

[0090] S5. Output the classification results for the doctor's reference.

[0091] The present invention provides a method for classifying scoliosis back image data based on unified pinball loss, which realizes data mapping based on patient back pictures using a machine learning method and a Gaussian kernel function, and finally constructs a scoliosis classification model based on unified pinball loss for classifying the degree of scoliosis. The process of minimizing the pinball loss is additionally performed to reduce the influence of misclassification, thereby optimizing the model and enabling the model to classify and predict more accurately.

[0092] Example 2

[0093] like Figure 5 As shown, another embodiment of the present invention provides a scoliosis back image data classification system based on unified pinball loss, including: an image acquisition module, a data processing module, a model training module, a classification decision module and an output module, wherein the image acquisition module is used to obtain basic information of the patient's back and scoliosis back image data; the data processing module is used to preprocess the scoliosis back image data to obtain preprocessed data, and extract back spine image features from the preprocessed data; the model training module is used to construct and train a scoliosis classification model based on unified pinball loss according to the preprocessed data, optimize model parameters, and the model generates a pair of non-parallel separation hyperplanes to obtain hyperplane parameters; the classification decision module uses the hyperplane parameters and new back spine image features to make classification decisions to obtain classification results; the output module is used to output the classification results.

[0094] Figure 6 It is a timing diagram of a scoliosis back image data classification system based on unified pinball loss provided by the present invention. In the image acquisition module, the user automatically or manually uploads the back image information and inputs the image to the data processing module. The data processing module performs preprocessing operations on the image, and the preprocessing includes image segmentation, grayscale processing, filtering and denoising processing, size standardization processing and image normalization. The back spine image features are extracted from the preprocessed data. The back spine image features include texture features, shape features and statistical features, and are divided into 75% training sets and 25% test sets; the key areas are judged by ROI detection, the image data is cropped 224×224, and the texture features are improved using the local binary method (LBP) to avoid brightness interference; the model training module constructs a scoliosis classification model based on unified pinball loss, the unified pinball loss function updates the twin large margin distribution machine model parameters, solves the distance from the sample point to the hyperplane, obtains the hyperplane parameters, and realizes the optimization of the classification effect; the classification decision module completes the classification of "scoliosis" and "non-scoliosis" according to the decision function of the final scoliosis image classification.

[0095] The example of the present invention provides a scoliosis back image data classification system based on unified pinball loss, which realizes data mapping based on patient back pictures using a machine learning method using a Gaussian kernel function, and finally constructs a scoliosis classification model based on unified pinball loss for classifying the degree of scoliosis. The additional process of minimizing the pinball loss reduces the impact of misclassification and optimizes the model, so that the model can classify and predict more accurately.

[0096] Example 3

[0097] Another embodiment of the present invention further provides an embodiment of a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by a processor, the processor executes the method described in the first embodiment.

[0098] The computer-readable storage medium may be an internal storage unit of the terminal described in the foregoing embodiments, such as a hard disk or memory of the terminal. The computer-readable storage medium may also be an external storage device of the terminal, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), etc. equipped on the terminal. Further, the computer-readable storage medium may also include both an internal storage unit of the terminal and an external storage device. The computer-readable storage medium is used to store the computer program and other programs and data required by the terminal. The computer-readable storage medium may also be used to temporarily store data that has been output or is to be output.

[0099] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0100] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the terminals and units described above can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here.

[0101] In the several embodiments provided in the present application, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, or it can be an electrical, mechanical or other form of connection.

[0102] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for classifying scoliosis back image data based on unified pinball loss, characterized in that: The following steps are involved: Obtain basic information of the patient's back and image data of the scoliotic back; Preprocessing the scoliosis back image data to obtain preprocessed data, and extracting back spine image features from the preprocessed data; According to the preprocessed data, a scoliosis classification model based on unified pinball loss is constructed and trained, and the model parameters are optimized. The model generates a pair of non-parallel separation hyperplanes and obtains the hyperplane parameters. Using the hyperplane parameters and the new back spine image features to make a classification decision and obtain a classification result; The classification result is output.

2. The method according to claim 1, characterized in that The method for preprocessing the back image data specifically includes: image segmentation, grayscale processing, filtering and denoising processing, size standardization processing and image normalization.

3. The method according to claim 1, characterized in that The back spine image features include texture features, shape features and statistical features.

4. The method according to claim 1, characterized in that: The method of constructing and training a scoliosis classification model based on a unified pinball loss according to the preprocessed data specifically includes: The uniform pinball loss function is defined as: Where y is the true label of the sample, f(x) is the predicted output of the model, τ is the parameter that controls the smoothness of the pinball loss, τ takes values ​​in the interval [-1,0)∪(0,1], and u=1-yf ω,b (x) represents the distance of the sample point relative to the hyperplane of its corresponding category; Find a pair of non-parallel hyperplane decision functions f based on the unified pinball loss scoliosis classification model + (x) and f - (x); Among them, f + (x) and f - (x) represent the decision functions of two non-parallel hyperplanes, and is the weight parameter of the classification hyperplane; is a Gaussian kernel function used to map the features of the input scoliosis image to a high-dimensional space; The distance from a single data sample to the hyperplane is calculated as: in, represents the distance from the i-th positive sample to the hyperplane, represents the distance from the i-th negative sample to the hyperplane, l1 and l2 represent the number of positive and negative samples respectively, and Represents the i-th positive and negative samples, positive samples Belongs to the category of more severe scoliosis, negative samples They belong to the category of mild or normal scoliosis; and Represents the true category label of the i-th sample.

5. The method according to claim 4, characterized in that The optimization model parameters include: solving the problem of maximizing the classification interval between samples of different scoliosis degrees and minimizing the uniform pinball loss function, specifically: Compute a pair of unknown vectors ω by simultaneously maximizing the mean of the positive and negative intervals and minimizing the variance of the positive and negative intervals + ,ω - , the calculation formula is: Among them, τ∈[-1,1], λ1,λ2,λ3,λ4 are the trade-off parameters between interval variance and interval mean, λ1,λ2,λ3,λ4>0,‖ω - ‖ 2 is the regularization term, c1 and c2 are the hyperparameters corresponding to the regularization term, c3 and c4 are the parameters that weigh the total error, where, and is the interval mean, and is the interval variance; The interval mean and interval variance of the twin large margin classifier based on the unified pinball loss function are divided into the interval mean and interval variance of the positive and negative classes during the calculation process. The calculation refers to the distance to the other type of hyperplane. The relationship between the interval mean and the interval variance is calculated as follows:

6. The method according to claim 5, characterized in that The specific method of the classification decision includes: calculating the relative position relationship between the new back spine image features and the hyperplane parameters, and classifying according to the relative position relationship.

7. A scoliosis back image data classification system based on unified pinball loss, characterized in that: include: An image acquisition module, a data processing module, a model training module, a classification decision module and an output module, wherein the image acquisition module is used to obtain basic information of the patient's back and scoliosis back image data; The data processing module is used to preprocess the scoliosis back image data to obtain preprocessed data, and extract back spine image features from the preprocessed data; The model training module is used to construct and train a scoliosis classification model based on unified pinball loss according to the preprocessed data, optimize the model parameters, and the model generates a pair of non-parallel separation hyperplanes to obtain hyperplane parameters; The classification decision module uses the hyperplane parameters and the new back spine image features to make classification decisions and obtain classification results; The output module is used to output the classification results.

8. The system according to claim 7, characterized in that The preprocessing includes image segmentation, grayscale processing, filtering and denoising processing, size standardization processing and image normalization.

9. The system according to claim 7, characterized in that The back spine image features include texture features, shape features and statistical features.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by a processor, the processor is caused to perform the method according to any one of claims 1 to 6.

Images