Method and system for evaluating curative effect of gastrocnemius spasm of cerebral palsy child patient

Abstract

The invention provides a cerebral palsy child gastrocnemius spasm curative effect evaluation method and system. According to the system, electroencephalogram data, MR I images, ultrasonic elastography and gastrocnemius spasm curative effect grades are utilized to construct a cross-modal gastrocnemius spasm curative effect evaluation model; the constructed cross-modal gastrocnemius spasm curative effect evaluation model generates the current gastrocnemius spasm curative effect grade of the user according to the real-time electroencephalogram data collected by the server, the MR I images in the selected time period and the corresponding ultrasonic elastography; and according to the current gastrocnemius spasm curative effect grade of the user, flexible rehabilitation adjustment is performed on the user so as to realize a humanized treatment target. According to the invention, the doctor can monitor the rehabilitation training curative effect in real time, the intelligent curative effect evaluation effect is realized, and the life quality of the user is ensured.

Description

Technical Field

[0001] The present invention belongs to the technical field of neuro-engineering rehabilitation, and in particular relates to a method and system for evaluating the therapeutic effect of gastrocnemius spasm in children with cerebral palsy. Background Art

[0002] Cerebral palsy is a group of persistent central motor and posture development disorders and activity restriction syndromes, which are caused by non-progressive damage to the developing fetus or infant brain. Spastic cerebral palsy is the most common, accounting for 60% to 70% of all children with cerebral palsy. Pointed feet are a common symptom of children with spastic cerebral palsy, among which gastrocnemius spasm is particularly typical. If not treated early, it will lead to Achilles tendon contracture, plantar flexion of the foot, reduced dorsiflexion angle of the foot, and ankle instability, thereby limiting the motor function of both lower limbs and affecting the balance ability of the child. The efficacy of continuous passive motion (CPM) combined with comprehensive rehabilitation therapy in improving functional disorders of the knee joint, shoulder joint, etc. has been confirmed, but its therapeutic effect on cerebral palsy spasticity has been rarely reported.

[0003] In addition, the existing data on the efficacy evaluation of gastrocnemius spasm in children with cerebral palsy only collected basic physiological indicators and did not take into account the correlation between the brain signals that control gastrocnemius spasm and the efficacy evaluation of gastrocnemius spasm.

[0004] Based on the above problems, the present invention designs a method and system for evaluating the therapeutic effect of gastrocnemius spasm in children with cerebral palsy, and uses EEG data, MRI images, ultrasonic elastic imaging and gastrocnemius spasm therapeutic effect level to construct a cross-modal gastrocnemius spasm therapeutic effect evaluation model. The constructed cross-modal gastrocnemius spasm therapeutic effect evaluation model generates the user's current gastrocnemius spasm therapeutic effect level according to the real-time EEG data collected by the server, MRI images in the selected time period and corresponding ultrasonic elastic imaging, and flexibly adjusts the user's rehabilitation according to the user's current gastrocnemius spasm therapeutic effect level to achieve a humanized treatment goal. The present invention satisfies the doctor's real-time monitoring of the therapeutic effect of rehabilitation training, realizes the intelligent therapeutic effect evaluation effect, and ensures the user's quality of life. Summary of the invention

[0005] In order to solve the above technical problems, the present invention proposes a method and system for evaluating the therapeutic effect of gastrocnemius spasm in children with cerebral palsy.

[0006] In a first aspect of the present invention, a method for evaluating the therapeutic effect of gastrocnemius spasm in children with cerebral palsy is provided, the method comprising:

[0007] To obtain EEG data, MRI images, ultrasound elastography and gastrocnemius spasm efficacy grades of children with cerebral palsy;

[0008] Generate gastrocnemius spasm characteristic variables of children with cerebral palsy using the EEG data, the MRI image, and the ultrasound elastic imaging image;

[0009] Obtaining the gastrocnemius spasm efficacy level corresponding to the gastrocnemius spasm characteristic variable of the cerebral palsy child;

[0010] A cross-modal gastrocnemius spasm efficacy evaluation model is constructed according to the gastrocnemius spasm characteristic variables of the cerebral palsy children and the gastrocnemius spasm efficacy grade;

[0011] Receive real-time EEG data, time-delayed MRI images and real-time ultrasound elasticity imaging images of children with cerebral palsy, generate real-time feature variables based on the real-time EEG data, the time-delayed MRI images and the real-time ultrasound elasticity imaging images, use the cross-modal gastrocnemius spasm efficacy evaluation model to generate a current gastrocnemius spasm efficacy level according to the real-time feature variables, and perform rehabilitation adjustments on the children with cerebral palsy based on the current gastrocnemius spasm efficacy level.

[0012] Furthermore, the EEG data includes historical EEG data, the MRI images include historical MRI images of the gastrocnemius muscle of children with cerebral palsy after rehabilitation training, and the ultrasound elasticity imaging images include historical ultrasound imaging images of the gastrocnemius muscle of children with cerebral palsy after rehabilitation training.

[0013] Furthermore, the EEG data was collected using Neuroscan Synamps2 EEG acquisition equipment, which can collect EEG signals of 64 EEG channels.

[0014] Furthermore, specific brain acquisition areas of the EEG signals of the EEG data are T5, T6, P3, P4, PZ, OZ, O1 and O2.

[0015] Furthermore, before using the cross-modal gastrocnemius spasm efficacy evaluation model, the MRI image or the ultrasound elastography image is processed to separate the target brain part from other MRI backgrounds or the target gastrocnemius part from other ultrasound elastography image backgrounds, and the inter-class variance E between the target brain part and other MRI backgrounds or the target gastrocnemius part and other ultrasound elastography image backgrounds is defined.

[0016] Furthermore, before using the cross-modal gastrocnemius spasm efficacy evaluation model, the MRI image and the ultrasound elastic imaging image are subjected to image stitching processing to obtain a stitched MRI ultrasound elastic image, and the target part of the stitched MRI ultrasound elastic image is separated from other backgrounds, and the inter-class variance E1 between the target part and other backgrounds is defined.

[0017] Furthermore, the EEG data, the MRI image, and the ultrasound elastic imaging image are spliced ​​to obtain the gastrocnemius spasm characteristic variable of the cerebral palsy child or the average grayscale feature of the segmented target part and the EEG parameter B f The characteristic variables of gastrocnemius spasm in children with cerebral palsy are obtained by splicing.

[0018] Furthermore, the cross-modal gastrocnemius spasm efficacy evaluation model adopts a classifier based on the Fischer criterion.

[0019] A system for evaluating the therapeutic effect of gastrocnemius spasm in children with cerebral palsy is also provided, the system comprising a physiological data acquisition module, a physiological data storage module, a cross-modal gastrocnemius spasm therapeutic effect evaluation model construction module, and a rehabilitation adjustment module;

[0020] The physiological data acquisition module is used to collect EEG data, MRI images, ultrasound elastic imaging and gastrocnemius spasm efficacy level of children with cerebral palsy; it is also used to collect real-time EEG data, time-delay MRI images and real-time ultrasound elastic imaging of children with cerebral palsy;

[0021] The EEG parameters include historical EEG data, the MRI images include historical MRI images of the gastrocnemius muscle of children with cerebral palsy after rehabilitation training, and the ultrasound elastic imaging images include historical ultrasound imaging images of the gastrocnemius muscle of children with cerebral palsy after rehabilitation training;

[0022] The physiological data storage module is used to store EEG data, MRI images, ultrasound elastic imaging images and gastrocnemius spasm efficacy levels of children with cerebral palsy, generate gastrocnemius spasm characteristic variables of children with cerebral palsy using the EEG data, the MRI images and the ultrasound elastic imaging images, and generate real-time characteristic variables using real-time EEG data, the delayed MRI images and the real-time ultrasound elastic imaging images;

[0023] The cross-modal gastrocnemius spasm efficacy evaluation model construction module is used to receive the gastrocnemius spasm characteristic variables of the cerebral palsy child and the gastrocnemius spasm efficacy grade to construct the cross-modal gastrocnemius spasm efficacy evaluation model;

[0024] The rehabilitation adjustment module is used to receive the real-time characteristic variables in the physiological data storage module, and is connected to the cross-modal gastrocnemius spasm efficacy evaluation model construction module, input the real-time characteristic variables into the cross-modal gastrocnemius spasm efficacy evaluation model construction module, use the cross-modal gastrocnemius spasm efficacy evaluation model to generate a current gastrocnemius spasm efficacy level, and perform rehabilitation adjustment on children with cerebral palsy according to the current gastrocnemius spasm efficacy level.

[0025] The present invention combines image data and cross-modal data such as EEG data in the evaluation of the efficacy of gastrocnemius spasm in children with cerebral palsy, and can better evaluate the efficacy of gastrocnemius spasm after rehabilitation treatment. By performing specific segmentation processing on MRI images and ultrasound elastic imaging images in the scenario of evaluating the efficacy of gastrocnemius spasm in specific children with cerebral palsy, the data of the training model is made more reliable, and the multi-dimensional evaluation of the efficacy of gastrocnemius spasm using cross-modal data can achieve more accurate changes in the rehabilitation treatment plan. At the same time, the EEG data used can be collected in real time, and the evaluation data can be processed more conveniently. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 It is a flow chart of a method for evaluating the therapeutic effect of gastrocnemius spasm in children with cerebral palsy of the present invention;

[0027] Figure 2 It is a schematic diagram of the system structure of a method for evaluating the therapeutic effect of gastrocnemius spasm in children with cerebral palsy according to the present invention;

[0028] Figure 3 It is a classification principle diagram of the classifier based on Fisher criterion in the present invention;

[0029] Figure 4 This is an MRI image of the gastrocnemius muscle without image segmentation after rehabilitation training in an embodiment of the present invention;

[0030] Figure 5 This is an ultrasonic elastic imaging image without image segmentation after rehabilitation training in an embodiment of the present invention. DETAILED DESCRIPTION

[0031] The invention is further described below in conjunction with the accompanying drawings and specific implementation methods.

[0032] The first embodiment of the present invention:

[0033] In a first aspect of the present invention, in order to solve the above technical problems, a method for evaluating the therapeutic effect of gastrocnemius spasm in children with cerebral palsy is provided, the method comprising:

[0034] To obtain EEG data, MRI images, ultrasound elastography and gastrocnemius spasm efficacy grades of children with cerebral palsy;

[0035] Generate gastrocnemius spasm characteristic variables of children with cerebral palsy using the EEG data, the MRI image, and the ultrasound elastic imaging image;

[0036] Obtaining the gastrocnemius spasm efficacy level corresponding to the gastrocnemius spasm characteristic variable of the cerebral palsy child;

[0037] A cross-modal gastrocnemius spasm efficacy evaluation model is constructed according to the gastrocnemius spasm characteristic variables of the cerebral palsy children and the gastrocnemius spasm efficacy grade;

[0038] Receive real-time EEG data, time-delayed MRI images and real-time ultrasound elasticity imaging images of children with cerebral palsy, generate real-time feature variables based on the real-time EEG data, the time-delayed MRI images and the real-time ultrasound elasticity imaging images, use the cross-modal gastrocnemius spasm efficacy evaluation model to generate a current gastrocnemius spasm efficacy level according to the real-time feature variables, and perform rehabilitation adjustments on the children with cerebral palsy based on the current gastrocnemius spasm efficacy level.

[0039] Furthermore, the EEG data includes historical EEG data, the MRI images include historical MRI images of the gastrocnemius muscle of children with cerebral palsy after rehabilitation training, and the ultrasound elasticity imaging images include historical ultrasound imaging images of the gastrocnemius muscle of children with cerebral palsy after rehabilitation training.

[0040] Furthermore, the EEG data was collected using Neuroscan Synamps2 EEG acquisition equipment, which can collect EEG signals of 64 EEG channels.

[0041] Furthermore, specific brain acquisition areas of the EEG signals of the EEG data are T5, T6, P3, P4, PZ, OZ, O1 and O2.

[0042] Furthermore, the calculation formula of the EEG data is as follows:

[0043]

[0044] In the formula, B f is the EEG data, t is the adjustment coefficient, S1, S2, ..., S8 are the EEG signal amplitudes measured over a period of time corresponding to the eight EEG channels T5, T6, P3, P4, PZ, OZ, O1 and O2, in μV.

[0045] In this embodiment, since the gastrocnemius muscle is controlled by the temporal lobe and part of the brainstem, the EEG data of these 8 brain region channels are selected for value acquisition, and the adjustment coefficient is set between 0.1-0.5 according to the selected brain region channel.

[0046] Furthermore, before using the cross-modal gastrocnemius spasm efficacy evaluation model, the MRI image or the ultrasound elastic imaging image is processed to separate the target brain part from other MRI backgrounds or the target gastrocnemius part from other ultrasound elastic imaging image backgrounds, and the inter-class variance E between the target brain part and other MRI backgrounds or the target gastrocnemius part and other ultrasound elastic imaging image backgrounds is defined as:

[0047] E=p0(h0-h) 2 +p1(h1-h) 2 ;

[0048] Wherein, p0 is the ratio of the number of pixels belonging to the target brain part or the target gastrocnemius part to the MRI image or the ultrasound elastic imaging image, h is the total average grayscale of the MRI image or the ultrasound elastic imaging image, p1 is the ratio of the number of pixels belonging to other MRI backgrounds or other ultrasound elastic imaging image backgrounds to the MRI image or the ultrasound elastic imaging image, h0 is the average grayscale of the target brain part or the target gastrocnemius part, and h1 is the average grayscale of other MRI backgrounds or other ultrasound elastic imaging image backgrounds.

[0049] Furthermore, before using the cross-modal gastrocnemius spasm efficacy evaluation model, the MRI image and the ultrasound elastography image are spliced ​​to obtain a spliced ​​MRI ultrasound elastography image, and the target part of the spliced ​​MRI ultrasound elastography image is separated from other backgrounds. The inter-class variance E1 between the target part and other backgrounds is defined as:

[0050]

[0051] In the formula, h 0m is the average grayscale of the target brain area in the MRI image, h 0U h is the average grayscale of the gastrocnemius muscle in the target area of ​​ultrasound elastography. 1m is the average grayscale of other MRI background parts of the MRI image, h 1U is the average grayscale of the background of other ultrasound elastic imaging images, p 0p is the proportion of the target part in the spliced ​​MRI ultrasound elastic map, h p is the total average grayscale of the spliced ​​MRI ultrasound elastogram, p 1p h is the ratio of the number of pixels belonging to other backgrounds to the spliced ​​MRI ultrasound elasticity map, 0p is the average grayscale of the target part, h 1p is the average grayscale of other backgrounds, and the average grayscale feature of the target part is obtained through the above variance E1 segmentation.

[0052] Furthermore, the EEG data, the MRI image, and the ultrasound elastic imaging image are spliced ​​to obtain the gastrocnemius spasm characteristic variable of the cerebral palsy child or the average grayscale feature of the segmented target part and the EEG parameter B f The characteristic variables of gastrocnemius spasm in children with cerebral palsy are obtained by splicing.

[0053] Furthermore, the cross-modal gastrocnemius spasm efficacy evaluation model adopts a classifier based on the Fisher criterion, and the calculation formula is as follows:

[0054]

[0055] A is the characteristic variable of gastrocnemius spasm in children with cerebral palsy, g(S) is the output gastrocnemius spasm efficacy grade, W T is the normal vector perpendicular to the hyperplane, n is the number of EEG channels, h 0m is the average grayscale of the target brain area in the MRI image, h 0U h is the average grayscale of the gastrocnemius muscle in the target area of ​​ultrasound elastography. 1m is the average grayscale of other MRI background parts of the MRI image, h 1U It is the average grayscale of the background of other ultrasound elastography images.

[0056] In this embodiment, since the specific EEG channels are 8 EEG channels, namely T5, T6, P3, P4, PZ, OZ, O1 and O2, n is 8. The technical personnel in this field use a classifier based on the Fisher criterion to perform binary classification. When g(S) is greater than 0, it means that the treatment effect of gastrocnemius spasm in children with cerebral palsy is good. When g(S) is equal to 0, it means that the treatment effect of gastrocnemius spasm in children with cerebral palsy is average. When g(S) is less than 0, it means that the treatment effect of gastrocnemius spasm in children with cerebral palsy is poor.

[0057] In this embodiment, rehabilitation training is divided into three levels: a low-intensity level with a training volume of 40 minutes each time, 4 times a week, a medium-intensity level with a training volume of 50 minutes each time, 5 times a week, and a high-intensity level with a training volume of 55 minutes each time, 6 times a week. The rehabilitation training is adjusted according to the therapeutic effect level of gastrocnemius spasm in children with cerebral palsy. If the gastrocnemius spasm of children with cerebral palsy is poorly treated, high-intensity or low-intensity rehabilitation training is considered according to the child's condition. If the gastrocnemius spasm of children with cerebral palsy is generally effective, medium-intensity rehabilitation training is considered. If the gastrocnemius spasm of children with cerebral palsy is good, the rehabilitation training is maintained unchanged.

[0058] A system for evaluating the therapeutic effect of gastrocnemius spasm in children with cerebral palsy is also provided, the system comprising a physiological data acquisition module, a physiological data storage module, a cross-modal gastrocnemius spasm therapeutic effect evaluation model construction module, and a rehabilitation adjustment module;

[0059] The physiological data acquisition module is used to collect EEG data, MRI images, ultrasound elastic imaging and gastrocnemius spasm efficacy level of children with cerebral palsy; it is also used to collect real-time EEG data, time-delay MRI images and real-time ultrasound elastic imaging of children with cerebral palsy;

[0060] The EEG parameters include historical EEG data, the MRI images include historical MRI images of the gastrocnemius muscle of children with cerebral palsy after rehabilitation training, and the ultrasound elastic imaging images include historical ultrasound imaging images of the gastrocnemius muscle of children with cerebral palsy after rehabilitation training;

[0061] The physiological data storage module is used to store EEG data, MRI images, ultrasound elastic imaging images and gastrocnemius spasm efficacy levels of children with cerebral palsy, generate gastrocnemius spasm characteristic variables of children with cerebral palsy using the EEG data, the MRI images and the ultrasound elastic imaging images, and generate real-time characteristic variables using real-time EEG data, the delayed MRI images and the real-time ultrasound elastic imaging images;

[0062] The cross-modal gastrocnemius spasm efficacy evaluation model construction module is used to receive the gastrocnemius spasm characteristic variables of the cerebral palsy child and the gastrocnemius spasm efficacy grade to construct the cross-modal gastrocnemius spasm efficacy evaluation model;

[0063] The rehabilitation adjustment module is used to receive the real-time characteristic variables in the physiological data storage module, and is connected to the cross-modal gastrocnemius spasm efficacy evaluation model construction module, input the real-time characteristic variables into the cross-modal gastrocnemius spasm efficacy evaluation model construction module, use the cross-modal gastrocnemius spasm efficacy evaluation model to generate a current gastrocnemius spasm efficacy level, and perform rehabilitation adjustment on children with cerebral palsy according to the current gastrocnemius spasm efficacy level.

[0064] The present invention combines image data and cross-modal data such as EEG data in the evaluation of the efficacy of gastrocnemius spasm in children with cerebral palsy, and can better evaluate the efficacy of gastrocnemius spasm after rehabilitation treatment. By performing specific segmentation processing on MRI images and ultrasound elastic imaging images in the scenario of evaluating the efficacy of gastrocnemius spasm in specific children with cerebral palsy, the data of the training model is made more reliable, and the multi-dimensional evaluation of the efficacy of gastrocnemius spasm using cross-modal data can achieve more accurate changes in the rehabilitation treatment plan. At the same time, the EEG data used can be collected in real time, and the evaluation data can be processed more conveniently.

[0065] A combination of multiple embodiments of the present invention can achieve all of the above effects, but it is not required that each embodiment of the present invention achieve all of the above advantages and effects, because each embodiment of the present invention can constitute an independent technical solution and make one or more contributions to the prior art.

[0066] The present invention does not particularly specify the structure of some modules, which shall be subject to the contents recorded in the prior art. The prior art mentioned in the above background technology section and the specific embodiment section of the present invention can be used as part of the present invention to understand the meaning of some technical features or parameters. The scope of protection of the present invention shall be subject to the contents actually recorded in the claims.

Claims

1. A method for evaluating the therapeutic effect of gastrocnemius spasm in children with cerebral palsy, characterized in that: The method comprises: To obtain EEG data, MRI images, ultrasound elastography images, and gastrocnemius spasm efficacy grades of children with cerebral palsy; Generate gastrocnemius spasm characteristic variables of children with cerebral palsy using the EEG data, the MRI image, and the ultrasound elastic imaging image; Obtaining the gastrocnemius spasm efficacy level corresponding to the gastrocnemius spasm characteristic variable of the cerebral palsy child; A cross-modal gastrocnemius spasm efficacy evaluation model is constructed according to the gastrocnemius spasm characteristic variables of the cerebral palsy children and the gastrocnemius spasm efficacy grade; Receive real-time EEG data, time-delay MRI images and real-time ultrasound elasticity imaging images of children with cerebral palsy, generate real-time feature variables based on the real-time EEG data, the time-delay MRI images and the real-time ultrasound elasticity imaging images, use the cross-modal gastrocnemius spasm efficacy evaluation model to generate a current gastrocnemius spasm efficacy level based on the real-time feature variables, and perform rehabilitation adjustments on the children with cerebral palsy based on the current gastrocnemius spasm efficacy level.

2. A method for evaluating the therapeutic effect of gastrocnemius spasm in children with cerebral palsy as claimed in claim 1, characterized in that: The EEG data include historical EEG data, the MRI images include historical MRI images of the gastrocnemius muscle of children with cerebral palsy after rehabilitation training, and the ultrasound elasticity imaging images include historical ultrasound imaging images of the gastrocnemius muscle of children with cerebral palsy after rehabilitation training.

3. A method for evaluating the therapeutic effect of gastrocnemius spasm in children with cerebral palsy as claimed in claim 1, characterized in that: The EEG data was collected using Neuroscan Synamps2 EEG acquisition equipment, which can collect EEG signals of 64 EEG channels.

4. A method for evaluating the therapeutic effect of gastrocnemius spasm in children with cerebral palsy as claimed in claim 2, characterized in that: The specific brain areas for collecting EEG signals of the EEG data are T5, T6, P3, P4, PZ, OZ, O1 and O2.

5. A method for evaluating the therapeutic effect of gastrocnemius spasm in children with cerebral palsy as claimed in claim 1 or 2, characterized in that: Before using the cross-modal gastrocnemius spasm efficacy evaluation model, the MRI image or the ultrasound elastography image is processed to separate the target brain part from other MRI backgrounds or the target gastrocnemius part from other ultrasound elastography image backgrounds, and the inter-class variance E between the target brain part and other MRI backgrounds or the target gastrocnemius part and other ultrasound elastography image backgrounds is defined.

6. A method for evaluating the therapeutic effect of gastrocnemius spasm in children with cerebral palsy as claimed in claim 1 or 2, characterized in that: Before using the cross-modal gastrocnemius spasm efficacy evaluation model, the MRI image and the ultrasound elastography image are spliced ​​to obtain a spliced ​​MRI ultrasound elastography image, and the target part of the spliced ​​MRI ultrasound elastography image is separated from other backgrounds. The inter-class variance between the target part and other backgrounds is definition.

7. A method for evaluating the therapeutic effect of gastrocnemius spasm in children with cerebral palsy as claimed in claim 6, characterized in that: The EEG data, the MRI image, and the ultrasound elastic imaging image are spliced ​​to obtain the gastrocnemius spasm characteristic variable of the cerebral palsy child or the average grayscale feature of the segmented target part and the EEG parameter The characteristic variables of gastrocnemius spasm in children with cerebral palsy are obtained by splicing.

8. A method for evaluating the therapeutic effect of gastrocnemius spasm in children with cerebral palsy as claimed in claim 7, characterized in that: The cross-modal gastrocnemius spasm efficacy evaluation model adopts a classifier based on the Fisher criterion.

9. A system for evaluating the therapeutic effect of gastrocnemius spasm in children with cerebral palsy, the system comprising a physiological data acquisition module, a physiological data storage module, a cross-modal gastrocnemius spasm therapeutic effect evaluation model construction module, and a rehabilitation adjustment module, characterized in that: The physiological data acquisition module is used to collect EEG data, MRI images, ultrasound elastic imaging and gastrocnemius spasm efficacy level of children with cerebral palsy; it is also used to collect real-time EEG data, time-delay MRI images and real-time ultrasound elastic imaging of children with cerebral palsy; The EEG parameters include historical EEG data, the MRI images include historical MRI images of the gastrocnemius muscle of children with cerebral palsy after rehabilitation training, and the ultrasound elastic imaging images include historical ultrasound imaging images of the gastrocnemius muscle of children with cerebral palsy after rehabilitation training; The physiological data storage module is used to store EEG data, MRI images, ultrasonic elastic imaging images and gastrocnemius spasm efficacy levels of children with cerebral palsy, generate gastrocnemius spasm characteristic variables of children with cerebral palsy using the EEG data, the MRI images and the ultrasonic elastic imaging images, and generate real-time characteristic variables using real-time EEG data, the delayed MRI images and the real-time ultrasonic elastic imaging images; The cross-modal gastrocnemius spasm efficacy evaluation model construction module is used to receive the gastrocnemius spasm characteristic variables of the cerebral palsy child and the gastrocnemius spasm efficacy grade to construct the cross-modal gastrocnemius spasm efficacy evaluation model; The rehabilitation adjustment module is used to receive the real-time characteristic variables in the physiological data storage module, and is connected to the cross-modal gastrocnemius spasm efficacy evaluation model construction module, input the real-time characteristic variables into the cross-modal gastrocnemius spasm efficacy evaluation model construction module, use the cross-modal gastrocnemius spasm efficacy evaluation model to generate a current gastrocnemius spasm efficacy level, and perform rehabilitation adjustment on children with cerebral palsy according to the current gastrocnemius spasm efficacy level.

Images