Lung-diaphragm combined ultrasound-guided postoperative pulmonary rehabilitation training evaluation and guidance method

Abstract

This invention belongs to the field of pulmonary rehabilitation training assessment technology, specifically involving a method for postoperative pulmonary rehabilitation training assessment and guidance guided by ultrasound in the lung and diaphragm system. By comparing postoperative parameters with baseline datasets, this invention can identify areas of diaphragmatic movement disorder and abnormal lung ventilation, overcoming the limitations of traditional assessment methods that rely solely on single indicators or subjective symptoms. Based on a sliding window mechanism, it calculates deviations in movement and ventilation parameters and matches them with standardized training parameters, initially establishing a correlation between the training program and the patient's degree of functional impairment. Furthermore, by collecting the patient's adaptation parameters under free training to generate sensitivity coefficients, the standardized training parameters are dynamically corrected until the patient reaches a stable adaptation state. This fully considers individual patient differences and real-time physiological feedback, transforming the training program from standardized to personalized, and achieving real-time quantitative monitoring and guidance of both the diaphragm and lung tissue.

Description

Technical Field

[0001] This invention belongs to the field of pulmonary rehabilitation training assessment technology, specifically involving a method for postoperative pulmonary rehabilitation training assessment and guidance guided by combined lung-diaphragm ultrasound. Background Technology

[0002] With the popularization of minimally invasive surgery, the demand for postoperative lung function recovery among lung surgery patients is becoming increasingly prominent. Postoperative lung function recovery is also receiving increasing clinical attention. The recovery of lung function can help patients rebuild respiratory mechanical balance more quickly, reduce the risk of complications such as atelectasis and pneumonia, enable patients to return to daily activities earlier after surgery, and shorten the hospitalization period without affecting the rehabilitation effect.

[0003] In existing technologies, pulmonary rehabilitation training mostly relies on subjective symptom assessment or single pulmonary function tests, lacking quantitative monitoring of diaphragmatic movement, making it difficult to identify respiratory muscle synergy disorders. Relying solely on pulmonary ventilation parameters cannot fully reflect changes in respiratory dynamics, easily leading to a mismatch between training programs and individual physiological states. Furthermore, existing training methods are mostly standardized programs with fixed intensity and frequency, making it difficult to adapt to individual differences in postoperative recovery stages among different patients. This results in inconsistent training effects and an inability to accurately respond to real-time physiological changes in patients, which undoubtedly affects the efficiency and safety of patient rehabilitation. Based on this, this solution provides a method for assessing and guiding postoperative pulmonary rehabilitation training using combined lung-diaphragm ultrasound guidance to address the above problems. Summary of the Invention

[0004] The purpose of this invention is to provide a method for assessing and guiding postoperative pulmonary rehabilitation training using ultrasound-guided lung-diaphragm combined therapy. This method enables real-time quantitative monitoring of diaphragmatic movement and pulmonary ventilation in two dimensions, and also provides patients with personalized rehabilitation training programs.

[0005] The specific technical solution adopted by this invention is as follows: Methods for assessing and guiding postoperative pulmonary rehabilitation training under ultrasound guidance involving the lung and diaphragm, including: Preoperative ultrasound combined with diaphragmatic scanning was performed to obtain preoperative diaphragmatic motion parameters and preoperative lung ventilation parameters, which were then compiled into an individualized baseline parameter dataset. Postoperative diaphragmatic motion parameters and postoperative lung ventilation parameters of patients during the postoperative rehabilitation stage were collected and compared with the preoperative baseline parameter dataset to identify areas of diaphragmatic motion disorder and areas of abnormal lung ventilation. Based on the sliding window mechanism, the deviations of motion parameters and ventilation parameters in the regions of diaphragmatic movement disorder and abnormal lung ventilation are determined, and standardized training parameters corresponding to the deviations of motion parameters and ventilation parameters are matched. Diaphragmatic motion parameters and lung ventilation parameters were collected from patients during free training and recorded as the first adaptation parameter and the second adaptation parameter, respectively. Sensitivity coefficients for deviations in motion and ventilation parameters are generated based on the first and second adaptation parameters. The standardized training parameters are then corrected based on these sensitivity coefficients until the patient reaches a stable adaptation state.

[0006] In a preferred embodiment, the step of performing a combined lung-diaphragm scan via preoperative ultrasound to obtain preoperative diaphragmatic motion parameters and preoperative lung ventilation parameters, and summarizing them into an individualized baseline parameter dataset, includes: Simultaneous ultrasound imaging scans were performed at different observation points in multiple standard body positions while the patient was at rest before surgery. At the diaphragm observation point, the thickness, range of motion, and contraction speed of the diaphragm were measured and recorded, and summarized as preoperative diaphragm motion parameters; At the lung observation point, the relative motion of lung tissue and the intensity of lung slip sign were measured and recorded, and summarized as preoperative lung tissue ventilation parameters; Clustering was performed on preoperative diaphragmatic motion parameters and preoperative lung ventilation parameters, and the combination with the highest significance was selected as the individualized baseline parameter dataset.

[0007] In a preferred embodiment, the step of clustering and screening preoperative diaphragmatic motion parameters and preoperative lung ventilation parameters to select the combination with the highest significance as the individualized baseline parameter dataset includes: Preoperative diaphragmatic motion parameters and lung ventilation parameters were extracted to construct diaphragmatic motion feature vectors and lung ventilation feature vectors. Multiple feature clusters were obtained by analyzing the diaphragmatic motion feature vector and the lung ventilation feature vector using unsupervised clustering. Calculate the intra-class scatter and inter-class separation of each feature cluster, and determine the significance score of each feature cluster based on the intra-class scatter and inter-class separation. The feature cluster with the highest significance score is selected as the optimal feature cluster, and all parameters corresponding to the optimal feature cluster are labeled as the individualized baseline parameter dataset.

[0008] In a preferred embodiment, the step of collecting postoperative diaphragmatic motion parameters and postoperative lung ventilation parameters of patients during the postoperative rehabilitation phase, and comparing them with the preoperative baseline parameter dataset to identify areas of diaphragmatic motion impairment and areas of abnormal lung ventilation includes: After the operation, the patient was in a resting state and under the same standard body position and observation points as before the operation; At the diaphragm observation point, the thickness, range of motion, and contraction speed of the diaphragm after surgery were measured and recorded, and recorded as postoperative diaphragm motion parameters; At the lung observation point, the relative motion of lung tissue and the intensity of lung sliding sign were measured and recorded after surgery, and recorded as postoperative lung tissue ventilation parameters; Postoperative diaphragmatic motion parameters and postoperative lung ventilation parameters were compared with the corresponding parameters in the preoperative individualized baseline parameter dataset, and the parameter differences at each observation point under the same conditions were calculated. Compare the parameter difference values ​​with a preset difference threshold; If the parameter difference value exceeds the difference threshold and belongs to the diaphragm observation point, then the area where the corresponding diaphragm observation point is located is marked as the diaphragm movement disorder area. If the parameter difference value exceeds the difference threshold and belongs to the lung observation point, then the area where the corresponding lung observation point is located will be marked as an area of ​​abnormal lung ventilation. If the parameter difference value does not exceed the difference threshold, the corresponding observation point is determined to be in a stable functional state and marked as a normal functional area.

[0009] In a preferred embodiment, the step of determining the deviations of motion parameters and ventilation parameters between the diaphragm motion impairment region and the lung ventilation abnormality region based on the sliding window mechanism includes: The sliding window length is set to N consecutive time points, and postoperative diaphragmatic motion parameters and postoperative lung ventilation parameters are collected once at each time point; Using the current time point as the end point of the window, extract the parameter sequence of N consecutive time points, calculate the mean value of the diaphragm motion parameters within the sliding window, and define the difference between the parameter value at the current time point and the mean value as the motion parameter deviation. Using the current time point as the end point of the window, extract the parameter sequence of N consecutive time points, calculate the mean of lung tissue ventilation parameters within the window, and the difference between the current parameter value and the mean value is the deviation of ventilation parameters.

[0010] In a preferred embodiment, the step of collecting diaphragmatic motion parameters and lung ventilation parameters under free training of the patient, and recording them as a first adaptation parameter and a second adaptation parameter, respectively, includes: During the rehabilitation training exercises that patients choose independently, diaphragmatic movement parameters and lung ventilation parameters are collected in real time using ultrasound. Dynamic data such as changes in diaphragm thickness, fluctuations in amplitude of movement, and peak contraction speed during self-training were recorded as the first adaptation parameters. The dynamic change curve of the relative motion of lung tissue and the real-time value of the intensity of lung slip sign during the self-training process were used as the second adaptation parameter.

[0011] In a preferred embodiment, the step of generating sensitivity coefficients for the deviations of motion parameters and ventilation parameters based on the first adaptation parameter and the second adaptation parameter includes: Calculate the relative rate of change of the first adaptation parameter relative to the corresponding diaphragmatic motion parameter in the preoperative baseline parameter dataset within a single training cycle. This relative rate of change is denoted as the diaphragmatic motion adaptation rate. Calculate the relative rate of change of the second adaptation parameter relative to the corresponding lung ventilation parameter in the preoperative baseline parameter dataset within a single training cycle. This relative rate of change is denoted as the lung ventilation adaptation rate. Extract the deviation of the motion parameters corresponding to the current training cycle from the sequence of deviations in motion parameters, and extract the deviation of the ventilation parameters corresponding to the current training cycle from the sequence of deviations in ventilation parameters. The ratio of diaphragmatic movement adaptation rate to the deviation of movement parameters is calculated, and this ratio is defined as the sensitivity coefficient of movement parameter deviation. Calculate the ratio of lung ventilation adaptation rate to the deviation of ventilation parameters, and record it as the sensitivity coefficient of ventilation parameter deviation.

[0012] In a preferred embodiment, the step of correcting the standardized training parameters based on the sensitivity coefficient includes: The sensitivity coefficients for deviations in motion parameters and ventilation parameters are mapped to preset training intensity adjustment curves to obtain the corresponding intensity adjustment factors. Multiply the intensity adjustment factor by the reference term in the currently executed standardized training parameters to obtain the initially corrected training parameters; Substitute the initial training parameters into the pre-constructed training effect prediction function, and take the first and second adaptation parameters of the previous training cycle as input to output the predicted adaptation parameters for the next cycle. Compare the trend change rate of the predicted adaptation parameter with the first adaptation parameter and the second adaptation parameter, and determine the initial training parameter as the final corrected training parameter when the trend change rate meets the preset rehabilitation goal; If the rate of change of the trend does not meet the preset target, the intensity adjustment factor is iteratively optimized according to the degree of trend deviation until the iterative optimization process meets the convergence condition, or stops after the number of iterations reaches the preset upper limit.

[0013] The present invention also provides a postoperative pulmonary rehabilitation training assessment system, using the above-mentioned lung-diaphragm combined ultrasound-guided postoperative pulmonary rehabilitation training assessment and guidance method, comprising: The data acquisition module is used to perform a combined lung-diaphragm scan via preoperative ultrasound, obtain preoperative diaphragmatic motion parameters and preoperative lung tissue ventilation parameters, and summarize them into an individualized baseline parameter dataset. The anomaly identification module is used to collect postoperative diaphragmatic motion parameters and postoperative lung ventilation parameters of patients during the postoperative rehabilitation stage, and compare them with the preoperative baseline parameter dataset to identify areas of diaphragmatic motion disorder and areas of abnormal lung ventilation. The training parameter matching module is used to determine the deviation of motion parameters and ventilation parameters in the diaphragm movement disorder area and the lung tissue ventilation abnormality area based on the sliding window mechanism, and to match the standardized training parameters corresponding to the deviation of motion parameters and ventilation parameters. The training data acquisition module is used to collect diaphragmatic motion parameters and lung ventilation parameters under the patient's free training, and record them as the first adaptation parameter and the second adaptation parameter, respectively. The parameter correction module is used to generate sensitivity coefficients for deviations in motion parameters and ventilation parameters based on the first and second adaptation parameters. Based on these sensitivity coefficients, the standardized training parameters are then corrected until the patient reaches a stable adaptation state.

[0014] And, an electronic device, comprising: At least one processor; and a memory communicatively connected to the at least one processor; The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform the above-described method for assessing and guiding postoperative pulmonary rehabilitation training using combined lung-diaphragm ultrasound guidance.

[0015] The technical effects achieved by this invention are as follows: This invention constructs an individualized baseline parameter dataset through preoperative ultrasound scanning, enabling the establishment of benchmarks for diaphragmatic movement and lung ventilation status in patients. This provides a reliable reference standard for postoperative assessment. By comparing postoperative parameters with the baseline dataset, it can accurately identify areas of diaphragmatic movement disorder and abnormal lung ventilation, overcoming the limitations of traditional assessment methods that rely solely on a single indicator or subjective symptoms. It achieves the localization and quantification of respiratory function abnormalities. Based on a sliding window mechanism, it calculates the deviation of movement parameters and ventilation parameters and matches them with standardized training parameters, initially realizing the correlation between the training program and the degree of patient functional impairment. Furthermore, by collecting the patient's adaptation parameters under free training to generate sensitivity coefficients, it dynamically corrects the standardized training parameters until the patient reaches a stable adaptation state. It fully considers individual patient differences and real-time physiological feedback, transforming the training program from standardized to personalized. It achieves real-time quantitative monitoring and precise guidance of the diaphragm and lung tissue in two dimensions, effectively avoiding the problem of mismatch between the training program and individual physiological state. This helps improve the effectiveness and safety of postoperative pulmonary rehabilitation training, promotes faster and safer recovery of lung function, and reduces the risk of complications. Attached Figure Description

[0016] Figure 1 This is a schematic diagram of the method flow of the present invention; Figure 2 This is a schematic diagram of the system modules of the present invention; Figure 3 This is a schematic diagram of the electronic device structure of the present invention. Detailed Implementation

[0017] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0018] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0019] Secondly, the term "an embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in a preferred embodiment" appearing in different places throughout this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that mutually excludes other embodiments.

[0020] Please see Figure 1 As shown, this invention provides a method for postoperative pulmonary rehabilitation training assessment and guidance guided by combined lung-diaphragm ultrasound, including: S1. Preoperative ultrasound was used to perform a combined lung-diaphragm scan to obtain preoperative diaphragmatic motion parameters and preoperative lung ventilation parameters, which were then compiled into an individualized baseline parameter dataset. In step S1, in elderly lung cancer patients, postoperative pulmonary rehabilitation training is related to the quality of respiratory function recovery. Elderly lung cancer patients, due to their advanced age, may have poor preoperative lung function reserve, and surgical trauma directly affects diaphragmatic movement and lung ventilation. If scientific and effective pulmonary rehabilitation training is not performed postoperatively, complications such as lung infection or atelectasis are highly likely. In this embodiment, a resting ultrasound scan of the patient's lungs and diaphragm is performed preoperatively to establish individualized baseline data. The step of performing a combined lung-diaphragm scan using preoperative ultrasound to obtain preoperative diaphragmatic movement parameters and preoperative lung ventilation parameters, and summarizing them into an individualized baseline parameter dataset, includes: Simultaneous ultrasound imaging scans were performed at different observation points in multiple standard body positions while the patient was at rest before surgery. At the diaphragm observation point, the thickness, range of motion, and contraction speed of the diaphragm were measured and recorded, and summarized as preoperative diaphragm motion parameters; At the lung observation point, the relative motion of lung tissue and the intensity of lung slip sign were measured and recorded, and summarized as preoperative lung tissue ventilation parameters; Clustering was performed on preoperative diaphragmatic motion parameters and preoperative lung ventilation parameters, and the combination with the highest significance was selected as the individualized baseline parameter dataset. Specifically, when determining the individualized baseline parameter dataset for each patient, ultrasound scans are first performed in multiple standard positions while the patient is at rest preoperatively. Multiple diaphragm and lung observation points are selected in each position to ensure the scan covers the major lung lobes and the diaphragm's active area. At the diaphragm observation points, the thickness changes of the diaphragm during the respiratory cycle are recorded, such as the thickness difference between end-inspiratory and end-expiratory phases, the maximum amplitude of movement (the vertical displacement distance from end-expiratory to end-inspiratory phases), and the contraction velocity (the distance moved per unit time). At the lung observation points, the relative motion between the lung tissue and pleura is observed. Specifically, the degree of relative lung tissue motion can be recorded using a visual scoring method, and the intensity of the pulmonary sliding sign is assessed using color Doppler ultrasound. Then, all preoperative diaphragm motion parameters and lung ventilation parameters are clustered to remove outliers and low-correlation indicators, retaining individualized baseline parameters that reflect the patient's breathing habits.

[0021] Secondly, the steps of clustering and screening preoperative diaphragmatic motion parameters and preoperative lung ventilation parameters to select the most significant combination as the individualized baseline parameter dataset include: Preoperative diaphragmatic motion parameters and lung ventilation parameters were extracted to construct diaphragmatic motion feature vectors and lung ventilation feature vectors. Multiple feature clusters were obtained by analyzing the diaphragmatic motion feature vector and the lung ventilation feature vector using unsupervised clustering. Calculate the intra-class scatter and inter-class separation of each feature cluster, and determine the significance score of each feature cluster based on the intra-class scatter and inter-class separation. The feature cluster with the highest significance score is selected as the optimal feature cluster, and all parameters corresponding to the optimal feature cluster are labeled as the individualized baseline parameter dataset. Specifically, when performing clustering screening on preoperative diaphragmatic motion parameters and preoperative lung ventilation parameters, the first step is to extract features from these parameters. For example, time-domain and frequency-domain features are extracted from the diaphragmatic thickness change sequence to construct a diaphragmatic motion feature vector. Features are also extracted from the dynamic change curves of relative lung movement and the intensity of the lung slip sign, such as the slope, amplitude of fluctuation, and duration of the curves, forming a lung ventilation feature vector. Then, unsupervised clustering is used to jointly cluster the diaphragmatic motion feature vector and the lung ventilation feature vector, dividing them into multiple feature clusters based on parameter similarity. The intra-cluster dispersion of each feature cluster is then calculated, which is the average distance between all sample parameter values ​​within the cluster and the cluster center. A smaller intra-cluster dispersion indicates a more concentrated set of parameters within the cluster. Simultaneously, the inter-cluster separation is calculated, which is the distance between the centers of different clusters. A larger inter-cluster separation indicates a more significant difference between different clusters. The formula for calculating intra-cluster dispersion is: Intra-cluster dispersion = in, The number of samples within the cluster. Let be the parameter value of the i-th sample within the cluster. Given the cluster center parameter value, the formula for calculating the inter-class separation is: Inter-class separation = 2, of which, and The central parameter values ​​of two different clusters are given. Then, the inverse of the intra-class dispersion is multiplied by the inter-class separation to obtain the significance score of the corresponding feature cluster. The higher the significance score, the stronger the representativeness of the parameter combination in the corresponding feature cluster to the patient's individual respiratory function. Finally, the feature cluster with the highest significance score is selected, and all diaphragmatic motion parameters and lung ventilation parameters contained in this feature cluster are summarized into an individualized baseline parameter dataset to provide a corresponding reference standard for subsequent postoperative evaluation.

[0022] S2. Collect postoperative diaphragmatic motion parameters and postoperative lung ventilation parameters of patients during the postoperative rehabilitation stage, and compare them with the preoperative baseline parameter dataset to identify areas of diaphragmatic motion disorder and areas of abnormal lung ventilation. In step S2, after the patient completes lung surgery and enters the rehabilitation phase, an ultrasound re-examination is performed using the same standard body position and observation points as before the surgery. This allows for the acquisition of postoperative diaphragmatic motion parameters and postoperative lung ventilation parameters. The parameters collected at each observation point after surgery are compared one by one with the corresponding parameters in the preoperative baseline parameter dataset to determine the areas of diaphragmatic motion impairment and abnormal lung ventilation. The steps of collecting postoperative diaphragmatic motion parameters and postoperative lung ventilation parameters during the postoperative rehabilitation phase and comparing them with the preoperative baseline parameter dataset to identify areas of diaphragmatic motion impairment and abnormal lung ventilation include: After the operation, the patient was in a resting state and under the same standard body position and observation points as before the operation; At the diaphragm observation point, the thickness, range of motion, and contraction speed of the diaphragm after surgery were measured and recorded, and recorded as postoperative diaphragm motion parameters; At the lung observation point, the relative motion of lung tissue and the intensity of lung sliding sign were measured and recorded after surgery, and recorded as postoperative lung tissue ventilation parameters; Postoperative diaphragmatic motion parameters and postoperative lung ventilation parameters were compared with the corresponding parameters in the preoperative individualized baseline parameter dataset, and the parameter differences at each observation point under the same conditions were calculated. Compare the parameter difference values ​​with a preset difference threshold; If the parameter difference value exceeds the difference threshold and belongs to the diaphragm observation point, then the area where the corresponding diaphragm observation point is located is marked as the diaphragm movement disorder area. If the parameter difference value exceeds the difference threshold and belongs to the lung observation point, then the area where the corresponding lung observation point is located will be marked as an area of ​​abnormal lung ventilation. If the parameter difference value does not exceed the difference threshold, the corresponding observation point is determined to be in a stable functional state and marked as a normal functional area. Specifically, in identifying areas of diaphragmatic movement disorder and abnormal lung ventilation, ultrasound scans are first performed on the patient at rest post-surgery, using the same standard body position and observation points as before surgery, to ensure data consistency and comparability. At the diaphragmatic observation points, postoperative diaphragmatic thickness, movement amplitude, and contraction speed are measured, and these data are integrated into postoperative diaphragmatic movement parameters. At the lung observation points, the interface activity between lung tissue and pleura is observed, and the relative movement degree of lung tissue and the intensity of pulmonary sliding sign are recorded to form postoperative lung ventilation parameters. Then, the diaphragmatic movement parameters and lung ventilation parameters at each postoperative observation point are compared item by item with the corresponding parameters at the same observation point in the preoperative individualized baseline parameter dataset under the same body position. The parameter difference value at each observation point under the same conditions is calculated, such as the difference between the postoperative diaphragmatic movement amplitude and the preoperative baseline movement amplitude. The difference between the intensity of the postoperative pulmonary sliding sign and the preoperative baseline intensity is used to measure the difference. Then, the difference values ​​of parameters at each observation point are compared with the preset difference threshold (the difference threshold is determined based on clinical experience and statistical analysis of a large number of case data). If the difference value of the parameter at a certain diaphragm observation point exceeds the preset difference threshold, it is determined that there is a motor dysfunction in the diaphragm region corresponding to the observation point, and it is marked as a diaphragm motor dysfunction region. If the difference value of the parameter at a certain lung observation point exceeds the preset difference threshold, it is determined that there is a ventilation dysfunction in the lung tissue region corresponding to the observation point, and it is marked as a lung tissue ventilation abnormality region. If the difference value of the parameter does not exceed the preset difference threshold, it is considered that the diaphragm or lung tissue function at the observation point is not significantly abnormal compared with the preoperative baseline, and it is marked as a functional normal region. In this way, it is relatively easy to locate the specific areas of postoperative diaphragm motor dysfunction and lung tissue ventilation abnormality in patients.

[0023] S3. Based on the sliding window mechanism, determine the deviation of motion parameters and ventilation parameters in the regions of diaphragmatic movement disorder and abnormal lung ventilation, and match the standardized training parameters corresponding to the deviation of motion parameters and ventilation parameters. In step S3, after identifying the postoperative diaphragmatic motion disorder area and the abnormal lung ventilation area, it is necessary to further determine the corresponding training parameters to help the patient recover to the preoperative state more quickly and ensure that their quality of life is not impaired due to postoperative functional abnormalities. The steps of determining the deviations of motion parameters and ventilation parameters under the diaphragmatic motion disorder area and the abnormal lung ventilation area based on the sliding window mechanism include: The sliding window length is set to N consecutive time points, and postoperative diaphragmatic motion parameters and postoperative lung ventilation parameters are collected once at each time point; Using the current time point as the end point of the window, extract the parameter sequence of N consecutive time points, calculate the mean value of the diaphragm motion parameters within the sliding window, and define the difference between the parameter value at the current time point and the mean value as the motion parameter deviation. Using the current time point as the end point of the window, extract the parameter sequence of N consecutive time points, calculate the mean of lung tissue ventilation parameters within the window, and the difference between the current parameter value and the mean value is the deviation of ventilation parameters. Specifically, when determining the deviations in motion and ventilation parameters in areas of diaphragmatic motion disorder and abnormal lung ventilation, a sliding window length N is first set. The specific length of the sliding window can be adjusted according to the cycle of clinical rehabilitation training and the frequency of parameter acquisition. For example, if parameters are acquired hourly, N can be set to 24, covering the parameter changes over a day. At each time point, ultrasound parameters are acquired for the identified areas of diaphragmatic motion disorder and abnormal lung ventilation to obtain the postoperative diaphragmatic motion parameters and postoperative lung ventilation parameters for that area. Then, using the current time point as the end point of the window, the parameter sequence of N consecutive time points is extracted to form the sliding window. For areas of diaphragmatic motion disorder, the arithmetic mean of the diaphragmatic motion parameters at all time points within the corresponding sliding window is calculated. Subtracting this arithmetic mean from the diaphragmatic motion parameter value at the current time point yields the deviation of the motion parameters for the corresponding area at the current time point. The deviation of the motion parameters reflects the fluctuation of the current parameters relative to the recent average level. Similarly, for areas of abnormal lung ventilation, the lung ventilation parameters within the sliding window are calculated... The arithmetic mean of the numbers is used to calculate the deviation of the ventilation parameters. The difference between the current lung tissue ventilation parameter value and this mean is the deviation of the ventilation parameters. Through a sliding window mechanism, the short-term trend of parameter changes can be dynamically captured, avoiding the influence of accidental fluctuations of parameters at a single time point on the deviation calculation. This makes the obtained deviations of the exercise parameters and ventilation parameters more representative and stable. After obtaining the deviations of the exercise parameters and ventilation parameters, corresponding standardized training parameters are matched. Specifically, a mapping relationship database between parameter deviations and standardized training parameters is pre-established based on the data of cured patients. The mapping relationship database contains different ranges of combinations of exercise parameter deviations and ventilation parameter deviations, as well as the optimal standardized training parameters corresponding to each combination. The standardized training parameters include the type of breathing training, training intensity, training duration, and specific training movements for the diaphragm and lung tissue. After calculating the current deviations of the exercise parameters and ventilation parameters, the mapping relationship database is searched to find the record that is closest to the current deviation combination, and this record is used as the personalized rehabilitation training plan for the corresponding patient.

[0024] S4. Collect diaphragmatic movement parameters and lung ventilation parameters of the patient under free training, and record them as the first adaptation parameter and the second adaptation parameter, respectively. In step S4, to ensure the effectiveness of rehabilitation training, before formally intervening in rehabilitation training, the patient will undergo corresponding free training to observe the training load they can bear without guidance. The diaphragmatic movement parameters collected during free training will be recorded as the first adaptation parameter, and the lung ventilation parameters as the second adaptation parameter. The steps of collecting the patient's diaphragmatic movement parameters and lung ventilation parameters during free training and recording them as the first and second adaptation parameters, respectively, include: During the rehabilitation training exercises that patients choose independently, diaphragmatic movement parameters and lung ventilation parameters are collected in real time using ultrasound. Dynamic data such as changes in diaphragm thickness, fluctuations in amplitude of movement, and peak contraction speed during self-training were recorded as the first adaptation parameters. The dynamic change curve of the relative motion degree of lung tissue and the real-time value of the intensity of lung slip sign during the self-training process are used as the second adaptation parameters. Specifically, during the patient's free training state, the patient is first allowed to choose common breathing training movements based on their own feelings and daily habits, such as abdominal breathing, pursed-lip breathing, or simple chest expansion exercises. During the patient's self-training, the marked areas of diaphragmatic movement disorder and abnormal lung ventilation are scanned and monitored in real time. Simultaneously, changes in diaphragmatic thickness during training are recorded, including the increase or decrease in thickness at different respiratory stages, the fluctuation range of diaphragmatic movement with the training movements (specifically, the difference between the maximum movement distance during inhalation and the minimum movement distance during exhalation), and the peak data of contraction velocity during training, i.e., the maximum distance the diaphragm moves per unit time. This allows for the recording of diaphragmatic-related data. The integrated records are used as the first adaptation parameter. Simultaneously, in terms of lung ventilation parameter monitoring, the dynamic change curve of the relative motion of lung tissue with the training movements is continuously observed, and the characteristics such as the rising slope, falling slope, and fluctuation period of the curve are recorded. The numerical changes of the intensity of the pulmonary sliding sign are collected in real time, specifically the increasing or decreasing trend of the intensity of the pulmonary sliding sign from the beginning to the end of the training. Finally, the dynamic data related to lung tissue ventilation are recorded as the second adaptation parameter. By collecting the first and second adaptation parameters, the patient's self-training ability and the body's initial adaptation to the training can be intuitively reflected, providing a corresponding reference for the subsequent development of targeted and personalized rehabilitation training programs.

[0025] S5. Generate sensitivity coefficients for deviations in motion parameters and ventilation parameters based on the first and second adaptation parameters. Then, based on the sensitivity coefficients, further correct the standardized training parameters until the patient reaches a stable adaptation state. In step S5, after the first and second adaptation parameters are output, sensitivity coefficients for the deviations in exercise and ventilation parameters are generated to quantify the patient's adaptability and response to different parameter deviations. Then, the standardized training parameters are corrected based on these sensitivity coefficients to ensure the training program always aligns with the individual's physiological rhythms. The step of generating sensitivity coefficients for the deviations in exercise and ventilation parameters based on the first and second adaptation parameters includes: Calculate the relative rate of change of the first adaptation parameter relative to the corresponding diaphragmatic motion parameter in the preoperative baseline parameter dataset within a single training cycle. This relative rate of change is denoted as the diaphragmatic motion adaptation rate. Calculate the relative rate of change of the second adaptation parameter relative to the corresponding lung ventilation parameter in the preoperative baseline parameter dataset within a single training cycle. This relative rate of change is denoted as the lung ventilation adaptation rate. Extract the deviation of the motion parameters corresponding to the current training cycle from the sequence of deviations in motion parameters, and extract the deviation of the ventilation parameters corresponding to the current training cycle from the sequence of deviations in ventilation parameters. The ratio of diaphragmatic movement adaptation rate to the deviation of movement parameters is calculated, and this ratio is defined as the sensitivity coefficient of movement parameter deviation. Calculate the ratio of lung ventilation adaptation rate to the deviation of ventilation parameters, and record it as the sensitivity coefficient of ventilation parameter deviation; Specifically, when determining the sensitivity coefficients for deviations in motion and ventilation parameters, it is first necessary to calculate the relative rate of change of the first adaptation parameter compared to the corresponding diaphragmatic motion parameter in the preoperative baseline parameter dataset within a single training cycle, i.e., the diaphragmatic motion adaptation rate. For the pulmonary ventilation adaptation rate, the relative rate of change of the second adaptation parameter compared to the corresponding pulmonary ventilation parameter in the preoperative baseline parameter dataset is calculated. Then, from the motion and ventilation parameter deviation sequences obtained through the sliding window mechanism, the specific values ​​of the motion and ventilation parameter deviations corresponding to the current free training cycle are extracted. Finally, the diaphragmatic motion adaptation rate is divided by the relative values ​​of the first adaptation parameter compared to the corresponding pulmonary ventilation parameter in the preoperative baseline parameter dataset. The sensitivity coefficient of the deviation of the corresponding exercise parameter is obtained by dividing the pulmonary ventilation adaptation rate by the corresponding deviation of the ventilation parameter. The sensitivity coefficient of the exercise parameter is calculated as: diaphragmatic adaptation rate / deviation of exercise parameter. The sensitivity coefficient of the ventilation parameter is obtained by dividing the pulmonary ventilation adaptation rate by the corresponding deviation of the ventilation parameter. That is, the sensitivity coefficient of the ventilation parameter is: pulmonary ventilation adaptation rate / deviation of ventilation parameter. The larger the absolute value of the sensitivity coefficient, the stronger the patient's ability to adapt to the deviation of the parameter, that is, a unit deviation can cause a greater change in the adaptation rate. Conversely, the smaller the absolute value of the sensitivity coefficient, the slower the patient's response to the deviation of the parameter, and a larger deviation is required to achieve a certain degree of adaptation.

[0026] Secondly, the steps for correcting the standardized training parameters based on the sensitivity coefficient include: The sensitivity coefficients for deviations in motion parameters and ventilation parameters are mapped to preset training intensity adjustment curves to obtain the corresponding intensity adjustment factors. Multiply the intensity adjustment factor by the reference term in the currently executed standardized training parameters to obtain the initially corrected training parameters; Substitute the initial training parameters into the pre-constructed training effect prediction function, and take the first and second adaptation parameters of the previous training cycle as input to output the predicted adaptation parameters for the next cycle. Compare the trend change rate of the predicted adaptation parameter with the first adaptation parameter and the second adaptation parameter, and determine the initial training parameter as the final corrected training parameter when the trend change rate meets the preset rehabilitation goal; If the rate of change of the trend does not meet the preset target, the intensity adjustment factor is iteratively optimized according to the degree of trend deviation until the iterative optimization process meets the convergence condition, or stops after the number of iterations reaches the preset upper limit. In this implementation, after the sensitivity coefficients are determined, the sensitivity coefficients for both the motion parameter and the ventilation parameter can be input into a preset training intensity adjustment curve. This curve is fitted based on a large amount of clinical rehabilitation data and outputs a corresponding intensity adjustment factor based on the magnitude of the sensitivity coefficient. When the motion parameter sensitivity coefficient is high, it indicates that the patient is sensitive to deviations in the diaphragmatic motion parameters. The intensity adjustment factor is generally set to a relatively small value to avoid excessively rapid increases in training intensity that could cause patient discomfort. Conversely, if the sensitivity coefficient is low, the intensity adjustment factor may be appropriately increased to promote faster patient adaptation to training. The obtained intensity adjustment factor is then multiplied by reference items in the current standardized training parameters, such as base training intensity and single training duration, to obtain the initially corrected initial training parameters. These initial training parameters are then substituted into a pre-constructed training effect prediction function. , In the formula, This indicates the predicted values ​​of diaphragm operating parameters for the next cycle. This represents the training intensity adjustment factor. Indicates training duration. This represents the first adaptive parameter in the current period. Indicates the second adaptation parameter. and (Representing regression coefficients), using initial training parameters and the first and second adaptation parameters recorded in the previous training cycle as input variables, the system simulates the patient's physiological response process and outputs predicted values ​​for the first and second adaptation parameters in the next training cycle, i.e., predicted adaptation parameters. Then, the rate of change of the predicted adaptation parameters is compared with the current first and second adaptation parameters. Specifically, it analyzes whether the predicted first and second adaptation parameters show an improving trend, remain unchanged, or worsen compared to the current parameters, and whether the rate of change meets the preset rehabilitation goals, such as the expected increase in weekly diaphragmatic movement amplitude and the target range for improvement in pulmonary gliosis intensity. If the predicted rate of change meets the preset rehabilitation goals, the initial training parameters are considered appropriate. The final training parameters are determined based on these parameters. If the rate of change of the trend does not meet the preset target, such as if the predicted increase in diaphragmatic movement is too slow or the improvement in the intensity of pulmonary gliosis does not meet expectations, the intensity adjustment factor needs to be iteratively optimized based on the degree of deviation between the actual trend and the target trend. If the predicted improvement effect is insufficient, the intensity adjustment factor is appropriately increased, the initial training parameters are recalculated, and the prediction function is substituted again for evaluation. This process is repeated iteratively until the predicted rate of change of the trend meets the preset convergence condition, or the number of iterations reaches the preset upper limit, to avoid excessive iteration that could lead to an indeterminate training plan. Based on this correction process, the training parameters can be made more closely aligned with the patient's immediate adaptability and rehabilitation progress, achieving truly personalized adjustments and making the patient's rehabilitation process both safe and efficient.

[0027] Please see Figure 2 A postoperative pulmonary rehabilitation training assessment system, using the aforementioned lung-diaphragm combined ultrasound-guided postoperative pulmonary rehabilitation training assessment and guidance method, includes: The data acquisition module is used to perform a combined lung-diaphragm scan via preoperative ultrasound, obtain preoperative diaphragmatic motion parameters and preoperative lung tissue ventilation parameters, and summarize them into an individualized baseline parameter dataset. The anomaly identification module is used to collect postoperative diaphragmatic motion parameters and postoperative lung ventilation parameters of patients during the postoperative rehabilitation stage, and compare them with the preoperative baseline parameter dataset to identify areas of diaphragmatic motion disorder and areas of abnormal lung ventilation. The training parameter matching module is used to determine the deviation of motion parameters and ventilation parameters in the diaphragm movement disorder area and the lung tissue ventilation abnormality area based on the sliding window mechanism, and to match the standardized training parameters corresponding to the deviation of motion parameters and ventilation parameters. The training data acquisition module is used to collect diaphragmatic motion parameters and lung ventilation parameters under the patient's free training, and record them as the first adaptation parameter and the second adaptation parameter, respectively. The parameter correction module is used to generate sensitivity coefficients for deviations in motion parameters and ventilation parameters based on the first and second adaptation parameters, and then corrects the standardized training parameters based on the sensitivity coefficients until the patient reaches a stable adaptation state. The execution process of the above evaluation system is consistent with the process of the aforementioned method, so it will not be repeated here.

[0028] Please see Figure 3 An electronic device, comprising: At least one processor; and memory that is communicatively connected to at least one processor; The memory stores a computer program that can be executed by at least one processor, which enables the at least one processor to perform the above-mentioned lung-diaphragm combined ultrasound-guided postoperative pulmonary rehabilitation training assessment and guidance method.

[0029] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, apparatus, article, or method that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, apparatus, article, or method. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, apparatus, article, or method that includes that element.

[0030] The above description is merely a preferred embodiment of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention. Structures, devices, and operating methods not specifically described or explained in this invention are implemented according to conventional methods in the art unless otherwise specified or limited.

Claims

1. Lung-diaphragm combined ultrasound-guided postoperative pulmonary rehabilitation training evaluation and guidance method, characterized in that, include: Preoperative ultrasound combined with diaphragmatic scanning was performed to obtain preoperative diaphragmatic motion parameters and preoperative lung ventilation parameters, which were then compiled into an individualized baseline parameter dataset. Postoperative diaphragmatic motion parameters and postoperative lung ventilation parameters of patients during the postoperative rehabilitation stage were collected and compared with the preoperative baseline parameter dataset to identify areas of diaphragmatic motion disorder and areas of abnormal lung ventilation. Based on the sliding window mechanism, the deviations of motion parameters and ventilation parameters in the regions of diaphragmatic movement disorder and abnormal lung ventilation are determined, and standardized training parameters corresponding to the deviations of motion parameters and ventilation parameters are matched. Diaphragmatic motion parameters and lung ventilation parameters were collected from patients during free training and recorded as the first adaptation parameter and the second adaptation parameter, respectively. Sensitivity coefficients for deviations in motion and ventilation parameters are generated based on the first and second adaptation parameters. The standardized training parameters are then corrected based on these sensitivity coefficients until the patient reaches a stable adaptation state.

2. The combined lung-diaphragm ultrasound-guided postoperative pulmonary rehabilitation training evaluation and guidance method according to claim 1, characterized in that, The step of performing a combined lung-diaphragm scan via preoperative ultrasound to obtain preoperative diaphragmatic motion parameters and preoperative lung ventilation parameters, and summarizing them into an individualized baseline parameter dataset, includes: Simultaneous ultrasound imaging scans were performed at different observation points in multiple standard body positions while the patient was at rest before surgery. At the diaphragm observation point, the thickness, range of motion, and contraction speed of the diaphragm were measured and recorded, and summarized as preoperative diaphragm motion parameters; At the lung observation point, the relative motion of lung tissue and the intensity of lung slip sign were measured and recorded, and summarized as preoperative lung tissue ventilation parameters; Clustering was performed on preoperative diaphragmatic motion parameters and preoperative lung ventilation parameters, and the combination with the highest significance was selected as the individualized baseline parameter dataset.

3. The method for postoperative pulmonary rehabilitation training assessment and guidance guided by ultrasound with combined lung-diaphragm approach according to claim 2, characterized in that, The step of clustering and screening preoperative diaphragmatic motion parameters and preoperative lung ventilation parameters, and selecting the combination with the highest significance as the individualized baseline parameter dataset, includes: Preoperative diaphragmatic motion parameters and lung ventilation parameters were extracted to construct diaphragmatic motion feature vectors and lung ventilation feature vectors. Multiple feature clusters were obtained by analyzing the diaphragmatic motion feature vector and the lung ventilation feature vector using unsupervised clustering. Calculate the intra-class scatter and inter-class separation of each feature cluster, and determine the significance score of each feature cluster based on the intra-class scatter and inter-class separation. The feature cluster with the highest significance score is selected as the optimal feature cluster, and all parameters corresponding to the optimal feature cluster are labeled as the individualized baseline parameter dataset.

4. The method for postoperative pulmonary rehabilitation training assessment and guidance guided by ultrasound with combined lung-diaphragm technique according to claim 1, characterized in that, The steps of collecting postoperative diaphragmatic motion parameters and postoperative lung ventilation parameters of patients during the postoperative rehabilitation phase, and comparing them with the preoperative baseline parameter dataset to identify areas of diaphragmatic motion impairment and areas of abnormal lung ventilation include: After the operation, the patient was in a resting state and under the same standard body position and observation points as before the operation; At the diaphragm observation point, the thickness, range of motion, and contraction speed of the diaphragm after surgery were measured and recorded, and recorded as postoperative diaphragm motion parameters; At the lung observation point, the relative motion of lung tissue and the intensity of lung sliding sign were measured and recorded after surgery, and recorded as postoperative lung tissue ventilation parameters; Postoperative diaphragmatic motion parameters and postoperative lung ventilation parameters were compared with the corresponding parameters in the preoperative individualized baseline parameter dataset, and the parameter differences at each observation point under the same conditions were calculated. Compare the parameter difference values ​​with a preset difference threshold; If the parameter difference value exceeds the difference threshold and belongs to the diaphragm observation point, then the area where the corresponding diaphragm observation point is located is marked as the diaphragm movement disorder area. If the parameter difference value exceeds the difference threshold and belongs to the lung observation point, then the area where the corresponding lung observation point is located will be marked as an area of ​​abnormal lung ventilation. If the parameter difference value does not exceed the difference threshold, the corresponding observation point is determined to be in a stable functional state and marked as a normal functional area.

5. The method for postoperative pulmonary rehabilitation training assessment and guidance guided by ultrasound with combined lung and diaphragm function according to claim 4, characterized in that, The steps for determining the deviations in motion parameters and ventilation parameters between the diaphragmatic movement disorder region and the lung ventilation abnormality region based on the sliding window mechanism include: The sliding window length is set to N consecutive time points, and postoperative diaphragmatic motion parameters and postoperative lung ventilation parameters are collected once at each time point; Using the current time point as the end point of the window, extract the parameter sequence of N consecutive time points, calculate the mean value of the diaphragm motion parameters within the sliding window, and define the difference between the parameter value at the current time point and the mean value as the motion parameter deviation. Using the current time point as the end point of the window, extract the parameter sequence of N consecutive time points, calculate the mean of lung tissue ventilation parameters within the window, and the difference between the current parameter value and the mean value is the deviation of ventilation parameters.

6. The method for postoperative pulmonary rehabilitation training assessment and guidance guided by ultrasound with combined lung-diaphragm approach according to claim 1, characterized in that, The step of collecting diaphragmatic movement parameters and lung ventilation parameters under free training of the patient, and recording them as the first adaptation parameter and the second adaptation parameter, respectively, includes: During the rehabilitation training exercises that patients choose independently, diaphragmatic movement parameters and lung ventilation parameters are collected in real time using ultrasound. Dynamic data such as changes in diaphragm thickness, fluctuations in amplitude of movement, and peak contraction speed during self-training were recorded as the first adaptation parameters. The dynamic change curve of the relative motion of lung tissue and the real-time value of the intensity of lung slip sign during the self-training process were used as the second adaptation parameter.

7. The method for postoperative pulmonary rehabilitation training assessment and guidance guided by ultrasound with combined lung-diaphragm approach according to claim 1, characterized in that, The step of generating sensitivity coefficients for the deviations of motion parameters and ventilation parameters based on the first adaptation parameter and the second adaptation parameter includes: Calculate the relative rate of change of the first adaptation parameter relative to the corresponding diaphragmatic motion parameter in the preoperative baseline parameter dataset within a single training cycle. This relative rate of change is denoted as the diaphragmatic motion adaptation rate. Calculate the relative rate of change of the second adaptation parameter relative to the corresponding lung ventilation parameter in the preoperative baseline parameter dataset within a single training cycle. This relative rate of change is denoted as the lung ventilation adaptation rate. Extract the deviation of the motion parameters corresponding to the current training cycle from the sequence of deviations in motion parameters, and extract the deviation of the ventilation parameters corresponding to the current training cycle from the sequence of deviations in ventilation parameters. The ratio of diaphragmatic movement adaptation rate to the deviation of movement parameters is calculated, and this ratio is defined as the sensitivity coefficient of movement parameter deviation. Calculate the ratio of lung ventilation adaptation rate to the deviation of ventilation parameters, and record it as the sensitivity coefficient of ventilation parameter deviation.

8. The method for postoperative pulmonary rehabilitation training assessment and guidance guided by ultrasound with combined lung and diaphragm function according to claim 1, characterized in that, The step of correcting the standardized training parameters based on the sensitivity coefficient includes: The sensitivity coefficients for deviations in motion parameters and ventilation parameters are mapped to preset training intensity adjustment curves to obtain the corresponding intensity adjustment factors. Multiply the intensity adjustment factor by the reference term in the currently executed standardized training parameters to obtain the initially corrected training parameters; Substitute the initial training parameters into the pre-constructed training effect prediction function, and take the first and second adaptation parameters of the previous training cycle as input to output the predicted adaptation parameters for the next cycle. Compare the trend change rate of the predicted adaptation parameter with the first adaptation parameter and the second adaptation parameter, and determine the initial training parameter as the final corrected training parameter when the trend change rate meets the preset rehabilitation goal; If the rate of change of the trend does not meet the preset target, the intensity adjustment factor is iteratively optimized according to the degree of trend deviation until the iterative optimization process meets the convergence condition, or stops after the number of iterations reaches the preset upper limit.

9. A postoperative pulmonary rehabilitation training and assessment system, characterized in that, The method for postoperative pulmonary rehabilitation training assessment and guidance using ultrasound-guided lung-diaphragm combined therapy as described in any one of claims 1 to 8 includes: The data acquisition module is used to perform a combined lung-diaphragm scan via preoperative ultrasound, obtain preoperative diaphragmatic motion parameters and preoperative lung tissue ventilation parameters, and summarize them into an individualized baseline parameter dataset. The anomaly identification module is used to collect postoperative diaphragmatic motion parameters and postoperative lung ventilation parameters of patients during the postoperative rehabilitation stage, and compare them with the preoperative baseline parameter dataset to identify areas of diaphragmatic motion disorder and areas of abnormal lung ventilation. The training parameter matching module is used to determine the deviation of motion parameters and ventilation parameters in the diaphragm movement disorder area and the lung tissue ventilation abnormality area based on the sliding window mechanism, and to match the standardized training parameters corresponding to the deviation of motion parameters and ventilation parameters. The training data acquisition module is used to collect diaphragmatic motion parameters and lung ventilation parameters under the patient's free training, and record them as the first adaptation parameter and the second adaptation parameter, respectively. The parameter correction module is used to generate sensitivity coefficients for deviations in motion parameters and ventilation parameters based on the first and second adaptation parameters. Based on these sensitivity coefficients, the standardized training parameters are then corrected until the patient reaches a stable adaptation state.

10. An electronic device, characterized in that, include: At least one processor; and a memory communicatively connected to the at least one processor; The memory stores a computer program that can be executed by the at least one processor, which is then executed by the at least one processor to enable the at least one processor to perform the postoperative pulmonary rehabilitation training assessment and guidance method guided by ultrasound with lung-diaphragm combination as described in any one of claims 1 to 8.

Images