Device for evaluating bladder filling degree before radiotherapy based on perceptual training

Abstract

The invention discloses a device for evaluating bladder filling degree before radiotherapy based on perceptual training, and the device comprises a sensing module which is used for obtaining bladder data information; the bladder filling degree prediction module is used for predicting the bladder filling degree according to the bladder data information; the perception training module is used for generating a dynamic perception training plan according to the bladder filling degree predicted by the bladder filling degree prediction module, and the dynamic perception training plan is used for controlling the bladder filling degree of the patient to be kept on the preset bladder filling degree. The technical problem that an effective bladder filling degree self-evaluation and training means is lacked in the prior art is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of bladder fullness assessment, and more specifically, to a device for assessing bladder fullness before radiotherapy based on perceptual training. Background Art

[0002] Radiotherapy is an important means in the treatment of gynecological malignancies. Especially for gynecological tumors such as cervical cancer, radiotherapy provides an effective local control method. During the radiotherapy process, ensuring the stability of the organ position is crucial for the success of the treatment. However, maintaining the consistency of the bladder fullness of the patient during radiotherapy to keep the stable position of the uterus and reduce the errors caused by the autonomous movement of the organs is a key problem to be solved in current radiotherapy.

[0003] In the existing technology, radiotherapy usually adopts a form of one-time positioning followed by 25 to 27 irradiations to complete the whole treatment course. This treatment mode requires the patient to maintain the consistency of the bladder fullness during each irradiation to ensure the stability of the uterine position. However, due to the lack of effective monitoring and training means, it is difficult to ensure the consistency of the bladder fullness of the patient during radiotherapy.

[0004] The radiotherapy therapist needs to adjust the patient's body position during each irradiation to ensure the repeatability of the body position, which is the cornerstone for ensuring the accurate implementation of the radiotherapy plan. However, due to the characteristics of radiotherapy technology, even a slight change in bladder fullness may cause different degrees of extrusion to the uterus, thus easily causing the deviation of the radiotherapy target area position. This deviation will not only affect the treatment effect but also increase the risk of damage to normal tissues.

[0005] In addition, traditional methods for measuring bladder volume usually rely on invasive operations such as catheterization or ultrasound examination. These methods not only bring discomfort to the patient but also cannot achieve real-time monitoring and feedback. Patients often lack effective self-assessment and training means and are difficult to obtain an interactive experience during the preparation before radiotherapy, resulting in the inconsistency of each volume. Summary of the Invention

[0006] The present invention provides a device for assessing bladder fullness before radiotherapy based on perceptual training, which solves the technical problem of the lack of effective self-assessment and training means for bladder fullness in the existing technology.

[0007] To solve the above technical problem, the technical solution of the present invention is as follows:

[0008] The present invention provides a device for assessing bladder fullness before radiotherapy based on perceptual training, including:

[0009] A sensing module, which is used to obtain bladder data information;

[0010] A bladder fullness prediction module that predicts the bladder fullness according to the bladder data information;

[0011] A perception training module that generates a dynamic perception training plan according to the bladder fullness predicted by the bladder fullness prediction module, and is used to control the patient's bladder fullness to maintain at a preset bladder fullness.

[0012] In the above technical means, the bladder data information is obtained non-invasively through the sensing module, and the bladder fullness prediction module then predicts the bladder fullness according to the bladder data information, which can monitor and evaluate the bladder fullness in real time, is beneficial to the patient's own perception of the bladder fullness, and at the same time the perception training module generates a dynamic perception training plan according to the predicted bladder fullness, realizes the accuracy of the patient's self-assessment of the bladder fullness and controls the patient's bladder fullness to remain unchanged during each chemotherapy.

[0013] Further, the sensing module includes an ultrasonic probe, a near-infrared spectrometer, and a bioelectrical impedance measuring instrument, wherein:

[0014] The ultrasonic probe is placed on the patient's abdomen to obtain an ultrasonic image of the bladder;

[0015] The near-infrared spectrometer is placed on the patient's lower abdomen to obtain a light absorption image of the bladder;

[0016] The bioelectrical impedance measuring instrument is placed on the patient's abdomen and injects a current with a preset frequency to obtain the electro-biological impedance data of the bladder.

[0017] Further, a preset bladder fullness prediction model is deployed in the bladder fullness prediction module. The input of the bladder fullness prediction model is the ultrasonic image, the light absorption image, and the electro-biological impedance data of the bladder, and the output of the bladder fullness prediction model is the bladder fullness.

[0018] Further, the preset bladder fullness prediction model includes:

[0019] After the ultrasonic image and the light absorption image with the same size after preprocessing are respectively subjected to multi-layer convolution to extract features, the features of the ultrasonic image and the features of the light absorption image extracted are fused through the first feature fusion layer to obtain the first fusion information;

[0020] The preprocessed electro-biological impedance data of the bladder is used to extract time series features in the first long short-term memory network layer;

[0021] The first fusion information and the time series features are fused through the second feature fusion layer to obtain the second fusion information;

[0022] After passing the second fusion information through multiple fully connected layers and activation functions in sequence, the predicted bladder fullness is obtained.

[0023] Further, in the first feature fusion layer, the features of the ultrasonic image and the light absorption image extracted are fused by means of splicing or weighted summation fusion to obtain the first fusion information:

[0024] Splicing fusion is as follows:

[0025] F concat = Concat(F 1 , F 2 )

[0026] In the formula, F concat is the first fusion information obtained by splicing fusion, Concat(.) is the splicing function, F 1 , F 2 are respectively the features of the ultrasonic image and the light absorption image extracted;

[0027] Weighted summation fusion is:

[0028] F ws = αF 1 + (1 - α)F 2

[0029] In the formula, F ws is the first fusion information obtained by weighted summation fusion, and α is the preset weight.

[0030] Further, the second feature fusion layer is a fully connected layer or a second long short-term memory network layer.

[0031] Further, the bladder fullness prediction module also updates and optimizes the bladder fullness prediction model according to the deviation between the predicted bladder fullness and the true bladder fullness.

[0032] Further, the dynamic perception training plan includes:

[0033] Set the target bladder fullness according to historical data and clinical experience;

[0034] When the predicted bladder fullness is lower than the target bladder fullness, the generated dynamic perception training plan is:

[0035] It is recommended that the patient appropriately increase water intake and increase urine retention training;

[0036] When the predicted bladder fullness is higher than the target bladder fullness, the generated dynamic perception training plan is:

[0037] It is recommended that the patient appropriately reduce water intake and increase the number of urinations.

[0038] Further, the dynamic perception training plan is also generated according to the patient's mood, weather changes, medication conditions, postoperative recovery conditions, and urinary system functions.

[0039] Further, the perception training module is further configured to:

[0040] Record the deviation between the bladder fullness after each training according to the generated dynamic perception training plan and the target bladder fullness, which is used to optimize the generated dynamic perception training plan.

[0041] Compared with the prior art, the beneficial effects of the technical solution of the present invention are as follows:

[0042] The present invention non-invasively obtains bladder data information through the sensing module, reduces the discomfort of patients, improves the comfort during the treatment process, and improves the patient experience; predicts the bladder fullness through the bladder fullness prediction module to achieve real-time monitoring of the bladder fullness, reduces the dependence on expensive equipment and professional personnel, simplifies the operation process of measuring the bladder fullness, reduces the technical requirements for professional operators, and makes the technology easier to popularize and apply; finally, uses the perception training module to generate a dynamic training plan, provides a personalized perception training plan according to the specific conditions of different patients, realizes the stability of the bladder fullness during chemotherapy to maintain the stable position of organs such as the uterus during radiotherapy, especially the correspondence between the bladder capacity perception and the actual fullness of the patient before each treatment to ensure the consistency of the irradiation position and the CT positioning. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 It is a schematic structural diagram of a device for evaluating bladder fullness before radiotherapy based on perception training provided by an embodiment of the present invention;

[0044] Figure 2 It is a schematic structural diagram of a bladder fullness prediction model provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0045] The drawings are only for illustrative purposes and cannot be construed as a limitation of this patent;

[0046] In order to better illustrate this embodiment, some components in the drawings will be omitted, enlarged, or reduced, and do not represent the dimensions of the actual product;

[0047] For those skilled in the art, it is understandable that some well-known structures and their descriptions in the drawings may be omitted.

[0048] The technical solution of the present invention will be further described below with reference to the drawings and embodiments.

[0049] Embodiment

[0050] In current radiotherapy, it is necessary to maintain the stability of the organ position. Among them, studies have shown that the consistency of the bladder fullness of patients during radiotherapy can determine the stable position of the uterus. Therefore, by controlling the consistency of the bladder fullness of patients during radiotherapy to maintain the stable position of the uterus and reduce the errors caused by the autonomous movement of the organ is the key problem to be solved in current radiotherapy.

[0051] This embodiment provides a device for evaluating bladder fullness before radiotherapy based on perception training, as Figure 1 shown, including:

[0052] A sensing module, which is used to obtain bladder data information;

[0053] A bladder fullness prediction module, which predicts the bladder fullness according to the bladder data information;

[0054] A perception training module, which generates a dynamic perception training plan according to the bladder fullness predicted by the bladder fullness prediction module, and is used to control the patient's bladder fullness to remain at a preset bladder fullness.

[0055] In this embodiment, the bladder data information is obtained non-invasively through the sensing module, and the bladder fullness prediction module then predicts the bladder fullness according to the bladder data information, which can monitor and evaluate the bladder fullness in real time, is beneficial to the patient's own perception of the bladder fullness. At the same time, the perception training module generates a dynamic perception training plan according to the predicted bladder fullness, realizes the accuracy of the patient's self-evaluation of the bladder fullness and controls the patient's bladder fullness to remain unchanged during each chemotherapy.

[0056] In a further embodiment, the sensing module includes an ultrasonic probe, a near-infrared spectrometer, and a bioelectrical impedance measuring instrument, where:

[0057] The ultrasonic probe is placed on the patient's abdomen to obtain ultrasonic images of the bladder;

[0058] The near-infrared spectrometer is placed on the patient's lower abdomen to obtain light absorption images of the bladder;

[0059] The bioelectrical impedance measuring instrument is placed on the patient's abdomen and injects a current with a preset frequency to obtain the electro-biological impedance data of the bladder.

[0060] In a specific embodiment, the ultrasonic image obtained by the ultrasonic probe, the light absorption image obtained by the near-infrared spectrometer, and the electro-biological impedance data obtained by the bioelectrical impedance measuring instrument can be transmitted to the central processing unit or the mobile device in real time through wireless technology (such as Bluetooth or Wi-Fi), and then handed over to the bladder fullness prediction module for prediction processing, ensuring the continuity and real-time nature of the monitoring.

[0061] In a further embodiment, a preset bladder fullness prediction model is deployed in the bladder fullness prediction module. The input of the bladder fullness prediction model is the ultrasonic image, the light absorption image, and the electro-biological impedance data of the bladder, and the output of the bladder fullness prediction model is the bladder fullness.

[0062] In this embodiment, by using an artificial intelligence-based bladder fullness prediction model to analyze the bladder data information of the patient, and then predicting the bladder fullness, expensive measurement equipment is not required. At the same time, the trained bladder fullness prediction model can also output accurate bladder fullness, thereby realizing accurate non-invasive real-time monitoring of bladder fullness.

[0063] In a further embodiment, the preset bladder fullness prediction model, as Figure 2 shown, includes:

[0064] After the preprocessed ultrasonic image and light absorption image with the same size are respectively subjected to multi-layer convolution to extract features, the features of the ultrasonic image and the light absorption image extracted are fused through the first feature fusion layer to obtain the first fusion information;

[0065] The preprocessed electro-biological impedance data of the bladder is used to extract time series features in the first long short-term memory network layer;

[0066] The first fusion information and the time series features are fused through the second feature fusion layer to obtain the second fusion information;

[0067] The second fusion information is successively passed through multiple fully connected layers and activation functions to obtain the predicted bladder fullness.

[0068] In a further embodiment, an activation function (such as ReLU) and a pooling layer (such as max pooling) are connected after each convolutional layer.

[0069] In a specific embodiment, the preset bladder fullness prediction model provided by the embodiment of the present invention combines the advantages of a convolutional neural network (CNN) and a long short-term memory network (LSTM). The convolutional neural network is used to extract spatial features from ultrasonic images and light absorption images, while the long short-term memory network is used to capture temporal features in the time series data formed by electro-biological impedance data. After extracting the corresponding features, a feature fusion method is adopted to achieve multi-modal data feature fusion, providing more comprehensive bladder state information and improving the accuracy and robustness of bladder fullness prediction.

[0070] In a further embodiment, the preprocessing of ultrasonic images may include the following steps:

[0071] 1) Denoising: Use methods such as wavelet transform, singular value decomposition, or Fourier transform to remove noise in the ultrasonic image and improve the signal-to-noise ratio;

[0072] 2) Preliminary feature extraction: Extract relevant features such as edges, shapes, and texture features from the denoised ultrasonic image to reduce data and highlight important information;

[0073] 3) Image enhancement: Apply anisotropic diffusion denoising models, color restoration-based retina enhancement algorithms SSR and MSR, and the MSRCR enhancement algorithm to enhance the details of the ultrasonic image;

[0074] 4) Size normalization: Normalize the size of the enhanced ultrasonic image to H×W×C, where H is the height, W is the width, and C is the number of channels, usually 3.

[0075] In a further embodiment, the preprocessing of light absorption images may include the following steps:

[0076] 1) Baseline correction: Remove baseline shifts or drifts caused by external factors to ensure that the spectrum reflects the characteristics of the bladder itself;

[0077] 2) Noise reduction: Use techniques such as moving average, Savitzky-Golay filtering, and wavelet transform to reduce random noise in the spectral data;

[0078] 3) Size normalization: Normalize the size of the light absorption image to H×W×C, which is the same as that of the ultrasonic image, where H is the height, W is the width, and C is the number of channels, usually 3.

[0079] In a further embodiment, the preprocessing of electro-biological impedance data may include the following steps:

[0080] 1) Filtering: Use a low-pass filter to remove high-frequency noise and retain low-frequency signals related to bladder fullness;

[0081] 2) Normalization: Normalize the impedance data with a length of T for subsequent analysis.

[0082] In a further embodiment, in the first feature fusion layer, the features of the ultrasonic image and the features of the light absorption image are fused by means of splicing or weighted summation fusion to obtain the first fusion information:

[0083] The splicing fusion is as follows:

[0084] F concat = Concat(F 1 , F 2 )

[0085] In the formula, F concat is the first fusion information obtained by splicing fusion, Concat(.) is the splicing function, and F 1 , F 2 are respectively the features of the ultrasonic image and the features of the light absorption image extracted;

[0086] The weighted summation fusion is:

[0087] F ws = αF 1 + (1 - α)F 2

[0088] In the formula, F ws is the first fusion information obtained by weighted summation fusion, and α is the preset weight.

[0089] In a specific embodiment, the features of the ultrasonic image and the features of the light absorption image are fused by means of splicing or weighted summation fusion to achieve the preliminary fusion of image features.

[0090] In a further embodiment, the dimension of the output features of the above splicing fusion is the sum of the input feature dimensions, retaining all the information of the input features. Therefore, it can provide a richer feature representation. However, since there are more temperatures to be processed, the computational complexity is relatively high, so it is suitable for scenarios that need to retain multiple feature information; while the dimension of the output features of the weighted summation fusion is the same as the dimension of the input features. By adjusting the importance of different features through weights, the computational complexity is low, which is suitable for scenarios that need to emphasize certain features and suppress other features, and is usually used in cases where further processing is required after feature fusion. At the same time, in the weighted summation fusion, the determination of the preset weight α can be determined by manual setting or adaptive dynamic adjustment.

[0091] In a further embodiment, the second feature fusion layer is a fully connected layer or a second long short-term memory network layer.

[0092] In this embodiment, the second feature fusion layer is used to fuse the image features and the temporal features.

[0093] In a further embodiment, the bladder fullness prediction module also updates and optimizes the bladder fullness prediction model according to the deviation between the predicted bladder fullness and the actual bladder fullness.

[0094] In this embodiment, after obtaining the deviation between the predicted bladder fullness and the actual bladder fullness, the bladder fullness prediction model is updated and optimized, so that the bladder fullness prediction model is applicable to different individuals, and personalized and accurate bladder fullness prediction can be provided for the specific conditions of different patients to support the formulation of personalized treatment decision-making plans.

[0095] In a further embodiment, the dynamic perception training plan includes:

[0096] Setting a target bladder fullness according to historical data and clinical experience;

[0097] When the predicted bladder fullness is lower than the target bladder fullness, the generated dynamic perception training plan is:

[0098] Advising the patient to increase the amount of water intake appropriately and increase the urine retention training;

[0099] When the predicted bladder fullness is higher than the target bladder fullness, the generated dynamic perception training plan is:

[0100] Advising the patient to reduce the amount of water intake appropriately and increase the frequency of urination.

[0101] In a further embodiment, the dynamic perception training plan is also generated according to the patient's mood, weather changes, medication conditions, postoperative recovery conditions and urinary system functions.

[0102] In a specific embodiment, the generation of the dynamic perception training plan may include the following steps:

[0103] Evaluating the current bladder fullness through the bladder fullness prediction module;

[0104] Determining a preset target value, and determining the preset target value of the bladder fullness according to the specific conditions and treatment needs of the patient; the preset target value is the bladder fullness that needs to be maintained during the patient's chemotherapy, and this bladder fullness remains unchanged during each chemotherapy and can be measured by the bladder filling volume. Generally, the bladder filling volume is 330 - 450 ml.

[0105] The plan may include a drinking plan, timed urination training, pelvic floor muscle training, bladder sphincter control training, micturition reflex training and compensatory micturition method training, where:

[0106] The drinking plan is specifically as follows:

[0107] Based on the current bladder fullness and the preset target value, a drinking plan is formulated. If the current fullness is lower than the target value, the patient needs to increase the water intake; if it is higher than the target value, the water intake needs to be reduced. The appropriate amount of water intake each time is 400 - 450 ml, so that the bladder capacity during urination reaches the preset target value.

[0108] The timed urination training is specifically as follows:

[0109] Adjust the urination time interval according to the bladder fullness. Generally, urinate once every 2 hours during the day and once every 4 hours at night, and the urine volume each time is less than 350 mL.

[0110] The pelvic floor muscle training is specifically as follows:

[0111] Conduct pelvic floor muscle exercises, 2 - 3 times a day, 10 - 15 minutes each time, to enhance bladder control.

[0112] The training of bladder sphincter control is specifically as follows:

[0113] Train the bladder sphincter control by actively contracting the pubococcygeus muscle (anal sphincter). Each contraction lasts for 10 seconds, repeat 10 times, 3 - 5 times a day.

[0114] The urination reflex training is specifically as follows:

[0115] Discover and induce the "trigger point", and promote the contraction of the detrusor muscle through the reflex mechanism to initiate active urination. Common methods include gently tapping the suprapubic area, pulling the pubic hair, rubbing the inner thigh, squeezing the glans penis, etc.

[0116] The training of compensatory urination methods is specifically as follows:

[0117] Compensatory urination methods such as the Valsalva maneuver or the Crede maneuver can be used to promote urination.

[0118] Finally, based on the monitored bladder fullness, determine the residual urine volume to avoid urine retention. Further adjust and dynamically train the plan according to the monitoring results.

[0119] In a further embodiment, the perception training module is further configured to:

[0120] Record the deviation between the bladder fullness after each training according to the generated dynamic perception training plan and the target bladder fullness, for optimizing the generated dynamic perception training plan.

[0121] In a further embodiment, it further includes an intelligent reminder module. The intelligent reminder module intelligently arranges the training time and reminders according to the patient's daily life and radiotherapy schedule, ensuring the continuity and regularity of the training. At the same time, the intelligent reminder module can issue a warning when the urine retention volume exceeds the safety threshold to prevent potential health risks.

[0122] In a further embodiment, it further includes a multimedia interaction interface. The multimedia interaction interface provides touch screen and voice input / output functions to meet the needs of different patients, especially those with visual or motor impairments. The interface design is simple and intuitive, easy to understand and operate.

[0123] In a further embodiment, it further includes a visualization module. The visualization module uses advanced statistical analysis and visualization tools to display the patient's training data and progress trends, helping medical professionals and patients better understand the training effect.

[0124] In a further embodiment, clinical trials are also designed, including a control group and an experimental group, to study the deviation values of different patient groups, providing further scientific basis for the optimization of the dynamic training method.

[0125] The same or similar reference numerals correspond to the same or similar components;

[0126] The terms describing the positional relationship in the drawings are for illustrative purposes only and should not be construed as a limitation of this patent;

[0127] Obviously, the above embodiments of the present invention are merely examples for clearly illustrating the present invention, and are not limitations on the implementation manners of the present invention. For those of ordinary skill in the art, other different forms of changes or modifications can be made based on the above description. It is not necessary and impossible to enumerate all the implementation manners here. Any modifications, equivalent replacements, and improvements made within the spirit and principle of the present invention shall be included in the protection scope of the claims of the present invention.

Claims

1. A device for assessing bladder filling degree before radiotherapy based on sensory training, characterized in that: include: A sensor module, wherein the sensor module is used to obtain bladder data information; a bladder filling degree prediction module, wherein the bladder filling degree prediction module predicts the bladder filling degree according to the bladder data information; A perception training module, wherein the perception training module generates a dynamic perception training plan according to the bladder filling degree predicted by the bladder filling degree prediction module, so as to control the patient's bladder filling degree to remain at a preset bladder filling degree.

2. The device for assessing bladder filling degree before radiotherapy based on sensory training according to claim 1, characterized in that: The sensor module includes an ultrasonic probe, a near-infrared spectrometer and a bioelectrical impedance meter, wherein: The ultrasound probe is placed on the patient's abdomen to obtain an ultrasound image of the bladder; The near-infrared spectrometer is placed in the patient's lower abdomen to obtain a light absorption image of the bladder; The bioelectrical impedance measuring instrument is placed on the abdomen of the patient and injects a current of a preset frequency to obtain the electrical bioimpedance data of the bladder.

3. The device for assessing bladder filling degree before radiotherapy based on sensory training according to claim 2, characterized in that: A preset bladder filling prediction model is deployed in the bladder filling prediction module. The input of the bladder filling prediction model is the ultrasonic image, light absorption image and electrical bioimpedance data of the bladder, and the output of the bladder filling prediction model is the bladder filling degree.

4. The device for assessing bladder filling degree before radiotherapy based on sensory training according to claim 3, characterized in that: The preset bladder filling prediction model includes: After extracting features from the ultrasonic image and the light absorption image of the same size after preprocessing through multi-layer convolution, the extracted features of the ultrasonic image and the features of the light absorption image are fused through a first feature fusion layer to obtain first fusion information; The preprocessed bladder electrical bioimpedance data is passed through the first long short-term memory network layer to extract time series features; The first fusion information and the time series feature are fused through a second feature fusion layer to obtain second fusion information; After the second fusion information passes through multiple layers of fully connected layers and activation functions in sequence, the predicted bladder filling degree is obtained.

5. The device for assessing bladder filling degree before radiotherapy based on sensory training according to claim 4, characterized in that: In the first feature fusion layer, the extracted features of the ultrasonic image and the features of the light absorption image are fused by splicing or weighted sum fusion to obtain first fusion information: The splicing fusion is as follows: F concat =Concat(F1,F2) In the formula, F concat The first fusion information is obtained by splicing fusion, Concat(.) is the splicing function, F1 and F2 are the extracted features of the ultrasonic image and the features of the light absorption image respectively; The weighted sum fusion is: F ws =αF1+(1-α)F2 In the formula, F ws The first fusion information is fused by weighted summation, and α is a preset weight.

6. The device for assessing bladder filling degree before radiotherapy based on sensory training according to claim 4, characterized in that: The second feature fusion layer is a fully connected layer or a second long short-term memory network layer.

7. The device for assessing bladder filling degree before radiotherapy based on sensory training according to claim 4, characterized in that: The bladder filling degree prediction module also updates and optimizes the bladder filling degree prediction model according to the deviation between the predicted bladder filling degree and the actual bladder filling degree.

8. The device for assessing bladder fullness before radiotherapy based on sensory training according to any one of claims 4 to 7, characterized in that: The dynamic perception training program includes: Set target bladder filling based on historical data and clinical experience; When the predicted bladder filling is lower than the target bladder filling, the generated dynamic perception training plan is: Patients are advised to drink more water and increase urine retention training; When the predicted bladder filling is higher than the target bladder filling, the generated dynamic perception training plan is: Patients are advised to reduce their water intake and increase their urination frequency.

9. The device for assessing bladder filling degree before radiotherapy based on sensory training according to claim 8, characterized in that: The dynamic perception training plan is also generated according to the patient's mood, weather changes, medication status, postoperative recovery status and urinary system function.

10. The device for assessing bladder filling degree before radiotherapy based on sensory training according to claim 9, characterized in that: The perception training module is also used for: The deviation between the bladder filling degree and the target bladder filling degree after each training according to the generated dynamic perception training plan is recorded for optimizing the generated dynamic perception training plan.

Images