Neck radiotherapy sequelae management and intervention system and management and intervention method

Abstract

The invention discloses a neck radiotherapy sequelae management and intervention system and method, and relates to the technical field of radiotherapy management, and the system comprises a symptom detection module, a data processing module used for analyzing data obtained by the symptom detection module, an intervention suggestion module used for generating personalized intervention suggestions, and a user interface module. Specifically, physiological parameters of a patient, images of neck skin and muscles and subjective symptom feedback are obtained in real time; integrating data from different sources to form a complete patient symptom database; processing the data by using a machine learning algorithm and a statistical analysis method, and identifying a symptom mode and trend; according to the analysis result, a patient symptom report is generated, and the patient symptom report comprises the severity, the change trend and the potential risk of the current symptom; and personalized intervention suggestions are provided for the patient. According to the invention, early detection, evaluation and personalized intervention of the neck radiotherapy sequelae can be realized, and the method has high clinical application value.

Description

Technical Field

[0001] The present invention relates to the technical field of radiotherapy management, and in particular to a management and intervention system and a management and intervention method for neck radiotherapy sequelae. Background Art

[0002] Radiation therapy (RT) is an important means of treating cancer, especially for patients with head and neck tumors. However, while RT destroys cancer cells, it may also damage surrounding normal tissues, leading to a variety of sequelae, such as skin lesions, dysphagia, dry mouth, neck stiffness and pain, etc. These sequelae seriously affect the quality of life of patients. Therefore, how to effectively manage and intervene in these sequelae has become one of the focuses of clinical attention.

[0003] At present, the management and intervention methods for the sequelae of neck radiotherapy are relatively scattered, lacking in systematicness and scientificity. Patients mainly rely on the doctor's experience and individualized treatment plans, lacking unified standards and systematic management tools. Therefore, there is an urgent need for a system that can comprehensively manage and intervene in the sequelae of neck radiotherapy to improve the quality of life and rehabilitation effect of patients. Summary of the invention

[0004] The purpose of the present invention is to overcome the above-mentioned deficiencies in the prior art and to provide a management and intervention system and management and intervention method for neck radiotherapy sequelae to solve the problem that the management and intervention methods for neck radiotherapy sequelae are relatively scattered and lack of systematicity and scientificity.

[0005] In order to achieve the above-mentioned object of the invention, the present invention provides the following technical solutions:

[0006] On one hand, the present invention provides a neck radiotherapy sequelae management and intervention system, comprising:

[0007] Symptom detection module, which includes a sensor submodule, an image acquisition submodule and a questionnaire submodule, and is used to detect the sequelae of neck radiotherapy in patients;

[0008] A data processing module, used for analyzing the data acquired by the symptom detection module;

[0009] Intervention suggestion module, used to generate personalized intervention suggestions;

[0010] User interface module for interacting with patients to provide symptom feedback and intervention recommendations.

[0011] Further, the sensor submodule includes a plurality of biosensors for real-time monitoring of the patient's physiological parameters;

[0012] The image acquisition submodule includes a high-resolution camera and an infrared camera to obtain images of the neck skin and muscles;

[0013] The questionnaire submodule is used to collect patients' subjective symptom feedback, which includes pain level, dysphagia and skin itching.

[0014] Another aspect of the present invention provides a method for managing and intervening aftereffects of neck radiotherapy, which is implemented based on the above-mentioned system for managing and intervening aftereffects of neck radiotherapy, and includes the following steps:

[0015] S1, real-time acquisition of patients’ physiological parameters, images of neck skin and muscles, and subjective symptom feedback;

[0016] S2, integrate data from different sources to form a complete patient symptom database;

[0017] S3, using machine learning algorithms and statistical analysis methods to process data and identify symptom patterns and trends;

[0018] S4. Generate a patient symptom report based on the analysis results, including the severity of current symptoms, changing trends and potential risks;

[0019] S5. Provide personalized intervention recommendations to patients.

[0020] Furthermore, the image processing process in the data processing in step S3 includes the following steps:

[0021] S31. Image preprocessing:

[0022] Grayscale conversion: convert RGB images into grayscale images to reduce computational complexity;

[0023] Noise removal, applying Gaussian filtering or median filtering to remove noise from the image;

[0024] Image enhancement, using histogram equalization or adaptive histogram equalization (CLAHE) to improve image contrast;

[0025] S32, Image Segmentation:

[0026] Edge detection, using the Canny edge detection algorithm to identify edges in the image;

[0027] Region segmentation, using the watershed algorithm or threshold-based segmentation method to divide the image into different regions;

[0028] S33, feature extraction:

[0029] Texture features, use gray-level co-occurrence matrix (GLCM) to extract the texture features of the image;

[0030] Shape features: shape features of the lesion area, such as area, perimeter, and aspect ratio, are extracted through contour detection algorithms;

[0031] Color features, extracting color histograms in RGB and HSV color spaces to determine the severity of skin damage;

[0032] S34. Feature selection and classification:

[0033] Feature selection, using principal component analysis (PCA) or recursive feature elimination (RFE) methods to select important features;

[0034] Classification algorithm, using support vector machine (SVM), random forest or convolutional neural network (CNN) to classify the extracted features and determine the type and extent of the lesion.

[0035] Furthermore,

[0036] Providing personalized intervention suggestions to the patient in step S5 includes the following steps:

[0037] S51. Multiple intervention strategies are built into the system, such as physical therapy, medication, and lifestyle adjustments;

[0038] S52. Select the most appropriate intervention plan from the intervention strategies based on the patient’s specific symptoms and health status;

[0039] S53. Generate detailed intervention recommendations, including specific steps, precautions, and expected results.

[0040] Compared with the prior art, the present invention has the following advantages and beneficial effects:

[0041] Through advanced image processing technology and intelligent algorithms, the present invention realizes early detection, evaluation and personalized intervention of the sequelae of neck radiotherapy, and has high clinical application value. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 Schematic diagram of the process of management and intervention method in the present invention. DETAILED DESCRIPTION

[0043] The present invention is further described in detail below in conjunction with test examples and specific implementation methods. However, this should not be understood as the scope of the above subject matter of the present invention being limited to the following embodiments, and all technologies realized based on the content of the present invention belong to the scope of the present invention.

[0044] On the one hand, this embodiment provides a neck radiotherapy sequelae management and intervention system. Figure 1 As shown, including:

[0045] Symptom detection module, which includes a sensor submodule, an image acquisition submodule and a questionnaire submodule, and is used to detect the sequelae of neck radiotherapy in patients;

[0046] A data processing module, used for analyzing the data acquired by the symptom detection module;

[0047] Intervention suggestion module, used to generate personalized intervention suggestions;

[0048] User interface module for interacting with patients to provide symptom feedback and intervention recommendations.

[0049] User Interface Module:

[0050] Interface design: Design a friendly user interface to facilitate patients' browsing and operation.

[0051] Information display: Symptom detection results and intervention recommendations are displayed through an interface in the form of charts, text, and videos.

[0052] Interactive feedback: patients can provide feedback on symptom changes and intervention effects through the interface, and the system will make further adjustments based on the feedback.

[0053] The above embodiment is further optimized, where the sensor submodule includes a plurality of biosensors for real-time monitoring of physiological parameters of the patient;

[0054] These sensors may include but are not limited to:

[0055] Skin conductivity sensor: used to detect changes in skin conductivity to reflect skin damage and healing conditions.

[0056] Pressure sensor: used to detect the pressure and tension of the neck muscles.

[0057] Temperature sensor: used to monitor local temperature changes and reflect inflammation conditions.

[0058] Motion sensor: used to monitor the range of motion and flexibility of the neck.

[0059] These sensors can transmit data via wireless connection to a data processing module for analysis.

[0060] The image acquisition submodule includes a high-resolution camera and an infrared camera to obtain images of the neck skin and muscles; through image processing algorithms, skin damage, pigmentation, scar formation, etc. can be analyzed.

[0061] The questionnaire submodule is used to collect subjective symptom feedback from patients, including pain level, dysphagia, and skin itching. The questionnaire can be completed through a mobile application, web page, or paper form. The specific process is as follows:

[0062] Questionnaire design: A questionnaire was designed based on common sequelae of neck radiotherapy, including multiple-choice questions and open-ended questions.

[0063] Data collection: Patients regularly fill out questionnaires to provide feedback on their current symptoms.

[0064] Data transmission: Questionnaire results are transmitted to the data processing module via the network.

[0065] On the other hand, this embodiment provides a method for managing and intervening aftereffects of neck radiotherapy, which is implemented based on the above-mentioned system for managing and intervening aftereffects of neck radiotherapy, and includes the following steps:

[0066] S1, real-time acquisition of patients’ physiological parameters, images of neck skin and muscles, and subjective symptom feedback;

[0067] S2, integrate data from different sources to form a complete patient symptom database;

[0068] S3, using machine learning algorithms and statistical analysis methods to process data and identify symptom patterns and trends;

[0069] S4. Generate a patient symptom report based on the analysis results, including the severity of current symptoms, changing trends and potential risks;

[0070] S5. Provide personalized intervention recommendations to patients.

[0071] Through advanced image processing technology and intelligent algorithms, the present invention realizes early detection, evaluation and personalized intervention of the sequelae of neck radiotherapy, and has high clinical application value.

[0072] The above embodiment is further optimized, and the image processing process in the data processing in step S3 includes the following steps:

[0073] S31. Image preprocessing:

[0074] Grayscale conversion: convert RGB images into grayscale images to reduce computational complexity;

[0075] Noise removal, applying Gaussian filtering or median filtering to remove noise from the image;

[0076] Image enhancement, using histogram equalization or adaptive histogram equalization (CLAHE) to improve image contrast;

[0077] S32, Image Segmentation:

[0078] Edge detection, using the Canny edge detection algorithm to identify edges in the image;

[0079] Region segmentation, using the watershed algorithm or threshold-based segmentation method to divide the image into different regions; among them, the Canny edge detection algorithm can be divided into the following key steps:

[0080] Gaussian Filtering: First, use a Gaussian filter to smooth the image to reduce the impact of noise. The function of the Gaussian filter is to remove high-frequency noise in the image while retaining edge information. The commonly used Gaussian filter is a two-dimensional Gaussian function.

[0081] Gradient Calculation: Perform a first-order partial derivative operation on the smoothed image to calculate the gradient strength and direction of the image. The Sobel operator is usually used to calculate the gradient of the image in the horizontal (x direction) and vertical (y direction). Through these two gradients, the gradient magnitude and gradient direction of each pixel can be obtained.

[0082] Non-Maximum Suppression: The purpose of this step is to refine the edge. If the gradient magnitude of a pixel is not a local maximum, it is suppressed (i.e. set to zero). This process is achieved by comparing the gradient magnitude of the neighboring pixels of the pixel in the gradient direction, thereby obtaining an accurate single-pixel width edge.

[0083] Double Thresholding: Double threshold detection is applied to the image after non-maximum suppression to determine potential edges. Two thresholds are set: high threshold and low threshold. Pixels greater than the high threshold are considered strong edges, pixels less than the low threshold are suppressed as non-edges, and pixels between the high and low thresholds are considered weak edges.

[0084] Edge Tracking by Hysteresis: Tracking edges by hysteresis, starting from a weak edge, if there is a strong edge in its neighborhood, keep it as an edge, otherwise suppress it. This process ensures the continuity of the edge and prevents breaks.

[0085] Through the above steps, the Canny edge detection algorithm can effectively detect the edges in the image while reducing the interference of noise.

[0086] S33, feature extraction:

[0087] Texture features, use gray-level co-occurrence matrix (GLCM) to extract the texture features of the image;

[0088] Shape features: shape features of the lesion area, such as area, perimeter, and aspect ratio, are extracted through contour detection algorithms;

[0089] Color features, extracting color histograms in RGB and HSV color spaces to determine the severity of skin damage;

[0090] S34. Feature selection and classification:

[0091] Feature selection, using principal component analysis (PCA) or recursive feature elimination (RFE) methods to select important features;

[0092] Classification algorithm, using support vector machine (SVM), random forest or convolutional neural network (CNN) to classify the extracted features and determine the type and extent of the lesion.

[0093] Further optimize the above embodiment,

[0094] Providing personalized intervention suggestions to the patient in step S5 includes the following steps:

[0095] S51. Multiple intervention strategies are built into the system, such as physical therapy, medication, and lifestyle adjustments;

[0096] S52. Select the most appropriate intervention plan from the intervention strategies based on the patient’s specific symptoms and health status;

[0097] S53. Generate detailed intervention recommendations, including specific steps, precautions, and expected results.

[0098] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A neck radiotherapy sequelae management and intervention system, characterized in that: include: Symptom detection module, which includes a sensor submodule, an image acquisition submodule and a questionnaire submodule, and is used to detect the sequelae of neck radiotherapy in patients; A data processing module, used for analyzing the data acquired by the symptom detection module; Intervention suggestion module, used to generate personalized intervention suggestions; User interface module for interacting with patients to provide symptom feedback and intervention recommendations.

2. A neck radiotherapy sequelae management and intervention system according to claim 1, characterized in that: The sensor submodule includes multiple biosensors for real-time monitoring of the patient's physiological parameters; The image acquisition submodule includes a high-resolution camera and an infrared camera to obtain images of the neck skin and muscles; The questionnaire submodule is used to collect patients' subjective symptom feedback, which includes pain level, dysphagia and skin itching.

3. A method for managing and intervening aftereffects of neck radiotherapy, implemented based on a system for managing and intervening aftereffects of neck radiotherapy as described in any one of claims 1-2, characterized in that: The steps include: S1, real-time acquisition of patients’ physiological parameters, images of neck skin and muscles, and subjective symptom feedback; S2, integrate data from different sources to form a complete patient symptom database; S3, using machine learning algorithms and statistical analysis methods to process data and identify symptom patterns and trends; S4. Generate a patient symptom report based on the analysis results, including the severity of current symptoms, changing trends and potential risks; S5. Provide personalized intervention recommendations to patients.

4. A method for management and intervention of neck radiotherapy sequelae according to claim 3, characterized in that: The image processing process in the data processing in step S3 includes the following steps: S31. Image preprocessing: Grayscale conversion: convert RGB images into grayscale images to reduce computational complexity; Noise removal, applying Gaussian filtering or median filtering to remove noise from the image; Image enhancement, using histogram equalization or adaptive histogram equalization (CLAHE) to improve image contrast; S32, Image Segmentation: Edge detection, using the Canny edge detection algorithm to identify edges in the image; Region segmentation, using the watershed algorithm or threshold-based segmentation method to divide the image into different regions; S33, feature extraction: Texture features, use gray-level co-occurrence matrix (GLCM) to extract the texture features of the image; Shape features: shape features of the lesion area, such as area, perimeter, and aspect ratio, are extracted through contour detection algorithms; Color features, extracting color histograms in RGB and HSV color spaces to determine the severity of skin damage; S34. Feature selection and classification: Feature selection, using principal component analysis (PCA) or recursive feature elimination (RFE) methods to select important features; Classification algorithm, using support vector machine (SVM), random forest or convolutional neural network (CNN) to classify the extracted features and determine the type and extent of the lesion.

5. A method for management and intervention of sequelae of neck radiotherapy according to claim 4, characterized in that: Providing personalized intervention suggestions to the patient in step S5 includes the following steps: S51. Multiple intervention strategies are built into the system, such as physical therapy, medication, and lifestyle adjustments; S52. Select the most appropriate intervention plan from the intervention strategies based on the patient’s specific symptoms and health status; S53. Generate detailed intervention recommendations, including specific steps, precautions, and expected results.

Images