Lymphedema treatment pressure visualization intelligent auxiliary method and related equipment

Abstract

The invention discloses a pressure visualization intelligent auxiliary method for lymphedema treatment and related equipment. The method comprises the steps that based on basic physiological information and edema related information of a patient, ideal pressure values of different edema parts of the patient are determined through a treatment pressure decision model, and the treatment pressure decision model is obtained through training according to historical clinical treatment data; displaying the ideal pressure values of the different edema parts of the patient; in the binding process, the actual pressure value between the bandage and the skin of the patient is obtained, and the actual pressure value is displayed. The problems that existing lymphedema bandaging pressure setting depends on subjective feelings of therapists, and the treatment effect is affected can be solved.

Description

Technical Field

[0001] This application relates to the field of smart healthcare, and more specifically, to a visual intelligent auxiliary method and related equipment for treating lymphedema with pressure visualization. Background Technology

[0002] Lymphedema is a relatively common condition, and comprehensive decongestive therapy (CDT) dominates its treatment. CDT primarily encompasses four key components: skin care, manual drainage, pressure therapy, and functional exercises. Among pressure therapy methods, air pressure wave therapy and bandaging are commonly used. During the treatment process, the pressure applied by bandaging needs to be adjusted according to the patient's specific condition to achieve the desired therapeutic effect for lymphedema.

[0003] However, current methods for setting bandage pressure have significant flaws. Currently, bandage pressure is primarily determined by the therapist's subjective feeling. Because the location of lymphedema varies from patient to patient, and the appropriate pressure differs for each location, the effectiveness of bandage application also varies greatly among therapists due to differences in their experience and pressure perception. When the bandage is too tight, it significantly affects patient tolerance, causing intense discomfort and reducing treatment adherence. Patients are more likely to remove the elastic bandage themselves, leading to treatment interruption. Conversely, if the bandage is too loose, the applied pressure will not reach the effective therapeutic range, ultimately severely impacting the patient's treatment outcome. Summary of the Invention

[0004] The summary section introduces a series of simplified concepts, which will be further explained in detail in the detailed description section. The summary section of this invention is not intended to limit the key features and essential technical features of the claimed technical solution, nor is it intended to determine the scope of protection of the claimed technical solution.

[0005] To address the problem that current methods for setting bandage pressure in lymphedema treatment rely solely on the therapist's subjective feeling, thus affecting treatment effectiveness, this invention proposes, firstly, a visualized intelligent auxiliary method for lymphedema treatment pressure. This method includes: Based on the patient's basic physiological information and edema-related information, the ideal pressure value for different edema sites in the patient is determined by a treatment pressure decision model, which is trained based on historical clinical treatment data. The ideal pressure values ​​for different edema sites in the patient are displayed; The actual pressure value between the bandage and the patient's skin is obtained during the bandaging process and displayed.

[0006] Optionally, acquiring the actual pressure value between the bandage and the patient's skin during the bandaging process, and displaying the actual pressure value, includes: During the bandaging process, real-time image data of the taut segment of the skin near the edematous area of ​​the patient is acquired when the bandage is wrapped; The actual pressure value between the bandage and the patient's skin is calculated based on the image data of the taut section, and the actual pressure value is displayed.

[0007] Optionally, the step of calculating the actual pressure value between the bandage and the patient's skin based on the taut segment image data, and displaying the actual pressure value, includes: Based on the image data of the taut segment, the actual pressure value between the current bandage and the patient's skin is calculated using a bandage tension state assessment model, and the actual pressure value is displayed.

[0008] Optionally, the step of calculating the actual pressure value between the bandage and the patient's skin based on the taut segment image data, and displaying the actual pressure value, includes: Based on the image data of the taut section, the bandage type and the mesh morphology of the taut section of the bandage are analyzed to calculate the actual pressure value between the bandage and the patient's skin, and the actual pressure value is displayed.

[0009] Optional, also includes: The difference between the actual pressure value and the ideal pressure value is displayed.

[0010] Optional, also includes: Based on the ideal pressure value, pressure ranges are divided, and a corresponding display color is assigned to each pressure range to display the corresponding color according to the pressure range in which the actual pressure value falls. The pressure ranges include an excessively loose pressure range, an ideal pressure range, and an excessively tight pressure range; and / or, The ideal pressure value and the target color value are calibrated to generate a mapping relationship between pressure value and color value, so as to display the color corresponding to the actual pressure value.

[0011] Optional, also includes: The image of the taut segment is displayed in association with the corresponding actual pressure value.

[0012] Secondly, the present invention also proposes a visual intelligent auxiliary device for treating lymphedema, comprising: The determination unit is used to determine the ideal pressure value for different edema sites of the patient based on the patient's basic physiological information and edema-related information through a treatment pressure decision model, wherein the treatment pressure decision model is trained based on historical clinical treatment data. The first prompting unit is used to display the ideal pressure values ​​for different edema sites of the patient; The second prompting unit is used to obtain the actual pressure value between the bandage and the patient's skin during the bandaging process, and to display the actual pressure value.

[0013] Thirdly, an electronic device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program stored in the memory to implement the steps of the lymphedema treatment pressure visualization intelligent assistance method as described in any of the first aspects above.

[0014] Fourthly, the present invention also proposes a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, it implements the lymphedema treatment pressure visualization intelligent auxiliary method of any of the above claims in the first aspect.

[0015] In summary, the intelligent visual assistance method for lymphedema treatment proposed in this application determines the ideal pressure value for different edema sites based on the patient's basic physiological information and edema-related information through a treatment pressure decision model trained on historical clinical treatment data. The method displays the ideal pressure values ​​for different edema sites and acquires and displays the actual pressure value between the bandage and the patient's skin during bandaging. By transforming the traditional experience-oriented treatment process into a data-driven, real-time feedback-based visual assistance prompt, it fundamentally solves the problems of inconsistent bandage pressure setting standards and uncontrollable quality in lymphedema treatment. It can significantly improve the scientific rigor, individualization, and repeatability of pressure setting; reduce the probability of patient discomfort or treatment ineffectiveness due to inappropriate pressure; improve therapist efficiency and reduce training difficulty; and support continuous optimization of treatment quality and remote assisted supervision.

[0016] The present invention provides a visual intelligent auxiliary method for treating lymphedema with pressure. Other advantages, objectives, and features of the present invention will be apparent in part from the following description, and in part will be understood by those skilled in the art through study and practice of the invention. Attached Figure Description

[0017] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit this specification. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings: Figure 1 This application provides a schematic flowchart of a pressure-visualized intelligent auxiliary method for treating lymphedema, as illustrated in an embodiment of the present application. Figure 1a This application provides a schematic diagram of another intelligent auxiliary method for visualizing pressure in the treatment of lymphedema. Figure 2 A schematic diagram of a pressure visualization intelligent auxiliary device for lymphedema treatment provided in this application embodiment; Figure 3 This is a schematic diagram of a pressure-visualizing intelligent auxiliary electronic device for lymphedema treatment provided in an embodiment of this application. Detailed Implementation

[0018] The terms "first," "second," "third," "fourth," etc. (if present) in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments described herein can be implemented in a sequence other than that illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus. The technical solutions of the embodiments of this application will now be clearly and completely described in conjunction with the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them.

[0019] To address the issue that current methods for setting bandage pressure for lymphedema treatment rely on the therapist's subjective judgment, thus affecting treatment outcomes, please refer to [link to relevant documentation]. Figure 1 This is a schematic diagram of a visual intelligent auxiliary method for treating lymphedema pressure provided in an embodiment of this application, which may specifically include steps S110 to S130.

[0020] S110, based on the patient's basic physiological information and edema-related information, the ideal pressure value for different edema sites of the patient is determined by a treatment pressure decision model, which is trained based on historical clinical treatment data.

[0021] S120 displays the ideal pressure values ​​for different edema sites in the patient.

[0022] S130, during the bandaging process, the actual pressure value between the bandage and the patient's skin is obtained and displayed.

[0023] For example, a multi-parameter decision model can be used to generate individualized ideal bandaging pressure values ​​for each patient. Before treatment, basic physiological information and edema-related data are collected, including but not limited to age, gender, weight, circumference of the affected limb, local skin elasticity, microcirculation perfusion level, edema stage, tissue stiffness score, and the presence of comorbidities (such as diabetes, heart disease, and hypertension). The collected data are used as input variables and fed into a multivariate learning model (such as XGBoost or a random forest regression model). This model is trained using clinical sample data and has the ability to map input physiological characteristics to corresponding optimal treatment pressure ranges. The model outputs recommended ideal bandaging pressure values ​​for various edema areas of the patient's body (such as the dorsum of the foot, calf, thigh, and arm), usually expressed in millimeters of mercury (mmHg), and provides an acceptable fluctuation range (e.g., ±5 mmHg). In this way, pressure setting is transformed from the traditional "experience-based" to a "data-driven" personalized recommendation, which in principle improves the accuracy of the pre-bandaging plan and significantly reduces the problem of inconsistent pressure caused by different subjective judgments of therapists. It is especially suitable for novice operators or scenarios where multiple therapists take turns caring for patients.

[0024] For example, recommended pressure values ​​for each body part can be visualized and guided through a graphical user interface. After calculating the ideal pressure, the system displays the recommended pressure for each edema area of ​​the patient's body in the form of a heat map or segment bars through a visual interface (such as an iPad or PC treatment control platform). The pressure values ​​can be overlaid on a body model or actual patient photographs. Each area is clearly labeled with its recommended pressure range, such as "upper limb pressure is approximately 20-30 mmHg, lower limb pressure is approximately 50-60 mmHg," and a color gradient is set to indicate the area's pressure sensitivity. For example, light colors represent low-pressure areas (distal), and dark colors represent high-pressure areas (proximal). This interface is viewed by the therapist before bandaging as a reference for operation. Simultaneously, the system provides bandaging sequence prompts (from distal to proximal), guiding the therapist to reasonably allocate bandage tension and the number of wraps according to the area's pressure requirements during layer-by-layer bandaging. The core technology of this step lies in the combination of human-computer interaction and dynamic guidance mechanisms. Visual output bridges the cognitive gap between model output and manual operation, thereby improving the consistency of treatment plan execution and avoiding the problem of knowing what to do but not knowing how to perform the operation.

[0025] For example, during bandaging, a flexible pressure sensing device can acquire real-time pressure data between the bandage and the skin. An array of flexible pressure sensors (e.g., wearable e-skin sensing material or ultra-thin pressure patches based on piezoresistive / capacitive methods) is pre-attached between the patient's skin and the bandage. Each sensor can monitor a unit pressure value in a small area. The sensors are connected to a processing terminal via Bluetooth or wired connection, providing real-time feedback on the current pressure with each bandage wrap and comparing it to a recommended pressure value. At each time point, the system calculates whether the current pressure in that area falls within the target pressure range. If it exceeds a set error range (e.g., a deviation exceeding ±5 mmHg), an alarm is triggered, and the interface prompts "Current pressure is too high, please adjust the tightness." The core principle of this module is a closed-loop feedback control mechanism. Through continuous monitoring and dynamic correction, it further improves treatment accuracy at the execution level and significantly reduces regional failures or patient discomfort caused by bandaging too tightly or too loosely, achieving dynamic operational guidance and early risk warning.

[0026] For example, multiple flexible pressure sensor arrays (e.g., based on resistive pressure-sensitive materials, piezoelectric films, or conductive fabric structures) can be integrated into the bandage body. These sensors are attached to the inner surface of the bandage and are applied to the skin layer by layer as the bandage is wound. The corresponding sensing unit of each loop of the bandage will collect the pressure data (in mmHg) at that location in real time and transmit it back to the system processing module via Bluetooth, NFC, or near-field electromagnetic coupling.

[0027] For example, after bandaging, pressure distribution verification and individualized treatment records are retained. After the bandaging operation is completed, the system centrally processes the final pressure data from all sensor points and outputs a "pressure distribution heatmap" to assess the consistency between the actual operation and the target setting. The system will indicate which areas meet the target and which areas are too low or too high, and record this information along with the patient's subjective feedback (such as pain and tightness) in the electronic medical record to generate an individualized treatment record file. In addition, if there is a deviation, the system provides "retrospective operation suggestions," such as "The current third bandage is too tight; adjustment is recommended." The principle behind this process is to establish a learning curve mechanism based on historical data, thereby continuously optimizing the therapist's behavior in multiple treatments and providing modeling data support for future similar patients, achieving closed-loop learning, adaptive individual adjustment, and traceable quality.

[0028] like Figure 1a As shown, when performing pressure therapy, lymphedema therapists or home-based patients can adjust the actual pressure in real time according to the ideal pressure value to achieve better treatment results.

[0029] In summary, the intelligent auxiliary method for visualizing treatment pressure in lymphedema provided in this application determines the ideal pressure value for different edema sites based on the patient's basic physiological information and edema-related information through a treatment pressure decision model trained on historical clinical treatment data. The method displays the ideal pressure values ​​for different edema sites and acquires and displays the actual pressure value between the bandage and the patient's skin during bandaging. By using a treatment pressure decision model based on the patient's individual physiological parameters and edema-related state, intelligent prediction and individualized setting of ideal bandaging pressure are achieved. This overcomes the limitations of traditional bandaging methods that primarily rely on the therapist's subjective experience to estimate pressure, significantly reducing treatment uncertainty caused by differences in operator skill levels. The data-driven nature of this model allows for the establishment of a stable mathematical mapping relationship between complex individual variables (such as BMI, limb circumference, edema stage, etc.) and the optimal treatment pressure value, thereby ensuring the scientific validity, consistency, and clinical reproducibility of the pressure setting. Technically, this mechanism enhances the precision of treatment plans, enabling the rapid provision of the most suitable pressure regimen for patients with different locations, proportions of edema, and even different stages of disease, effectively optimizing pressure gradient configuration and enhancing lymphatic drainage efficiency. Secondly, the structured visualization of ideal pressure values ​​within the protocol serves as a bridge for operational guidance during the bandaging process. Presenting the ideal pressure value directly to the operator in graphical or numerical form allows them to clearly understand the target pressure range before each bandage application, thereby improving their control over tension adjustment. This approach provides a quantifiable standard for treatment, significantly improving the consistency and controllability of the treatment process while reducing the risks of patient discomfort, slippage, and bandage failure due to tension control errors. Particularly in scenarios involving therapist rotation, cross-team collaboration, novice operators, or home-based self-pressure bandaging by patients, this mechanism effectively ensures standardized treatment outcomes and significantly enhances operational stability. Finally, by acquiring and displaying actual pressure values ​​during the bandaging process, a real-time feedback mechanism for pressure application is established. The operator can directly know whether the actual pressure applied to the current area is within the recommended pressure range while wrapping the bandage, thus enabling dynamic adjustments and improving operational initiative and the integrity of the treatment loop. This mechanism breaks through the traditional delayed control mode of wrapping and then checking, instead achieving real-time correction and process monitoring of operational behavior, thereby greatly reducing global rework or treatment failure caused by improper tension in a single wrap. In addition, this pressure feedback also provides structured data support for subsequent efficacy tracking, quality assessment, and treatment record establishment, further promoting the digital upgrade of the treatment process.

[0030] In some examples, acquiring and displaying the actual pressure value between the bandage and the patient's skin during the bandaging process includes: During the bandaging process, real-time image data of the taut segment of the skin near the edematous area of ​​the patient is acquired when the bandage is wrapped; The actual pressure value between the bandage and the patient's skin is calculated based on the image data of the taut section, and the actual pressure value is displayed.

[0031] In some examples, calculating the actual pressure value between the bandage and the patient's skin based on the taut segment image data, and displaying the actual pressure value, includes: Based on the image data of the taut segment, the actual pressure value between the current bandage and the patient's skin is calculated using a bandage tension state assessment model, and the actual pressure value is displayed.

[0032] For example, once the bandage application process begins, the system does not rely on physical pressure sensors. Instead, it uses a camera device (such as a head-mounted or bedside camera) to capture image data of a section of the bandage close to the skin during treatment. This image primarily includes key visual features such as the deformation of the bandage's lateral texture, the depth of the indentation, the stretching shape of the skin-bandage boundary, and the deformation trend across multiple frames of the same area. These images are then input into an image recognition and pressure estimation model. During the system training phase, this model learns features by inputting a large number of image samples with known pressure labels into a deep neural network (such as a ResNet or UNet structure), enabling the model to predict the actual pressure between the bandage and the skin from the image. The image pressure estimation result is displayed in real-time on the system interface, for example, "Current pressure: 48 mmHg, Target range: 45–50 mmHg." If the pressure deviates from the target range, the system automatically issues a prompt, "Tension is too high; it is recommended to loosen this bandage," guiding the therapist to make immediate adjustments. This step is based on image mechanics modeling and image regression analysis, ensuring dynamic and continuous pressure sensing without the need for wearable electronic sensors; it strikes a balance between real-time operation, non-invasiveness, and system deployment ease, significantly improving feedback accuracy and control capabilities during the bandaging process.

[0033] For example, after bandaging is completed, the system archives the entire process image data and corresponding pressure estimates. Based on a comparison of historical and target pressure, it automatically generates an individualized treatment quality report containing information such as "pressure consistency score," "excessive tension area reminder," and "operation time analysis." It also supports doctors filling in subjective observations and patient feedback (such as pressure pain and slippage). This aggregated data can be used for individual patient efficacy evaluation and can provide new sample inputs for subsequent model iterations, forming a complete closed loop from treatment execution to data learning and feedback optimization. The principle behind this stage is to promote the traceability, accountability, and continuous optimization of treatment plans through structured retention of treatment data and visual analysis of results; to achieve standardized management of medical behavior; and to support the future expansion of intelligent decision-making platforms, such as remote bandaging guidance and training assessment.

[0034] Understandably, this solution fully realizes an intelligent assisted lymphedema bandaging system that does not rely on physical pressure sensors, from individualized recommendations to visual back-inference and then to feedback closed loop.

[0035] In some examples, calculating the actual pressure value between the bandage and the patient's skin based on the taut segment image data, and displaying the actual pressure value, includes: Based on the image data of the taut section, the bandage type and the mesh morphology of the taut section of the bandage are analyzed to calculate the actual pressure value between the bandage and the patient's skin, and the actual pressure value is displayed.

[0036] For example, during actual bandaging, the system uses a high-definition camera at a fixed angle to capture real-time "tight section image data" of the bandage wrapped around the skin, focusing on two key features in the image: bandage type identification and mesh morphology analysis. First, the system identifies the current bandage material type (e.g., low-elasticity pressure bandage, high-elasticity pressure bandage, or tubular bandage) using texture feature analysis algorithms or deep classification networks. The system has pre-set typical texture structures and unit tensile force-porosity mapping models for different bandage types. Then, the system extracts parameters from the tight section image, such as mesh structure porosity size, porosity deformation shape, and transverse density changes on the bandage surface, especially the flatness, compression ratio, and angle contraction trend of the mesh from its initial relaxed state to its current state. By comparing these parameters with image parameters of the same bandage type under standard tensile tension in the database, the system uses regression calculations or a deep learning regression network to estimate the actual unit pressure value (in mmHg) corresponding to the current image and displays this value in real-time on the treatment interface. For example, "The current pressure in the area is 47 mmHg, and the recommended pressure is 45–50 mmHg." If the system determines that the pressure value exceeds the preset safe range, it will automatically highlight a prompt, such as "The pressure is too high. It is recommended to loosen it by one turn or reduce the tension," thus achieving dynamic closed-loop adjustment during the bandaging process.

[0037] Understandably, the elastic compression effect of a bandage directly affects its surface texture, especially under skin pressure. The morphology of the mesh structure's pores (such as reduced area, edge distortion, and changes in uniformity) has a stable mapping relationship with the actual tension. By establishing a regression model between "mesh deformation parameters and pressure values" using image processing technology, the system can estimate bandaging pressure solely from images. Without the need for wearing sensors, it can continuously and non-contactly acquire bandaging pressure status, greatly improving system deployment flexibility, reducing costs, and accurately covering different styles and techniques of various bandaging operations.

[0038] For example, after the bandaging procedure is completed, the system archives the image data from the process, the calculated pressure value per bandage, the deviation from the recommended value, and the treatment time, generating a standardized treatment quality report. It also supports simultaneous recording of the patient's subjective feelings (such as pressure, slippage, and stinging sensations). The system automatically analyzes the compliance of each pressure area in the background, generating a bandaging quality heatmap and feedback suggestions, such as "The pressure in the proximal lower limb area is too low; the number of bandage wraps can be increased appropriately next time." Furthermore, this data can be fed back to the decision model for further optimization and training, thereby continuously improving the model's accuracy and constructing a complete data feedback closed-loop mechanism. This achieves traceability and optimization of bandaging treatment, allowing patient treatment and the system's intelligent capabilities to grow in tandem.

[0039] Understandably, by introducing bandage type and mesh gap image analysis as the core path of image regression inference, not only is real-time perception and feedback of bandaging pressure achieved, but dependence on pressure sensors is also completely avoided. The principle is based on the mechanical mapping between tension and visual changes in surface structure, and has the advantages of strong versatility, low deployment cost and high feedback efficiency. It is highly scalable in clinical applications and is especially suitable for the construction of intelligent compression therapy systems and remote medical application scenarios.

[0040] For example, during the actual bandaging process, the system uses a camera to capture images of the taut section of the bandage near the skin, before it is fully wrapped but in a stretched state—that is, the state where the bandage is stretched to a certain tension and is about to be placed. These images clearly show features such as the bandage mesh compression shape, yarn gap deformation, and changes in cross-grain density, reflecting the tension level corresponding to the current stretching state without needing to be in contact with the skin. The image recognition module first identifies the current bandage type (e.g., short stretch / long stretch) and calls its preset standard force-shape mapping curve. The system then extracts parameters such as mesh compression ratio, edge distortion degree, and pattern compression gradient from the image, inputting them into a trained image regression model to estimate the expected bandaging pressure value (unit: mmHg) in this state—that is, how much pressure will be applied if the current tension is placed on the skin surface.

[0041] In some examples, it also includes: The difference between the actual pressure value and the ideal pressure value is displayed.

[0042] For example, when the therapist prepares to perform a bandaging procedure, the system displays the aforementioned ideal pressure values ​​on a terminal (such as a tablet or bedside screen) through a graphical interactive interface. The system labels the target pressure for each area using a simulated anatomical diagram or zone labels, and simultaneously sets visual reinforcement elements (such as color coding, fluctuation bars, and numerical ranges) to allow the operator to clearly understand the target tension level for each area. This facilitates guidance on the number of bandage wraps, the pre-stretching degree of the bandage, and the selection of the wrapping angle. This visualization module, based on human-computer interaction principles, ensures that the therapist has sufficient perception and preparation before the procedure, significantly reducing treatment deviations caused by subjective experience differences or operational misjudgments.

[0043] For example, during actual bandaging, the system uses a fixed-angle camera to capture image data of the taut section of the bandage wrapped around the skin. The image recognition module first identifies the bandage type (such as a short stretch bandage, elastic mesh bandage, etc.), and then matches it with its preset image feature model based on this type. On this basis, the system further extracts the morphological changes of the mesh gaps in the taut section, including the gap area shrinkage ratio, striation density, and indentation deformation morphology, and inputs these into the image-pressure inverse model. This model has already completed the function learning of bandage mesh changes and actual pressure values ​​during the training phase using a deep regression network or support vector regression algorithm. Therefore, it can inversely deduce the actual pressure value (unit: mmHg) between the bandage and the skin based on the current image state and display it in real time on the user interface, for example, "Current pressure: 47 mmHg".

[0044] For example, to further enhance the intuitiveness of feedback and support real-time correction, the system synchronously displays the difference between the actual pressure value and the ideal pressure value next to each monitoring point or bandaging area, such as "Recommended pressure: 45 mmHg; Current pressure: 47 mmHg; Difference: +2 mmHg," and uses color to indicate whether the difference is within the safe tolerance range (e.g., ±5 mmHg). If it exceeds the tolerance range, the interface will trigger highlighting or warning text, such as "Pressure too high: Please loosen this bandage appropriately," providing therapists with immediate decision-making assistance based on quantitative differences. The implementation principle of this function is to perform real-time differential analysis between static target values ​​and dynamic image-derived values ​​to indicate the degree of compliance of bandaging behavior, thereby improving operational controllability, making risks explicit, and enhancing the consistency of therapeutic effects.

[0045] For example, after bandaging is completed, the system archives the entire process image data, the ideal pressure value for each area, the actual estimated value, and the difference results, automatically generating a "Bandaging Quality Feedback Report." The report includes: 1) a heatmap showing the achievement of standards in each area; 2) a highlighting of areas with the greatest pressure deviation; 3) a trend analysis of bandaging behavior; 4) a summary of the patient's subjective feedback (such as discomfort from pressure, feeling of looseness); and 5) a score indicating the degree of consistency between the therapist's actions and the system's recommendations. This feedback is not only used for single-treatment quality assessment but also serves as part of the patient's individual treatment record, supporting subsequent efficacy tracking, treatment plan optimization, and model retraining. In principle, this archiving mechanism constructs a traceable closed loop for treatment data, enabling long-term quality control, cross-therapist standardization maintenance, and strengthening the self-evolutionary capabilities of the intelligent system.

[0046] Understandably, by using data-driven ideal pressure modeling as a foundation, combined with grid morphology reasoning based on image recognition to complete non-contact real-time pressure estimation, and by using a pressure difference display mechanism to enhance the operator's immediate feedback perception of the bandaging behavior, an intelligent, personalized, and standardized end-to-end bandaging auxiliary control system has been achieved without the intervention of external sensors, which is highly feasible in clinical practice and has great potential for industrial application.

[0047] In some examples, it also includes: Based on the ideal pressure value, pressure ranges are divided, and a corresponding display color is assigned to each pressure range so that the corresponding color is displayed according to the pressure range in which the actual pressure value is located. The pressure ranges include the too-loose pressure range, the ideal pressure range, and the too-tight pressure range.

[0048] For example, during treatment, the system uses a fixed-position camera device (such as a bedside camera) to capture real-time image data of the taut section of the bandage wrapped around the patient's skin. The image recognition module first analyzes the material type of the bandage (such as a short-stretch bandage or an elastic mesh bandage), and then further extracts the morphological change features of the bandage's mesh gaps in the image, including mesh compression rate, texture density, and skin contact deformation. By inputting these features into a depth image regression model, the system calculates and estimates the actual unit pressure value corresponding to the current image, which is output in millimeters of mercury (mmHg). The image-pressure model has established a mapping between the mesh deformation morphology and the standard pressure value during the training phase, so accurate estimation can be achieved even without the use of physical sensors. This image estimation mechanism realizes non-contact, continuous, and quantitative pressure detection during bandaging. Its core principle is based on visual-mechanical correlation mapping, which can significantly improve equipment adaptability and system deployment convenience.

[0049] For example, the system will display the actual pressure value of each loop or each monitoring area in real time on the treatment interface, and automatically map the value to the corresponding pressure range under the aforementioned color coding mechanism. That is, the background or border of the monitoring area will be automatically rendered as blue (too loose), green (ideal), or red (too tight) according to the pressure range, and the numerical difference will be displayed simultaneously, such as "Current: 47 mmHg, Recommended: 45–50 mmHg, Difference: +2 mmHg, Status: Green (Ideal)". If a pressure falls into the too loose or too tight range, the system will indicate "Current pressure deviates from the ideal range" with a highlighted animation, flashing border, or warning symbol, and may also pop up specific suggestions: "Current bandage tension is slightly tight, it is recommended to loosen one loop and reduce tension by 20%". The implementation of this pressure-color mapping mechanism is based on a real-time status classification algorithm and a graphics rendering module, which in principle enhances the therapist's ability to quickly assess the quality of operation in each area; it eliminates the need to read pressure values ​​one by one, and only visually identifies whether the current bandage is up to standard through color, significantly improving operational efficiency and reducing error rate, especially suitable for multi-area, multi-layer wrapping or novice operator environments.

[0050] For example, after bandaging is completed, the system archives the image data of each bandage / layer, the actual pressure value, the recommended pressure range, and the color status label, and generates a structured treatment record document, including a pressure distribution map, a color target achievement statistics table, maximum pressure deviation prompts, and patient subjective feedback. The system automatically marks the bandage locations with "red" (too tight) areas, providing key data support for subsequent adjustments or follow-ups. This record can also be uploaded to the cloud for model fine-tuning and subsequent patient treatment adjustments.

[0051] According to some embodiments, it also includes: The ideal pressure value and the target color value are calibrated to generate a mapping relationship between pressure value and color value, so as to display the color corresponding to the actual pressure value.

[0052] For example, the system then displays the recommended pressure value for each area on the operating terminal (such as a mobile app or bedside operating screen). Based on this, it further calibrates the ideal pressure value with continuous target color values, establishing a one-to-one mapping function from pressure value to color representation. Specifically, the system presets a continuous gradient color spectrum within a pressure range (e.g., 30-60 mmHg), uniformly mapping the entire pressure range to the color space. For example, it gradually transitions from blue (too loose) through green (ideal) to red (too tight), with intermediate color segments such as light green, yellow-green, and orange-yellow indicating subtle trends of being too low or too high. This mapping relationship can be established using the HSV or CIELab color space to ensure that the visual presentation is physiologically distinguishable. After the mapping is generated, the system saves it as a standard lookup table function or interpolation calculation model, supporting its use during subsequent real-time pressure display.

[0053] For example, during the bandaging process, the system acquires image data of the taut section of the bandage using a camera device. The image processing module first identifies the bandage type (e.g., short stretch, multi-layer elastic), then extracts its mesh-like morphological parameters, including the degree of mesh compression, changes in texture line spacing, and local deformation shape, and inputs these image features into a pre-trained image-pressure regression model. This model can deduce the actual pressure value (in mmHg) of the bandage at that location based on convolutional neural networks (e.g., ResNet) or morphological regression methods. Then, the system substitutes this actual pressure value into the previously generated "pressure value-color value mapping function" to obtain a target color value, and immediately provides real-time color feedback for the current bandaged area in the operation interface using this color value. For example, if the current estimated pressure is 47 mmHg, the corresponding color value is greenish-yellow (RGB approximately #C5E400), and this color area is displayed; if the actual pressure is 36 mmHg, it is mapped to a bluish (RGB approximately #5DADEC), and displayed in blue. The principle behind this color value mapping mechanism lies in constructing a finer-grained visual feedback layer through a continuous numerical-color mapping function. This allows therapists to quickly and intuitively adjust tension based on the warmth, coolness, and depth of color, rather than relying on numerical judgments, significantly improving operational efficiency and perceptual sensitivity. It enhances the human eye's ability to recognize treatment precision, improves the speed of adjustment in bandaging movements, and supports segmented fine-tuning of more complex areas (such as the back of the hand and ankle).

[0054] For example, after the entire bandaging process is completed, the system automatically records information such as the actual pressure value, target pressure value, pressure difference, corresponding color value, image frame, and color status, and generates a quality report containing dimensions such as a pressure-color value heatmap, highlighted local deviations, and achievement rate score. The report not only serves as a record of the current treatment but can also be used for efficacy comparison analysis, cross-time trend tracking, and continuous model fine-tuning. This reporting mechanism establishes a full-link control system from model calculation, image recognition, color value visualization to closed-loop evaluation, ensuring the reliability of the treatment closed loop in principle, and supporting remote quality review, cross-therapist standardization, and system learning iteration.

[0055] According to some embodiments, it also includes: The image of the taut segment is displayed in association with the corresponding actual pressure value.

[0056] For example, the system displays graphical prompts for recommended pressure values ​​on the interactive terminal and sets three main pressure ranges: ideal pressure range, too loose range, and too tight range. Each pressure range is assigned a set of gradient color values. For instance, a continuous color spectrum mapping range from blue to green to red is established within the 30–60 mmHg range, and each pressure value is precisely labeled with a color value using a color value mapping function, enabling subsequent numerical-visual visualization comparison. This process allows therapists to judge the effectiveness of the operation through color, fundamentally transforming continuous quantitative information into instantaneously perceptible signals, significantly optimizing the efficiency of immediate adjustments during operation.

[0057] For example, during the bandaging process, the camera system captures real-time images of the taut section of the bandage wrapped around the skin in the therapist's hand. The system first identifies the type and structural parameters of the current bandage (e.g., short stretch, multi-layered elastic), and extracts features such as grid morphology, texture density, and indentation depth from the image. These image features are input into an image-pressure regression model, which the system uses to estimate the actual pressure value of the currently bandaged area. Simultaneously, the system maps this actual pressure value to a color value, displaying the current status such as "47 mmHg, green (meets standards)," and performs further enhancement processing. In some embodiments, the system binds the image of the taut section with its corresponding estimated actual pressure value in real time, that is, directly overlays the pressure value and color label next to the image, or displays it in the form of a graphic box: "Image A Actual pressure value: 47 mmHg, Status: Ideal (green)".

[0058] Understandably, the dual binding of visual and numerical information can improve operator trust and adjustment accuracy, while also providing a basis for subsequent quality control. It enhances the interpretability of pressure estimation, increases therapists' trust in the system, facilitates improved understanding of operational skills through visual comparison during training, and enables later review and analysis and quality traceability, especially suitable for remote guidance scenarios. It allows therapists to not only see pressure values ​​and color cues, but also to intuitively see the correspondence between the visual features of the corresponding image area and the estimated pressure, which is of significant value for clinical bandaging training, quality control analysis, and operational traceability.

[0059] Please see Figure 2 One embodiment of the intelligent auxiliary device for visualizing pressure in the treatment of lymphedema in this application may include: The determining unit 21 is used to determine the ideal pressure value for different edema sites of the patient based on the patient's basic physiological information and edema-related information through a treatment pressure decision model, wherein the treatment pressure decision model is trained based on historical clinical treatment data. The first prompting unit 22 is used to display the ideal pressure values ​​for different edema sites of the patient; The second prompting unit 23 is used to obtain the actual pressure value between the bandage and the patient's skin during the bandaging process, and to display the actual pressure value.

[0060] In summary, the lymphedema treatment pressure visualization intelligent auxiliary device provided in this application determines the ideal pressure value for different edema sites of the patient based on the patient's basic physiological information and edema-related information through a treatment pressure decision model trained on historical clinical treatment data. It displays the ideal pressure values ​​for different edema sites and acquires and displays the actual pressure value between the bandage and the patient's skin during bandaging. By transforming the traditional experience-oriented treatment process into a data-driven, real-time feedback-based visualization auxiliary prompt, it fundamentally solves the problems of inconsistent bandage pressure setting standards and uncontrollable quality in lymphedema treatment. It can significantly improve the scientific nature, individualization, and repeatability of pressure setting; reduce the probability of patient discomfort or treatment ineffectiveness due to inappropriate pressure; improve therapist operational efficiency and reduce training difficulty; and support continuous optimization of treatment quality and remote auxiliary supervision.

[0061] like Figure 3 As shown, this application embodiment also provides an electronic device 300, including a memory 310, a processor 320, and a computer program 311 stored in the memory 320 and executable on the processor. When the processor 320 executes the computer program 311, it implements the steps of any of the above-mentioned methods for visual intelligent assistance in treating lymphedema pressure.

[0062] Since the electronic device described in this embodiment is the device used to implement the lymphedema treatment pressure visualization intelligent auxiliary device in the embodiments of this application, those skilled in the art can understand the specific implementation method and various variations of the electronic device in this embodiment based on the method described in the embodiments of this application. Therefore, how the electronic device implements the method in the embodiments of this application will not be described in detail here. Any device used by those skilled in the art to implement the method in the embodiments of this application is within the scope of protection of this application.

[0063] In practical implementation, when the computer program 311 is executed by the processor, it can achieve the following: Figure 1 Any of the corresponding implementation methods in the embodiments.

[0064] It should be noted that the descriptions of each embodiment in the above embodiments have different focuses. For parts that are not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0065] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0066] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create a machine for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0067] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0068] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0069] This application also provides a computer program product, which includes computer software instructions that, when executed on a processing device, cause the processing device to perform actions such as... Figure 1 The corresponding embodiment describes the process of visualizing and intelligently assisting in the treatment of lymphedema.

[0070] A computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the flow or function according to the embodiments of this application is generated. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can store or a data storage device such as a server or data center that integrates one or more available media. The available medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid-state disk (SSD)).

[0071] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0072] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, or indirect coupling or communication connection between apparatuses or units, and may be electrical, mechanical, or other forms.

[0073] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0074] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0075] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0076] The above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A visual intelligent auxiliary method for treating lymphedema, characterized in that, include: Based on the patient's basic physiological information and edema-related information, the ideal pressure value for different edema sites in the patient is determined by a treatment pressure decision model, which is trained based on historical clinical treatment data. The ideal pressure values ​​for different edema sites in the patient are displayed; The actual pressure value between the bandage and the patient's skin is obtained during the bandaging process and displayed.

2. The method as described in claim 1, characterized in that, The step of acquiring and displaying the actual pressure value between the bandage and the patient's skin during the bandaging process includes: During the bandaging process, real-time image data of the taut segment of the skin near the edematous area of ​​the patient is acquired when the bandage is wrapped; The actual pressure value between the bandage and the patient's skin is calculated based on the image data of the taut section, and the actual pressure value is displayed.

3. The method as described in claim 2, characterized in that, The step of calculating the actual pressure value between the bandage and the patient's skin based on the image data of the taut segment, and displaying the actual pressure value, includes: Based on the image data of the taut segment, the actual pressure value between the current bandage and the patient's skin is calculated using a bandage tension state assessment model, and the actual pressure value is displayed.

4. The method as described in claim 2, characterized in that, The step of calculating the actual pressure value between the bandage and the patient's skin based on the image data of the taut segment, and displaying the actual pressure value, includes: Based on the image data of the taut section, the bandage type and the mesh morphology of the taut section of the bandage are analyzed to calculate the actual pressure value between the bandage and the patient's skin, and the actual pressure value is displayed.

5. The method as described in claim 1, characterized in that, Also includes: The difference between the actual pressure value and the ideal pressure value is displayed.

6. The method as described in claim 1, characterized in that, Also includes: Based on the ideal pressure value, pressure ranges are divided, and a corresponding display color is assigned to each pressure range so that the actual pressure value falls within the corresponding pressure range. These pressure ranges include an excessively loose pressure range, an ideal pressure range, and an excessively tight pressure range; and / or, The ideal pressure value and the target color value are calibrated to generate a mapping relationship between pressure value and color value, so as to display the color corresponding to the actual pressure value.

7. The method as described in claim 3 or 4, characterized in that, Also includes: The image of the taut segment is displayed in association with the corresponding actual pressure value.

8. A visual intelligent auxiliary device for treating lymphedema, characterized in that, include: The determination unit is used to determine the ideal pressure value for different edema sites of the patient based on the patient's basic physiological information and edema-related information through a treatment pressure decision model, wherein the treatment pressure decision model is trained based on historical clinical treatment data. The first prompting unit is used to display the ideal pressure values ​​for different edema sites of the patient; The second prompting unit is used to obtain the actual pressure value between the bandage and the patient's skin during the bandaging process, and to display the actual pressure value.

9. An electronic device, comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor, when executing the computer program stored in the memory, implements the steps of the intelligent auxiliary method for visualizing pressure in the treatment of lymphedema as described in any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, it implements the intelligent auxiliary method for visualizing lymphedema treatment pressure as described in any one of claims 1-7.

Images