Wound surface identification charging system based on precision medical treatment

Abstract

The invention belongs to the technical field of medical image processing, and discloses a wound identification and charging system based on precision medical treatment, which realizes intelligent management of wound treatment through cooperative work of multiple modules. The method comprises the following steps: firstly, collecting a multi-angle digital image of a wound surface, performing standardization processing, performing image enhancement and noise reduction, and then performing identification and segmentation by using a deep learning algorithm; and performing three-dimensional reconstruction based on the accurate contour map to form parameter feature vectors, and performing intelligent wound type discrimination and severity evaluation. And according to an evaluation result, matching an optimal dressing change type and predicting required consumables, generating a precise dressing change scheme, and further calculating personalized charges and performing transparency verification. And finally, the system automatically generates a standardized medical service file through historical data comparison and rationality analysis. According to the system, the precision, standardization and transparency of wound treatment are realized, the medical service quality is improved, and the resource allocation is optimized.

Description

Technical Field

[0001] The present invention relates to the technical field of medical image processing, and more specifically, to a wound surface identification and charging system based on precision medicine. Background Art

[0002] Wound management, as an important part of clinical medicine, involves multiple specialized fields such as surgery, burns, dermatology, and diabetic foot clinics. With the development of medical technology, wound management has evolved from simple debridement and bandaging to a comprehensive treatment system. At present, wound assessment mainly relies on the visual observation and experience of medical staff, and usually adopts methods such as ruler measurement, transparent film tracing, and digital camera photography to obtain basic information about the wound. In terms of wound area measurement, commonly used clinical methods include the length-width product method, transparent grid film tracing method, and digital image processing technology. For wound classification, the red, yellow, and black three-color classification system and the NPUAP / EPUAP pressure injury grading system are generally adopted internationally.

[0003] In terms of wound treatment charges, most medical institutions adopt a pricing model based on level or tiered charging based on area, such as wounds less than 5 cm 2 , 5-10cm 2 , greater than 10cm 2 With the advancement of medical information technology, some hospitals have begun to use digital imaging technology to assist in wound assessment. For example, two-dimensional image analysis software can achieve semi-automatic measurement of wound area, but the accuracy and consistency still need to be improved.

[0004] In clinical practice, medical staff often rely on visual observation and subjective experience to assess wound condition, resulting in significant discrepancies between different doctors' assessments of the same wound, which in turn impacts treatment choices. Traditional manual measurement methods, such as tracing with a transparent film or measuring with a ruler, are not only time-consuming and labor-intensive, but also suffer from low accuracy and poor reproducibility. Measurement errors are particularly pronounced for wounds of irregular shapes or varying depths. Medical institutions lack standardized standards for matching dressing types, leading to arbitrary selection of consumables. This not only wastes valuable consumables but can also delay wound healing. In terms of billing, the lack of a scientific pricing mechanism based on objective parameters can lead to multiple variations in charges for the same wound care. This makes it difficult for medical staff to clearly explain the complexity of wound care and the rationality of charges to patients. Furthermore, wound care data is stored in disparate systems, lacking a comprehensive traceability mechanism. This not only increases the risk of medical errors but also hinders big data analysis and clinical research, ultimately limiting the overall improvement of wound care and the optimal allocation of medical resources.

[0005] In view of this, the present invention proposes a wound surface identification and charging system based on precision medicine to solve the above problems. Summary of the Invention

[0006] In order to overcome the above-mentioned defects of the prior art and to achieve the above-mentioned objectives, the present invention provides the following technical solutions: a wound surface identification and charging system based on precision medicine, comprising:

[0007] Image acquisition and standardization module, used to collect multi-angle digital images of the wound surface and perform standardization processing to obtain a standardized image data set of the wound surface;

[0008] An image enhancement and noise reduction processing module is used to perform enhancement and noise reduction processing on the standardized wound surface image dataset to obtain optimized image data;

[0009] A boundary recognition and segmentation module is used to apply a deep learning algorithm based on the optimized image data to accurately identify and segment the wound boundary to obtain an accurate contour map of the wound surface;

[0010] A parameter measurement and reconstruction module is used to automatically measure the area, length and depth and perform three-dimensional reconstruction based on the precise contour map of the wound surface to obtain a wound surface parameter feature vector;

[0011] A wound type identification and assessment module is used to perform intelligent identification of wound types and severity assessment based on the wound parameter feature vector to obtain a wound classification assessment matrix;

[0012] A matching and consumables prediction module is used to match dressing types and predict consumables based on the wound classification assessment matrix to obtain an accurate dressing change plan;

[0013] A charge calculation and verification module, for performing personalized charge calculation and transparency verification based on the precise dressing change plan to obtain a dynamic charge model;

[0014] The analysis and file generation module is used to compare historical data and conduct rationality analysis based on the dynamic charging model to obtain a charging rationality evaluation report; based on the charging rationality evaluation report and the precise dressing change plan, the dressing change prescription and charging details are automatically generated to obtain a standardized medical service file. The various modules are connected by wired and / or wireless means.

[0015] Preferably, the collecting of multi-angle digital images of the wound surface and performing standardization processing to obtain a standardized wound surface image dataset includes:

[0016] Using a medical-grade high-definition camera under standard light conditions to capture multi-angle images of the wound surface to obtain an original wound surface image group, and performing light equalization processing on the original wound surface image group to obtain a light-corrected image;

[0017] Performing color calibration and standard scale embedding on the illumination-corrected image to obtain a scale-standardized image, and performing perspective correction on the scale-standardized image to obtain a perspective-consistent image;

[0018] performing image resolution unification processing on the perspective consistency image to obtain a normalized image, and performing metadata annotation on the normalized image to obtain annotated image data;

[0019] Performing spatial registration and multi-angle fusion on the annotated image data to obtain a multi-dimensional view model, and performing image format standardization conversion on the multi-dimensional view model to obtain a standard format image;

[0020] The standard format images are associated with the patient's medical information and stored to obtain a standardized wound surface image dataset.

[0021] Preferably, the enhancing and denoising the standardized wound surface image dataset to obtain optimized image data comprises:

[0022] applying an adaptive histogram equalization algorithm to the standardized wound image dataset to obtain a contrast-enhanced image, and performing non-local means filtering on the contrast-enhanced image to obtain a preliminary noise-reduced image;

[0023] Applying wavelet transform to the preliminary denoised image to remove high-frequency noise to obtain a frequency domain optimized image, and performing edge-preserving smoothing on the frequency domain optimized image to obtain a detail-enhanced image;

[0024] Performing image layer analysis on the detail-enhanced image to obtain a layered feature map, and performing targeted image enhancement based on the layered feature map to obtain a feature-highlighted image;

[0025] Applying a deep learning denoising network to the feature-salient image to perform advanced noise removal to obtain a high-quality denoised image, and performing image quality assessment on the high-quality denoised image to obtain a quality score table;

[0026] The optimal processing parameters are selected based on the quality score table to reprocess the image and obtain optimized image data.

[0027] Preferably, the applying of a deep learning algorithm based on the optimized image data to accurately identify and segment the wound boundary to obtain an accurate contour map of the wound comprises:

[0028] Applying a pre-trained convolutional neural network to the optimized image data to perform preliminary positioning of the wound area to obtain a candidate region proposal map, and applying a pixel-level semantic segmentation network to the candidate region proposal map to obtain a preliminary segmentation mask;

[0029] Applying an active contour model to the preliminary segmentation mask to perform boundary refinement adjustment to obtain a refined boundary map, and applying a region growing algorithm to the refined boundary map to process fuzzy boundary areas to obtain a complete contour map;

[0030] Applying a conditional random field to optimize spatial consistency of the complete contour map to obtain a spatially optimized contour, and performing multi-scale feature fusion verification on the spatially optimized contour to obtain a verified contour map;

[0031] Performing medical expert knowledge rule constraint correction on the verified contour image to obtain a clinically verified contour, and performing boundary coordinate extraction and vectorization processing on the clinically verified contour to obtain contour vector data;

[0032] The contour vector data is superimposed on the original image and displayed, and boundary marks and measurement reference points are added to obtain an accurate contour map of the wound surface.

[0033] Preferably, the automatic measurement and three-dimensional reconstruction of area, length and depth based on the precise contour map of the wound surface to obtain the wound surface parameter feature vector includes:

[0034] Calculating the pixel area of ​​the wound based on the precise wound contour map and converting it into the actual area using a scale to obtain precise area data, and measuring the length of the wound along the maximum extension direction of the wound to obtain a length parameter;

[0035] Constructing a wound depth map using multi-angle image information to obtain a depth distribution map, and calculating the average depth and maximum depth of the wound based on the depth distribution map to obtain a depth parameter set;

[0036] constructing a three-dimensional mesh model of the wound surface based on the precise wound surface contour map and the depth parameter set to obtain a three-dimensional wound surface model, and calculating the volume and surface area of ​​the three-dimensional wound surface model to obtain three-dimensional parameter data;

[0037] Performing morphological analysis on the precise wound contour map to extract morphological features such as perimeter, ellipticity, and complexity to obtain a morphological feature set, and performing tissue type identification and area ratio analysis on the interior of the wound to obtain tissue feature data;

[0038] The precise area data, the length parameter, the depth parameter set, the three-dimensional parameter data, the morphological feature set and the tissue feature data are integrated to obtain a wound surface parameter feature vector.

[0039] Preferably, the intelligent identification of wound types and severity assessment based on the wound parameter feature vector are performed to obtain a wound classification assessment matrix, including:

[0040] Applying a multi-classification machine learning algorithm to the wound parameter feature vector to obtain a preliminary wound type discrimination result, and querying a wound type knowledge base based on the preliminary wound type discrimination result to obtain a standard wound type definition;

[0041] Calculating a wound severity score based on the standard wound type definition and the wound parameter characteristic vector to obtain a severity assessment index, and predicting healing difficulty based on the severity assessment index to obtain a healing assessment report;

[0042] Performing abnormality detection on the wound parameter feature vector to identify special wound types, obtaining special type labels, and setting processing priority weights according to the special type labels to obtain a priority coefficient table;

[0043] Mapping the severity assessment index, the healing assessment report, and the priority coefficient table with a clinical treatment guideline rule set to obtain a clinical intervention recommendation list, and determining a required dressing change resource level based on the clinical intervention recommendation list to obtain a resource requirement table;

[0044] The standard wound type definition, the severity assessment index, the healing assessment report, the priority coefficient table and the resource requirement table are integrated to obtain a wound classification assessment matrix.

[0045] Preferably, the dressing change type matching and consumables prediction based on the wound classification assessment matrix to obtain an accurate dressing change plan includes:

[0046] Automatically determining the dressing change type based on the area, length, and depth data of the wound classification assessment matrix to obtain a preliminary dressing change type determination result, and querying a standard dressing change type definition library based on the preliminary dressing change type determination result to obtain a standard dressing change specification;

[0047] Performing a secondary determination on the tissue characteristics and severity assessment indicators in the wound classification assessment matrix to obtain an auxiliary determination correction result, and fusing the auxiliary determination correction result with the initial dressing change type determination result to obtain a final dressing change type confirmation;

[0048] Predicting the types and quantities of medical consumables required based on the final dressing change type confirmation and the wound classification assessment matrix, obtaining a consumables list estimate table, and calculating consumables costs based on the consumables list estimate table to obtain material cost accounting data;

[0049] Based on the final dressing change type, the required medical staff hours and professional level are confirmed and predicted to obtain a human resource demand forecast, and the labor cost is calculated based on the human resource demand forecast to obtain labor cost accounting data;

[0050] The material cost accounting data, the labor cost accounting data and the final dressing change type are confirmed and integrated to obtain an accurate dressing change plan.

[0051] Preferably, the personalized charging calculation and transparency verification based on the precise dressing change plan to obtain a dynamic charging model includes:

[0052] Calculating a basic charge based on the dressing change type and consumables cost in the precise dressing change plan to obtain a basic charging standard, and calculating a complexity adjustment coefficient based on the complexity index in the wound classification assessment matrix to obtain an adjusted charge;

[0053] Applying medical insurance policy rules and regional differences to the adjusted charges to obtain regionalized charging standards, and making personalized adjustments based on the regionalized charging standards and the patient's special circumstances to obtain a personalized charging plan;

[0054] Conducting a cost-benefit analysis on the personalized charging plan to obtain a cost-benefit evaluation report, and constructing a charging fairness verification mechanism based on the cost-benefit evaluation report to obtain a fairness verification result;

[0055] Generate a detailed charge explanation document based on the fairness verification result to obtain a charge transparency document, and design a patient-friendly charge explanation interface based on the charge transparency document to obtain a visual charge explanation;

[0056] The personalized charging plan, the cost-benefit evaluation report and the charging transparency document are integrated to construct a dynamic charging model.

[0057] Preferably, the dynamic charging model is used to perform historical data comparison and rationality analysis to obtain a charging rationality assessment report; based on the charging rationality assessment report and the precise dressing change plan, a dressing change prescription and charging details are automatically generated to obtain a standardized medical service file, including:

[0058] Compare and analyze the dynamic charging model with historical charging data of similar wounds to obtain longitudinal comparison results, and compare it with the charges of similar services of medical institutions in the same region to obtain horizontal comparison results;

[0059] Calculating a charging deviation index based on the vertical comparison results and the horizontal comparison results to obtain a charging deviation evaluation table, and establishing a rationality evaluation standard based on the charging deviation evaluation table to obtain a rationality evaluation framework;

[0060] The dynamic charging model is evaluated using the rationality evaluation framework to obtain a charging rationality analysis result, and a charging recommendation is formed based on the charging rationality analysis result to obtain a charging rationality evaluation report;

[0061] Selecting an optimal charging plan based on the charging rationality evaluation report to obtain a final charging decision, and automatically generating a standardized electronic prescription based on the final charging decision and the precise medication change plan to obtain electronic prescription data;

[0062] The electronic prescription data, the wound parameter characteristic vector, the wound classification assessment matrix, the precise dressing change plan and the charging rationality assessment report are integrated and archived to obtain a standardized medical service file, which includes wound assessment records, dressing change plans, charging basis and disposal recommendations.

[0063] Preferably, the standardized wound image data set, the optimized image data, the precise wound contour map, the wound parameter feature vector, the wound classification assessment matrix, the precise dressing change plan, the dynamic charging model, the charging rationality assessment report and the standardized medical service file are all stored in a secure medical data platform, forming a complete wound treatment information chain. The wound treatment information chain ensures data integrity and non-tamperability through blockchain technology, and the secure medical data platform is provided with a hierarchical access control mechanism.

[0064] The technical effects and advantages of the wound surface identification and charging system based on precision medicine of the present invention are as follows:

[0065] The present invention significantly improves the objectivity and standardization of wound treatment by establishing a precision medical wound identification and charging system, and solves the problem of large subjective differences in traditional assessments. The system realizes the transparency of the entire process from assessment to charging, enhances the mutual trust between doctors and patients, and reduces medical disputes. Through scientific and reasonable charging standards and detailed explanation mechanisms, patients can clearly understand the composition of medical expenses and improve their satisfaction with medical services. At the same time, accurate resource allocation predictions reduce the waste of medical resources, reduce medical costs, and improve the operational efficiency of medical institutions. Standardized treatment processes and data management not only facilitate medical quality control, but also provide a reliable basis for clinical research and medical insurance policy formulation. Personalized treatment plans significantly improve wound healing effects, shorten patients' recovery cycles, and reduce patients' pain and financial burden. In addition, the system's data security mechanism protects patient privacy and meets the requirements of modern medical ethics. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] Figure 1 This is a schematic diagram of a wound surface identification and charging system based on precision medicine according to the present invention;

[0067] Figure 2 This is a schematic diagram of the detailed steps for obtaining an accurate contour map of the wound surface in the present invention. DETAILED DESCRIPTION

[0068] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0069] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0070] This application example provides a precision medicine-based wound surface identification and billing system. The execution entities of this precision medicine-based wound surface identification and billing system include, but are not limited to, the following: medical equipment, data processing terminals, hospital information systems, cloud servers, etc., which can be considered as general computing nodes of this application. The data processing terminals include, but are not limited to, at least one of a medical image processing system, a wound surface analysis system, and a medical billing management system.

[0071] See also Figure 1 The present invention provides a wound surface identification and charging system based on precision medicine, comprising:

[0072] Image acquisition and standardization module, used to collect multi-angle digital images of the wound surface and perform standardization processing to obtain a standardized image data set of the wound surface;

[0073] Image enhancement and noise reduction processing module, used to enhance and reduce noise on the standardized wound surface image data set to obtain optimized image data;

[0074] The boundary recognition and segmentation module is used to accurately identify and segment the wound boundary based on the optimized image data using a deep learning algorithm to obtain an accurate contour map of the wound surface;

[0075] Parameter measurement and reconstruction module, used to automatically measure the area, length and depth and perform three-dimensional reconstruction based on the precise contour map of the wound surface to obtain the wound surface parameter feature vector;

[0076] Wound type identification and assessment module, used to intelligently identify wound types and assess severity based on wound parameter feature vectors, and obtain a wound classification assessment matrix;

[0077] The matching and consumables prediction module is used to match dressing types and predict consumables based on the wound classification assessment matrix to obtain an accurate dressing change plan;

[0078] The fee calculation and verification module is used to perform personalized fee calculation and transparency verification based on the precise dressing change plan to obtain a dynamic fee model;

[0079] The analysis and file generation module is used to compare historical data and conduct rationality analysis based on the dynamic charging model to obtain a charging rationality assessment report; based on the charging rationality assessment report and the precise dressing change plan, it automatically generates dressing change prescriptions and charging details to obtain a standardized medical service file; each module is connected through wired and / or wireless means to realize data transmission between modules.

[0080] The present invention establishes a wound data foundation through high-definition image acquisition and standardized processing to ensure data quality and consistency, uses advanced image enhancement and noise reduction technologies to improve image quality, creates conditions for accurate identification, and applies deep learning algorithms to achieve accurate identification and segmentation of wound boundaries, overcoming the limitations of traditional manual measurement. Through precise measurement and three-dimensional reconstruction, key parameter characteristics of wounds are obtained, providing a comprehensive quantitative evaluation basis, and combined with machine learning to achieve intelligent discrimination of wound types and severity assessment, forming a scientific classification assessment matrix, and based on the assessment results, accurate dressing type matching and consumables prediction are carried out to achieve accurate allocation of medical resources, build a personalized fee calculation and transparency verification mechanism to ensure the rationality and explainability of charges, and generate standardized medical service files through historical data comparison and rationality analysis to provide support for medical decision-making and quality management.

[0081] In the embodiment of the present invention, the image acquisition and standardization module is used to acquire multi-angle digital images of the wound surface and perform standardization processing to obtain a standardized wound surface image dataset, specifically for:

[0082] A medical-grade high-definition camera under standard light conditions is used to capture multi-angle images of the wound surface to obtain a set of original wound surface images. The original wound surface image set is then subjected to light equalization processing to obtain a light-corrected image.

[0083] Perform color calibration and standard scale embedding on the illumination-corrected image to obtain a scale-normalized image, and perform perspective correction on the scale-normalized image to obtain a perspective-consistent image.

[0084] Performing image resolution unification processing on the perspective consistency image to obtain a normalized image, and annotating metadata on the normalized image to obtain annotated image data;

[0085] Perform spatial registration and multi-angle fusion on the annotated image data to obtain a multi-dimensional view model, and perform image format standardization conversion on the multi-dimensional view model to obtain a standard format image;

[0086] The standard format images are associated with the patient's medical information and stored to obtain a standardized wound image dataset.

[0087] In this embodiment, a medical-grade high-definition camera (with a resolution of not less than 4000×3000 pixels) equipped with a standard color temperature (5500K) LED ring light source is used to collect wound images at a fixed distance and multiple angles (0°, 45°, 90°, etc.) to ensure that the overall appearance and detailed areas of the wound are covered. At the same time, a standard color card and a length reference ruler are placed in the image to form an original wound image group. An adaptive illumination equalization algorithm (such as a Retinex algorithm or a multi-scale adaptive histogram equalization) is applied to the collected original wound image group to eliminate shadows and highlight areas, balance the overall brightness of the image, improve the visibility of dark area details, and generate a lighting-corrected image. Color calibration is performed using the standard color card in the image, and a color management system (CMS) is applied to map the image color to a standard sRGB or Adobe RGB color space to ensure color consistency and accuracy under different devices and lighting conditions. At the same time, the conversion ratio of pixels to actual length is calculated based on the reference ruler in the image, and the standard scale information is embedded in the image metadata to generate a proportional standardized image. Based on the feature points and reference markers in the scale-normalized images, a perspective transformation algorithm is applied to correct the image's perspective. This converts wound images captured from oblique perspectives to a standard, top-down perspective, ensuring consistent viewing angles for images captured at different angles. This generates perspective-consistent images. All perspective-consistent images are resized to a predetermined standard resolution (e.g., 4096 × 3072 pixels). Bicubic interpolation or super-resolution algorithms are applied to ensure image quality. Image cropping and border filling are performed simultaneously to ensure consistent wound position and scale within the image, generating normalized images. Comprehensive metadata annotation is added to the normalized images, including basic patient information (anonymized to protect privacy), acquisition time, device parameters, lighting conditions, viewing angle information, scale data, and a preliminary description of the wound. This metadata is stored in a DICOM or custom XML format to generate annotated image data. Using feature point matching and image registration techniques (such as SIFT, SURF, or ORB algorithms), annotated image data captured from different angles are spatially aligned to establish pixel-level correspondences. Multi-view geometry and image fusion techniques (such as weighted averaging, gradient domain fusion, or wavelet fusion) are then used to integrate the multi-angle image information, generating a multidimensional view model with enhanced detail and stereo information. The multidimensional view model is converted to a standard medical imaging format (such as DICOM) or a universal image format (such as lossless TIFF or PNG) to ensure data compatibility and long-term preservation value, while preserving all metadata and scale information to generate a standardized image format. The standardized image format is then linked to medical information in the patient's electronic medical record system (such as medical history, previous wound treatment records, and relevant laboratory test results). This linked information is stored using secure database technology to ensure data integrity and secure access. Ultimately, a standardized wound image dataset is generated, providing a high-quality data foundation for subsequent analysis.

[0088] In an embodiment of the present invention, the image enhancement and noise reduction processing module is used to perform enhancement and noise reduction processing on a standardized wound surface image dataset to obtain optimized image data, specifically for:

[0089] An adaptive histogram equalization algorithm was applied to the standardized wound surface image dataset to obtain a contrast-enhanced image, and the contrast-enhanced image was subjected to non-local mean filtering to obtain a preliminary denoised image.

[0090] Applying wavelet transform to the preliminary denoised image to remove high-frequency noise to obtain a frequency domain optimized image, and performing edge-preserving smoothing on the frequency domain optimized image to obtain a detail enhanced image;

[0091] Performing image layer analysis on the detail-enhanced image to obtain a layered feature map, and performing targeted image enhancement based on the layered feature map to obtain a feature-highlighted image;

[0092] Applying a deep learning denoising network to the feature-salient image to perform advanced noise removal to obtain a high-quality denoised image, and then performing image quality assessment on the high-quality denoised image to obtain a quality score table;

[0093] The optimal processing parameters are selected based on the quality score table to reprocess the image and obtain optimized image data.

[0094] In this embodiment, the contrast-limited adaptive histogram equalization (CLAHE) algorithm is applied to the standardized wound image dataset. The image contrast is enhanced by local area histogram equalization, while limiting the contrast enhancement amplitude to prevent noise amplification. Different contrast parameters are used for different areas of the wound (such as granulation tissue, necrotic tissue, epithelial tissue, etc.) to enhance the recognizability of various tissues and generate contrast-enhanced images. The non-local mean (NLM) filtering algorithm is applied to the contrast-enhanced image. This algorithm can effectively remove noise while retaining image structure and texture details by searching for similar areas in the image and performing weighted averaging. It is particularly suitable for processing subtle textures and tissue boundaries in wound images. The algorithm parameters (such as search window size and similarity threshold) are automatically adjusted according to the wound type to generate a preliminary denoised image. A multi-scale wavelet transform (such as biorthogonal wavelet or curvelet transform) is applied to the preliminary denoised image to decompose the image into different frequency sub-bands. The soft threshold or hard threshold shrinkage method is applied to the high-frequency sub-band to selectively remove noise while retaining important edge and texture information. The coefficients of the low-frequency sub-band are adjusted to enhance the basic structure, and then the image is reconstructed to generate a frequency domain optimized image. Edge-preserving smoothing algorithms (such as bilateral filtering, guided filtering, or anisotropic diffusion filtering) are applied to the frequency-domain optimized image. These algorithms can smooth homogeneous regions while preserving and enhancing edge information, making them particularly suitable for processing wound boundaries and transition areas between different tissue types. Algorithm parameters (such as spatial and range parameters and number of iterations) are automatically adjusted based on wound characteristics to produce detail-enhanced images. Image layering analysis techniques are applied to the detail-enhanced image. Through color space conversion (such as RGB to HSV or Lab) and clustering algorithms (such as K-means or mean shift), the wound area is divided into different tissue layers (such as granulation layer, fibrin layer, and necrotic layer). Feature descriptors are extracted for each layer to form a layered feature map, which intuitively displays the tissue composition and distribution of the wound. Based on the layered feature map, targeted enhancement processing is applied to different tissue layers, such as enhancing the red channel contrast of granulation tissue, enhancing texture detail in the fibrin layer, and enhancing boundary clarity in necrotic tissue. Color saturation and brightness are also adjusted to highlight tissue differences, generating a feature-enhanced image that makes different tissue types easier to identify and distinguish. Pre-trained deep learning denoising neural networks (such as DnCNN, FFDNet or Noise2Noise architecture) are used to perform advanced noise removal on feature-salient images. These networks are trained on a large number of medical images and can recognize and remove complex noise patterns while retaining medically important detail information. The network parameters are automatically adjusted according to the wound type and image quality to generate high-quality denoised images.A comprehensive image quality assessment is performed on high-quality denoised images, including objective metrics (such as peak signal-to-noise ratio (PSNR), structural similarity index (SSIM), and feature similarity index (FSIM)) and specialized evaluation metrics for medical images (such as diagnostic relevance index, detail preservation, and edge integrity). The comprehensive score reflects the practical value of the image in clinical applications and forms a quality score sheet. Based on the evaluation results in the quality score sheet, an intelligent parameter optimization algorithm (such as Bayesian optimization or genetic algorithm) is used to automatically select the optimal combination of processing parameters, including contrast enhancement parameters, filter strength, wavelet threshold, and edge preservation parameters. The original image is reprocessed to ensure optimal image quality and clinical usability. Ultimately, optimized image data is generated, providing high-quality input data for subsequent wound boundary identification and segmentation.

[0095] In the embodiment of the present invention, see Figure 2 , which is a detailed flowchart of the steps for obtaining an accurate wound contour map. The boundary recognition and segmentation module is used to accurately identify and segment the wound boundary based on the optimized image data using a deep learning algorithm to obtain an accurate wound contour map. Specifically, it is used to:

[0096] Apply a pre-trained convolutional neural network to the optimized image data to perform preliminary positioning of the wound area, obtain a candidate region proposal map, and apply a pixel-level semantic segmentation network to the candidate region proposal map to obtain a preliminary segmentation mask;

[0097] Apply the active contour model to the preliminary segmentation mask to perform boundary refinement to obtain a refined boundary map, and apply the region growing algorithm to the refined boundary map to process the fuzzy boundary area to obtain a complete contour map;

[0098] Apply conditional random fields to optimize spatial consistency of the complete contour map to obtain a spatially optimized contour, and perform multi-scale feature fusion verification on the spatially optimized contour to obtain a verified contour map;

[0099] The verified contour image is corrected according to medical expert knowledge rules to obtain a clinically verified contour, and the boundary coordinates of the clinically verified contour are extracted and vectorized to obtain contour vector data;

[0100] The contour vector data is superimposed on the original image, and boundary marks and measurement reference points are added to obtain an accurate contour map of the wound surface.

[0101] In this embodiment, a pre-trained deep convolutional neural network (such as Faster R-CNN, YOLO v4 or RetinaNet) is used to quickly scan the optimized image data to identify and locate areas that may contain wounds. The network is trained on a large number of annotated wound images and can adapt to wounds of different shapes, sizes and positions. It outputs a rectangular bounding box containing the wound and a confidence score to form a candidate region proposal map. A high-precision pixel-level semantic segmentation network (such as U-Net, DeepLab v3+ or Mask R-CNN) is applied to the candidate region proposal map. These networks are specially designed for medical image segmentation tasks and can classify each pixel and accurately distinguish between wound areas and normal skin. The network uses an encoder-decoder structure and jump connections to retain spatial details and outputs a binary mask of the wound area to form a preliminary segmentation mask. Using the initial segmentation mask as the initialization condition, active contour models (such as the level set method or the Snake algorithm) are applied to refine the boundary. These models use the principle of energy minimization to gradually evolve the contour toward the true wound boundary. While considering image gradients, curvature constraints, and regional statistical properties, they can adapt to complex wound boundary shapes and generate a refined boundary map. For fuzzy or uncertain boundary regions that still exist in the refined boundary map, an adaptive region growing algorithm is applied. Using the determined boundary points as seeds, the region is gradually expanded based on pixel similarity (such as color, texture, and gradient). Algorithm parameters (such as the growing threshold and similarity metric) are automatically adjusted based on local image features to fill boundary gaps and uncertain regions, generating a complete contour map. Conditional random field (CRF) post-processing is applied to the complete contour map to optimize the spatial consistency of the segmentation results. CRF considers the spatial relationship and appearance similarity between pixels, can refine boundary details, eliminate isolated areas and small holes, and is particularly suitable for processing subtle transition areas at the wound edge, generating a spatially optimized contour. The spatially optimized contour is verified using multi-scale feature fusion. Edge detection results (such as Canny, Sobel, or LoG operators) and texture analysis at different resolutions are combined to ensure boundary consistency and accuracy at different scales. Conflicts between scales are resolved through a voting mechanism or weighted fusion, improving the reliability of boundary positioning and generating a verified contour map. The verified contour map is then compared with a medical expert knowledge rule base. A rule-based constraint correction system is applied. These rules include wound morphological features (such as boundary smoothness, concavity, and symmetry), histological characteristics (such as the typical distribution of different tissue types), and clinical experience (such as the common morphology of wounds in specific locations). Based on these rules, boundary regions that do not conform to medical knowledge are adjusted to generate a clinically verified contour.Boundary tracking algorithms (such as contour tracing or boundary chain code extraction) are applied to the clinically verified contour to extract the precise coordinate sequence of the boundary. Then, the Douglas-Peucker algorithm or B-spline curve fitting is used for vectorization processing. This converts the pixel-based boundary into a mathematically described smooth curve, reducing data redundancy while retaining the key features of the boundary, generating contour vector data. The contour vector data is superimposed on the original optimized image and displayed. High-contrast colored lines (such as red or green) are used to mark the wound boundary. Key measurement reference points (such as the two endpoints of the maximum length, characteristic points, and boundary inflection points) are added to the boundary. A dimension ruler and direction indicator are embedded in the image to form a precise wound contour map, which intuitively displays the precise scope and morphological characteristics of the wound, providing a basis for subsequent parameter measurement and three-dimensional reconstruction.

[0102] In an embodiment of the present invention, the parameter measurement and reconstruction module is used to automatically measure the area, length, and depth and perform three-dimensional reconstruction based on the precise contour map of the wound surface to obtain the wound surface parameter feature vector, specifically for:

[0103] The pixel area of ​​the wound surface is calculated based on the precise contour map of the wound surface and converted into the actual area using the scale to obtain the precise area data. The length of the wound surface is measured along the maximum extension direction of the wound surface to obtain the length parameter.

[0104] Using multi-angle image information to construct a wound depth map, obtain a depth distribution map, and calculate the average depth and maximum depth of the wound based on the depth distribution map to obtain a depth parameter set;

[0105] A three-dimensional mesh model of the wound surface is constructed based on the precise contour map of the wound surface and the depth parameter set to obtain a three-dimensional wound surface model, and the volume and surface area of ​​the three-dimensional wound surface model are calculated to obtain three-dimensional parameter data;

[0106] Perform morphological analysis on the precise contour map of the wound surface, extract morphological features such as perimeter, ellipticity, and complexity, and obtain a morphological feature set. Furthermore, perform tissue type identification and area ratio analysis on the wound surface to obtain tissue feature data.

[0107] The precise area data, length parameters, depth parameter set, three-dimensional parameter data, morphological feature set and tissue feature data are integrated to obtain the wound surface parameter feature vector.

[0108] In this embodiment, a pixel counting method is used to calculate the total number of pixels contained in the wound contour, and then the number of pixels is converted into an actual area (square centimeters or square millimeters) in combination with the standard scale in the image (embedded through the previous standardization process). The conversion process takes into account the angle correction between the image plane and the wound surface to ensure the accuracy of the measurement and generate accurate area data. The two farthest points on the wound contour are identified as the endpoints of the long axis, the Euclidean distance between the two points is calculated, and the actual length (centimeter or millimeter) is converted in combination with the scale. At the same time, the maximum width perpendicular to the long axis is identified and the aspect ratio is calculated. These measurement results constitute the length parameter. Using wound images taken from different angles, stereo vision technology (such as structured light, binocular stereo matching or multi-view stereo reconstruction) is applied to construct the depth information of the wound. The algorithm calculates the relative depth of each pixel by identifying the parallax of the corresponding points, and generates a depth distribution map representing the three-dimensional morphology of the wound. Based on the depth distribution map, the average depth, maximum depth, depth standard deviation and depth distribution histogram of the wound are calculated. These indicators comprehensively describe the depth characteristics of the wound, which are of great significance for assessing the severity of the wound and the difficulty of treatment, forming a depth parameter set. Combining the precise wound contour image and the depth parameter set, a 3D surface reconstruction algorithm (such as Poisson surface reconstruction, Malchn cube, or level set method) is applied to construct a 3D mesh model of the wound surface. This model uses a triangular or quadrilateral mesh to represent the geometric shape of the wound surface, including accurate depth variations and surface relief, generating a 3D wound model. Computational geometry algorithms are then applied to the 3D wound model to calculate the wound volume (cubic centimeters or cubic millimeters) and actual surface area (square centimeters or square millimeters, accounting for surface curvature and relief). These parameters more accurately reflect the true size of the wound than the planar projection area, particularly for wounds with uneven depth, generating three-dimensional parameter data. Morphological analysis of the precise wound contour image is performed using digital image processing techniques to calculate perimeter (actual length of the contour), circularity (similarity to a circle of equal area), ellipticity (similarity to a best-fit ellipse), convexity (ratio to its convex hull), irregularity (fractal dimension of the boundary), and complexity (standard deviation of the variation in boundary curvature). These parameters quantitatively describe the shape characteristics of the wound surface, forming a morphological feature set. A deep learning image segmentation network (such as FCN, SegNet or DeepLab) is used to identify tissue types inside the wound, divide the wound area into different tissue types (such as granulation tissue, fibrin tissue, necrotic tissue, epithelial tissue, etc.), calculate the area of ​​each type of tissue and the percentage of the total area, and analyze the tissue distribution pattern and boundary characteristics. This information is crucial for evaluating the wound healing stage and formulating treatment plans, and forms tissue feature data.The precise area data, length parameters, depth parameter set, three-dimensional parameter data, morphological feature set and tissue feature data are integrated into a unified data structure to form a wound parameter feature vector that comprehensively describes the geometry and tissue characteristics of the wound. This vector contains quantitative measurement results and qualitative feature descriptions, providing a scientific basis for subsequent wound type discrimination and severity assessment.

[0109] In an embodiment of the present invention, the wound type discrimination and assessment module is used to perform intelligent wound type discrimination and severity assessment based on the wound parameter feature vector to obtain a wound classification assessment matrix, which is specifically used to:

[0110] Apply a multi-classification machine learning algorithm to the wound parameter feature vector to obtain preliminary wound type identification results. Based on the preliminary wound type identification results, the wound type knowledge base is queried to obtain the standard wound type definition.

[0111] The wound severity score is calculated based on the standard wound type definition and wound parameter characteristic vector to obtain the severity assessment index. The healing difficulty is predicted based on the severity assessment index to obtain a healing assessment report.

[0112] Perform anomaly detection on the wound parameter feature vector to identify special wound types, obtain special type tags, and set processing priority weights according to the special type tags to obtain a priority coefficient table;

[0113] Map the severity assessment index, healing assessment report, and priority coefficient table with the clinical treatment guideline rule set to obtain a clinical intervention recommendation list, and determine the required dressing change resource level based on the clinical intervention recommendation list to obtain a resource requirement table;

[0114] The standard wound type definitions, severity assessment indicators, healing assessment reports, priority coefficient tables, and resource requirement tables were integrated to obtain a wound classification assessment matrix.

[0115] In this embodiment, the wound parameter feature vector is input into a multi-classification machine learning model (such as random forest, support vector machine, gradient boosting decision tree or deep neural network) that has been trained on a large number of clinical cases. The model identifies the type of wound according to the pattern of the feature vector, such as pressure injury, diabetic foot ulcer, venous ulcer, arterial ulcer, mixed ulcer, burn wound, etc., and outputs the probability distribution and confidence score of each type to form a preliminary identification result of the wound type. The preliminary identification result of the wound type is matched with the wound type knowledge base built into the system. The knowledge base contains structured information such as standard definitions, typical characteristics, pathogenesis, evolution laws and common complications of various types of wounds, which is maintained and updated by medical experts. The query result outputs the standard wound type definition that best matches the current wound, including precise medical term descriptions and ICD codes. Based on standard wound type definitions and wound parameter feature vectors, professional scoring systems (such as the Wagner classification, NPUAP classification, PUSH score, or DESIGN-R score) are used to calculate wound severity scores. The scoring system selects appropriate assessment criteria based on wound type, taking into account factors such as area, depth, tissue type, infection status, and exudate volume, to generate standardized severity assessment indicators, including numerical scores and grading results. Based on the severity assessment indicators and wound parameter feature vectors, machine learning prediction models (such as survival analysis models, Cox proportional hazards models, or deep learning time-series prediction models) are used to predict wound healing difficulty and healing time. The models are trained based on historical wound healing data and take into account factors such as wound characteristics, patient basic conditions, and treatment plans. They output a healing difficulty rating, estimated healing time, and healing risk factor analysis to form a healing assessment report. Anomaly detection algorithms (such as isolation forests, single-class support vector machines, or autoencoder reconstruction error detection) are applied to the wound parameter feature vectors to identify abnormal features that do not conform to common wound patterns, such as signs of malignant transformation, rare lesion characteristics, and unique manifestations of infection. These features may indicate that the wound requires special treatment or specialist consultation. The detection results output a description of the abnormal features and a quantitative score of the degree of abnormality, forming a special type marker. Based on the special type marker and severity assessment indicators, priority weights for wound treatment are set. The weights take into account factors such as wound urgency (such as infection risk and deterioration rate), treatment sensitivity, and resource requirements. A multi-criteria decision-making method is used to calculate a comprehensive priority score, forming a priority coefficient table to guide the rational allocation of medical resources. The severity assessment indicators, healing assessment report, and priority coefficient table are mapped and matched to a set of clinical treatment guideline rules, which contains evidence-based wound management guidelines and best practice recommendations. Based on the current wound characteristics and assessment results, the system automatically matches applicable clinical intervention measures, including debridement methods, dressing material selection, antibiotic use recommendations, and follow-up frequency, to form a list of clinical intervention recommendations.Based on the clinical intervention recommendation list, the system analyzes the required medical resource levels, including the professional level requirements for medical staff, special equipment needs, types and quantities of consumables, and estimated treatment times. Based on the complexity and specialization of resource requirements, the system classifies and quantifies resource requirements to form a resource requirement table, which provides a basis for subsequent dressing plan design and cost estimation. Standard wound type definitions, severity assessment indicators, healing assessment reports, priority coefficient tables, and resource requirement tables are integrated into a multidimensional data structure to construct a wound classification assessment matrix. This matrix comprehensively describes wound type, severity, healing expectations, treatment priorities, and resource requirements, providing a scientific basis for precision medicine decision-making.

[0116] In an embodiment of the present invention, the matching and consumables prediction module is used to match dressing types and predict consumables based on the wound classification assessment matrix to obtain an accurate dressing change plan, specifically for:

[0117] Automatically determine the dressing change type based on the area, length, and depth data of the wound classification assessment matrix to obtain a preliminary dressing change type judgment result. Based on the preliminary dressing change type judgment result, query the standard dressing change type definition library to obtain the standard dressing change specification.

[0118] Perform a secondary assessment of the tissue characteristics and severity assessment indicators in the wound classification assessment matrix to obtain an auxiliary assessment correction result, which is then integrated with the initial dressing type assessment result to obtain the final dressing type confirmation.

[0119] Predict the types and quantities of medical consumables required based on the final dressing change type confirmation and wound classification assessment matrix, obtain an estimated consumables list, and calculate the consumables cost based on the estimated consumables list to obtain material cost accounting data;

[0120] Based on the final dressing change type, the required medical staff hours and professional level are predicted to obtain the human resource demand forecast. The labor cost is calculated based on the human resource demand forecast to obtain the labor cost accounting data;

[0121] Integrate material cost accounting data, labor cost accounting data and final dressing change type confirmation to obtain an accurate dressing change plan.

[0122] In the present embodiment, the area, length and depth data in the wound classification assessment matrix are analyzed, and the decision tree algorithm is applied to automatically determine the applicable dressing change type level, such as simple dressing change, complex dressing change, special dressing change, etc. The judgment standard is based on the standardized dressing change classification system of the medical institution, taking into account factors such as wound size, depth and complexity, and outputting the dressing change type preliminary judgment result, including dressing change type code and preliminary description. The dressing change type preliminary judgment result is matched with the standard dressing change type definition library built into the system, and the definition library contains the standard specifications, technical requirements, applicable conditions and operating procedures of various types of dressing change operations, and is regularly updated and maintained by medical professionals. The query result outputs the standard dressing change specification that best matches the current wound, and provides standardized guidance for subsequent disposal. Further analyze the tissue characteristics (such as granulation tissue ratio, necrotic tissue presence, infection signs) and severity assessment indicators in the wound classification assessment matrix, and apply a rule-based expert system for secondary judgment. The expert system contains a large amount of judgment rules summarized by clinical experience, and can identify the wound condition that needs special treatment (such as needing debridement, antibiotic treatment or special dressing), and outputs the correction suggestions to the preliminary judgment result, forming an auxiliary judgment correction result. The revised results of the auxiliary determination are integrated with the initial dressing change type determination using a weighted fusion method. The weight allocation considers the clinical importance and predictive reliability of each indicator, resolving potential conflicts and forming a consistent judgment. Ultimately, the dressing change type most suitable for the current wound condition is determined, including detailed information on the procedure type, required technical level, and special precautions, forming the final dressing change type confirmation. Based on the final dressing change type confirmation and the wound classification assessment matrix (particularly area, depth, and tissue characteristic data), a prediction algorithm is applied to estimate the type and quantity of required medical consumables, including cleaning solutions, disinfectants, dressings (such as alginate dressings, hydrocolloid dressings, foam dressings, and silver ion dressings), fixation materials (such as tapes and bandages), and auxiliary supplies (such as gloves, instruments, and containers). The prediction algorithm is trained on historical dressing change records and considers the correlation between wound characteristics and dressing change types to generate an estimated consumables list, detailing the name, specifications, and quantity of each type of consumable. Based on the estimated consumables list and the medical institution's consumables price database, the total consumables cost required for the dressing change process is calculated, including the cost of basic consumables, special dressings, and auxiliary materials. Discounts for bulk use and the impact of packaging specifications are also taken into account to generate detailed material cost accounting data, providing a basis for charge calculations. Based on the final dressing change type confirmation and wound complexity, the required medical staff man-hours and professional level requirements are predicted to complete the dressing change operation. The man-hour forecast takes into account the complexity of wound treatment, the number of steps, and special treatment requirements. The professional level requirements take into account the technical difficulty and risk level. The forecast results output the required nurse / doctor level (e.g., junior nurse, senior nurse, specialist), number of people, and estimated working hours to form a human resource demand forecast.Based on human resource demand forecasts and the medical institution's labor cost standards, the labor costs of the dressing change process are calculated, including basic operating fees, technical difficulty surcharges, and special period fees (such as nighttime and holiday surcharges). At the same time, the differentiated charging standards of medical staff at different levels are taken into consideration to form labor cost accounting data, providing a complete basis for total cost calculation. The material cost accounting data and labor cost accounting data are integrated with the final dressing change type confirmation into a unified data structure to construct a precise dressing change plan. This plan includes a detailed description of the dressing change type, operating process guidance, a list of required consumables, human resource allocation recommendations, and cost structure analysis. This provides comprehensive dressing change guidance for medical staff and a scientific basis for fee calculation.

[0123] In an embodiment of the present invention, the fee calculation and verification module is used to perform personalized fee calculation and transparency verification based on the precise dressing change plan to obtain a dynamic fee model, which is specifically used to:

[0124] The basic charge is calculated based on the dressing change type and consumables cost in the precise dressing change plan to obtain the basic charge standard. The complexity adjustment coefficient is calculated based on the complexity index in the wound classification assessment matrix to obtain the adjusted charge.

[0125] Apply medical insurance policy rules and regional differences to the adjusted charges to obtain regionalized charging standards, and make personalized adjustments based on the regionalized charging standards and the patient's special circumstances to obtain a personalized charging plan;

[0126] Conduct a cost-benefit analysis on the personalized charging plan to obtain a cost-benefit evaluation report, and build a charging fairness verification mechanism based on the cost-benefit evaluation report to obtain fairness verification results;

[0127] Generate a detailed fee explanation document based on the fairness verification results to obtain a fee transparency document. Design a patient-friendly fee explanation interface based on the fee transparency document to obtain a visual fee explanation.

[0128] Integrate personalized charging plans, cost-benefit assessment reports and charging transparency documents to build a dynamic charging model.

[0129] In this embodiment, based on the dressing change type (such as simple dressing change, complex dressing change, special dressing change) and detailed consumables cost data in the precise dressing change plan, the standard charging rules of the medical institution are applied to calculate the basic charging amount. The basic charge includes basic operating fees, consumables fees and basic technical fees. The calculation process follows the medical service price management regulations to ensure the compliance and integrity of the charging items and form a basic charging standard. The complexity indicators in the wound classification assessment matrix, such as wound depth, tissue complexity, infection status and special site coefficient, are analyzed, and the weighted calculation method is applied to determine the complexity adjustment coefficient. The coefficient reflects the impact of the difficulty of wound treatment on the charge. The adjustment coefficient is applied to the technical fee part of the basic charge to generate an adjusted charge, reflecting the technical value of the medical service. The adjusted charge is matched with the local medical insurance policy rule library, and the medical insurance reimbursement rules (such as reimbursement ratio, maximum limit, special material policy) and regional difference adjustment parameters (such as regional medical service price index) are applied for calculation to ensure that the charge meets the medical insurance policy requirements and the regional medical price level, and outputs a regionalized charging standard that meets local standards. Based on the specific circumstances of patients (such as those with chronic diseases, elderly patients, low-income groups, and special populations) and the special policies of medical institutions (such as medical assistance, preferential policies, and membership systems), personalized adjustment rules are applied to make targeted adjustments to regionalized charging standards to ensure that charges comply with regulations and take into account the actual conditions of patients, thus forming a personalized charging plan. A cost-effectiveness analysis is conducted on the personalized charging plan, calculating the cost recovery rate, profit margin, and sustainability indicators of medical services. At the same time, the cost-effectiveness ratio between patient affordability and expected treatment effects is evaluated. The analysis results include cost structure analysis, benefit forecasting, and long-term economic impact assessment, forming a cost-effectiveness evaluation report to provide an economic basis for the rationality of charging. Based on the cost-effectiveness evaluation report, a multi-dimensional charging fairness verification mechanism is constructed. Through methods such as horizontal comparison (comparison with charges for similar services of similar medical institutions), vertical comparison (comparison with historical charging standard trends), and internal consistency testing (analysis of differences in charges for similar services of different patients), the fairness and rationality of charges are comprehensively evaluated. The verification results output fairness scores and potential problem analysis, forming fairness verification results. Based on the fairness verification results, a detailed fee explanation document is generated. The document includes a detailed list of fee items, calculation basis, adjustment factors, and policy references. It uses a clear structure and professional but easy-to-understand language to ensure the transparency and explainability of the charging process, forming a fee transparency document that provides detailed basis for patients to understand the charges. Based on the fee transparency document, an intuitive and easy-to-understand patient-friendly fee explanation interface is designed. The interface uses graphical displays (such as pie charts and bar charts), comparative analysis, and concise explanations to convert professional medical terms into easy-to-understand expressions, highlight key fee items and adjustment factors, and form a visual fee explanation to help patients clearly understand the fee structure.Integrate personalized charging plans, cost-effectiveness assessment reports and charging transparency documents into a unified data model to build a dynamic charging model. This model can update charging estimates in real time based on factors such as changes in wound conditions, treatment progress and policy adjustments, providing medical institutions and patients with accurate, transparent and reasonable charging references, while providing data support for medical management decisions.

[0130] In an embodiment of the present invention, the analysis and file generation module is used to compare historical data and conduct rationality analysis based on a dynamic charging model to obtain a charging rationality assessment report; based on the charging rationality assessment report and the precise dressing change plan, the dressing change prescription and charging details are automatically generated to obtain a standardized medical service file, which is specifically used to:

[0131] The dynamic charging model was compared and analyzed with the historical charging data of similar wounds to obtain longitudinal comparison results, and the horizontal comparison results were obtained by comparing the charging of similar services of medical institutions in the same region;

[0132] Based on the longitudinal and transverse comparison results, the charging deviation index is calculated to obtain a charging deviation evaluation table, and rationality evaluation criteria are established based on the charging deviation evaluation table to obtain a rationality evaluation framework;

[0133] Use the rationality evaluation framework to evaluate the dynamic charging model, obtain the charging rationality analysis results, and form charging recommendations based on the charging rationality analysis results to obtain a charging rationality evaluation report;

[0134] Based on the fee rationality evaluation report, the optimal fee plan is selected to obtain the final fee decision. Based on the final fee decision and the precise medication change plan, a standardized electronic prescription is automatically generated to obtain electronic prescription data.

[0135] The electronic prescription data, wound parameter characteristic vectors, wound classification assessment matrix, precise dressing change plan and charging rationality assessment report are integrated and archived to obtain a standardized medical service file, which includes wound assessment records, dressing change plan, charging basis and disposal recommendations.

[0136] In this embodiment, historical charging records of similar wounds (similar in type, severity and treatment method) are extracted from the medical database, and the time series analysis method is used to compare the consistency of the current dynamic charging model with the historical charging trend, analyze the rationality and influencing factors of the charging changes, output the charging change rate, deviation and change reason analysis, and form a longitudinal comparison result. Collect charging data of similar wound treatment services provided by other medical institutions in the same region (such as the same city or the same province), apply statistical analysis methods to compare the differences in charging levels between institutions, consider the influence of factors such as the grade of medical institutions, service quality and geographical location, output relative charging levels, market positioning and competitiveness analysis, and form a horizontal comparison result. Based on the longitudinal comparison results and the horizontal comparison results, calculate the charging deviation index, which quantifies the degree of deviation of the current charging plan from historical trends and market levels. The index calculation takes into account time factors (such as inflation, policy changes) and spatial factors (such as regional differences, institutional characteristics), and analyzes the composition and main sources of the deviation at the same time to form a charging deviation evaluation table to intuitively display the relative position of the charges. Based on the fee deviation assessment table and medical service pricing theory, a scientific rationality assessment standard was established. The standard encompasses the principles of cost coverage, value reflection, affordability, and sustainability. Quantitative indicators and acceptable ranges were set for each dimension, forming a rationality assessment framework to provide an objective basis for assessing fee rationality. The rationality assessment framework was applied to conduct a multi-dimensional assessment of the dynamic fee model, calculating scores for each indicator and an overall rationality score, identifying potential unreasonable factors and areas for improvement. The assessment results included a detailed indicator analysis and problem diagnosis, resulting in a fee rationality analysis. Based on the fee rationality analysis results, targeted fee adjustment recommendations were generated, including the direction, magnitude, and rationale for the adjustments. The recommendations also considered implementation feasibility and impact projections, resulting in a systematic fee rationality assessment report to provide professional support for fee decision-making. Based on the recommendations and analysis in the fee rationality assessment report, an optimal fee plan was selected that balanced medical institution cost recovery, patient affordability, and medical insurance policy requirements. This plan selection employed a multi-objective decision-making approach, considering the balance of interests and long-term sustainability. The final fee decision was made, and the actual fee standards and items to be implemented were determined. Based on the final charging decision and precise dressing change plan, a standardized electronic prescription that complies with medical standards is automatically generated. The prescription contains basic patient information, wound diagnosis results, treatment plan details, details of the drugs and consumables used, key operating points and precautions, etc. Standard medical terminology and coding are used to ensure the standardization and enforceability of the prescription, generate electronic prescription data, and provide direct guidance for clinical implementation.The electronic prescription data is systematically integrated with the previously generated wound parameter characteristic vectors, wound classification assessment matrix, precise dressing change plan and charging rationality assessment report to construct a structured medical service file. The file adopts a standardized data format and organizational structure to ensure the integrity, consistency and traceability of the information. It contains a complete wound assessment record, a detailed dressing change plan, a transparent charging basis and scientific disposal recommendations, forming a standardized medical service file to provide a comprehensive basis for patient management, medical quality control and medical insurance review.

[0137] In an embodiment of the present invention, standardized wound image data sets, optimized image data, precise wound contour maps, wound parameter feature vectors, wound classification assessment matrices, precise dressing change plans, dynamic charging models, charging rationality assessment reports, and standardized medical service files are all stored in a secure medical data platform, forming a complete wound treatment information chain. The wound treatment information chain uses blockchain technology to ensure data integrity and non-tamperability. The secure medical data platform is equipped with a hierarchical access control mechanism to protect patient privacy and data security.

[0138] In this embodiment, a dedicated secure medical data platform is established, utilizing a high-performance server cluster and distributed storage architecture to ensure efficient data processing and reliable storage. The platform is equipped with comprehensive network security protection measures, including firewalls, intrusion detection systems, and security audit systems, to prevent unauthorized access and data leakage. All system-generated data is stored on this platform, including standardized wound image datasets, optimized image data, precise wound contour maps, wound parameter feature vectors, wound classification assessment matrices, precise dressing change plans, dynamic charging models, charging rationality assessment reports, and standardized medical service archives. This data is organized in a standardized format to form a complete wound management information chain, enabling data connectivity throughout the entire process from image acquisition to charging management. Blockchain technology is applied to securely manage the wound management information chain. Each data processing step and result forms a block, which is linked cryptographically to form an immutable blockchain. Each operation and modification is recorded on the blockchain with a timestamp and operator identification, ensuring data integrity, authenticity, and traceability, and preventing illegal modification or falsification of data. This is particularly suitable for the security management needs of medical data. A strict hierarchical access control mechanism is implemented on the secure medical data platform, and different data access rights are assigned according to user roles (such as doctors, nurses, managers, patients) and scope of responsibilities to ensure that users can only access the minimum data set required for their duties. All access operations are subject to strict identity authentication (such as multi-factor authentication) and behavioral audits. The system automatically records all data access and operation logs, conducts regular security audits, and promptly detects and handles abnormal access behaviors to fully protect patient privacy and data security.

[0139] The present invention acquires high-quality wound image data through standardized image acquisition and processing procedures, applies deep learning algorithms to achieve accurate identification and segmentation of wound boundaries, performs automatic measurement and three-dimensional reconstruction of wound parameters, discriminates wound types and assesses severity based on multi-dimensional features, achieves accurate dressing change plan matching and consumables prediction, builds a transparent and reasonable dynamic charging model, and generates standardized medical service files. The entire process forms a complete information chain, and blockchain technology is used to ensure data security and non-tamperability.

[0140] The foregoing description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art will be able to modify the technical solutions described in the foregoing embodiments or to substitute equivalents for some of the technical features. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention shall be included within the scope of protection of the present invention.

[0141] It should be noted that, in this document, the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus. In the absence of further limitations, an element defined by the phrase "comprising a..." does not exclude the presence of additional identical elements in the process, method, article, or apparatus that includes the element.

[0142] In the description of the present invention, it should be understood that the terms "first", "second", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0143] In the description of the present invention, unless otherwise specified, "plurality" means two or more.

[0144] In the description of the present invention, "several" means one or more, and "a large number" means two or more.

[0145] Throughout this specification, reference to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples" means that a specific feature, structure, material, or characteristic described in conjunction with that embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

[0146] The formulas in this manual are all dimensionless and calculated using numerical values. The formulas are obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters and thresholds in the formulas are set by technicians in this field based on actual conditions.

[0147] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to the embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the claims and their equivalents.

Claims

1. A wound surface identification and charging system based on precision medicine, characterized in that: include: Image acquisition and standardization module, used to collect multi-angle digital images of the wound surface and perform standardization processing to obtain a standardized image data set of the wound surface; An image enhancement and noise reduction processing module is used to perform enhancement and noise reduction processing on the standardized wound surface image dataset to obtain optimized image data; A boundary recognition and segmentation module is used to apply a deep learning algorithm based on the optimized image data to accurately identify and segment the wound boundary to obtain an accurate contour map of the wound surface; A parameter measurement and reconstruction module is used to automatically measure the area, length and depth and perform three-dimensional reconstruction based on the precise contour map of the wound surface to obtain a wound surface parameter feature vector; A wound type identification and assessment module is used to perform intelligent identification of wound types and severity assessment based on the wound parameter feature vector to obtain a wound classification assessment matrix; A matching and consumables prediction module is used to match dressing types and predict consumables based on the wound classification assessment matrix to obtain an accurate dressing change plan; A charge calculation and verification module, for performing personalized charge calculation and transparency verification based on the precise dressing change plan to obtain a dynamic charge model; The analysis and file generation module is used to compare historical data and conduct rationality analysis based on the dynamic charging model to obtain a charging rationality evaluation report; based on the charging rationality evaluation report and the precise dressing change plan, the dressing change prescription and charging details are automatically generated to obtain a standardized medical service file. The various modules are connected by wired and / or wireless means.

2. The wound surface identification and charging system based on precision medicine according to claim 1 is characterized in that: The method of collecting multi-angle digital images of the wound surface and performing standardization processing to obtain a standardized wound surface image dataset includes: Using a medical-grade high-definition camera under standard light conditions to capture multi-angle images of the wound surface to obtain an original wound surface image group, and performing light equalization processing on the original wound surface image group to obtain a light-corrected image; Performing color calibration and standard scale embedding on the illumination-corrected image to obtain a scale-standardized image, and performing perspective correction on the scale-standardized image to obtain a perspective-consistent image; performing image resolution unification processing on the perspective consistency image to obtain a normalized image, and performing metadata annotation on the normalized image to obtain annotated image data; Performing spatial registration and multi-angle fusion on the annotated image data to obtain a multi-dimensional view model, and performing image format standardization conversion on the multi-dimensional view model to obtain a standard format image; The standard format images are associated with the patient's medical information and stored to obtain a standardized wound surface image dataset.

3. The wound surface identification and charging system based on precision medicine according to claim 2 is characterized in that: The step of performing enhancement and noise reduction processing on the standardized wound surface image dataset to obtain optimized image data includes: applying an adaptive histogram equalization algorithm to the standardized wound image dataset to obtain a contrast-enhanced image, and performing non-local means filtering on the contrast-enhanced image to obtain a preliminary noise-reduced image; Applying wavelet transform to the preliminary denoised image to remove high-frequency noise to obtain a frequency domain optimized image, and performing edge-preserving smoothing on the frequency domain optimized image to obtain a detail-enhanced image; Performing image layer analysis on the detail-enhanced image to obtain a layered feature map, and performing targeted image enhancement based on the layered feature map to obtain a feature-highlighted image; Applying a deep learning denoising network to the feature-salient image to perform advanced noise removal to obtain a high-quality denoised image, and performing image quality assessment on the high-quality denoised image to obtain a quality score table; The optimal processing parameters are selected based on the quality score table to reprocess the image and obtain optimized image data.

4. The wound surface identification and charging system based on precision medicine according to claim 3 is characterized in that: The method of applying a deep learning algorithm based on the optimized image data to accurately identify and segment the wound boundary to obtain an accurate outline of the wound includes: Applying a pre-trained convolutional neural network to the optimized image data to perform preliminary positioning of the wound area to obtain a candidate region proposal map, and applying a pixel-level semantic segmentation network to the candidate region proposal map to obtain a preliminary segmentation mask; Applying an active contour model to the preliminary segmentation mask to perform boundary refinement adjustment to obtain a refined boundary map, and applying a region growing algorithm to the refined boundary map to process fuzzy boundary areas to obtain a complete contour map; Applying a conditional random field to optimize spatial consistency of the complete contour map to obtain a spatially optimized contour, and performing multi-scale feature fusion verification on the spatially optimized contour to obtain a verified contour map; Performing medical expert knowledge rule constraint correction on the verified contour image to obtain a clinically verified contour, and performing boundary coordinate extraction and vectorization processing on the clinically verified contour to obtain contour vector data; The contour vector data is superimposed on the original image and displayed, and boundary marks and measurement reference points are added to obtain an accurate contour map of the wound surface.

5. The wound surface identification and charging system based on precision medicine according to claim 4 is characterized in that: The automatic measurement and three-dimensional reconstruction of the area, length and depth based on the precise contour map of the wound surface to obtain the wound surface parameter feature vector includes: Calculating the pixel area of ​​the wound based on the precise wound contour map and converting it into the actual area using a scale to obtain precise area data, and measuring the length of the wound along the maximum extension direction of the wound to obtain a length parameter; Constructing a wound depth map using multi-angle image information to obtain a depth distribution map, and calculating the average depth and maximum depth of the wound based on the depth distribution map to obtain a depth parameter set; constructing a three-dimensional mesh model of the wound surface based on the precise wound surface contour map and the depth parameter set to obtain a three-dimensional wound surface model, and calculating the volume and surface area of ​​the three-dimensional wound surface model to obtain three-dimensional parameter data; Performing morphological analysis on the precise wound contour map to extract morphological features such as perimeter, ellipticity, and complexity to obtain a morphological feature set, and performing tissue type identification and area ratio analysis on the interior of the wound to obtain tissue feature data; The precise area data, the length parameter, the depth parameter set, the three-dimensional parameter data, the morphological feature set and the tissue feature data are integrated to obtain a wound surface parameter feature vector.

6. The wound surface identification and charging system based on precision medicine according to claim 5 is characterized in that: The intelligent identification of wound types and severity assessment based on the wound parameter feature vector are performed to obtain a wound classification assessment matrix, including: Applying a multi-classification machine learning algorithm to the wound parameter feature vector to obtain a preliminary wound type discrimination result, and querying a wound type knowledge base based on the preliminary wound type discrimination result to obtain a standard wound type definition; Calculating a wound severity score based on the standard wound type definition and the wound parameter characteristic vector to obtain a severity assessment index, and predicting healing difficulty based on the severity assessment index to obtain a healing assessment report; performing abnormality detection on the wound parameter feature vector to identify special wound types, obtaining special type tags, and setting processing priority weights based on the special type tags to obtain a priority coefficient table; mapping the severity assessment index, the healing assessment report, and the priority coefficient table with a clinical treatment guideline rule set to obtain a clinical intervention recommendation list, and determining the required dressing change resource level based on the clinical intervention recommendation list to obtain a resource requirement table; The standard wound type definitions, the severity assessment indicators, the healing assessment report, the priority coefficient table and the resource requirement table are integrated to obtain a wound classification assessment matrix.

7. The wound surface identification and charging system based on precision medicine according to claim 6 is characterized in that: The dressing change type matching and consumables prediction based on the wound classification assessment matrix are performed to obtain an accurate dressing change plan, including: Automatically determining the dressing change type based on the area, length, and depth data of the wound classification assessment matrix to obtain a preliminary dressing change type determination result, and querying a standard dressing change type definition library based on the preliminary dressing change type determination result to obtain a standard dressing change specification; Performing a secondary determination on the tissue characteristics and severity assessment indicators in the wound classification assessment matrix to obtain an auxiliary determination correction result, and integrating the auxiliary determination correction result with the initial dressing change type determination result to obtain a final dressing change type confirmation; Predicting the types and quantities of medical consumables required based on the final dressing change type confirmation and the wound classification assessment matrix, obtaining a consumables list estimate table, and calculating consumables costs based on the consumables list estimate table to obtain material cost accounting data; Based on the final dressing change type, the required medical staff hours and professional level are confirmed and predicted to obtain a human resource demand forecast, and the labor cost is calculated based on the human resource demand forecast to obtain labor cost accounting data; The material cost accounting data, the labor cost accounting data and the final dressing change type are confirmed and integrated to obtain an accurate dressing change plan.

8. The wound surface identification and charging system based on precision medicine according to claim 7 is characterized in that: The personalized charging calculation and transparency verification based on the precise dressing change plan to obtain a dynamic charging model includes: Calculating a basic charge based on the dressing change type and consumables cost in the precise dressing change plan to obtain a basic charging standard, and calculating a complexity adjustment coefficient based on the complexity index in the wound classification assessment matrix to obtain an adjusted charge; Applying medical insurance policy rules and regional differences to the adjusted charges to obtain regionalized charging standards, and making personalized adjustments based on the regionalized charging standards and the patient's special circumstances to obtain a personalized charging plan; Conducting a cost-benefit analysis on the personalized charging plan to obtain a cost-benefit evaluation report, and constructing a charging fairness verification mechanism based on the cost-benefit evaluation report to obtain a fairness verification result; generating a charging detailed explanation document based on the fairness verification result to obtain a charging transparency document, and designing a patient-friendly charging explanation interface based on the charging transparency document to obtain a visual charging explanation; The personalized charging plan, the cost-benefit evaluation report and the charging transparency document are integrated to construct a dynamic charging model.

9. The wound surface identification and charging system based on precision medicine according to claim 8 is characterized in that: The dynamic charging model is used to compare historical data and conduct rationality analysis to obtain a charging rationality assessment report; based on the charging rationality assessment report and the precise dressing change plan, a dressing change prescription and charging details are automatically generated to obtain a standardized medical service file, including: Compare and analyze the dynamic charging model with historical charging data of similar wounds to obtain longitudinal comparison results, and compare it with the charges of similar services of medical institutions in the same region to obtain horizontal comparison results; Calculating a charging deviation index based on the vertical comparison results and the horizontal comparison results to obtain a charging deviation evaluation table, and establishing a rationality evaluation standard based on the charging deviation evaluation table to obtain a rationality evaluation framework; The dynamic charging model is evaluated using the rationality evaluation framework to obtain a charging rationality analysis result, and a charging recommendation is formed based on the charging rationality analysis result to obtain a charging rationality evaluation report; Selecting an optimal charging plan based on the charging rationality evaluation report to obtain a final charging decision, and automatically generating a standardized electronic prescription based on the final charging decision and the precise medication change plan to obtain electronic prescription data; The electronic prescription data, the wound parameter characteristic vector, the wound classification assessment matrix, the precise dressing change plan and the charging rationality assessment report are integrated and archived to obtain a standardized medical service file, which includes wound assessment records, dressing change plans, charging basis and disposal recommendations.

10. The wound surface identification and charging system based on precision medicine according to claim 9 is characterized in that: The standardized wound image dataset, the optimized image data, the precise wound contour map, the wound parameter characteristic vector, the wound classification assessment matrix, the precise dressing change plan, the dynamic charging model, the charging rationality assessment report and the standardized medical service file are all stored in a secure medical data platform, forming a complete wound treatment information chain. The wound treatment information chain ensures data integrity and non-tamperability through blockchain technology, and the secure medical data platform is equipped with a hierarchical access control mechanism.

Images