Stoma surrounding skin AI evaluation method based on DET evaluation scale

Abstract

The invention relates to a DET evaluation scale-based ostomy surrounding skin AI evaluation method, which is characterized in that ostomy surrounding skin images corresponding to D, E and T are acquired and feature training is carried out based on a DET evaluation scale mode, so that an ostomy surrounding skin AI model based on a DET evaluation scale is constructed and is used for intelligent identification of ostomy skin; the DET features in the image of the skin around the stoma can be intelligently recognized, and the corresponding severity score can be matched and output. The area score of the image of the skin around the stoma is calculated based on contour recognition and calculus, and state evaluation of the skin around the stoma can be intelligently and automatically achieved. A stoma patient only needs to shoot images of skin around the stoma and upload the images to a server, objective state evaluation can be carried out through the system, clinical manual evaluation of medical staff is not needed, the medical time and resources are saved, and the evaluation burden of the medical staff is relieved. The assessment risk of different assessment levels caused by subjective influence on assessment personnel can be avoided, and the assessment is efficient.

Description

Technical Field

[0001] The present disclosure relates to the field of medical assessment technology, and in particular to an AI assessment method, system and electronic device for peristomal skin based on a DET assessment scale. Background Art

[0002] The DET scoring standard solves the practical problem that some treatments for peristomal skin abnormalities are based on clinical experience without a definite practice standard. It scores the peristomal skin condition from three dimensions: skin color change, skin lesions / ulcers, and hyperplasia. It has the advantages of being simple to use, easy for assessors to master, and applicable to various stoma types. Through intuitive, direct, and standardized evaluation, it provides a simple method for caregivers and patients to obtain the peristomal skin condition.

[0003] As attached Figure 1 The DET assessment scale is shown in Figure 1. The total DET score is calculated based on three areas: discoloration (D), erosion (E), and tissue overgrowth (T). In each area, two aspects are considered: the area of ​​peristomal skin affected (the peristomal skin covered by the stoma base plate) and the severity. The area score ranges from 0 to 3 points, and the severity score is 0 to 3 points.

[0004] (1) Area scoring. The peristomal skin is scored as 0 to 2 points. If the skin is not affected, it is scored as 0 points; if the affected area is less than 25%, it is scored as 1 point; if the affected area is 25% to 50%, it is scored as 2 points; if the affected area is greater than 50%, it is scored as 3 points.

[0005] (2) Severity scoring. ① Discoloration (D): 0 points if there is no color change in the skin around the stoma; 1 point if there is color change; 2 points if there is color change in the skin around the stoma and complications (pain, radiance, induration, fever, itching or burning sensation, etc.). ② Erosion (E): 0 points if there is no maceration or ulceration; 1 point if the injury involves the epidermis; 2 points if the injury involves the dermis and complications (moisture, bleeding or ulceration). ③ Tissue proliferation (T): 0 points if there is no tissue proliferation; 1 point if there is raised tissue on the skin surface; 2 points if there is raised tissue on the skin surface and complications (bleeding, pain, moisture). After calculating the scores of the three areas according to the scoring criteria, the affected area scores and severity scores of the three areas are added together to obtain a composite value, namely the discoloration, erosion, and tissue proliferation (DET) score, and finally the range of this score is 0 to 15 points. 0 points means that the peristomal skin is healthy. As the score increases, the severity of the peristomal skin problem increases. A score is given at each visit, and the change in the score can reflect the improvement or deterioration of the peristomal skin problem.

[0006] The current clinical evaluation method for the clinical development and recovery status of peristomal skin (peristomal skin condition) mainly relies on medical staff to evaluate stoma patients based on the above-mentioned DET evaluation scale. Therefore, this evaluation method requires the evaluator to have rich clinical experience and objective evaluation standards. However, evaluators are often affected by subjective factors, resulting in different evaluation levels, and the professional ability and experience of evaluators are also uneven, which will cause inconsistent evaluation results and evaluation reports of stoma patients in the hospital.

[0007] In addition, clinical evaluation requires a lot of time from medical staff, which delays their work and fails to save medical resources. Summary of the invention

[0008] In order to solve the above problems, the present application proposes an AI assessment method, system and electronic device for peristomal skin based on the DET assessment scale.

[0009] On the one hand, the present application proposes an AI evaluation method for peristomal skin based on the DET evaluation scale, comprising the following steps:

[0010] Through the stoma patient APP, collect the skin images around the stoma of the stoma patient and upload them to the backend server;

[0011] The backend server receives and forwards the peristomal skin image to an image processing module, and the image processing module performs image contour processing on the peristomal skin image, evaluates and outputs an area score of the peristomal skin image;

[0012] The backend server receives and forwards the peristomal skin image to a preset stoma skin AI assessment model, identifies the DET features in the peristomal skin image through the stoma skin AI assessment model, and matches and outputs the corresponding severity score;

[0013] The area score and the severity score are written into the medical record file of the stoma patient in the HIS medical record system.

[0014] As an optional implementation scheme of the present application, optionally, the following steps are also included:

[0015] Log into the HIS medical record system on the backend server through the medical PC to view the medical record files of the stoma patient.

[0016] As an optional implementation scheme of the present application, optionally, the following steps are also included:

[0017] The peristomal skin image is stored in a stoma patient management system and is bound to the stoma patient's medical ID.

[0018] As an optional embodiment of the present application, optionally, the image processing module performs image contour processing on the peristomal skin image, evaluates and outputs an area score of the peristomal skin image, including:

[0019] Based on an image contour algorithm, identifying and marking an affected area on the peristomal skin image;

[0020] Performing difference or approximation preprocessing on the affected area;

[0021] Calculate the affected area S1 of the affected area after pretreatment by using calculus;

[0022] Calculate the area score δ of the peristomal skin image:

[0023] δ=S1 / S0,

[0024] S0 is the original area of ​​the peristomal skin image.

[0025] As an optional embodiment of the present application, optionally, the method for generating the stoma skin AI assessment model comprises:

[0026] Collecting stoma skin images of several stoma patients, wherein the stoma skin images of the stoma patients are collected respectively according to the color change image, erosion image and tissue hyperplasia image in the DET assessment scale;

[0027] Performing image feature engineering on the stoma skin image, extracting image features in the stoma skin image, and forming a corresponding stoma image feature set, the stoma image feature set comprising:

[0028] Color change feature D(n),

[0029] Slow corrosion characteristics E(n),

[0030] Tissue proliferation characteristics T(n);

[0031] Dividing the stoma image feature set into a training set and a validation set according to a preset ratio;

[0032] The CNN model is trained using the training set, and the recognition performance of the initial model generated by the training is verified using the verification set;

[0033] If the verification is passed, the stoma skin AI evaluation model is obtained, and the stoma skin AI evaluation model is deployed on the background server and put into use.

[0034] On the other hand, the present application proposes a system for implementing the above-mentioned peristomal skin AI assessment method based on the DET assessment scale, comprising:

[0035] Stoma patient APP, used to collect peristomal skin images of stoma patients and upload them to the backend server;

[0036] A backend server is used to receive the peristomal skin image and store it in a stoma patient management system, and bind it to the stoma patient's medical ID; and forward the peristomal skin image to an image processing module, the image processing module performs image contour processing on the peristomal skin image, evaluates and outputs the area score of the peristomal skin image; and forward the peristomal skin image to a preset stoma skin AI evaluation model, identify the DET features in the peristomal skin image through the stoma skin AI evaluation model and match and output the corresponding severity score; and write the area score and the severity score into the stoma patient's medical record file in the HIS medical record system;

[0037] A medical PC is used to log in to the HIS medical record system on the backend server and view the medical records of the stoma patient;

[0038] The stoma patient APP and the medical PC are respectively connected to the background server for communication.

[0039] In another aspect, the present application further provides an electronic device, comprising:

[0040] processor;

[0041] a memory for storing processor-executable instructions;

[0042] Wherein, the processor is configured to implement the AI ​​assessment method for peristomal skin based on the DET assessment scale when executing the executable instructions.

[0043] Technical effects of the present invention:

[0044] The present invention is based on the model of the DET assessment scale, collects peristomal skin images corresponding to D, E, and T and performs feature training, thereby constructing a peristomal skin AI model based on the DET assessment scale, and is used for intelligent identification of stoma skin, which can intelligently identify the DET features in the peristomal skin image and match and output the corresponding severity score. In addition, the present invention calculates the area integral of the peristomal skin image based on contour recognition and calculus, so it can intelligently and automatically realize the status assessment of the peristomal skin. Stoma patients only need to take pictures of the peristomal skin images and upload them to the server, and they can use this system to conduct objective status assessment, without the need for clinical manual assessment by medical staff, saving medical time and resources, and relieving their assessment burden.

[0045] The present invention can avoid the risk of evaluators being affected by subjective factors, resulting in different evaluation levels, and the evaluation is highly efficient.

[0046] Further features and aspects of the present disclosure will become apparent from the following detailed description of exemplary embodiments with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate exemplary embodiments, features, and aspects of the disclosure and, together with the description, serve to explain the principles of the disclosure.

[0048] Figure 1 Shown as DET assessment scale;

[0049] Figure 2 It is shown as a schematic diagram of the implementation process of the present invention;

[0050] Figure 3 Shown is a schematic diagram of the application composition of the system of the present invention;

[0051] Figure 4 It is shown as a schematic diagram of the model training process of the present invention;

[0052] Figure 5 It is a schematic diagram showing the application of the electronic device of the present invention. DETAILED DESCRIPTION

[0053] Various exemplary embodiments, features and aspects of the present disclosure will be described in detail below with reference to the accompanying drawings. The same reference numerals in the accompanying drawings represent elements with the same or similar functions. Although various aspects of the embodiments are shown in the accompanying drawings, the drawings are not necessarily drawn to scale unless otherwise specified.

[0054] The word “exemplary” is used exclusively herein to mean “serving as an example, example, or illustration.” Any embodiment described herein as “exemplary” is not necessarily to be construed as preferred or advantageous over other embodiments.

[0055] In addition, in order to better illustrate the present disclosure, numerous specific details are given in the following specific embodiments. It should be understood by those skilled in the art that the present disclosure can also be implemented without certain specific details. In some examples, means, components and circuits well known to those skilled in the art are not described in detail in order to highlight the main purpose of the present disclosure.

[0056] Example 1

[0057] like Figure 2 As shown, on the one hand, the present application proposes an AI evaluation method for peristomal skin based on the DET evaluation scale, comprising the following steps:

[0058] S1. Collect the skin image around the stoma of the stoma patient through the stoma patient APP and upload it to the backend server;

[0059] S2, the backend server receives and forwards the peristomal skin image to the image processing module, the image processing module performs image contour processing on the peristomal skin image, evaluates and outputs the area score of the peristomal skin image;

[0060] S3, the backend server receives and forwards the peristomal skin image to a preset stoma skin AI assessment model, identifies the DET features in the peristomal skin image through the stoma skin AI assessment model, and matches and outputs the corresponding severity score;

[0061] S4. Writing the area score and the severity score into the stoma patient's medical record file in the HIS medical record system.

[0062] Combined with Figure 3 The present invention introduces an AI evaluation system for peristomal skin, which can realize the stoma status of stoma patients and intelligently and automatically evaluate the stoma status.

[0063] Patients can log in to the backend server through the APP, upload their stoma images, and the backend server will process and recognize the stoma images. Image contour processing algorithms can be used to identify the affected area in the skin image around the stoma and mark its contour. Combined with calculation tools such as calculus, the area of ​​the affected area can be further evaluated and output, and the area score can be calculated.

[0064] After the background server receives the image, the peristomal skin image is stored in the stoma patient management system and bound to the stoma patient's medical ID, so that subsequent doctors can log in to the background to view the stoma images of each patient and remotely view and manage patients.

[0065] As for the severity of the condition, the stoma skin AI assessment model pre-trained and deployed on the background can be used to intelligently identify the image features in the stoma images of the patient. The DET image features pre-trained and learned by the model are used to identify the DET features in the captured images, and the corresponding stoma severity scores are matched and output.

[0066] Therefore, the area and severity can be scored respectively through the above two modes, and then the identified scoring results can be written into the patient's medical record file in the HIS medical record system. Subsequent medical staff can log in to the backend server through the doctor's PC (or PDA terminal, etc.) to view the stoma status assessment results of each stoma patient, so as to realize intelligent and automatic identification and assessment, avoid the subjective influence of the assessor, and objectively assess and release the workload of medical staff.

[0067] In this embodiment, the communication configuration and link between the APP or OC and the background server are managed and configured by the administrator, and this embodiment does not limit this.

[0068] The scoring in step S2 is specifically based on the principle of the following image processing module:

[0069] As an optional embodiment of the present application, optionally, the image processing module performs image contour processing on the peristomal skin image, evaluates and outputs an area score of the peristomal skin image, including:

[0070] Based on an image contour algorithm, identifying and marking an affected area on the peristomal skin image;

[0071] Performing difference or approximation preprocessing on the affected area;

[0072] Calculate the affected area S1 of the affected area after pretreatment by using calculus;

[0073] Calculate the area score δ of the peristomal skin image:

[0074] δ=S1 / S0,

[0075] S0 is the original area of ​​the peristomal skin image.

[0076] This image processing module mainly processes image contours based on contour recognition algorithms. It intelligently recognizes the contours of the affected area in the peristomal skin image and marks it. Then, the system uses a program to calculate the contour coordinates of the marked area and preprocess it. The calculus code is then used to integrate the marked contours to calculate the area of ​​the contour area.

[0077] The program calculation steps for calculus of contours mainly include the following aspects:

[0078] 1. Clarify the problem and goal

[0079] First, the purpose of the calculation must be clear, such as whether the length (perimeter) or area of ​​the contour is required, or other calculus quantities related to the contour shape (such as the curvature of the contour, the integral of a physical quantity inside the contour, etc.).

[0080] 2. Establishing a mathematical model

[0081] 1. Determine the mathematical description of the contour: Usually, the contour can be described by a series of point sets or parametric equations. If the contour is composed of discrete points, it can be converted into a continuous curve through interpolation methods (such as linear interpolation, spline interpolation, etc.).

[0082] 2. Choose the appropriate calculus method: Choose the appropriate calculus method according to the calculation goal. For example, if you calculate the length (perimeter) of a contour, you can use a definite integral to calculate the length of the curve segment; if you calculate the area of ​​a contour, you can use a double integral to calculate the area of ​​the region enclosed by the curve.

[0083] 3. Write program code

[0084] 1. Data input: Write code to input contour data, which may be point set coordinates, parameter values ​​of parametric equations, etc.

[0085] 2. Interpolation and approximation (if necessary): If the contour is composed of discrete points, interpolation or approximation is required to convert it into a continuous function suitable for calculus calculations.

[0086] 3. Calculus calculation: According to the selected calculus method, write the corresponding code to calculate the required quantity. For example, use numerical integration methods (such as trapezoidal method, Simpson method, etc.) to calculate the value of definite integral.

[0087] 4. Output results: Output the calculation results in an appropriate form, such as printing to the console, saving to a file, or displaying on a graphical interface.

[0088] 4. Verification and Optimization

[0089] 1. Verify the results: Verify the correctness of the program by comparing it with the results of other methods (such as manual calculations, using mathematical software, etc.).

[0090] 2. Optimize the program: Based on the test results and actual needs, optimize the program code to improve computing efficiency or add new functions.

[0091] The original area can be pre-configured in the system. After the image processing module recognizes the contour area, the original area can be substituted into the formula to calculate the area score of the peristomal skin image. The area score here refers to the area ratio, that is:

[0092] The score for peristomal skin is 0 to 2. If the skin is not affected, it is 0 points; if the affected area is less than 25%, it is 1 point; if the affected area is 25% to 50%, it is 2 points; if the affected area is more than 50%, it is 3 points.

[0093] Combined with Figure 4 As shown, as an optional embodiment of the present application, optionally, the method for generating the stoma skin AI assessment model includes:

[0094] Collecting stoma skin images of several stoma patients, wherein the stoma skin images of the stoma patients are collected respectively according to the color change image, erosion image and tissue hyperplasia image in the DET assessment scale;

[0095] Performing image feature engineering on the stoma skin image, extracting image features in the stoma skin image, and forming a corresponding stoma image feature set, the stoma image feature set comprising:

[0096] Color change feature D(n),

[0097] Slow corrosion characteristics E(n),

[0098] Tissue proliferation characteristics T(n);

[0099] Dividing the stoma image feature set into a training set and a validation set according to a preset ratio;

[0100] The CNN model is trained using the training set, and the recognition performance of the initial model generated by the training is verified using the verification set;

[0101] If the verification is passed, the stoma skin AI evaluation model is obtained, and the stoma skin AI evaluation model is deployed on the background server and put into use.

[0102] Using the CNN model to train and learn image features to build the corresponding application model can be divided into the following steps:

[0103] 1. Data preparation

[0104] Loading the dataset: First, you need to load and preprocess the image dataset. The image dataset should contain enough labeled samples so that the network can learn effective features. This includes reading image files, assigning labels, etc.

[0105] Data preprocessing: In order to improve the performance and generalization ability of the model, it is usually necessary to preprocess the image, such as scaling, cropping, normalization, etc. In addition, data enhancement (such as rotation, flipping, adding noise, etc.) is also a common means to increase the diversity of training samples.

[0106] 2. Design network structure

[0107] Select layer type: Design the network structure of CNN according to task requirements, including the number, order, and parameter settings of convolutional layers, pooling layers, and fully connected layers.

[0108] Activation function: Select appropriate activation functions after the convolutional layer and the fully connected layer, such as ReLU, Sigmoid, etc., to introduce nonlinearity and enhance the expressiveness of the model.

[0109] Normalization layer (optional): In order to accelerate the convergence speed of the model and improve the generalization ability, a normalization layer, such as Batch Normalization, can be added to the network.

[0110] 3. Configure training parameters

[0111] Optimizer: Choose a suitable optimizer (such as Adam, SGD, etc.) to update the network weights to minimize the loss function.

[0112] Loss function: Select an appropriate loss function according to the task type (such as classification, regression, etc.), such as cross entropy loss function, mean square error loss function, etc.

[0113] Learning rate: Set an appropriate learning rate to control the step size of parameter updates. A learning rate that is too high may cause the model to fail to converge, while a learning rate that is too low may cause the training process to be too slow.

[0114] 4. Training the Model

[0115] Forward propagation: The input image is sent into the CNN model, passed layer by layer through the convolution layer, pooling layer and fully connected layer, and finally the output result is obtained.

[0116] Back propagation: Calculate the loss value based on the output results and the true label, and update the network parameters through the back propagation algorithm to reduce the loss value.

[0117] Iterative training: Repeat the forward propagation and backpropagation process until the preset training rounds are reached or the loss value no longer decreases significantly.

[0118] 5. Model evaluation and tuning

[0119] Evaluate the model: Use the validation set or test set to evaluate the performance of the trained CNN model, including accuracy, recall, F1 score and other indicators. The administrator can perform optimization training and verification.

[0120] Model tuning: Tune the model based on the evaluation results, such as adjusting the network structure, optimizer parameters, learning rate, etc., to improve the performance of the model.

[0121] 6. Deployment and Application

[0122] Deploy the trained CNN model to actual application scenarios, such as image classification, object detection, face recognition and other tasks.

[0123] The model is further optimized and adjusted according to actual application requirements to improve its stability and practicality.

[0124] Through the above steps, a CNN-based image feature learning model can be built and applied to various image recognition tasks.

[0125] In this embodiment, the stoma skin AI assessment model is constructed by training the corresponding D, E, T (discoloration, D), erosion (E), and tissue overgrowth (T)) peristomal skin image set. The peristomal skin images of different types and degrees of D, E, T (discoloration, D), erosion (E), and tissue overgrowth (T)) are all annotated with corresponding scoring values.

[0126] Therefore, during the training process, after collecting peristomal skin images with different D, E, T (discoloration (D), erosion (E) and tissue overgrowth (T)), the score values ​​need to be annotated to facilitate the model to learn the score values ​​corresponding to different discoloration features D(n), slow erosion features E(n) and tissue overgrowth features T(n).

[0127] Therefore, the image feature engineering of the present application extracts the image features in the stoma skin image, including: color change feature D(n), slow erosion feature E(n), and tissue hyperplasia feature T(n). Image feature engineering can also be performed using a convolutional neural network, using a convolutional neural network to extract image features and obtain corresponding image features. Specifically, the principle of image feature extraction by CNN can be combined.

[0128] Therefore, by adopting the above method, a model can be trained to identify different color change features D(n), slow corrosion features E(n), and tissue proliferation features T(n). After identifying the features, the score value corresponding to the features can be output to facilitate system statistics.

[0129] Obviously, those skilled in the art should understand that the implementation of all or part of the processes in the above-mentioned embodiments can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the above-mentioned embodiments. Those skilled in the art can understand that the implementation of all or part of the processes in the above-mentioned embodiments can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the above-mentioned embodiments. Among them, the storage medium can be a disk, an optical disk, a read-only memory (ROM), a random access memory (RAM), a flash memory (Flash Memory), a hard disk (Hard Disk Drive, abbreviated as: HDD) or a solid-state drive (SSD), etc.; the storage medium can also include a combination of the above-mentioned types of memory.

[0130] Example 2

[0131] Based on the implementation principle of Example 1, on the other hand, the present application proposes a system for implementing the above-mentioned peristomal skin AI assessment method based on the DET assessment scale, comprising:

[0132] Stoma patient APP, used to collect peristomal skin images of stoma patients and upload them to the backend server;

[0133] A backend server is used to receive the peristomal skin image and store it in a stoma patient management system, and bind it to the stoma patient's medical ID; and forward the peristomal skin image to an image processing module, the image processing module performs image contour processing on the peristomal skin image, evaluates and outputs the area score of the peristomal skin image; and forward the peristomal skin image to a preset stoma skin AI evaluation model, identify the DET features in the peristomal skin image through the stoma skin AI evaluation model and match and output the corresponding severity score; and write the area score and the severity score into the stoma patient's medical record file in the HIS medical record system;

[0134] A medical PC is used to log in to the HIS medical record system on the backend server and view the medical records of the stoma patient;

[0135] The stoma patient APP and the medical PC are respectively connected to the background server for communication.

[0136] Please understand the specific interaction of the above system in conjunction with Example 1.

[0137] The modules or steps of the present invention described above can be implemented by a general-purpose computing system, they can be concentrated on a single computing system, or distributed on a network composed of multiple computing systems, and optionally, they can be implemented by a program code executable by a computing system, so that they can be stored in a storage system and executed by the computing system, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0138] Example 3

[0139] Combined with Figure 5 As shown, further, in another aspect, the present application also proposes an electronic device, including:

[0140] processor;

[0141] a memory for storing processor-executable instructions;

[0142] Wherein, the processor is configured to implement an AI assessment method for peristomal skin based on the DET assessment scale as described in Example 2 when executing the executable instructions.

[0143] The electronic device of the embodiment of the present disclosure includes a processor and a memory for storing instructions executable by the processor. The processor is configured to implement the AI ​​assessment method for peristomal skin based on the DET assessment scale described in the above embodiment 2 when executing the executable instructions.

[0144] Here, it should be noted that the number of processors can be one or more. At the same time, the electronic device of the embodiment of the present disclosure may also include an input system and an output system. Among them, the processor, memory, input system and output system may be connected through a bus or in other ways, which are not specifically limited here.

[0145] As a computer-readable storage medium, the memory can be used to store software programs, computer executable programs and various modules, such as the program or module corresponding to the AI ​​evaluation method for peristomal skin based on the DET evaluation scale in the embodiment of the present disclosure. The processor executes various functional applications and data processing of the electronic device by running the software programs or modules stored in the memory.

[0146] The input system can be used to receive input numbers or signals. The signal can be a key signal related to user settings and function control of the device / terminal / server. The output system can include display devices such as display screens.

[0147] The embodiments of the present disclosure have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and changes will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or technical improvements in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. A peristomal skin AI assessment method based on the DET assessment scale, characterized in that: The steps include: Through the stoma patient APP, collect the skin images around the stoma of the stoma patient and upload them to the backend server; The backend server receives and forwards the peristomal skin image to an image processing module, and the image processing module performs image contour processing on the peristomal skin image, evaluates and outputs an area score of the peristomal skin image; The backend server receives and forwards the peristomal skin image to a preset stoma skin AI assessment model, identifies the DET features in the peristomal skin image through the stoma skin AI assessment model, and matches and outputs the corresponding severity score; The area score and the severity score are written into the medical record file of the stoma patient in the HIS medical record system.

2. The method for evaluating peristomal skin AI based on the DET evaluation scale according to claim 1, characterized in that: The following steps are also included: Log into the HIS medical record system on the backend server through the medical PC to view the medical record files of the stoma patient.

3. The method for evaluating peristomal skin AI based on the DET evaluation scale according to claim 1, characterized in that: The following steps are also included: The peristomal skin image is stored in a stoma patient management system and is bound to the stoma patient's medical ID.

4. The method for evaluating peristomal skin AI based on the DET evaluation scale according to claim 1, characterized in that: The image processing module performs image contour processing on the peristomal skin image, evaluates and outputs an area score of the peristomal skin image, including: Based on an image contour algorithm, identifying and marking an affected area on the peristomal skin image; Performing difference or approximation preprocessing on the affected area; Calculate the affected area S1 of the affected area after pretreatment by using calculus; Calculate the area score δ of the peristomal skin image: δ=S1 / S0, S0 is the original area of ​​the peristomal skin image.

5. The method for evaluating peristomal skin AI based on the DET evaluation scale according to claim 1, characterized in that: The method for generating the stoma skin AI evaluation model comprises: Collecting stoma skin images of several stoma patients, wherein the stoma skin images of the stoma patients are collected respectively according to the color change image, erosion image and tissue hyperplasia image in the DET assessment scale; Perform image feature engineering on the stoma skin image, extract image features in the stoma skin image, and form a corresponding stoma image feature set, wherein the stoma image feature set includes: Color change feature D(n), Slow corrosion characteristics E(n), Tissue proliferation characteristics T(n); Dividing the stoma image feature set into a training set and a validation set according to a preset ratio; The CNN model is trained using the training set, and the recognition performance of the initial model generated by the training is verified using the verification set; If the verification is passed, the stoma skin AI evaluation model is obtained, and the stoma skin AI evaluation model is deployed on the background server and put into use.

6. A system for implementing a DET assessment scale-based peristomal skin AI assessment method according to any one of claims 1 to 5, characterized in that: include: Stoma patient APP, used to collect peristomal skin images of stoma patients and upload them to the backend server; A backend server is used to receive the peristomal skin image and store it in a stoma patient management system, and bind it to the stoma patient's medical ID; and forwarding the peristomal skin image to an image processing module, wherein the image processing module performs image contour processing on the peristomal skin image, evaluates and outputs an area score of the peristomal skin image; and forwarding the peristomal skin image to a preset stoma skin AI evaluation model, identifying the DET features in the peristomal skin image through the stoma skin AI evaluation model and matching and outputting the corresponding severity score; and writing the area score and the severity score into the stoma patient medical record file of the HIS medical record system; A medical PC is used to log in to the HIS medical record system on the backend server and view the medical records of the stoma patient; The stoma patient APP and the medical PC are respectively connected to the background server for communication.

7. An electronic device, characterized in that include: processor; a memory for storing processor-executable instructions; Wherein, the processor is configured to implement an AI assessment method for peristomal skin based on the DET assessment scale as described in any one of claims 1-5 when executing the executable instructions.

Images