Wound assessment monitoring method and device

Abstract

The present invention provides a wound assessment and monitoring method and device, which belongs to the field of medical equipment technology, and specifically includes: using different historical matching of wound image features of patients at different development stages of the wound to find similarities, and using the similarities to determine when the accuracy of distinguishing between different development stages meets the requirements, based on the historical matching of wound image features of patients at different development stages of the wound, determining the accurate image features in different development stages, obtaining the similarities between the accurate image features in different development stages and other wound types, and determining the wound assessment and monitoring method in combination with the accuracy of distinguishing between different development stages, thereby improving the reliability of wound assessment and monitoring.

Description

Technical Field

[0001] The present invention belongs to the technical field of medical equipment, and in particular relates to a wound assessment and monitoring method and equipment. Background Art

[0002] In order to realize the evaluation and monitoring of the wound healing process, the invention patent application CN202410474930.4 "A method and system for realizing wound healing monitoring" reproduces the three-dimensional model through the point cloud data set, obtains the three-dimensional data of the wound, divides the three regions, obtains the wound type, and establishes a recovery function to generate predictive evaluation parameters, so as to monitor the wound condition more comprehensively. However, there are the following technical problems:

[0003] When conducting wound assessment and monitoring, although the construction of a three-dimensional model of the wound can accurately achieve an accurate assessment of the wound's recovery, it will inevitably lead to a high degree of complexity in the wound assessment and monitoring. Therefore, if differentiated assessment and monitoring methods cannot be generated according to different wound types, it will be impossible to improve the efficiency of wound assessment and treatment while ensuring the accuracy of wound assessment.

[0004] In response to the above technical problems, the present invention provides a wound assessment and monitoring method and device. Summary of the invention

[0005] To achieve the purpose of the present invention, the present invention adopts the following technical solutions:

[0006] According to one aspect of the present invention, a wound assessment and monitoring method and device are provided.

[0007] A wound assessment and monitoring method, specifically comprising:

[0008] Acquiring wound image features of different parts of the wound based on the wound image, and when determining that the wound has a matching wound type using the analysis result of the wound image features, taking the patient corresponding to the matching wound type as a historical matching patient;

[0009] Using different historical matching to find similarities in wound image features of patients at different stages of wound development, and using the similarities to determine that the accuracy of distinguishing between different stages of wound development meets the requirement, based on the historical matching of wound image features of patients at different stages of wound development, determine the accurate image features for identification at different stages of wound development;

[0010] Obtain accurate image features for identification at different development stages and similarities with other wound types, and determine a wound assessment and monitoring method based on the accuracy of differentiation between different development stages.

[0011] The beneficial effects of the present invention are:

[0012] Based on the historical matching of wound image features of patients at different stages of wound development, accurate image features are determined in different stages of development, thereby realizing the identification of accurate image features from the similarities between wound image features at different stages of development and other stages of development. It also lays the foundation for determining the wound assessment and monitoring method based on the identification of accurate image features, and also improves the accuracy of patient wound identification and processing.

[0013] The wound assessment and monitoring method is determined based on the deviation between the accurate image features and other wound types in different development stages, and the differentiation accuracy between different development stages. It takes into account the deviation between the accurate image features and other wound types, avoiding the use of accurate image features to identify other wound types, and also takes into account the differentiation accuracy between development stages. By evaluating the accuracy of image recognition of wound types from multiple aspects, it also lays the foundation for further use of point cloud data or image recognition to conduct wound assessment and monitoring.

[0014] A further technical solution is that the wound image features include color features, texture features, shape features and spatial relationship features.

[0015] A further technical solution is to determine whether the wound has a matching wound type, specifically including:

[0016] Determining the similarity between wound image features at different locations and different wound types based on the analysis results of the wound image features;

[0017] Determining similar image features among wound image features at different locations according to similarities with different wound types;

[0018] The presence or absence of a matching wound type for the wound is determined by the number of similar image features with different wound types.

[0019] A further technical solution is that the similar image features are determined by the degree of similarity with the matching image features corresponding to the wound type, and specifically, image features with a degree of similarity greater than a preset similarity coefficient are considered similar image features.

[0020] A further technical solution is to determine whether the wound has a matching wound type by the number of similar image features with different wound types, specifically including:

[0021] When there are wound types with a number of similar image features greater than a preset number of features, the wound type with the largest number of similar image features is taken as the matching wound type.

[0022] A further technical solution is that the method for determining the wound assessment and monitoring method is:

[0023] Determine similarity coefficients between the accurate image features for identification at different development stages and other wound types according to similarities between the accurate image features for identification at different development stages and other wound types, and determine the identification deviation probabilities at different development stages using the similarity coefficients, and determine the comprehensive identification deviation probability of the wound based on the average of the identification deviation probabilities at different development stages;

[0024] determining a comprehensive differentiation accuracy of the wounds by using differentiation accuracy rates between different development stages;

[0025] The identification reliability coefficient of the wound is determined based on the ratio of the comprehensive differentiation accuracy of the wound to the comprehensive identification deviation probability, and the evaluation and monitoring method of the wound is determined according to the identification reliability coefficient.

[0026] A further technical solution is to determine the wound assessment and monitoring method according to the identification reliability coefficient, specifically including:

[0027] When the identification reliability coefficient is less than a preset reliability coefficient threshold, the point cloud data is used to evaluate and monitor the wound;

[0028] When the recognition reliability coefficient is not less than a preset reliability coefficient threshold, the wound is evaluated and monitored by using image recognition.

[0029] In a second aspect, the present invention provides a computer device comprising: a memory and a processor that are communicatively connected, and a computer program stored in the memory and executable on the processor, wherein the processor executes the above-mentioned wound assessment and monitoring method when running the computer program.

[0030] Other features and advantages will be described in the following description. The objects and other advantages of the present invention are realized and obtained by the structures particularly pointed out in the description and drawings.

[0031] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] The above and other features and advantages of the present invention will become more apparent by describing in detail exemplary embodiments thereof with reference to the attached drawings.

[0033] Figure 1 is a flow chart of a wound assessment monitoring approach;

[0034] Figure 2is a flow chart of a method for determining the presence of a wound that matches the wound type;

[0035] Figure 3 is a flow chart of a method for determining the accuracy of differentiation;

[0036] Figure 4 is a flow chart of a method for identifying a determination of accurate image features;

[0037] Figure 5 It is a flow chart of the method for determining the wound assessment monitoring method. DETAILED DESCRIPTION

[0038] In order to enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this specification, not all of the embodiments. Based on the embodiments of this specification, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of this specification.

[0039] When conducting wound assessment and monitoring, although the construction of a three-dimensional model of the wound can accurately achieve an accurate assessment of the wound's recovery, it will inevitably lead to a high degree of complexity in the wound assessment and monitoring.

[0040] The matching coefficient is determined by using the similarity between the wound image features and the preset image features of different wound types. Specifically, the proportion of wound image features with a similarity greater than 0.7 is used to determine the matching coefficient, and the wound type with the largest matching coefficient is used as the matching wound type.

[0041] Based on the similarity of wound image features of different historical matching patients at different development stages of the wound, historical matching patients whose similarity of wound image features between different development stages is greater than a preset similarity level are determined, and they are used as similar matching patients. According to the number of similar matching patients between different development stages, the image feature similarity coefficient between different development stages is determined, and the image feature similarity coefficient is used to determine the accuracy of distinguishing between development stages.

[0042] When the discrimination accuracy rates between different development stages are all greater than 0.7, it is determined that the discrimination accuracy rates between different development stages meet the requirements.

[0043] The wound image features whose deviations between different development stages are all greater than 0.7 are used as accurate image features for identification.

[0044] Use point cloud data to evaluate and monitor wounds, or use image recognition to evaluate and monitor wounds.

[0045] According to the similarity between the accurate identification image features in different development stages and other wound types, the similarity coefficient between the accurate identification image features in different development stages and other wound types is determined, and the identification deviation probability of different development stages is determined by using the similarity coefficient. The comprehensive identification deviation probability of the wound is determined based on the average value of the identification deviation probability of different development stages. The comprehensive distinction accuracy of the wound is determined by the distinction accuracy between different development stages. The identification reliability coefficient of the wound is determined based on the ratio of the comprehensive distinction accuracy of the wound to the comprehensive identification deviation probability. The evaluation and monitoring method of the wound is determined based on the identification reliability coefficient.

[0046] When the recognition reliability coefficient is less than the preset reliability coefficient threshold, the wound is evaluated and monitored using point cloud data; when the recognition reliability coefficient is not less than the preset reliability coefficient threshold, the wound is evaluated and monitored using image recognition.

[0047] Embodiment 1 To solve the above problem, according to one aspect of the present invention, Figure 1 As shown, a wound assessment and monitoring method is provided, which specifically includes:

[0048] Acquiring wound image features of different parts of the wound based on the wound image, and when determining that the wound has a matching wound type using the analysis result of the wound image features, taking the patient corresponding to the matching wound type as a historical matching patient;

[0049] Using different historical matching to find similarities in wound image features of patients at different stages of wound development, and using the similarities to determine that the accuracy of distinguishing between different stages of wound development meets the requirement, based on the historical matching of wound image features of patients at different stages of wound development, determine the accurate image features for identification at different stages of wound development;

[0050] Obtain accurate image features for identification at different development stages and similarities with other wound types, and determine a wound assessment and monitoring method based on the accuracy of differentiation between different development stages.

[0051] Furthermore, the wound image features include color features, texture features, shape features and spatial relationship features.

[0052] It should be noted that if Figure 2 As shown, determine whether the wound has a matching wound type, including:

[0053] Determining the similarity between wound image features at different locations and different wound types based on the analysis results of the wound image features;

[0054] Determining similar image features among wound image features at different locations according to similarities with different wound types;

[0055] The presence or absence of a matching wound type for the wound is determined by the number of similar image features with different wound types.

[0056] Furthermore, the similar image features are determined by the degree of similarity with the matching image features corresponding to the wound type, and specifically, image features with a degree of similarity greater than a preset similarity coefficient are considered similar image features.

[0057] Optionally, determining whether the wound has a matching wound type by the number of similar image features of different wound types specifically includes:

[0058] When there are wound types with a number of similar image features greater than a preset number of features, the wound type with the largest number of similar image features is taken as the matching wound type.

[0059] In another embodiment, determining that a wound has a matching wound type specifically includes:

[0060] Determining the similarity between wound image features at different locations and different wound types based on the analysis results of the wound image features;

[0061] Determine wound similarity coefficients with different wound types according to the similarity between wound image features at different parts and different wound types;

[0062] The wound similarity coefficient with different wound types is used to determine whether the wound has a matching wound type.

[0063] Optionally, determining that the wound has a matching wound type includes:

[0064] Determine the similarity between the wound image features at different parts and different wound types based on the analysis result of the wound image features, and when there is no wound type with a similarity that meets the requirement, determine that there is no matching wound type for the wound;

[0065] When there are wound types that meet the requirements to a similar degree:

[0066] The wound type that meets the similarity requirement is used as a candidate wound type, and the wound image features that meet the similarity requirement with the candidate wound type are used as similar image features. When the number of similar image features of different candidate wound types is less than the preset number of features, it is determined that there is no matching wound type for the wound;

[0067] When there are candidate wound types whose number of similar image features is not less than the preset number of features:

[0068] taking the candidate wound types whose number of similar image features is not less than the preset number of features as screening wound types, and determining that the wound has a matching wound type when there is only one screening wound type;

[0069] When multiple screening wound types are present:

[0070] According to the number of similar image features with different screening wound types, when the number of similar image features of different screening wound types and the number of screening wound types with the largest number of similar image features are both greater than a preset deviation number threshold, it is determined that the wound has a matching wound type;

[0071] When the number of similar image features of different screening wound types deviates from the number of screening wound types with the largest number of similar image features by more than a preset deviation number threshold:

[0072] Wound similarity coefficients with different wound types are determined according to the similarity between wound image features at different parts and different wound types, and whether the wound has a matching wound type is determined by the wound similarity coefficients with different wound types.

[0073] Specifically, the development stages include coagulation stage, inflammation stage, repair stage, and maturation stage.

[0074] Specifically, Figure 3 As shown, the method for determining the distinction accuracy is:

[0075] Based on the similarity of wound image features of different historical matching patients at different development stages of the wound, determine the historical matching patients whose similarity of wound image features between different development stages is greater than a preset similarity level, and use them as similar matching patients;

[0076] Determine the image feature similarity coefficient between different development stages according to the number of similar matching patients between different development stages;

[0077] The image feature similarity coefficient is used to determine the accuracy of distinguishing between development stages.

[0078] Furthermore, the value range of the distinction accuracy is between 0 and 1, wherein when the distinction accuracy is less than a preset accuracy, it is determined that the distinction accuracy between the development stages does not meet the requirement.

[0079] Optionally, when the accuracy of distinguishing between different development stages does not meet the requirements, wound assessment and monitoring is performed through point cloud data collection.

[0080] Optionally, the method for determining the distinction accuracy is:

[0081] Based on the similarity of wound image features between different historical matching patients at different wound development stages, determine the historical matching patients at the development stages and use them as similar matching patients;

[0082] The accuracy of differentiation is determined by using the percentage of the number of similar matching patients.

[0083] Furthermore, the similar development stage is a development stage in which the similarity of the wound image features between each other does not meet the requirements.

[0084] In another embodiment, the method for determining the distinction accuracy is:

[0085] S11, based on the similarity of wound image features of different historical matching patients at different development stages of the wound, determine the historical matching patients whose similarity of wound image features between the development stages is greater than a preset similarity level, and use them as similar matching patients;

[0086] Optionally, the above step S11 includes the following contents:

[0087] S111 determines that there is no historical matching patient whose wound image features are similar to each other at different development stages of the wound by comparing the similarities of the wound image features of different historical matching patients, and the differentiation accuracy meets the requirement. The differentiation accuracy is determined by using the average value of the similarities of the wound image features of different historical matching patients. When there is a development stage of a historical matching patient whose wound image features are similar to each other, and the stage is regarded as a similar matching patient, and the process proceeds to step S112.

[0088] S112: when it is determined that the number of similar matching patients between the development stages is greater than the preset matching patients, it is determined that the accuracy of distinguishing between the development stages does not meet the requirement; when the number of similar matching patients is not greater than the preset matching patients, the process proceeds to step S113;

[0089] S113 determines the similar wound image features of different similar matching patients based on the similarity of the wound image features of different similar matching patients between the said development stages. When the number of similar wound image features does not meet the requirement and the number of similar matching patients is greater than the preset number of similar patients, it is determined that the distinction accuracy between the said development stages does not meet the requirement. When the number of similar wound image features does not meet the requirement and the number of similar matching patients is not greater than the preset number of similar patients, proceed to step S12.

[0090] S12 determines patient feature similarity coefficients between different similar matching patients at the development stages according to similarities of wound image features between different similar matching patients at the development stages;

[0091] Optionally, the above step S12 includes the following contents:

[0092] S121 determines the patient feature similarity coefficients of different similar matching patients at the development stages according to the similarity of the wound image features of different similar matching patients at the development stages, and when there is a similar matching patient whose patient feature similarity coefficient is greater than a preset similarity coefficient threshold, proceeds to step S122; when there is no similar matching patient whose patient feature similarity coefficient is greater than the preset similarity coefficient threshold, proceeds to step S123;

[0093] S122: similar matching patients whose patient characteristic similarity coefficient is greater than a preset similarity coefficient threshold are selected as screened similar patients. When the number of the screened similar patients is greater than the preset number threshold, it is determined that the accuracy of distinguishing between the development stages does not meet the requirement. When the number of the screened similar patients is not greater than the preset number threshold, the process proceeds to step S123.

[0094] S123: When the number of similar matching patients is within the preset similar patient number interval, proceed to step S124; when the number of similar matching patients is not within the preset similar patient number interval, proceed to step S125;

[0095] S124: When the average value of the patient characteristic similarity coefficients of different similar matching patients does not meet the requirement, it is determined that the differentiation accuracy between the development stages does not meet the requirement; when the average value of the patient characteristic similarity coefficients of different similar matching patients meets the requirement, the process proceeds to step S125;

[0096] S125 determines the screening similarity coefficient based on the number of screened similar patients and the patient characteristic similarity coefficients of different screened similar patients. When the screening similarity coefficient does not meet the requirements, it is determined that the accuracy of distinguishing between the development stages does not meet the requirements. When the screening similarity coefficient meets the requirements, proceed to step S13.

[0097] S13 determines the differentiation accuracy using the patient characteristic similarity coefficients of different similar matching patients between the development stages.

[0098] Specifically, Figure 4 As shown, the method for determining the accurate image features is:

[0099] Determine a feature similarity coefficient between the wound image features of the patient at a specific development stage of the wound and the wound image features at other development stages according to the similarity between the wound image features of the patient at the specific development stage of the wound and the wound image features at other development stages of the wound;

[0100] Determining the resolution accuracy of the wound image features of the historically matched patient based on feature similarity coefficients with other development stages;

[0101] The average accuracy of the wound image feature is determined by taking the average resolution accuracy of the wound image feature of different historical matching patients, and whether the wound image feature is an identified accurate image feature is determined based on the average accuracy.

[0102] Furthermore, the resolution accuracy of the wound image feature is determined based on the maximum value of the feature similarity coefficient between the wound image feature and other development stages.

[0103] It should be noted that when the average accuracy of the wound image feature is greater than a preset accuracy threshold, the wound image feature is determined to be an identified accurate image feature.

[0104] Specifically, Figure 5 As shown, the method for determining the wound assessment and monitoring method is:

[0105] Determine similarity coefficients between the accurate image features for identification at different development stages and other wound types according to similarities between the accurate image features for identification at different development stages and other wound types, and determine the identification deviation probabilities at different development stages using the similarity coefficients, and determine the comprehensive identification deviation probability of the wound based on the average of the identification deviation probabilities at different development stages;

[0106] determining a comprehensive differentiation accuracy of the wounds by using differentiation accuracy rates between different development stages;

[0107] The identification reliability coefficient of the wound is determined based on the ratio of the comprehensive differentiation accuracy of the wound to the comprehensive identification deviation probability, and the evaluation and monitoring method of the wound is determined according to the identification reliability coefficient.

[0108] Further, determining the wound assessment and monitoring method according to the identification reliability coefficient specifically includes:

[0109] When the identification reliability coefficient is less than a preset reliability coefficient threshold, the point cloud data is used to evaluate and monitor the wound;

[0110] When the recognition reliability coefficient is not less than a preset reliability coefficient threshold, the wound is evaluated and monitored by using image recognition.

[0111] Embodiment 2 In a second aspect, the present invention provides a computer device, comprising: a memory and a processor that are communicatively connected, and a computer program stored in the memory and executable on the processor, wherein the processor executes the above-mentioned wound assessment and monitoring method when running the computer program.

[0112] In another embodiment, the method for determining the accurate image features is:

[0113] Determine the feature similarity coefficient between the wound image features of the historically matched patient at a specific development stage of the wound and the wound image features at other development stages according to the similarity between the wound image features at other development stages; when the feature similarity coefficients between different historically matched patients and other development stages are all less than a preset similarity threshold, determine that the wound image features are accurately identified image features;

[0114] When there is a historical matching patient whose characteristic similarity coefficient with other development stages is not less than the preset similarity threshold:

[0115] Obtaining the number of historical matching patients whose feature similarity coefficients in different other development stages are not less than a preset similarity threshold, and when there are other development stages whose number of historical matching patients whose feature similarity coefficients are not less than the preset similarity threshold does not meet the requirements, determining that the wound image feature does not belong to the accurately identified image feature;

[0116] When there are no other development stages where the number of historical matching patients whose feature similarity coefficient is not less than the preset similarity threshold does not meet the requirements:

[0117] Determine the resolution accuracy of the wound image feature of the historically matched patient based on the feature similarity coefficient with other development stages, and when the resolution accuracy of the wound image feature of the historically matched patient is greater than a preset accuracy threshold, determine that the wound image feature belongs to an accurately identified image feature;

[0118] When the resolution accuracy of the wound image features of the historically matched patients is not greater than a preset accuracy threshold:

[0119] The historical matching patients whose resolution accuracy is not greater than a preset accuracy threshold are regarded as resolution deviation patients, and when the number of the resolution deviation patients does not meet the requirement, it is determined that the wound image feature belongs to the recognition accurate image feature;

[0120] When the number of patients with discrimination deviation meets the requirement:

[0121] The average accuracy of the wound image feature is determined by taking the average resolution accuracy of the wound image feature of different historical matching patients, and whether the wound image feature is an identified accurate image feature is determined based on the average accuracy.

[0122] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device, equipment, and non-volatile computer storage medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0123] The above is a description of a specific embodiment of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0124] The above description is only one or more embodiments of this specification and is not intended to limit this specification. For those skilled in the art, one or more embodiments of this specification may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of one or more embodiments of this specification shall be included in the scope of the claims of this specification.

Claims

1. A wound assessment and monitoring method, characterized in that: Specifically include: Acquiring wound image features of different parts of the wound based on the wound image, and when determining that the wound has a matching wound type using the analysis result of the wound image features, taking the patient corresponding to the matching wound type as a historical matching patient; Using different historical matching to find similarities in wound image features of patients at different stages of wound development, and using the similarities to determine that the accuracy of distinguishing between different stages of wound development meets the requirement, based on the historical matching of wound image features of patients at different stages of wound development, determine the accurate image features for identification at different stages of wound development; Obtain accurate image features for identification at different development stages and similarities with other wound types, and determine wound assessment and monitoring methods based on the accuracy of differentiation between different development stages; The method for determining the distinction accuracy is: Based on the similarity of wound image features of different historical matching patients at different development stages of the wound, determine the historical matching patients whose similarity of wound image features between different development stages is greater than a preset similarity level, and use them as similar matching patients; Determine the image feature similarity coefficient between different development stages according to the number of similar matching patients between different development stages; Determining the accuracy of distinguishing between development stages using the image feature similarity coefficient; The wound assessment and monitoring method is determined by: Determine similarity coefficients between the accurate image features for identification at different development stages and other wound types according to similarities between the accurate image features for identification at different development stages and other wound types, and determine the identification deviation probabilities at different development stages using the similarity coefficients, and determine the comprehensive identification deviation probability of the wound based on the average of the identification deviation probabilities at different development stages; determining a comprehensive differentiation accuracy of the wounds by using differentiation accuracy rates between different development stages; The identification reliability coefficient of the wound is determined based on the ratio of the comprehensive differentiation accuracy of the wound to the comprehensive identification deviation probability, and the evaluation and monitoring method of the wound is determined according to the identification reliability coefficient.

2. The wound assessment and monitoring method according to claim 1, characterized in that: The wound image features include color features, texture features, shape features and spatial relationship features.

3. The wound assessment and monitoring method according to claim 1, characterized in that: Confirm that the wound has a matching wound type, including: Determining the similarity between wound image features at different locations and different wound types based on the analysis results of the wound image features; Determining similar image features among wound image features at different locations according to similarities with different wound types; The presence or absence of a matching wound type for the wound is determined by the number of similar image features with different wound types.

4. The wound assessment and monitoring method according to claim 3, characterized in that: The similar image features are determined by the degree of similarity with the matching image features corresponding to the wound type, and specifically, image features with a degree of similarity greater than a preset similarity coefficient are considered similar image features.

5. The wound assessment and monitoring method according to claim 3, characterized in that: Determining whether the wound has a matching wound type by the number of similar image features with different wound types specifically includes: When there are wound types with a number of similar image features greater than a preset number of features, the wound type with the largest number of similar image features is taken as the matching wound type.

6. The wound assessment and monitoring method according to claim 1, characterized in that: The development stages include coagulation stage, inflammation stage, repair stage, and maturation stage.

7. The wound assessment and monitoring method according to claim 1, characterized in that: The value range of the distinction accuracy is between 0 and 1, wherein when the distinction accuracy is less than a preset accuracy, it is determined that the distinction accuracy between the development stages does not meet the requirement.

8. A computer device comprising: A memory and a processor connected in communication, and a computer program stored in the memory and capable of running on the processor, characterized in that the processor executes a wound assessment and monitoring method as described in any one of claims 1-7 when running the computer program.

Images