Image comparison-based monkey pox virus classification method and device, and storage medium

Abstract

The invention belongs to the technical field of image recognition, and discloses a monkey pox virus classification method and system based on image comparison and a storage medium, and the method comprises an individual reference construction module which is used for collecting normal skin and initial lesion images of the uninjured side of a patient, and generating a healthy texture template and a lesion initial reference library; performing gray normalization on the health texture template and the focus initial reference library through adaptive histogram stretching, and outputting a comparison reference image group; the symptom density quantification module is used for acquiring a current monitoring image of a patient, segmenting a focus area by combining and comparing the reference image group, extracting layered features of the focus area to generate a three-dimensional symptom density vector, extracting texture roughness of the surface of the focus area, and forming a focus quantification data set; the accuracy of disease monitoring is improved, and the clinical nursing process is optimized.

Description

Technical Field

[0001] This invention relates to the field of image recognition technology, and more specifically, to a method, device, and storage medium for classifying monkeypox virus based on image comparison. Background Technology

[0002] Patent publication number CN119780184A discloses an integrated biosensing platform based on microneedles and hydrogels and its application in detecting monkeypox virus. The platform includes a three-electrode microneedle, a hydrogel, a recording needle, and a micro-electrochemical workstation. The working electrode of the microneedle is incorporating a nanozyme and an A29 protein antibody. Monkeypox virus is extracted from the sample through the specific binding of the antibody to the virus. The recording needle connects the three-electrode microneedle and the micro-electrochemical workstation and transmits electrochemical signals. After the three-electrode microneedle is inserted into the hydrogel, the nanozyme catalyzes the TMB contained in the hydrogel, generating a blue oxidation product, which in turn produces an electrochemical signal. This signal is acquired by the micro-electrochemical workstation via the recording needle. The electrochemical signal is collected via Bluetooth, and a colorimetric image of the hydrogel is obtained, thereby enabling the detection of monkeypox virus. This integrated biosensing platform has a low detection limit and broad application prospects for rapid on-site detection of monkeypox virus.

[0003] An existing image-matching-based monkeypox virus classification method has the following main problems:

[0004] The observation of lesions lacks continuity, and the time dimension is fragmented and ambiguous: In existing technologies, the evolution stages of lesions mostly rely on fixed-point observation or experience judgment, and lack a continuous time modeling mechanism that combines dynamic updates of labels, making it difficult to track the evolution of the disease in detail and reflect the gradual process or mutation signal between stages; especially when the boundaries of multiple stages are blurred, traditional methods cannot provide quantitative evidence with time anchoring.

[0005] Feature analysis is isolated and fragmented, lacking a multi-dimensional collaborative modeling mechanism: Traditional lesion identification methods are mostly based on single features (such as rash density or erythema size), lacking the ability to model the collaborative evolution between multiple key symptom indicators, making it difficult to capture the correlation and change trends of multiple symptoms in the same stage, thus limiting the comprehensive understanding and prediction ability of lesion evolution mechanism.

[0006] The logic for diagnosing disease progression is crude, lacking the ability to dynamically model trends: Existing methods often rely on static thresholds or human experience to determine disease stages, ignoring the differences in evolution speed and characteristic manifestations among individuals. They also fail to dynamically capture the rate of transition from one lesion state to another, lacking sensitivity to stage switching processes. Furthermore, the lack of an "indicative trend" makes it difficult to determine whether current characteristic changes are trending towards worsening or improvement. Especially in the early stages or potentially worsening phases, the lack of early warning mechanisms for trend changes poses a risk of delayed intervention.

[0007] In view of this, the present invention proposes a monkeypox virus classification method, device and storage medium based on image comparison to solve the above problems. Summary of the Invention

[0008] To overcome the aforementioned deficiencies of the prior art and to achieve the above objectives, the present invention provides the following technical solution: a monkeypox virus classification method based on image comparison, comprising:

[0009] S1. Collect images of normal skin and initial lesions on the healthy side of the patient, and generate a healthy texture template and an initial benchmark library for lesions; perform grayscale normalization on the healthy texture template and the initial benchmark library for lesions through adaptive histogram stretching, and output a set of comparison benchmark images;

[0010] S2. Obtain the patient's current monitoring image, segment the lesion area by comparing it with the baseline image group, extract the layered features of the lesion area to generate a three-dimensional symptom density vector, extract the texture roughness of the lesion area surface, and form a lesion quantification dataset.

[0011] S3. Pre-set the staging feature matrix for each stage of monkeypox virus infection, and determine the main stage label based on the matching degree between the lesion quantification dataset and the staging feature matrix.

[0012] S4. Using the main stage label as the time-series anchor point, dynamically fit the continuously monitored three-dimensional symptom density vector to generate the lesion evolution trajectory curve, and calculate the stage transition rate based on the slope change of the lesion evolution trajectory curve to obtain the disease deterioration risk coefficient.

[0013] S5 integrates the main stage label, lesion evolution trajectory curve, and disease progression risk coefficient to generate a visualized disease progression map and obtain standardized clinical staging records.

[0014] Preferably, the method for generating healthy texture templates and initial baseline libraries of lesions includes:

[0015] Images of normal skin on the healthy side of the patient and images of the initial lesion were acquired. The normal skin image on the healthy side was processed by region alignment and cropping to obtain a healthy texture patch that matches the size and shape of the initial lesion region. The brightness and color of the patch were then normalized. The lesion region was extracted from the initial lesion image. The extracted initial lesion region image was then standardized to generate an initial lesion baseline library containing color features, texture features, and region contours.

[0016] Preferably, the method for obtaining the comparison reference image set includes:

[0017] The healthy texture patch and the initial lesion image are converted from color images to a color space that separates luminance and color, and the luminance channel information in the healthy texture patch and the initial lesion image is extracted. An adaptive histogram stretching operation is performed on the luminance channel information. The stretching boundary value is determined based on the local luminance distribution of the image, and the original luminance of the healthy texture patch and the initial lesion image is mapped to the standard luminance range, thereby obtaining the comparison benchmark image group.

[0018] Preferably, the method for obtaining the lesion quantification dataset includes:

[0019] The current monitoring image of the patient is acquired and preprocessed. Based on the healthy texture template and the initial image of the lesion in the comparison reference image group, the abnormal area in the current monitoring image of the patient is identified as the lesion area through differential analysis.

[0020] Layered feature extraction was performed on the lesion area to obtain epidermal elevation, erythema infiltration depth and herpes density, and then a three-dimensional symptom density vector was constructed. The texture roughness of the lesion area surface was extracted and combined with the three-dimensional symptom density vector to form a lesion quantification dataset.

[0021] Preferably, the method for determining the primary installment label includes:

[0022] A staging feature matrix for each stage of monkeypox virus infection is pre-defined. The lesion quantification dataset is matched with the staging feature matrix for similarity, and the similarity matching result is used as the main stage label corresponding to the patient's current monitoring image.

[0023] Preferably, the method for obtaining the lesion evolution trajectory curve includes:

[0024] Three-dimensional symptom density vectors are recorded at fixed time intervals. After data cleaning, a continuous three-dimensional symptom density vector sequence is formed. The main stage label is associated with the three-dimensional symptom density vector sequence to form a time-series anchor point. For example, when the main stage label is determined for the first time in a monitoring process, the corresponding time point is the time-series anchor point of that label. If the main stage label is changed in the future, a corresponding time-series anchor point will be added. All time-series anchor points are collected to form a multi-anchor time-series axis.

[0025] The three-dimensional symptom density vector sequence is divided into sliding windows, and the fitting parameters are dynamically adjusted by combining multiple anchor point time axes to obtain the window dataset. The features of each dimension of the window dataset are fitted with quadratic polynomials to generate fitting curves, which are then combined to form the lesion evolution trajectory curve.

[0026] Preferably, the method for obtaining the risk factor for disease deterioration includes:

[0027] The first derivative of each fitted curve contained in the lesion evolution trajectory curve is calculated to obtain the slope of each fitted curve at different time points; the slope change rate of the fitted curve is obtained based on the slope difference between two adjacent time points; the slope change rates of all fitted curves are weighted to obtain the stage transition rate.

[0028] Based on the slope of each fitted curve at different time points, a directional coefficient for the change of disease characteristics is defined, and a feature deterioration label is generated for features that show a worsening trend. The directional coefficient is determined by the slope of each fitted curve. When the slope is greater than 0, it reflects that the value of the corresponding feature is increasing and the monkeypox disease is worsening. When the slope is less than or equal to 0, it reflects that the value of the corresponding feature is decreasing and the monkeypox disease is improving.

[0029] By setting a preset clinical baseline threshold and combining the stage transition rate and characteristic deterioration markers, a deterioration risk coefficient is generated.

[0030] Preferably, the method for obtaining standardized clinical staging records includes:

[0031] Using time points as an index, the main stage label and the risk coefficient of disease progression are linked to the lesion evolution trajectory curve, and a disease progression map is generated through visualization rendering; based on the disease progression map, a standardized clinical staging file is constructed.

[0032] An apparatus includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, it implements a monkeypox virus classification method based on image comparison.

[0033] A storage medium storing a computer program, which, when executed, implements a monkeypox virus classification method based on image comparison.

[0034] This invention provides a method, device, and storage medium for classifying monkeypox virus based on image comparison, which has the following beneficial effects:

[0035] By establishing time-series anchor points based on changes in the main stage label, a time axis with a multi-anchor point structure is formed, which effectively solves the fragmentation and ambiguity problems of traditional lesion observation methods in the time dimension. This structure not only clearly delineates the evolution stages of lesions, but also supports the fitting parameter update mechanism across stages, improving the sensitivity and adaptability to lesion stage switching.

[0036] By fitting the three-dimensional symptom density vector within each sliding window to form a multi-dimensional trajectory curve, it is possible to analyze the changing trend of each feature individually, and also to observe the co-evolutionary relationship between them (such as the simultaneous increase of epidermal elevation and herpes density at a certain stage). This co-feature fusion mode improves the accuracy and interpretability of staging identification and disease trend judgment.

[0037] An innovative directional coefficient mechanism is introduced to determine whether each feature is on a worsening trend (such as a continuous increase in herpes density) by the slope of the fitted curve. The feature deterioration markers are then used to weight and integrate the feature into the risk calculation process. Compared with a single threshold judgment, this mechanism is more in line with the complexity of disease changes under the combined effect of multiple symptoms in actual clinical practice.

[0038] By integrating the stage transition rate with the characteristic deterioration direction coefficient, a deterioration risk coefficient model was established to support the quantitative classification of the disease evolution state, provide doctors with continuous, objective, and quantitative risk warning information, and assist in clinical decision-making and intervention timing selection. Attached Figure Description

[0039] Figure 1 This is a schematic diagram of the process of a monkeypox virus classification method based on image comparison according to the present invention;

[0040] Figure 2 This is a schematic diagram of the structure of a monkeypox virus classification system based on image comparison according to the present invention;

[0041] Figure 3 This is a schematic diagram of the device of the present invention;

[0042] Figure 4 This is a schematic diagram of the storage medium of the present invention. Detailed Implementation

[0043] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0044] Example 1, please refer to Figure 1 In this embodiment, a monkeypox virus classification method based on image comparison includes:

[0045] Monkeypox is a zoonotic infectious disease caused by the monkeypox virus. Monkeypox outbreaks are mainly concentrated in Central and West Africa, but in recent years it has shown a significant trend of cross-regional transmission globally. Clinically, the symptoms of monkeypox are similar to those of smallpox, but the course of the disease is usually milder. The main symptoms are fever, headache, myalgia, swollen lymph nodes, fatigue, and characteristic skin lesions. The skin lesions usually go through an evolutionary process from the prodromal stage, papular stage, pustular stage, crusting stage, and healing stage. There are certain commonalities in the characteristics of each stage, but they also show great heterogeneity due to individual differences, viral strain variations, and different immune statuses.

[0046] Although monkeypox skin lesions have a relatively clear evolutionary process, there are still many technical shortcomings in the monitoring and assessment of skin lesion evolution and disease risk in the clinical diagnosis and treatment of monkeypox:

[0047] The observation of lesions lacks continuity, and the time dimension is fragmented and ambiguous: In existing technologies, the evolution stages of lesions mostly rely on fixed-point observation or experience judgment, and lack a continuous time modeling mechanism that combines dynamic updates of labels, making it difficult to track the evolution of the disease in detail and reflect the gradual process or mutation signal between stages; especially when the boundaries of multiple stages are blurred, traditional methods cannot provide quantitative evidence with time anchoring.

[0048] Feature analysis is isolated and fragmented, lacking a multi-dimensional collaborative modeling mechanism: Traditional lesion identification methods are mostly based on single features (such as rash density or erythema size), lacking the ability to model the collaborative evolution between multiple key symptom indicators, making it difficult to capture the correlation and change trends of multiple symptoms in the same stage, thus limiting the comprehensive understanding and prediction ability of lesion evolution mechanism.

[0049] The logic for diagnosing disease progression is crude, lacking the ability to dynamically model trends: Existing methods often rely on static thresholds or human experience to determine disease stages, ignoring the differences in evolution speed and characteristic manifestations among individuals. They also fail to dynamically capture the rate of transition from one lesion state to another, lacking sensitivity to stage switching processes. Furthermore, the lack of an "indicative trend" makes it difficult to determine whether current characteristic changes are trending towards worsening or improvement. Especially in the early stages or potentially worsening phases, the lack of early warning mechanisms for trend changes poses a risk of delayed intervention.

[0050] Therefore, there is an urgent need to construct an intelligent diagnostic and treatment method that combines image features, temporal evolution information, and multi-feature collaborative judgment, which can realize continuous modeling, accurate staging, and dynamic risk assessment of monkeypox skin lesion evolution, so as to improve the objectivity, foresight, and timeliness of clinical judgment and intervention.

[0051] To effectively address the above problems, this invention proposes a monkeypox virus classification method based on image comparison, comprising:

[0052] S1. Collect images of normal skin and initial lesions on the healthy side of the patient, and generate a healthy texture template and an initial benchmark library for lesions; perform grayscale normalization on the healthy texture template and the initial benchmark library for lesions through adaptive histogram stretching, and output a set of comparison benchmark images;

[0053] S2. Obtain the patient's current monitoring image, segment the lesion area by comparing it with the baseline image group, extract the layered features of the lesion area to generate a three-dimensional symptom density vector, extract the texture roughness of the lesion area surface, and form a lesion quantification dataset.

[0054] S3. Pre-set the staging feature matrix for each stage of monkeypox virus infection, and determine the main stage label based on the matching degree between the lesion quantification dataset and the staging feature matrix.

[0055] S4. Using the main stage label as the time-series anchor point, dynamically fit the continuously monitored three-dimensional symptom density vector to generate the lesion evolution trajectory curve, and calculate the stage transition rate based on the slope change of the lesion evolution trajectory curve to obtain the disease deterioration risk coefficient.

[0056] S5 integrates the main stage label, lesion evolution trajectory curve, and disease progression risk coefficient to generate a visualized disease progression map and obtain standardized clinical staging records.

[0057] Methods for generating healthy texture templates and initial baseline libraries for lesions include:

[0058] Images of healthy skin on the patient's unaffected side and images of the initial lesion were collected. The healthy skin image on the unaffected side was a healthy image of the uninfected area symmetrical to the initial lesion area. The healthy skin image on the unaffected side was processed by region alignment and cropping to obtain a healthy texture patch that matches the size and shape of the initial lesion area. The brightness and color of the patch were then normalized. The lesion area was extracted from the initial lesion image. The extracted initial lesion area image was then standardized to generate an initial lesion baseline library containing color features, texture features, and region contours.

[0059] Methods for obtaining the benchmark image set for comparison include:

[0060] The healthy texture patch and the initial lesion image are converted from color images to a color space that separates luminance and color, and the luminance channel information in the healthy texture patch and the initial lesion image is extracted. An adaptive histogram stretching operation is performed on the luminance channel information. The stretching boundary value is determined based on the local luminance distribution of the image, and the original luminance of the healthy texture patch and the initial lesion image is mapped to the standard luminance range, thereby obtaining the comparison benchmark image group.

[0061] Methods for obtaining lesion quantification datasets include:

[0062] The current monitoring image of the patient is acquired and preprocessed to ensure that the brightness and color distribution of the current monitoring image of the patient is consistent with the comparison reference image group; based on the healthy texture template and the initial image of the lesion in the comparison reference image group, the abnormal area in the current monitoring image of the patient is identified as the lesion area through differential analysis;

[0063] Layered feature extraction was performed on the lesion area to obtain epidermal elevation, erythema infiltration depth and herpes density, and then a three-dimensional symptom density vector was constructed. Local binary mode was introduced to calculate the LBP texture roughness factor, extract the texture roughness of the lesion area surface, and combine it with the three-dimensional symptom density vector to form a lesion quantification dataset.

[0064] Methods for determining the primary installment label include:

[0065] A staging feature matrix is ​​pre-defined for each stage of monkeypox virus infection. For example, based on clinical data, the development stages of monkeypox lesions can be divided into the prodromal stage, papular stage, pustular stage, crusting stage, and healing stage. The skin lesions corresponding to each stage differ in morphology, density, and texture. Therefore, parameters such as lesion area, mean gray value, texture statistical features, and surface texture roughness at different development stages of monkeypox lesions can be selected to construct the staging feature matrix. The lesion quantification dataset is then matched with the staging feature matrix for similarity. The similarity matching result is used as the main stage label (prodromal stage, papular stage, pustular stage, crusting stage, or healing stage) corresponding to the patient's current monitoring image, thereby reflecting the monkeypox lesion development stage corresponding to the patient's current condition.

[0066] Methods for obtaining lesion evolution trajectory curves include:

[0067] The three features contained in the three-dimensional symptom density vector are recorded at fixed time intervals: epidermal elevation, erythema infiltration depth, and herpes density. After data cleaning, a continuous three-dimensional symptom density vector sequence is formed.

[0068] For example: First, continuous monitoring data is collected at fixed 24-hour intervals. The system records the three core features of the three-dimensional symptom density vector: epidermal elevation, erythema infiltration depth, and herpes density. After the data collection is completed, the data cleaning process begins: Z-score standardization can be used to accurately identify and correct outliers. For minor deviations in monitoring time, a linear interpolation algorithm is used to uniformly map the data to a standard time axis to ensure the continuity and consistency of the time series data. Finally, the processed three-dimensional symptom density vector sequence is output.

[0069] The main stage label is associated with the three-dimensional symptom density vector sequence to form time-series anchor points. For example, when the main stage label is determined for the first time in a monitoring process, the corresponding time point is the time-series anchor point of that label. If the main stage label is changed in the future, a corresponding time-series anchor point will be added. All time-series anchor points are collected to form a multi-anchor time-series axis.

[0070] These time-series anchor points construct the time framework of lesion evolution, not only clearly delineating different stages of lesion evolution, but also providing key time node basis for subsequent dynamic fitting. Within the same major stage, given the significant stage homogeneity of lesion evolution, the trajectory can be reconstructed through standardized curve fitting methods (such as quadratic polynomial fitting). When the monitoring data crosses the boundaries of different stages, the system will automatically perform dynamic update operations of the fitting parameters according to the preset trigger mechanism, so as to accurately match the dynamic law of lesion evolution in the new stage.

[0071] For example, if a patient's primary stage is labeled "eruptive stage," after the target time-series anchor point is determined, continuous monitoring data is selected according to the set window size for parameter fitting. For instance, during the 10th monitoring, the data from the previous 5 monitoring sessions are used to fit curves of epidermal elevation, erythema infiltration depth, and herpes density. The curves show that the epidermal elevation speed is accelerating, the erythema infiltration depth is deepening, and the herpes density is increasing at a faster rate, which is consistent with the characteristics of the eruptive stage. This allows for clear tracking of the lesion's evolution process and provides basic data for subsequent calculations of the transition rate.

[0072] A sliding window is used to divide the three-dimensional symptom density vector sequence, and the fitting parameters are dynamically adjusted in combination with a multi-anchor time axis to obtain a window dataset. For example, the three-dimensional symptom density vector sequence is first divided into windows. For a certain time node in the multi-anchor time axis, the epidermal elevation, erythema infiltration depth, and herpes density data of the previous 5-7 consecutive monitoring are selected as the window dataset. The features of each dimension of the window dataset are fitted with quadratic polynomials to generate fitting curves, which are combined to form a lesion evolution trajectory curve, which can reflect the temporal changes of single features and the collaborative evolution of multiple features.

[0073] For example, considering the continuous evolution characteristics of the three-dimensional symptom density vector, a weighted least squares method is used for quadratic polynomial fitting (taking into account both linear trends and curvature changes, consistent with the clinical pattern of "slow development-acceleration-leveling" in monkeypox lesions). The mathematical expression is: ,in, For time anchor points First Fitted values ​​for each feature; Index of features , respectively representing the three features contained in the three-dimensional symptom density vector: epidermal elevation, erythema infiltration depth, and herpes density; , and These are the fitting coefficients. Reflecting curvature, Reflecting a linear trend, The constant term is used; by performing quadratic polynomial fitting on the epidermal elevation, erythema infiltration depth, and herpes density, fitting curves are generated respectively. , and These features combine to form a three-dimensional lesion evolution trajectory curve, which intuitively reflects: the temporal changes of single features (such as the rising and falling trend of herpes density over time) and the synergistic evolution of multiple features (such as the synchronous increase of epidermal elevation and herpes density during the papular stage).

[0074] Methods for obtaining the risk factor for disease progression include:

[0075] The stage transition rate is used to quantify the speed at which monkeypox disease transitions from the current stage to an adjacent stage (e.g., papular stage → ulcer stage). The core principle is to reflect the "severity of stage switching" through the rate of change of the slope of the lesion evolution trajectory curve. The steps are as follows:

[0076] The first derivative of each fitted curve contained in the lesion evolution trajectory curve is calculated to obtain the slope of each fitted curve at different time points; the slope change rate of the fitted curve is obtained based on the slope difference between two adjacent time points; the slope change rates of all fitted curves are weighted to obtain the stage transition rate; the larger the stage transition rate, the faster the lesion characteristics change and the higher the probability of stage transition.

[0077] Based on the slope of each fitted curve at different time points, a directional coefficient for the change of disease characteristics is defined, and a feature deterioration label is generated for features showing a deterioration trend; the directional coefficient is defined as... It is used to determine whether the degree of epidermal elevation, the depth of erythema infiltration, and the density of herpes lesions show a worsening trend; among them, Epidermal elevation at time points Directional coefficient; For the depth of erythema infiltration at time points Directional coefficient; Herpes density at time points Directional coefficient;

[0078] and The values ​​are either 0 or 1, and are determined by the slope of each fitted curve. When the slope is greater than 0, it reflects an increase in the value of the corresponding feature, indicating a worsening trend in monkeypox; when the slope is less than or equal to 0, it reflects a decrease in the value of the corresponding feature, indicating a tendency for monkeypox to improve. For example: = ;in, The fitted curve corresponding to the epidermal elevation at time point The slope;

[0079] Preset stage transition thresholds and single-feature deterioration thresholds are used as preset clinical benchmark thresholds. Combined with stage transition rate and feature deterioration markers, a deterioration risk coefficient is generated. The higher the deterioration risk coefficient, the higher the risk of monkeypox disease deterioration.

[0080] Risk of deterioration ;in, The weighting coefficients for the stage transition rate, The weighting coefficients represent the degree of feature deterioration. ,like , ; For time points The stage transition rate; The preset stage transition critical threshold; Indicates when The value is set to 1 to avoid excessive risk factor overflow caused by excessive stage transition rate. For the first The fitting curve corresponding to each feature at time point The slope; The pre-defined critical slope for single-feature deterioration; This indicates that only the percentage of slopes showing a deteriorating trend is retained;

[0081] For example: preset clinical baseline threshold; preset critical threshold for stage transition. Preset single-feature deterioration critical slope Weighting: , ;

[0082] Time point Monitoring data: stage transition rate The slopes of the fitted curves corresponding to epidermal elevation, erythema infiltration depth, and herpes density are as follows: (Increased skin elevation, worsening trend) (The depth of erythema infiltration is decreasing, showing a trend of improvement) (Increased density of herpes lesions, indicating a worsening trend); based on this, the directional coefficient is derived. ;

[0083] at this time ; ; ; Therefore, the risk coefficient at this time can be derived. ;

[0084] The evolution of a disease can be quantitatively assessed by using a risk factor for worsening, for example: if If so, it reflects low risk (stable or improving condition); if If it indicates a medium risk (requiring enhanced monitoring); if This indicates a high risk (requiring clinical intervention).

[0085] Methods for obtaining standardized clinical staging records include:

[0086] Using time points as an index, the main stage label and the risk coefficient of disease progression are linked to the lesion evolution trajectory curve, and a disease progression map is generated through visualization rendering. Based on the disease progression map, a standardized clinical staging file is constructed (such as basic patient information, disease stage statistics, risk records, trajectory evolution, and clinical recommendation summaries).

[0087] The preset clinical benchmark threshold is set by staff. By collecting different clinical benchmark indicators, the average value of multiple clinical benchmark indicators is taken as the preset clinical benchmark threshold. Similarly, preset stage transition thresholds and preset single feature deterioration critical slopes are set.

[0088] This embodiment establishes time-series anchor points based on changes in the main stage label, forming a time axis with a multi-anchor point structure. This effectively solves the fragmentation and ambiguity problems of traditional lesion observation methods in the time dimension. This structure not only clearly delineates the evolution stages of lesions, but also supports a cross-stage fitting parameter update mechanism, improving the sensitivity and adaptability to lesion stage switching.

[0089] By fitting the three-dimensional symptom density vector within each sliding window to form a multi-dimensional trajectory curve, it is possible to analyze the changing trend of each feature individually, and also to observe the co-evolutionary relationship between them (such as the simultaneous increase of epidermal elevation and herpes density at a certain stage). This co-feature fusion mode improves the accuracy and interpretability of staging identification and disease trend judgment.

[0090] An innovative directional coefficient mechanism is introduced to determine whether each feature is on a worsening trend (such as a continuous increase in herpes density) by the slope of the fitted curve. The feature deterioration markers are then used to weight and integrate the feature into the risk calculation process. Compared with a single threshold judgment, this mechanism is more in line with the complexity of disease changes under the combined effect of multiple symptoms in actual clinical practice.

[0091] By integrating the stage transition rate with the characteristic deterioration direction coefficient, a deterioration risk coefficient model was established to support the quantitative classification of the disease evolution state, provide doctors with continuous, objective, and quantitative risk warning information, and assist in clinical decision-making and intervention timing selection.

[0092] Example 2, please refer to Figure 2As shown, for parts not described in detail in this embodiment, please refer to the description in Embodiment 1. A monkeypox virus classification system based on image comparison is provided, including:

[0093] The individual baseline construction module collects images of normal skin and initial lesions on the healthy side of the patient, and generates a healthy texture template and an initial baseline library of lesions. Through adaptive histogram stretching, the healthy texture template and the initial baseline library of lesions are normalized to grayscale, and a set of comparison baseline images is output.

[0094] The symptom density quantization module acquires the patient's current monitoring image, segments the lesion area by comparing it with the baseline image group, extracts the hierarchical features of the lesion area to generate a three-dimensional symptom density vector, and extracts the texture roughness of the lesion area surface to form a lesion quantification dataset.

[0095] The stage identification transition module pre-sets the staging feature matrix of each stage of monkeypox virus infection, and determines the main stage label based on the matching degree between the lesion quantification dataset and the staging feature matrix.

[0096] The temporal evolution tracking module uses the main stage label as the temporal anchor point to dynamically fit the continuously monitored three-dimensional symptom density vector to generate a lesion evolution trajectory curve, and calculates the stage transition rate based on the slope change of the lesion evolution trajectory curve to obtain the risk coefficient of disease deterioration.

[0097] The clinical nursing advice module integrates the main stage label, lesion evolution trajectory curve, and disease deterioration risk coefficient, and obtains standardized clinical staging records by generating a visualized disease progression map.

[0098] Example 3, please refer to Figure 3 As shown, this application also provides a device 500. The device 500 may include one or more processors and one or more memories. The memories store computer-readable code, which, when executed by the one or more processors, can perform an image comparison-based monkeypox virus classification method as described above.

[0099] like Figure 3 As shown, device 500 may include a bus 501, one or more CPUs 502, ROM 503, RAM 504, a communication port 505 connected to a network, input / output 506, hard disk 507, etc. The storage device in device 500, such as ROM 503 or hard disk 507, may store a monkeypox virus classification method based on image comparison provided in this application. Furthermore, device 500 may also include a user interface 508. Of course, Figure 2 The architecture shown is merely exemplary and can be omitted as needed when implementing different devices. Figure 2 One or more components in the illustrated electronic device.

[0100] Example 4, please refer to Figure 4 The diagram shows a storage medium 250 according to one embodiment of this application. Computer-readable instructions are stored on the storage medium 250. When executed by a processor, the computer-readable instructions can perform a monkeypox virus classification method based on image comparison according to an embodiment of this application, as described with reference to the above figures. The storage medium 250 includes, but is not limited to, volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and cache memory. Non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc.

[0101] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed in this invention can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0102] In the several embodiments provided by this invention, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only one method, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0103] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

[0104] In conclusion, the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A monkeypox virus classification method based on image comparison, characterized in that, include: S1. Collect images of the patient's healthy skin and initial lesions on the healthy side, and generate healthy texture templates and initial baseline libraries for lesions; By adaptive histogram stretching, grayscale normalization is performed on the healthy texture template and the initial benchmark library of lesions, and a set of comparison benchmark images is output. S2. Obtain the patient's current monitoring image, segment the lesion area by comparing it with the baseline image group, extract the layered features of the lesion area to generate a three-dimensional symptom density vector, extract the texture roughness of the lesion area surface, and form a lesion quantification dataset. S3. Pre-set the staging feature matrix for each stage of monkeypox virus infection, and determine the main stage label based on the matching degree between the lesion quantification dataset and the staging feature matrix. S4. Using the main stage label as the time-series anchor point, dynamically fit the continuously monitored three-dimensional symptom density vector to generate the lesion evolution trajectory curve, and calculate the stage transition rate based on the slope change of the lesion evolution trajectory curve to obtain the disease deterioration risk coefficient. S5 integrates the main stage label, lesion evolution trajectory curve, and disease progression risk coefficient to generate a visualized disease progression map and obtain standardized clinical staging records.

2. The monkeypox virus classification method based on image comparison according to claim 1, characterized in that, The method for generating healthy texture templates and initial baseline libraries of lesions includes: Images of normal skin on the healthy side of the patient and images of the initial lesion were acquired. The normal skin image on the healthy side was processed by region alignment and cropping to obtain a healthy texture patch that matches the size and shape of the initial lesion region. The brightness and color of the patch were then normalized. The lesion region was extracted from the initial lesion image. The extracted initial lesion region image was then standardized to generate an initial lesion baseline library containing color features, texture features, and region contours.

3. The monkeypox virus classification method based on image comparison according to claim 2, characterized in that, The method for obtaining the comparison reference image set includes: The healthy texture patch and the initial lesion image are converted from color images to a color space that separates luminance and color, and the luminance channel information in the healthy texture patch and the initial lesion image is extracted. An adaptive histogram stretching operation is performed on the luminance channel information. The stretching boundary value is determined based on the local luminance distribution of the image, and the original luminance of the healthy texture patch and the initial lesion image is mapped to the standard luminance range, thereby obtaining the comparison benchmark image group.

4. The monkeypox virus classification method based on image comparison according to claim 3, characterized in that, The methods for obtaining the lesion quantification dataset include: The current monitoring image of the patient is acquired and preprocessed. Based on the healthy texture template and the initial image of the lesion in the comparison reference image group, the abnormal area in the current monitoring image of the patient is identified as the lesion area through differential analysis. Layered feature extraction was performed on the lesion area to obtain epidermal elevation, erythema infiltration depth and herpes density, and then a three-dimensional symptom density vector was constructed. The texture roughness of the lesion area surface was extracted and combined with the three-dimensional symptom density vector to form a lesion quantification dataset.

5. The monkeypox virus classification method based on image comparison according to claim 4, characterized in that, The method for determining the primary installment label includes: A staging feature matrix for each stage of monkeypox virus infection is pre-defined. The lesion quantification dataset is matched with the staging feature matrix for similarity, and the similarity matching result is used as the main stage label corresponding to the patient's current monitoring image.

6. The monkeypox virus classification method based on image comparison according to claim 5, characterized in that, The method for obtaining the lesion evolution trajectory curve includes: Three-dimensional symptom density vectors are recorded at fixed time intervals. After data cleaning, a continuous three-dimensional symptom density vector sequence is formed. The main stage label is associated with the three-dimensional symptom density vector sequence to form a time-series anchor point. For example, when the main stage label is determined for the first time in a monitoring process, the corresponding time point is the time-series anchor point of that label. If the main stage label is changed in the future, a corresponding time-series anchor point will be added. All time-series anchor points are collected to form a multi-anchor time-series axis. The three-dimensional symptom density vector sequence is divided into sliding windows, and the fitting parameters are dynamically adjusted by combining multiple anchor point time axes to obtain the window dataset. The features of each dimension of the window dataset are fitted with quadratic polynomials to generate fitting curves, which are then combined to form the lesion evolution trajectory curve.

7. The monkeypox virus classification method based on image comparison according to claim 6, characterized in that, The methods for obtaining the risk factor for disease worsening include: The first derivative of each fitted curve contained in the lesion evolution trajectory curve is calculated to obtain the slope of each fitted curve at different time points; the slope change rate of the fitted curve is obtained based on the slope difference between two adjacent time points; the slope change rates of all fitted curves are weighted to obtain the stage transition rate. Based on the slope of each fitted curve at different time points, a directional coefficient for the change of disease characteristics is defined, and a feature deterioration label is generated for features that show a worsening trend. The directional coefficient is determined by the slope of each fitted curve. When the slope is greater than 0, it reflects that the value of the corresponding feature is increasing and the monkeypox disease is worsening. When the slope is less than or equal to 0, it reflects that the value of the corresponding feature is decreasing and the monkeypox disease is improving. By setting a preset clinical baseline threshold and combining the stage transition rate and characteristic deterioration markers, a deterioration risk coefficient is generated.

8. The monkeypox virus classification method based on image comparison according to claim 7, characterized in that, The method for obtaining standardized clinical staging records includes: Using time points as an index, the main stage label and the risk coefficient of disease progression are linked to the lesion evolution trajectory curve, and a disease progression map is generated through visualization rendering; based on the disease progression map, a standardized clinical staging file is constructed.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the electronic device executes the computer program, it implements the monkeypox virus classification method based on image comparison as described in any one of claims 1-8.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, which, when executed, implements the image comparison-based monkeypox virus classification method according to any one of claims 1-9.

Images