Skin disease three-dimensional imaging and lesion evolution trend simulation system

Abstract

The invention relates to the technical field of image analysis, in particular to a skin disease three-dimensional imaging and focus evolution trend simulation system. The system acquires a state image of a skin disease; acquiring a focus area based on RGB channel values of pixel points in the state image; the change degree of each dimension of the lesion area is acquired according to the dimension change of the lesion area in each state image compared with the dimension change of the lesion area in the previous adjacent state image, then the dominant weight of each dimension is determined, the dominant dimension is acquired, and according to the dominant dimension difference of the adjacent state images and the dominant weight difference of the dimensions, the lesion of the lesion area is acquired. Determining each evolution stage of the skin disease; and according to the influence of different filtering kernel scales on the change degree of the dominant dimension in the evolution stage, obtaining the optimal filtering kernel scale of each evolution stage to perform three-dimensional imaging of skin diseases and focus evolution trend simulation. According to the method, the accuracy of skin disease area identification and focus evolution trend simulation is improved by self-adapting to the optimal filtering kernel scale of each evolution stage.

Description

Technical Field

[0001] This invention relates to the field of image analysis technology, specifically to a three-dimensional imaging system for skin diseases and a simulation system for the evolution trend of lesions. Background Technology

[0002] Early diagnosis and dynamic monitoring of skin diseases rely on precise analysis of lesion morphological evolution. Three-dimensional imaging technology provides comprehensive and detailed data support for the observation and analysis of skin diseases, enabling intelligent identification and localization of skin diseases and analysis of lesion morphological evolution trends. Specifically, three-dimensional imaging technology reconstructs a three-dimensional model of the skin surface through multi-angle image acquisition.

[0003] In reality, skin diseases undergo different evolutionary stages, each requiring a different filter kernel scale for image processing. For example, color-dominated evolution stages necessitate a relatively large filter kernel scale to smooth noise and prevent color interference, while shape-dominated evolution stages require a relatively small filter kernel scale to preserve boundary details. However, current technologies neglect to adjust the filter kernel scale for different evolutionary stages of skin diseases, instead using a fixed scale. This results in an inaccurate representation of the disease's characteristic information, leading to inaccurate 3D model construction and consequently, inaccurate simulation of lesion evolution trends. Summary of the Invention

[0004] To address the technical problem of inaccurate simulation of 3D models and lesion evolution trends in skin diseases due to inaccurate filtering kernel scale, the present invention aims to provide a 3D imaging and lesion evolution trend simulation system for skin diseases. The specific technical solution adopted is as follows: This invention provides a three-dimensional imaging and lesion evolution trend simulation system for skin diseases, which includes the following steps: The image acquisition module is used to acquire real-time images of skin diseases and to acquire reference images of normal skin areas. The lesion area acquisition module is used to filter out abnormal pixels in each status image based on the difference in RGB channel values ​​between each pixel in each status image and the pixel in the reference image, thereby determining the lesion area in each status image. The dominant weight acquisition module is used to obtain the degree of change of each dimension of each lesion region in each state image based on the changes of each lesion region in each state image compared with its changes in each dimension in the previous adjacent state image, and then determine the dominant weight of each dimension in each state image. The evolution stage acquisition module is used to acquire the dominant dimension in each state image based on the dominant weight. Based on the difference in dominant dimension between each state image and its previous adjacent state image, as well as the difference in dominant weight of each dimension, the segmented state images are filtered to determine the various evolution stages of the skin disease. The optimal filter kernel scale acquisition module is used to obtain the optimal filter kernel scale for each evolution stage based on the influence of different filter kernel scales on the degree of change of the dominant dimension of each lesion region in each state image within each evolution stage. The processing module is used for three-dimensional imaging of skin diseases and simulation of lesion evolution trends based on the optimal filter kernel scale.

[0005] Furthermore, the method for obtaining the abnormal pixels is as follows: For any channel in the RGB channels, the average value of that channel for all pixels in the reference image is used as the overall reference value for that channel. The result of normalizing the difference between the channel value of each pixel in the reference image and the overall reference value is used as the tolerance level of the channel of each pixel in the reference image. The sum of the maximum tolerance levels for each RGB channel of all pixels in the reference image is used as the overall color tolerance level. For any pixel in any state image, the sum of the tolerance levels of each RGB channel of that pixel and the difference between the sum and the overall color tolerance level are normalized to determine the degree of abnormality of that pixel. When the degree of abnormality exceeds the preset abnormality threshold, the corresponding pixel is considered an abnormal pixel.

[0006] Furthermore, the method for obtaining the degree of change is as follows: For any lesion region and any dimension of the lesion region in any state image, the previous adjacent state image of the state image is taken as the target image, and the difference between the data corresponding to that dimension of the lesion region in the state image and the target image is taken as the first difference. The result of normalizing the first difference with the ratio of the corresponding dimension of the lesion region in the target image is taken as the degree of change of that dimension of the lesion region in the state image.

[0007] Furthermore, the method for obtaining the dominant weight is as follows: For any state image, the covariance matrix corresponding to the degree of change of all dimensions of all lesion regions in the state image is obtained by the principal component analysis algorithm, and the eigenvector corresponding to the largest eigenvalue of the covariance matrix is ​​used as the principal component vector. The result of normalizing the absolute value of each element in the principal component vector is used as the dominant weight of the corresponding dimension in the state image.

[0008] Furthermore, the method for obtaining the segmented state image is as follows: For any state image, the difference in dominant weights of the dominant dimension between the state image and its previous neighboring state image is obtained as the first evolution analysis value of the state image; wherein, when the dominant dimension of the state image is different from that of its previous neighboring state image, the first evolution analysis value is 1 by default. The mean of the difference in dominant weights for each dimension between the current state image and its previous neighboring state image is obtained as the second evolution analysis value of the current state image. The normalized product of the first evolution analysis value and the second evolution analysis value is taken as the degree of evolution of the state image. When the degree of evolution exceeds the predicted degree of evolution threshold, the corresponding state image is used as the segmented state image.

[0009] Furthermore, the method for obtaining the evolution stage is as follows: The time corresponding to the first state image is taken as the start time, and the time corresponding to the last state image is taken as the end time; the time period consisting of the start time and the end time is taken as the overall stage. The overall stage is divided by taking the time immediately preceding the time corresponding to each segmented state image as the cutoff time, and each local stage after the division is taken as each evolution stage.

[0010] Furthermore, the method for obtaining the optimal filter kernel scale is as follows: For any evolution stage, the dominant dimension that appears most frequently in all segmented state images within that evolution stage is taken as the dominant dimension in all state images within that evolution stage. For any given filter kernel scale, each state image in the evolution stage is filtered using that filter kernel scale to obtain a filtered state image. The mean value of the degree of change of the dominant dimension of all lesion regions in all the filtered state images is obtained as the filtering degree of the filtering kernel scale for this evolution stage; The filter kernel size corresponding to the maximum filtering degree is taken as the optimal filter kernel size for this evolution stage.

[0011] Furthermore, the method for obtaining the dominant dimension is as follows: The dimension corresponding to the largest dominant weight in each state image is taken as the dominant dimension in each state image.

[0012] Furthermore, the method for obtaining the lesion area is as follows: For any state image, the connected components formed by the abnormal pixels in the state image are all regarded as abnormal regions. For any abnormal region, the region corresponding to the abnormal region after performing an opening operation followed by a closing operation is taken as the lesion region.

[0013] Furthermore, the method for obtaining the state image is as follows: For any given moment, the image obtained by registering and stitching together skin disease images acquired from multiple angles at that moment is taken as the state image at that moment.

[0014] The present invention has the following beneficial effects: This invention first filters out abnormal pixels in each state image based on the difference in RGB channel values ​​between each pixel in the state image and the pixel in the reference image. This prepares for subsequent determination of the lesion area of ​​skin disease in each state image, thereby improving the efficiency of subsequent analysis of lesion area changes and facilitating accurate classification of the various evolution stages of skin disease. To accurately analyze the changes in each lesion area, the degree of change in each dimension of each lesion area in each state image is obtained based on the changes in each dimension compared to its predecessor in the previous state image. This accurately reflects the changes in each dimension of each lesion area. Furthermore, to accurately classify the various evolution stages of skin disease, the dominant weight of each dimension in each state image is determined by the degree of change in each dimension of each lesion area, accurately reflecting the overall changes in each dimension of each state image. By accurately obtaining the dominant dimension in each state image based on the dominant weight, the main changing dimensions in each state image are accurately reflected, preparing for the subsequent determination of each evolution stage of the skin disease. Then, based on the difference in dominant dimension between each state image and its previous adjacent state image, as well as the difference in the dominant weight of each dimension, segmented state images are accurately selected, and segmented images between different evolution stages are accurately determined, thus determining each evolution stage of the skin disease. Furthermore, based on the influence of different filter kernel scales on the degree of change of the dominant dimension of each lesion region in each state image within each evolution stage, the optimal filter kernel scale for each evolution stage is obtained. This is beneficial for accurate filtering of skin disease images within the evolution stage, and then based on the optimal filter kernel scale, three-dimensional imaging and lesion evolution trend simulation of skin diseases are performed, effectively improving the accuracy of three-dimensional model construction of skin diseases, enabling accurate simulation of lesion evolution trends of skin diseases, and facilitating accurate analysis of the condition of skin diseases. Attached Figure Description

[0015] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0016] Figure 1 This is a structural block diagram of a three-dimensional imaging and lesion evolution trend simulation system for skin diseases provided in one embodiment of the present invention; Figure 2 This is a flowchart illustrating a method for obtaining a lesion area according to an embodiment of the present invention; Figure 3 This is a schematic diagram of a computer device provided according to an embodiment of the present invention. Detailed Implementation

[0017] To further illustrate the technical means and effects adopted by the present invention to achieve its intended purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effects of a three-dimensional imaging and lesion evolution trend simulation system for skin diseases proposed according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0018] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0019] The following description, in conjunction with the accompanying drawings, details the specific scheme of the three-dimensional imaging and lesion evolution trend simulation system for skin diseases provided by the present invention.

[0020] Example 1: This invention proposes a three-dimensional imaging and lesion evolution trend simulation system for skin diseases. Please refer to [link / reference]. Figure 1 The diagram shows a structural block diagram of a three-dimensional imaging and lesion evolution trend simulation system for skin diseases provided by an embodiment of the present invention. The system includes: an image acquisition module 10, a lesion region acquisition module 20, a dominant weight acquisition module 30, an evolution stage acquisition module 40, an optimal filter kernel scale acquisition module 50, and a processing module 60.

[0021] Image acquisition module 10 is used to acquire real-time images of the skin disease status and to acquire reference images of normal skin areas.

[0022] Specifically, this embodiment uses a skin disease patient as an example for analysis, and all subsequent analyses will focus on the patient's skin condition. To accurately analyze the evolution trend of the skin lesions, this embodiment acquires skin disease images from multiple angles at each time point. The images acquired from these multiple angles at each time point are then registered and stitched together to obtain the state image of the skin disease at that time point. The registration and stitching of the skin disease images acquired from multiple angles at each time point is a well-known technique and will not be described in detail here. This embodiment sets the time interval between two adjacent time points to 12 hours. The implementer can set the time interval between two adjacent time points according to the actual situation; it is not limited here. The angle from which the skin disease images are acquired at each time point can be set according to the actual situation; it is not limited here, but it must be ensured that the skin disease images acquired at each time point cover the entire skin disease area.

[0023] It is known that the distribution area of ​​skin diseases is irregular in actual situations. In order to accurately determine the lesion area in each status image, this embodiment obtains an image of the normal skin area of ​​the above-mentioned skin disease patient as a reference image. Since the skin color of the same person is similar, while the skin color of different people is different, by comparing each status image with the reference image, the lesion area in each status image can be accurately obtained, which is conducive to more efficient analysis of the changes in skin diseases.

[0024] The lesion area acquisition module 20 is used to filter out abnormal pixels in each status image based on the difference in RGB channel values ​​between each pixel in each status image and the pixel in the reference image, thereby determining the lesion area in each status image.

[0025] Specifically, it is known that lesions in skin diseases exhibit redness, swelling, and damage, showing a significant color difference from normal skin areas. Therefore, by analyzing the color characteristics of each pixel in each status image compared to those in a reference image, abnormal pixels in each status image can be identified, thus determining the lesion area within each image. Thus, this embodiment uses the difference in RGB channel values ​​between each pixel in each status image and those in a reference image to identify abnormal pixels and determine the lesion area in each status image.

[0026] Preferably, in one feasible embodiment, the method for obtaining the lesion area is described in [reference needed]. Figure 2 The document presents a flowchart of a method for obtaining a lesion area according to this embodiment, which includes the following steps: Step S201: Obtain abnormal pixels.

[0027] Considering that even healthy skin can exhibit some color unevenness, this embodiment first obtains the maximum fluctuation of skin color in a reference image as a reference for healthy skin. This is then used to compare the color fluctuation of each pixel in each status image, enabling accurate screening of abnormal pixels with significant color fluctuations in each status image. This facilitates the accurate acquisition of lesion areas in each status image.

[0028] In one possible implementation of this embodiment, the method for obtaining abnormal pixels is as follows: For any channel in the RGB channels, the average value of that channel for all pixels in the reference image is used as the overall reference value for that channel; the absolute value of the difference between the channel value of each pixel in the reference image and the overall reference value is normalized, and the result is used as the tolerance level of that channel for each pixel in the reference image; in this embodiment, the absolute value of the difference is normalized using the norm normalization function. The sum of the maximum tolerance levels of each RGB channel for all pixels in the reference image is used as the overall color tolerance level, i.e., the maximum fluctuation level of skin color in a healthy state. For any pixel in any state image, the sum of the tolerance levels of each RGB channel of that pixel and the difference between the sum and the overall color tolerance level are normalized to determine the pixel's anomaly level. This embodiment uses a normalization function to normalize this difference. A higher anomaly level indicates a greater color fluctuation compared to normal skin, making the pixel more likely to be an anomalous pixel. Therefore, this embodiment sets a preset anomaly level threshold of 0.6. Implementers can set the preset anomaly level threshold according to actual conditions; this is not limited here. When the anomaly level exceeds the preset anomaly level threshold, the corresponding pixel is considered an anomalous pixel.

[0029] At this point, the abnormal pixels in each status image have been obtained.

[0030] Step S202: Obtain the lesion area.

[0031] After identifying abnormal pixels in each state image, the connected components formed by these abnormal pixels are considered as abnormal regions. These abnormal regions are essentially lesion regions. However, considering that some noisy pixels may be mistakenly identified as abnormal in practice, this embodiment first performs an opening operation on each abnormal region to improve the purity of the lesion region and reduce false detections in order to accurately obtain the lesion region in each state image. After the opening operation, a closing operation is then performed to ensure the integrity of the lesion region. Finally, the region corresponding to each abnormal region after the opening and closing operations is considered as the lesion region, effectively ensuring the integrity and accuracy of the lesion region.

[0032] At this point, the lesion area in each status image has been obtained.

[0033] The dominant weight acquisition module 30 is used to obtain the degree of change of each dimension of each lesion region in each state image based on the changes of each lesion region in each state image compared with its changes in each dimension in the previous adjacent state image, and then determine the dominant weight of each dimension in each state image.

[0034] Specifically, the lesions of skin diseases change in multiple ways during their evolution, such as color, area, and shape. To analyze the changes in each lesion area, this embodiment uses the color, area, and shape of each lesion area as dimensions. Implementers can set the dimensions of the lesion areas according to the actual situation, and there is no limitation here. The number and types of dimensions for each lesion area must be the same. To analyze the changes in each dimension of each lesion region in each state image, and to subsequently determine the various stages of skin disease evolution, this embodiment obtains the degree of change in each dimension of each lesion region in each state image based on the changes in each dimension of each lesion region compared to its previous adjacent state image. This accurately reflects the changes in each dimension of each lesion region in each state image, preparing for obtaining the overall changes in each dimension of each state image. Furthermore, this embodiment determines the dominant weight of each dimension in each state image by the degree of change in each dimension of each lesion region. The larger the dominant weight, the greater the change in the corresponding dimension in the corresponding state image, which is beneficial for accurately determining the main changing dimensions in each state image, enabling accurate acquisition of the various stages of skin disease evolution.

[0035] Preferably, in one feasible embodiment, the method for obtaining the degree of change is as follows: for any lesion region and any dimension of the lesion region in any state image, the previous adjacent state image of the state image is taken as the target image, and the absolute value of the difference between the data corresponding to that dimension of the lesion region in the state image and the target image is taken as the first difference; the result of normalizing the ratio of the first difference to the data corresponding to that dimension of the lesion region in the target image is taken as the degree of change of that dimension of the lesion region in the state image; in this embodiment, the above ratio is normalized using the norm normalization function. It should be noted that in this embodiment, the data corresponding to the color dimension of the lesion region in the state image is set as: the average value of the abnormality of all pixels in the lesion region in the state image. Since the abnormality range is known to be from 0 to 1, it can be inferred that the data corresponding to the color dimension of the lesion region in the target image may be 0, i.e., the denominator may be 0. To avoid this, in this embodiment, when obtaining the degree of change of the color dimension of the lesion region in the state image, the sum of the data corresponding to the color dimension of the lesion region in the target image and a preset constant is used as the denominator. The preset constant is greater than 0; in this embodiment, the preset constant is set to 1. The implementer can set the size of the preset constant according to the actual situation, and this is not limited here. In this embodiment, the data corresponding to the area dimension of the lesion region in the state image is set as: the number of all pixels in the lesion region in the state image. In this embodiment, the shape dimension of the lesion region in the state image is set as the sum of the Euclidean distances between all edge pixels on the outer edge line of the lesion region in the state image and the centroid of the lesion region in the state image; wherein, the methods for obtaining the centroid and the Euclidean distance are well-known technologies and will not be described in detail. Furthermore, this embodiment uses the streamer method to obtain the position of the lesion region in the state image and the target image. The streamer method is a well-known technique and will not be described in detail here. If the lesion region is a newly appearing region in the state image (i.e., not present in the target image), the normalized data corresponding to each dimension of the lesion region in the state image is used as the degree of change of each dimension of the lesion region in the state image. This embodiment uses the norm normalization function to normalize the data corresponding to each dimension of the lesion region in the state image. If the lesion region in the current image is the overall region resulting from the expansion of multiple lesion regions in the target image, then the average value of the abnormality of all pixels in the corresponding lesion region in the target image is used as the data corresponding to the color dimension of the lesion region in the target image; the number of all pixels in the corresponding lesion region in the target image is used as the data corresponding to the area dimension of the lesion region in the target image; and the average value of the sum of the Euclidean distances between all edge pixels on the outer edge line of the corresponding lesion region in the target image and the centroid of the lesion region is used as the data corresponding to the shape dimension of the lesion region in the target image.

[0036] Thus, the degree of change in each dimension of each lesion region in each state image is obtained. It should be noted that, since the first state image does not have a preceding adjacent state image, this embodiment does not obtain the degree of change in each dimension of each lesion region in the first state image.

[0037] Preferably, in one feasible embodiment of this method, the dominant weight is obtained as follows: For any state image, the covariance matrix corresponding to the degree of change in all dimensions of all lesion regions in the state image is obtained through principal component analysis (PCA). The eigenvector corresponding to the largest eigenvalue of the covariance matrix is ​​used as the principal component vector. The PCA algorithm, eigenvalue, and eigenvector acquisition methods are all well-known techniques and will not be elaborated further. Each element in the principal component vector corresponds to a unique dimension. The result of normalizing the absolute value of each element in the principal component vector is used as the dominant weight of the corresponding dimension in the state image. In this embodiment, the ratio of the absolute value of each element in the principal component vector to the sum of the absolute values ​​of all elements in the principal component vector is used as the result of normalizing the absolute value of each element in the principal component vector.

[0038] At this point, the dominant weights of each dimension in each state image are obtained.

[0039] The evolution stage acquisition module 40 is used to acquire the dominant dimension in each state image based on the dominant weight, and to filter the segmented state images to determine the various evolution stages of the skin disease based on the difference in dominant dimension between each state image and its previous adjacent state image, as well as the difference in dominant weight of each dimension.

[0040] Specifically, the main change dimensions of lesions differ across different stages of skin disease evolution. For example, at a certain stage, the area of ​​the lesion region may change significantly, or its color may change significantly. It is known that to more accurately determine the lesion region and accurately simulate its evolution, the filter kernel scale corresponding to the skin disease images at different stages should be adaptively adjusted according to the actual situation. For example, if the main change dimension at a certain stage is color, a filter kernel scale that is too small will result in excessive noise, affecting the accurate filtering of the lesion region. Therefore, it is necessary to obtain the various stages of skin disease evolution. Considering that the main change dimensions differ significantly between different stages, and that changes within the same dimension also differ significantly, this embodiment first obtains the dominant dimension (i.e., the main change dimension) in each state image based on the dominant weight. Then, based on the difference in dominant dimension between each state image and its preceding adjacent state image, as well as the difference in the dominant weight of each dimension, segmented state images are selected to determine the various stages of skin disease evolution.

[0041] Preferably, in one feasible embodiment of this invention, the dominant dimension is obtained by taking the dimension corresponding to the largest dominant weight in each state image as the dominant dimension in each state image. If the largest dominant weight in a state image corresponds to at least two dimensions, then any one of the dimensions is selected as the dominant dimension in that state image.

[0042] Preferably, in one feasible embodiment of this invention, the method for obtaining the segmented state image is as follows: For any state image, the absolute value of the difference between the dominant weights of the dominant dimensions of the state image and its preceding adjacent state image is obtained as the first evolution analysis value of the state image; wherein, when the dominant dimensions of the state image and its preceding adjacent state image are different, the first evolution analysis value is 1 by default; the mean of the absolute values ​​of the differences between the dominant weights of each dimension of the state image and its preceding adjacent state image is obtained as the second evolution analysis value of the state image; when both the first and second evolution analysis values ​​are larger, it indicates that the state image is more likely to be a segmented image at different evolution stages. Therefore, in this embodiment, the product of the first and second evolution analysis values ​​is normalized to obtain the evolution degree of the state image; in this embodiment, the product of the first and second evolution analysis values ​​is normalized using the norm normalization function. The larger the evolution degree, the more likely the state image is to be a segmented image at different evolution stages. Therefore, in this embodiment, the predicted evolution degree threshold is set to 0.7. The implementer can set the size of the predicted evolution degree threshold according to the actual situation, which is not limited here. When the degree of evolution exceeds the predicted degree of evolution threshold, the corresponding state image is used as the segmented state image.

[0043] This allows us to obtain all segmented state images up to the current moment, which is helpful in accurately determining the various stages of skin disease evolution.

[0044] Preferably, in one feasible way of this embodiment, the method for obtaining the evolution stage is as follows: taking the time corresponding to the first state image as the start time and the time corresponding to the last state image as the end time; taking the time period formed by the start time and the end time as the overall stage; taking the time adjacent to the time corresponding to each segmented state image as the cutoff time to divide the overall stage, and taking each local stage after division as each evolution stage.

[0045] This completes the understanding of the various stages of skin disease development.

[0046] The optimal filter kernel scale acquisition module 50 is used to acquire the optimal filter kernel scale for each evolution stage based on the influence of different filter kernel scales on the degree of change of the dominant dimension of each lesion region in each state image within each evolution stage.

[0047] Specifically, the changes in lesion regions in state images within the same evolution stage are similar. Therefore, this embodiment obtains the optimal filter kernel scale for each evolution stage based on the influence of different filter kernel scales on the degree of change of the dominant dimension of each lesion region in each state image within each evolution stage. This enables the accurate construction of three-dimensional lesion regions of skin diseases through three-dimensional imaging technology, thereby accurately simulating the evolution trend of lesions.

[0048] Preferably, in one feasible embodiment of this invention, the optimal filter kernel scale is obtained as follows: For any evolution stage, the dominant dimension that appears most frequently in all segmented state images within that evolution stage is taken as the dominant dimension in all state images within that evolution stage. For any filter kernel scale, each state image within that evolution stage is filtered using that filter kernel scale to obtain a filtered state image; the average value of the degree of change of the dominant dimension of all lesion regions in all filtered state images is obtained as the filtering degree of that filter kernel scale for that evolution stage; the greater the filtering degree, the more likely the filter kernel scale is to be the optimal filter kernel scale for that evolution stage, because both excessively large and excessively small filter kernel scales will cause a deviation in the degree of change of the dominant dimension of the lesion region. For example, if the dominant dimension is the shape dimension, an excessively large filter kernel scale will blur edge details, while an excessively small filter kernel scale will retain noise, resulting in insignificant shape changes. Therefore, in this embodiment, the filter kernel scale corresponding to the largest filtering degree is taken as the optimal filter kernel scale for that evolution stage. It should be noted that in this embodiment, the filter kernel scales are set as follows: and The implementer can set the filter kernel scale according to the actual situation, and there is no limitation here.

[0049] Thus, the optimal filter kernel scale for each evolution stage is obtained.

[0050] Processing module 60 is used for three-dimensional imaging of skin diseases and simulation of lesion evolution trends based on the optimal filter kernel scale.

[0051] Specifically, each skin disease image at each time point within each evolution stage is filtered using the optimal filtering kernel scale for each evolution stage. The filtered skin disease images at each time point are then processed using 3D imaging technology to construct a 3D image of the skin disease at each time point. This allows for accurate simulation of the lesion evolution trend of the skin disease, which is beneficial for accurate analysis of the skin disease condition.

[0052] In summary, this embodiment acquires state images of skin diseases; identifies lesion regions based on the RGB channel values ​​of pixels in the state images; determines the degree of change in each dimension of the lesion region based on the dimensional changes of the lesion region in each state image compared to its dimensional changes in the previous adjacent state image, thereby determining the dominant weight of each dimension and obtaining the dominant dimension; and identifies various evolution stages of the skin disease based on the differences in dominant dimensions and dominant weights between adjacent state images. Finally, it obtains the optimal filter kernel scale for each evolution stage based on the influence of different filter kernel scales on the degree of change of the dominant dimension within the evolution stage, enabling three-dimensional imaging of the skin disease and simulation of lesion evolution trends. This invention improves the accuracy of skin disease region identification and lesion evolution trend simulation by adaptively determining the optimal filter kernel scale for each evolution stage.

[0053] Example 2: This invention also proposes a three-dimensional imaging and lesion evolution trend simulation device for skin diseases. The device includes a memory and a processor. The memory stores executable program code, and the processor is used to call and execute the executable program code to perform the three-dimensional imaging and lesion evolution trend simulation system for skin diseases provided in the embodiments of this application. Specifically, the device may be a chip, component, or module. The chip may include a connected processor and memory; wherein the memory stores instructions, and when the processor calls and executes the instructions, it can cause the chip to perform the three-dimensional imaging and lesion evolution trend simulation system for skin diseases provided in the above embodiments.

[0054] Furthermore, this application also protects a computer device; please refer to [link to relevant documentation]. Figure 3 The computer device includes a memory 401, a processor 402, and a computer program 403 stored in the memory 401 and running on the processor 402. When the processor 402 executes the computer program 403, the computer device can execute any of the aforementioned three-dimensional imaging and lesion evolution trend simulation systems for skin diseases.

[0055] Example 3: The present invention also provides a computer-readable storage medium storing computer program code, which, when executed on a computer, causes the computer to perform the aforementioned method steps to implement the three-dimensional imaging and lesion evolution trend simulation system for skin diseases provided in the above embodiments.

[0056] Example 4: The present invention also provides a computer program product, which, when run on a computer, causes the computer to perform the above-mentioned related steps to realize the three-dimensional imaging and lesion evolution trend simulation system for skin diseases provided in the above embodiments.

[0057] In this embodiment, the device, computer-readable storage medium, computer program product, or chip are all used to execute the corresponding methods provided above. Therefore, the beneficial effects they can achieve can be referred to the beneficial effects in the corresponding methods provided above, and will not be repeated here.

[0058] It should be noted that the order of the above embodiments of the present invention is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0059] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

Claims

1. A three-dimensional imaging and lesion evolution trend simulation system for skin diseases, characterized in that, The system includes the following steps: The image acquisition module is used to acquire real-time images of skin diseases and to acquire reference images of normal skin areas. The lesion area acquisition module is used to filter out abnormal pixels in each status image based on the difference in RGB channel values ​​between each pixel in each status image and the pixel in the reference image, thereby determining the lesion area in each status image. The dominant weight acquisition module is used to obtain the degree of change of each dimension of each lesion region in each state image based on the changes of each lesion region in each state image compared with its changes in each dimension in the previous adjacent state image, and then determine the dominant weight of each dimension in each state image. The evolution stage acquisition module is used to acquire the dominant dimension in each state image based on the dominant weight. Based on the difference in dominant dimension between each state image and its previous adjacent state image, as well as the difference in dominant weight of each dimension, the segmented state images are filtered to determine the various evolution stages of the skin disease. The optimal filter kernel scale acquisition module is used to obtain the optimal filter kernel scale for each evolution stage based on the influence of different filter kernel scales on the degree of change of the dominant dimension of each lesion region in each state image within each evolution stage. The processing module is used for three-dimensional imaging of skin diseases and simulation of lesion evolution trends based on the optimal filter kernel scale.

2. The three-dimensional imaging and lesion evolution trend simulation system for skin diseases as described in claim 1, characterized in that, The method for obtaining the abnormal pixels is as follows: For any channel in the RGB channels, the average value of that channel for all pixels in the reference image is used as the overall reference value for that channel. The result of normalizing the difference between the channel value of each pixel in the reference image and the overall reference value is used as the tolerance level of the channel of each pixel in the reference image. The sum of the maximum tolerance levels for each RGB channel of all pixels in the reference image is used as the overall color tolerance level. For any pixel in any state image, the sum of the tolerance levels of each RGB channel of that pixel and the difference between the sum and the overall color tolerance level are normalized to determine the degree of anomaly of that pixel. When the degree of abnormality exceeds the preset abnormality threshold, the corresponding pixel is considered an abnormal pixel.

3. The three-dimensional imaging and lesion evolution trend simulation system for skin diseases as described in claim 1, characterized in that, The method for obtaining the degree of change is as follows: For any lesion region and any dimension of the lesion region in any state image, the previous adjacent state image of the state image is taken as the target image, and the difference between the data corresponding to that dimension of the lesion region in the state image and the target image is taken as the first difference. The result of normalizing the first difference with the ratio of the corresponding dimension of the lesion region in the target image is taken as the degree of change of that dimension of the lesion region in the state image.

4. The three-dimensional imaging and lesion evolution trend simulation system for skin diseases as described in claim 1, characterized in that, The method for obtaining the dominant weight is as follows: For any state image, the covariance matrix corresponding to the degree of change of all dimensions of all lesion regions in the state image is obtained by the principal component analysis algorithm, and the eigenvector corresponding to the largest eigenvalue of the covariance matrix is ​​used as the principal component vector. The result of normalizing the absolute value of each element in the principal component vector is used as the dominant weight of the corresponding dimension in the state image.

5. The three-dimensional imaging and lesion evolution trend simulation system for skin diseases as described in claim 1, characterized in that, The method for obtaining the segmented state image is as follows: For any state image, the difference in dominant weights of the dominant dimension between the state image and its previous neighboring state image is obtained as the first evolution analysis value of the state image; wherein, when the dominant dimension of the state image is different from that of its previous neighboring state image, the first evolution analysis value is 1 by default. The mean of the difference in dominant weights for each dimension between the current state image and its previous neighboring state image is obtained as the second evolution analysis value of the current state image. The normalized product of the first evolution analysis value and the second evolution analysis value is taken as the degree of evolution of the state image. When the degree of evolution exceeds the predicted degree of evolution threshold, the corresponding state image is used as the segmented state image.

6. The three-dimensional imaging and lesion evolution trend simulation system for skin diseases as described in claim 1, characterized in that, The method for obtaining the evolution stage is as follows: The time corresponding to the first state image is taken as the start time, and the time corresponding to the last state image is taken as the end time; the time period consisting of the start time and the end time is taken as the overall stage. The overall stage is divided by taking the time immediately preceding the time corresponding to each segmented state image as the cutoff time, and each local stage after the division is taken as each evolution stage.

7. The three-dimensional imaging and lesion evolution trend simulation system for skin diseases as described in claim 1, characterized in that, The method for obtaining the optimal filter kernel scale is as follows: For any evolution stage, the dominant dimension that appears most frequently in all segmented state images within that evolution stage is taken as the dominant dimension in all state images within that evolution stage. For any given filter kernel scale, each state image in the evolution stage is filtered using that filter kernel scale to obtain a filtered state image. The mean value of the degree of change of the dominant dimension of all lesion regions in all the filtered state images is obtained as the filtering degree of the filtering kernel scale for this evolution stage; The filter kernel size corresponding to the maximum filtering degree is taken as the optimal filter kernel size for this evolution stage.

8. The three-dimensional imaging and lesion evolution trend simulation system for skin diseases as described in claim 1, characterized in that, The method for obtaining the dominant dimension is as follows: The dimension corresponding to the largest dominant weight in each state image is taken as the dominant dimension in each state image.

9. The three-dimensional imaging and lesion evolution trend simulation system for skin diseases as described in claim 1, characterized in that, The method for obtaining the lesion area is as follows: For any state image, the connected components formed by the abnormal pixels in the state image are all regarded as abnormal regions. For any abnormal region, the region corresponding to the abnormal region after performing an opening operation followed by a closing operation is taken as the lesion region.

10. The three-dimensional imaging and lesion evolution trend simulation system for skin diseases as described in claim 1, characterized in that, The method for obtaining the state image is as follows: For any given moment, the image obtained by registering and stitching together skin disease images acquired from multiple angles at that moment is taken as the state image at that moment.

Images