Image matching-based plastic wound repair analysis system and method

Abstract

The invention relates to the technical field of wound repair analysis, in particular to a plastic wound repair analysis system and method based on image matching, and the method comprises the steps: obtaining a first wound image before wound repair and a second wound image after repair; performing image registration on the first wound image and the second wound image by using an image matching algorithm; according to an image registration result, evaluating the consistency of periinvasive tissues before and after repair and the consistency of wound tissues after repair; evaluating suture strain distribution at a wound suture line according to the second wound image; and analyzing the wound repair effect according to the periinvasive tissue consistency and wound tissue consistency evaluation result and in combination with the suture strain distribution evaluation result. According to the method, the accuracy and the reliability of wound repair effect evaluation are improved by quantitatively analyzing the periinvasive tissue consistency, the wound tissue consistency and the suture strain distribution condition.

Description

Technical Field

[0001] The present application relates to the technical field of wound repair analysis, and in particular to a plastic surgery wound repair analysis system and method based on image matching. Background Art

[0002] As the outermost layer of the human body, the skin is vast and complex in structure, and is the main barrier against external threats. Damage to the composition and function of the skin will lead to poor wound healing, which requires local wound reconstruction surgery. The treatment form of local wound reconstruction surgery mainly uses local skin flap cutting surgery. Local skin flaps have the same color and similar physiological tissue as the adjacent skin, which is conducive to the healing of local wound flaps. It is one of the main surgical methods for repairing wounds in plastic surgery.

[0003] Early clinical testing methods for wound repair effects usually rely on doctors' direct visual observation to evaluate wound repair effects, which cannot accurately and quantitatively evaluate the actual repair effects. With the development of non-contact optical measurement technology, digital image correlation has developed rapidly. Due to its advantages of non-contact, non-destructive, and universal, it is widely used in the field of soft tissue materials and medical biometry.

[0004] In the process of wound repair effect evaluation, the consistency of periwound tissue before and after wound repair and the consistency of wound tissue after repair are crucial for wound repair effect evaluation. They reflect the degree of recovery of tissue around the wound and the healing of the wound itself, and are an important basis for evaluating the wound repair effect and the patient's prognosis. However, the existing analysis methods for plastic surgery wound repair ignore the influence of consistency indicators on the evaluation of wound repair effect and the influence of suture strain distribution at the wound suture line on the wound healing quality, which reduces the accuracy and precision of wound repair effect evaluation. Summary of the invention

[0005] In order to overcome the defects and shortcomings of the prior art, the present application provides a plastic surgery wound repair analysis system and method based on image matching, which improves the accuracy and reliability of wound repair effect evaluation by quantitatively analyzing the consistency of periwound tissue, wound tissue consistency and suture strain distribution.

[0006] In order to achieve the above objectives, this application adopts the following technical solutions:

[0007] In a first aspect, the present application provides a method for analyzing plastic surgery wound repair based on image matching, comprising the following steps:

[0008] Acquire a first wound surface image before wound surface repair and a second wound surface image after wound surface repair;

[0009] Performing image registration on the first wound surface image and the second wound surface image using an image matching algorithm;

[0010] The consistency of periwound tissue before and after repair and the consistency of wound tissue after repair were evaluated based on the image registration results;

[0011] evaluating the suture strain distribution at the wound suture line according to the second wound image;

[0012] The wound repair effect was analyzed based on the evaluation results of periwound tissue consistency and wound tissue consistency combined with the suture strain distribution evaluation results.

[0013] Preferably, assessing the peri-injury tissue consistency comprises:

[0014] Acquire a first wound surface image and a second wound surface image after image registration;

[0015] The periwound tissue consistency index is calculated by the first wound surface image and the second wound surface image. The periwound tissue consistency index is used to evaluate the periwound tissue consistency. The calculation formula of the periwound tissue consistency index is as follows:

[0016]

[0017] Where C(x,y) represents the RGB color value of the pixel at the position (x,y) of the pericranial tissue region in the first wound image, C′(x,y) represents the RGB color value of the pixel at the position (x,y) of the pericranial tissue region in the second wound image, ||C(x,y)-C′(x,y)|| represents the Euclidean distance of the color difference between C(x,y) and C′(x,y), Dmax represents the maximum color difference distance in the RGB color space, R represents the pixel position set of the pericranial tissue region, N represents the number of pixels in the pericranial tissue region, BCI represents the brightness consistency index of the pericranial tissue region, and δ 1 represents the first regulatory factor, and OCI represents the peri-injury tissue consistency index.

[0018] Preferably, the calculation formula of the brightness consistency index is:

[0019]

[0020] Where L(x, y) represents the brightness value of the pixel at the position (x, y) of the periwound tissue region in the first wound image, L′(x, y) represents the brightness value of the pixel at the position (x, y) of the periwound tissue region in the second wound image, R represents the pixel position set of the periwound tissue region, and BCI represents the brightness consistency index.

[0021] Preferably, evaluating the wound tissue consistency comprises:

[0022] Acquire a second wound surface image and convert the second wound surface image into a second wound surface grayscale image;

[0023] The gray-level co-occurrence matrix algorithm is used to extract the wound surface texture feature index and the peri-wound texture feature index of the second wound surface gray-level image;

[0024] The wound surface tissue consistency index was calculated by the periwound texture characteristic index and the wound surface texture characteristic index. The wound surface tissue consistency index was used to evaluate the wound surface tissue consistency. The calculation formula of the wound surface tissue consistency index was as follows:

[0025]

[0026] Where T w,k represents the value of the kth wound surface texture feature index, T s,k represents the value of the kth wound texture feature index, n represents the number of texture feature indicators, and WCI represents the wound tissue consistency index.

[0027] Preferably, the step of evaluating the suture strain distribution at the wound suture line comprises:

[0028] Acquire a second wound surface image, and use an image matching algorithm to perform image registration on the second wound surface images acquired at different times;

[0029] The suture strain distribution index is calculated through the second wound image after image registration. The suture strain distribution index is used to evaluate the suture strain distribution at the wound suture line. The calculation formula of the suture strain distribution index is as follows:

[0030]

[0031] Where H s represents the displacement of the sth seam pixel, represents the mean displacement of the stitching line pixels, M represents the number of stitching line pixels, DDI represents the stitching strain direction distribution index, δ 2 denotes the second adjustment factor, and SDI denotes suture strain distribution index.

[0032] Preferably, the calculation formula of the suture strain direction distribution index is:

[0033]

[0034] Where D s represents the displacement vector of the sth seam pixel, N s represents the normal vector of the seam line at the sth seam line pixel, represents the mean offset angle of all seam pixels, φ max represents the maximum deviation angle of the stitching line pixels, and DDI represents the stitching strain direction distribution index.

[0035] Preferably, the analysis of wound repair effect includes:

[0036] The periwound tissue consistency index, wound tissue consistency index and suture strain distribution index were obtained and the wound repair index was calculated. The wound repair index was used to quantitatively analyze the wound repair effect. The calculation formula of the wound repair index is as follows:

[0037] WRI=ω 1 ×OCI+ω 2 ×WCI+ω 3 ×SDI;

[0038] Where OCI represents the periwound tissue consistency index, WCI represents the wound tissue consistency index, SDI represents the suture strain distribution index, ω 1 represents the consistency weight of the creative week organization, ω 2 represents the consistency weight of wound tissue, ω 3 represents the suture strain distribution weight, and WRI represents the wound repair index.

[0039] It should be noted here that the first adjustment factor, the second adjustment factor, the periwound tissue consistency weight, the wound tissue consistency weight and the suture strain distribution weight are determined as follows: 5000 sets of first wound images and second wound images are collected to distinguish whether the wound repair effect meets the repair requirements, the first wound images and the second wound images are substituted into the wound repair index calculation formula for calculation, the calculated wound repair index and the distinction result are simultaneously imported into the fitting software, and the optimal first adjustment factor, the second adjustment factor, the periwound tissue consistency weight, the wound tissue consistency weight and the suture strain distribution weight that meet the distinction accuracy of the distinction result are output.

[0040] In a second aspect, the present application provides a plastic surgery wound repair analysis system based on image matching, comprising:

[0041] An image acquisition module, used to acquire a first wound surface image before wound surface repair and a second wound surface image after wound surface repair;

[0042] An image registration module, used for performing image registration on the first wound surface image and the second wound surface image using an image matching algorithm;

[0043] The first evaluation module is used to evaluate the consistency of periwound tissue before and after repair and the consistency of wound surface tissue after repair according to the image registration result;

[0044] A second evaluation module is used to evaluate the suture strain distribution at the wound suture line according to the second wound surface image;

[0045] The repair effect analysis module is used to analyze the wound repair effect based on the periwound tissue consistency and wound tissue consistency evaluation results combined with the suture strain distribution evaluation results.

[0046] In a third aspect, the present application provides an electronic device comprising: a processor and a memory, wherein the memory stores a computer program that can be called by the processor, and the processor executes a plastic wound repair analysis method based on image matching by calling the computer program stored in the memory.

[0047] In a fourth aspect, the present application provides a computer-readable storage medium storing instructions, which, when executed on a computer, enables the computer to execute a plastic surgery wound repair analysis method based on image matching.

[0048] Compared with the prior art, this application has the following advantages and beneficial effects:

[0049] This application uses an image matching algorithm to perform image registration on wound images before and after wound repair, and quantitatively evaluates the consistency of periwound tissue, wound tissue consistency, and suture strain distribution at the wound suture line based on the image registration results, and then analyzes the wound repair effect by combining the consistency evaluation results and the suture strain distribution evaluation results, thereby improving the accuracy and reliability of the wound repair effect evaluation. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Other features, objects and advantages of the present application will become more apparent by reading the detailed description of non-limiting embodiments made with reference to the following drawings:

[0051] Figure 1 It is a schematic diagram of the overall process of the plastic surgery wound repair analysis method based on image matching provided in an embodiment of the present application;

[0052] Figure 2 It is a flow chart of a feature point matching algorithm in a plastic surgery wound repair analysis method based on image matching provided in an embodiment of the present application;

[0053] Figure 3 It is a structural schematic diagram of a plastic surgery wound repair analysis system based on image matching provided in an embodiment of the present application;

[0054] Figure 4 It is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0055] The technical solution of the present application is described in detail below through the accompanying drawings and specific embodiments. It should be understood that the embodiments of the present application and the specific features in the embodiments are detailed descriptions of the technical solution of the present application, rather than limitations on the technical solution of the present application. In the absence of conflict, the embodiments of the present application and the technical features in the embodiments can be combined with each other.

[0056] See also Figure 1 , Figure 1The figure is a schematic diagram of the overall process of the plastic surgery wound repair analysis method based on image matching provided in the embodiment of the present application, which specifically includes the following steps:

[0057] S110: Acquire a first wound surface image before wound repair and a second wound surface image after wound repair, wherein the first wound surface image and the second wound surface image are acquired by a binocular camera, that is, the same wound surface is photographed by two cameras at different positions.

[0058] S120: performing image registration on the first wound surface image and the second wound surface image using an image matching algorithm;

[0059] Image matching algorithms include feature point matching algorithms and morphological registration algorithms. Feature-based matching algorithms are one of the commonly used technologies in the field of computer vision. They are used to find the same feature points between different images for tasks such as object recognition, image registration, and 3D reconstruction. Please refer to Figure 2 , Figure 2 The present invention is a flowchart of a feature point matching algorithm in a plastic surgery wound repair analysis method based on image matching provided by an embodiment of the present application, comprising: (1) feature point extraction, firstly extracting feature points with good distinguishability from a first wound image and a second wound image, wherein the feature points are usually at prominent positions, corners or local areas in the image, and commonly used features include SIFT (scale invariant feature transform), SURF (speeded up robust features), and ORB (Oriented FAST and Rotated BRIEF); (2) feature point description, describing the extracted feature points for matching, and converting the image area near the feature points into a set of vectors or descriptors that can be used for comparison, and commonly used descriptors include SIFT descriptors, SURF descriptors, and ORB descriptors; (3) feature point matching, finding similar or matching feature point pairs by comparing feature point descriptors in different images, and the matching process usually uses a distance measurement method, such as Euclidean distance, Hamming distance, etc.; (4) matching point verification, verifying the matched feature point pairs, and eliminating incorrect matches through geometric constraints (such as RANSAC algorithm);

[0060] The morphological registration algorithm is a method used for image registration in image processing. Its basic principle is to adjust the shape and structure of the image through morphological operations, such as erosion, dilation, opening and closing operations, so that the two images are as similar as possible in structure, thereby achieving alignment and matching between images. Morphological registration is widely used in medical image registration, map registration and other fields.

[0061] S130: Evaluate the consistency of periwound tissue before and after repair and the consistency of wound surface tissue after repair based on the image registration results;

[0062] The consistency of the periwound tissue is quantified by comprehensively evaluating the color consistency and brightness consistency of the periwound area before and after wound repair, and the consistency of the periwound tissue is evaluated, including:

[0063] Acquire a first wound surface image and a second wound surface image after image registration;

[0064] The periwound tissue consistency index is calculated by the first wound surface image and the second wound surface image. The periwound tissue consistency index is used to evaluate the periwound tissue consistency. The calculation formula of the periwound tissue consistency index is as follows:

[0065]

[0066] Where C(x,y) represents the RGB color value of the pixel at the position (x,y) in the periwound tissue region in the first wound image, C′(x,y) represents the RGB color value of the pixel at the position (x,y) in the periwound tissue region in the second wound image, ||C(x,y)-C′(x,y)|| represents the Euclidean distance of the color difference between C(x,y) and C′(x,y), R(x,y) represents the color value of the red channel in C(x,y), G(x,y) represents the color value of the green channel in C(x,y), B(x,y) represents the color value of the blue channel in C(x,y), R′(x,y) represents the color value of the red channel in C′(x,y), G′(x,y) represents the color value of the green channel in C′(x,y), B′(x,y) represents the color value of the blue channel in C′(x,y), and the color difference Euclidean distance is used to quantify the color difference of pixels at the same periwound tissue area (x,y) between the first wound image and the second wound image. D max Indicates the maximum color difference distance in the RGB color space, R represents the pixel position set of the perihelical tissue area, N represents the number of pixels in the perihelical tissue area, BCI represents the brightness consistency index of the perihelical tissue area, δ 1 represents the first adjustment factor, δ 1 It is used to control the influence of color consistency and brightness consistency in consistency assessment. OCI stands for peri-incisional tissue consistency index.

[0067] Wound repair is often accompanied by periwound skin edema, and there are many manifestations of skin edema, the common feature of which is local skin brightness. Therefore, the skin edema is evaluated by the periwound skin brightness. The calculation formula of the brightness consistency index is:

[0068]

[0069] Where L(x, y) represents the brightness value of the pixel at the position (x, y) of the periwound tissue region in the first wound image, L′(x, y) represents the brightness value of the pixel at the position (x, y) of the periwound tissue region in the second wound image, R represents the pixel position set of the periwound tissue region, BCI represents the brightness consistency index, and BCI is used to comprehensively analyze the similarity of the brightness of each pixel in the periwound tissue region and thus quantify the overall change of brightness in the periwound region;

[0070] The gray-level co-occurrence matrix algorithm is based on the statistical analysis of paired pixel gray values ​​and is used to describe the texture features of an image. It can describe the spatial information of adjacent intervals, directions, and amplitudes of change, and is helpful in distinguishing the consistency of wound texture after wound repair and the tissue texture around the wound, and evaluating the consistency of wound tissue, including:

[0071] Acquire a second wound surface image and convert the second wound surface image into a second wound surface grayscale image;

[0072] The gray level co-occurrence matrix algorithm is used to extract the wound surface texture feature index and the peri-wound texture feature index of the second wound surface gray image, wherein the wound surface texture feature index and the peri-wound texture feature index both include angular second-order moment (ASM), entropy (ENT), inverse difference moment (IDM), contrast (CON) and correlation (COR);

[0073] The wound surface tissue consistency index was calculated by the periwound texture characteristic index and the wound surface texture characteristic index. The wound surface tissue consistency index was used to evaluate the wound surface tissue consistency. The calculation formula of the wound surface tissue consistency index was as follows:

[0074]

[0075] Where T w,k represents the value of the kth wound surface texture feature index, T s,k It represents the value of the kth wound texture feature index, n represents the number of texture feature indicators, and n=5, which includes 5 texture feature indicators: angular second moment, entropy, inverse moment, contrast and correlation. WCI represents the wound tissue consistency index.

[0076] S140: evaluating the suture strain distribution at the wound suture line according to the second wound image;

[0077] The uniformity and stability of sutures can be judged by analyzing the strain distribution at the suture line. Uniform strain distribution indicates good suture effect and helps to avoid complications, while uneven strain distribution may cause local excessive pulling, which is not conducive to wound healing. The suture strain distribution at the wound suture line is evaluated, including:

[0078] Acquire a second wound surface image, and use an image matching algorithm to perform image registration on the second wound surface images acquired at different times;

[0079] The suture strain distribution index is calculated through the second wound image after image registration. The suture strain distribution index is used to evaluate the suture strain distribution at the wound suture line. The calculation formula of the suture strain distribution index is as follows:

[0080]

[0081] Where H s represents the displacement of the sth seam pixel, represents the mean displacement of the stitching line pixels, M represents the number of stitching line pixels, DDI represents the stitching strain direction distribution index, δ 2 represents the second adjustment factor, SDI represents the suture strain distribution index;

[0082] The uniform distribution of suture strain direction can reflect the stability and uniformity of the force on the wound surface during the healing process. If there is a significant deviation in the strain direction at the suture line, it may indicate that the suture is not firm or the wound healing is poor, increasing the risk of complications (such as wound dehiscence or infection). The calculation formula of the suture strain direction distribution index is:

[0083]

[0084] Where D s represents the displacement vector of the sth seam pixel, N s Represents the normal vector of the seam line at the sth seam line pixel. The normal vector refers to the vector passing through the sth seam line pixel and perpendicular to the tangent line of the seam line curve. It is used to calculate the relative offset angle between the displacement direction and the normal vector of the sth suture line pixel in the second wound surface image acquired at different times. represents the mean offset angle of all seam pixels, φ max represents the maximum deviation angle of the stitching line pixels, and DDI represents the stitching strain direction distribution index.

[0085] S150: Analyze the wound repair effect based on the periwound tissue consistency and wound tissue consistency evaluation results combined with the suture strain distribution evaluation results;

[0086] The overall effect of wound repair was quantitatively evaluated by comprehensively considering the consistency of periwound tissue, wound tissue consistency and suture strain distribution, and the wound repair effect was analyzed, including:

[0087] The periwound tissue consistency index, wound tissue consistency index and suture strain distribution index were obtained and the wound repair index was calculated. The wound repair index was used to quantitatively analyze the wound repair effect. The calculation formula of the wound repair index is as follows:

[0088] WRI=ω 1×OCI+ω 2 ×WCI+ω 3 ×SDI;

[0089] Where OCI represents the periwound tissue consistency index, WCI represents the wound tissue consistency index, SDI represents the suture strain distribution index, ω 1 represents the consistency weight of the creative week organization, ω 2 represents the consistency weight of wound tissue, ω 3 It represents the weight of suture strain distribution. Different indices are assigned corresponding weights to reflect their relative importance in the evaluation of wound repair effect. WRI represents wound repair index.

[0090] See also Figure 3 , Figure 3 : is a structural schematic diagram of a plastic surgery wound repair analysis system based on image matching provided in an embodiment of the present application. This embodiment provides a plastic surgery wound repair analysis system based on image matching, including:

[0091] An image acquisition module 210 is used to acquire a first wound surface image before wound surface repair and a second wound surface image after wound surface repair;

[0092] An image registration module 220 is used to perform image registration on the first wound surface image and the second wound surface image using an image matching algorithm;

[0093] A first evaluation module 230 is used to evaluate the consistency of periwound tissue before and after repair and the consistency of wound surface tissue after repair according to the image registration result;

[0094] A second evaluation module 240 is used to evaluate the suture strain distribution at the wound suture line according to the second wound surface image;

[0095] The repair effect analysis module 250 is used to analyze the wound repair effect according to the periwound tissue consistency and wound tissue consistency evaluation results combined with the suture strain distribution evaluation results.

[0096] In the embodiment of the present application, the first evaluation module 230 is used to evaluate the consistency of the periwound tissue before and after repair and the consistency of the wound tissue after repair according to the image registration result, and the evaluation of the consistency of the periwound tissue includes:

[0097] Acquire a first wound surface image and a second wound surface image after image registration;

[0098] The periwound tissue consistency index is calculated by the first wound surface image and the second wound surface image. The periwound tissue consistency index is used to evaluate the periwound tissue consistency. The calculation formula of the periwound tissue consistency index is as follows:

[0099]

[0100] Where C(x,y) represents the RGB color value of the pixel at the position (x,y) in the periwound tissue region in the first wound image, C′(x,y) represents the RGB color value of the pixel at the position (x,y) in the periwound tissue region in the second wound image, ||C(x,y)-C′(x,y)|| represents the Euclidean distance of the color difference between C(x,y) and C′(x,y), and D max represents the maximum color difference distance in the RGB color space, R represents the pixel position set of the perivascular tissue area, N represents the number of pixels in the perivascular tissue area, BCI represents the brightness consistency index of the perivascular tissue area, δ 1 represents the first regulatory factor, OCI represents the peri-incisional tissue consistency index;

[0101] The calculation formula of brightness consistency index is:

[0102]

[0103] Where L(x, y) represents the brightness value of the pixel at the position (x, y) of the periwound tissue region in the first wound image, L′(x, y) represents the brightness value of the pixel at the position (x, y) of the periwound tissue region in the second wound image, R represents the pixel position set of the periwound tissue region, and BCI represents the brightness consistency index;

[0104] Assess wound tissue consistency, including:

[0105] Acquire a second wound surface image and convert the second wound surface image into a second wound surface grayscale image;

[0106] The gray-level co-occurrence matrix algorithm is used to extract the wound surface texture feature index and the peri-wound texture feature index of the second wound surface gray-level image;

[0107] The wound surface tissue consistency index was calculated by the periwound texture characteristic index and the wound surface texture characteristic index. The wound surface tissue consistency index was used to evaluate the wound surface tissue consistency. The calculation formula of the wound surface tissue consistency index was as follows:

[0108]

[0109] Where T w,k represents the value of the kth wound surface texture feature index, T s,k represents the value of the kth wound texture feature index, n represents the number of texture feature indicators, and WCI represents the wound tissue consistency index.

[0110] In the embodiment of the present application, the second evaluation module 240 is used to evaluate the suture strain distribution at the wound suture line according to the second wound image, and the evaluation of the suture strain distribution at the wound suture line includes:

[0111] Acquire a second wound surface image, and use an image matching algorithm to perform image registration on the second wound surface images acquired at different times;

[0112] The suture strain distribution index is calculated through the second wound image after image registration. The suture strain distribution index is used to evaluate the suture strain distribution at the wound suture line. The calculation formula of the suture strain distribution index is as follows:

[0113]

[0114] Where H s represents the displacement of the sth seam pixel, represents the mean displacement of the stitching line pixels, M represents the number of stitching line pixels, DDI represents the stitching strain direction distribution index, δ 2 represents the second adjustment factor, SDI represents the suture strain distribution index;

[0115] The calculation formula of suture strain direction distribution index is:

[0116]

[0117] Where D s represents the displacement vector of the sth seam pixel, N s represents the normal vector of the seam line at the sth seam line pixel, represents the mean offset angle of all seam pixels, φ max represents the maximum deviation angle of the stitching line pixels, and DDI represents the stitching strain direction distribution index.

[0118] In the embodiment of the present application, the repair effect analysis module 250 is used to analyze the wound repair effect according to the periwound tissue consistency and wound tissue consistency evaluation results combined with the suture strain distribution evaluation results, and the wound repair effect is analyzed, including:

[0119] The periwound tissue consistency index, wound tissue consistency index and suture strain distribution index were obtained and the wound repair index was calculated. The wound repair index was used to quantitatively analyze the wound repair effect. The calculation formula of the wound repair index is as follows:

[0120] WRI=ω 1 ×OCI+ω 2 ×WCI+ω 3 ×SDI;

[0121] Where OCI represents the periwound tissue consistency index, WCI represents the wound tissue consistency index, SDI represents the suture strain distribution index, ω 1 represents the consistency weight of the creative week organization, ω 2 represents the consistency weight of wound tissue, ω 3represents the suture strain distribution weight, and WRI represents the wound repair index.

[0122] The above-mentioned parameters and steps for each unit module to implement corresponding functions in the plastic wound repair analysis system based on image matching of the present application can be referred to the parameters and steps in the embodiment of the plastic wound repair analysis method based on image matching above, and will not be repeated here.

[0123] like Figure 4 As shown, an embodiment of the present invention further provides an electronic device 300, including a memory 310, a processor 320 and a communication bus 330; the memory 310 and the processor 320 are connected via the communication bus 330. The memory 310 stores a plastic surgery wound repair analysis method based on image matching as provided in the above embodiment, which can be loaded and executed by the processor 320.

[0124] The memory 310 may be used to store instructions, programs, codes, code sets or instruction sets. The memory 310 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function, and instructions for implementing the plastic surgery wound repair analysis method based on image matching provided in the above embodiment, etc.; the data storage area may store data involved in the plastic surgery wound repair analysis method based on image matching provided in the above embodiment, etc.

[0125] The processor 320 may include one or more processing cores. The processor 320 calls the data stored in the memory 310 by running or executing the instructions, programs, code sets or instruction sets stored in the memory 310, and performs various functions and processes data of the present application. The processor 320 may be at least one of an application-specific integrated circuit (ASIC), a digital signal processor (DSP), a digital signal processing device (DSPD), a programmable logic device (PLD), a field programmable gate array (FPGA), a central processing unit (CPU), a controller, a microcontroller and a microprocessor. It is understandable that for different devices, the electronic device used to implement the above-mentioned processor 320 function can also be other, and the embodiment of the present application is not specifically limited.

[0126] The communication bus 330 may include a path to transmit information between the above components. The communication bus 330 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The communication bus 330 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 4 Only one double arrow is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0127] An embodiment of the present application provides a computer-readable storage medium storing a computer program that can be loaded by a processor and executes a plastic surgery wound repair analysis method based on image matching as provided in the above embodiment.

[0128] In an embodiment of the present application, a computer-readable storage medium may be a tangible device that holds and stores instructions used by an instruction execution device. A computer-readable storage medium may be, but is not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any combination thereof. Specifically, a computer-readable storage medium may be a portable computer disk, a hard disk, a USB flash drive, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a podium random access memory (SRAM), a portable compact disk read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, an optical disk, a magnetic disk, a mechanical encoding device, and any combination thereof.

[0129] The terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not expressly listed, or also includes elements inherent to such process, method, article, or apparatus.

[0130] The above description is only a preferred embodiment of the present application and an explanation of the technical principles used. Those skilled in the art should understand that the scope of application involved in the present application is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the aforementioned application concept. For example, the above features are replaced with (but not limited to) technical features with similar functions applied in the present application.

Claims

1. A plastic surgery wound repair analysis method based on image matching, characterized in that: The steps include: Acquire a first wound surface image before wound surface repair and a second wound surface image after wound surface repair; Performing image registration on the first wound surface image and the second wound surface image using an image matching algorithm; The consistency of periwound tissue before and after repair and the consistency of wound tissue after repair were evaluated based on the image registration results; evaluating the suture strain distribution at the wound suture line according to the second wound image; The wound repair effect was analyzed based on the evaluation results of periwound tissue consistency and wound tissue consistency combined with the suture strain distribution evaluation results.

2. The method for analyzing plastic surgery wound repair based on image matching according to claim 1, characterized in that: Assess perivascular tissue consistency, including: Acquire a first wound surface image and a second wound surface image after image registration; The periwound tissue consistency index is calculated by the first wound surface image and the second wound surface image. The periwound tissue consistency index is used to evaluate the periwound tissue consistency. The calculation formula of the periwound tissue consistency index is as follows: Where C(x,y) represents the RGB color value of the pixel at the position (x,y) in the periwound tissue region in the first wound image, C′(x,y) represents the RGB color value of the pixel at the position (x,y) in the periwound tissue region in the second wound image, ||C(x,y)-C′(x,y)|| represents the Euclidean distance of the color difference between C(x,y) and C′(x,y), and D max represents the maximum color difference distance in the RGB color space, R represents the pixel position set of the periosteum area, N represents the number of pixels in the periosteum area, BCI represents the brightness consistency index of the periosteum area, δ1 represents the first adjustment factor, and OCI represents the periosteum consistency index.

3. The method for analyzing plastic surgery wound repair based on image matching according to claim 2, characterized in that: The calculation formula of the brightness consistency index is: Where L(x, y) represents the brightness value of the pixel at the position (x, y) of the periwound tissue region in the first wound image, L′(x, y) represents the brightness value of the pixel at the position (x, y) of the periwound tissue region in the second wound image, R represents the pixel position set of the periwound tissue region, and BCI represents the brightness consistency index.

4. The method for analyzing plastic surgery wound repair based on image matching according to claim 1, characterized in that: Assess the wound tissue consistency, including: Acquire a second wound surface image and convert the second wound surface image into a second wound surface grayscale image; The gray-level co-occurrence matrix algorithm is used to extract the wound surface texture feature index and the peri-wound texture feature index of the second wound surface gray-level image; The wound surface tissue consistency index was calculated by the periwound texture characteristic index and the wound surface texture characteristic index. The wound surface tissue consistency index was used to evaluate the wound surface tissue consistency. The calculation formula of the wound surface tissue consistency index was as follows: Where T w,k represents the value of the kth wound surface texture feature index, T s,k represents the value of the kth wound texture feature index, n represents the number of texture feature indicators, and WCI represents the wound tissue consistency index.

5. The method for analyzing plastic surgery wound repair based on image matching according to claim 1, characterized in that: The method of evaluating the suture strain distribution at the wound suture line comprises: Acquire a second wound surface image, and use an image matching algorithm to perform image registration on the second wound surface images acquired at different times; The suture strain distribution index is calculated through the second wound image after image registration. The suture strain distribution index is used to evaluate the suture strain distribution at the wound suture line. The calculation formula of the suture strain distribution index is as follows: Where H s represents the displacement of the sth seam pixel, represents the mean displacement of the stitching line pixels, M represents the number of stitching line pixels, DDI represents the stitching strain direction distribution index, δ2 represents the second adjustment factor, and SDI represents the stitching strain distribution index.

6. The method for analyzing plastic surgery wound repair based on image matching according to claim 5, characterized in that: The calculation formula of the suture strain direction distribution index is: Where D s represents the displacement vector of the sth seam pixel, N s represents the normal vector of the seam line at the sth seam line pixel, represents the mean offset angle of all seam pixels, φ max represents the maximum deviation angle of the stitching line pixels, and DDI represents the stitching strain direction distribution index.

7. The method for analyzing plastic surgery wound repair based on image matching according to claim 1, characterized in that: The analysis of wound repair effect comprises: The periwound tissue consistency index, wound tissue consistency index and suture strain distribution index were obtained and the wound repair index was calculated. The wound repair index was used to quantitatively analyze the wound repair effect. The calculation formula of the wound repair index is as follows: WRI=ω1×OCI+ω2×WCI+ω3×SDI; Wherein, OCI represents the periwound tissue consistency index, WCI represents the wound tissue consistency index, SDI represents the suture strain distribution index, ω1 represents the periwound tissue consistency weight, ω2 represents the wound tissue consistency weight, ω3 represents the suture strain distribution weight, and WRI represents the wound repair index.

8. A plastic surgery wound repair analysis system based on image matching, applied to the plastic surgery wound repair analysis method based on image matching according to any one of claims 1 to 7, characterized in that: The system comprises: An image acquisition module, used to acquire a first wound surface image before wound surface repair and a second wound surface image after wound surface repair; An image registration module, used for performing image registration on the first wound surface image and the second wound surface image using an image matching algorithm; The first evaluation module is used to evaluate the consistency of periwound tissue before and after repair and the consistency of wound surface tissue after repair according to the image registration result; A second evaluation module is used to evaluate the suture strain distribution at the wound suture line according to the second wound surface image; The repair effect analysis module is used to analyze the wound repair effect based on the periwound tissue consistency and wound tissue consistency evaluation results combined with the suture strain distribution evaluation results.

9. An electronic device, comprising: A processor and a memory, wherein the memory stores a computer program that can be called by the processor; characterized in that the processor executes the plastic wound repair analysis method based on image matching as described in any one of claims 1 to 7 by calling the computer program stored in the memory.

10. A computer-readable storage medium, characterized in that: Instructions are stored, and when the instructions are executed on a computer, the computer executes the plastic surgery wound repair analysis method based on image matching as described in any one of claims 1 to 7.

Images