Kidney stone load evaluation method and device based on CT (Computed Tomography) plain-scan image

Abstract

The invention discloses a kidney stone load evaluation method and device based on a CT plain-scan image, and relates to the technical field of medical image processing, and the method comprises the steps: automatically analyzing and recording the semantic coordinate of each lesion region, and constructing a structured data set, the lesion region being the semantic boundary of suspected kidney stone in a CT plain-scan image sequence; constructing a local feature space for the focus, and exploring corresponding semantic features in the local feature space through a morphological method to judge the focus form; constructing a density space matrix by using the semantic features of the focus, designing a search strategy corresponding to the focus form, calculating in the density space matrix to obtain the optimal semantic density, and obtaining the number of kidney stones through an unsupervised clustering algorithm; according to the form and quantity analysis result of the kidney stone, the automatic volume measurement of the kidney stone is realized by utilizing a graphic method. According to the invention, full-automatic accurate measurement of the shape, the number and the volume of the kidney stone in the CT plain-scan image sequence can be realized.

Description

Technical Field

[0001] The present application relates to the technical field of medical image processing, and in particular to a method and device for evaluating kidney stone burden based on CT plain scan images. Background Art

[0002] With the continuous development of medical imaging technology, kidney stone burden assessment based on CT plain scan images has become one of the important means of clinical diagnosis. However, existing assessment methods often rely on manual annotation and semi-automatic tool judgment, which is not only time-consuming and labor-intensive, but also easily affected by subjective factors, resulting in poor accuracy and consistency of assessment results. Therefore, it is particularly important to develop an efficient, accurate and automated kidney stone burden assessment method. Summary of the invention

[0003] The main purpose of the embodiment of the present application is to propose a kidney stone burden assessment method based on CT plain scan images and a dedicated device thereof, so as to overcome the deficiencies of the prior art and achieve efficient and accurate assessment of kidney stone burden. The method combines medical clinical knowledge and unsupervised machine learning technology, and can efficiently and accurately assess the kidney stone burden in CT plain scan images without manual intervention.

[0004] To achieve the above object, one aspect of the embodiments of the present application provides a method for assessing kidney stone burden based on CT plain scan images, the method comprising the following steps:

[0005] Automatically parse and record the semantic coordinates of each lesion area to construct a structured data set, where each lesion area is the semantic boundary of the suspected kidney stone in each CT plain scan image in the CT plain scan image sequence;

[0006] Construct a local feature space for the lesion, and use morphological methods to explore the corresponding semantic features in the local feature space to determine the lesion morphology;

[0007] The density space matrix was constructed using the semantic features corresponding to the lesions, and a search strategy corresponding to the lesion morphology was designed to calculate the optimal semantic density in the density space matrix, and then the number of kidney stones was obtained through an unsupervised clustering algorithm.

[0008] According to the results of kidney stone morphology and quantity analysis, the automatic volume measurement of kidney stones is realized by using graphics method.

[0009] In some embodiments, the automatic parsing and recording of semantic coordinates of each lesion area and constructing a structured data set comprises the following steps:

[0010] Measuring the attributes of each lesion area by a morphological method, and then parsing and recording the two-dimensional semantic coordinates of each lesion area;

[0011] The two-dimensional semantic coordinates of each of the lesion areas are expanded into three-dimensional semantic coordinates according to the sequence number of the CT plain scan image sequence, and a structured data set is formed.

[0012] In some embodiments, constructing a local feature space for the lesion and exploring corresponding semantic features in the local feature space by a morphological method to determine the lesion morphology comprises the following steps:

[0013] The number of the lesion areas in the CT plain scan image sequence is counted and recorded in a dictionary manner; if the maximum number of the lesion areas in the CT plain scan image is less than or equal to 1, the morphology of the lesion in the CT plain scan image is determined to be an isolated lesion; if the maximum number of the lesion areas in the CT plain scan image is greater than 1, the morphology of the lesion in the CT plain scan image is temporarily determined to be an interlaced lesion or a staghorn lesion;

[0014] For lesions tentatively identified as staggered or antler-shaped, all CT plain scan images with a number of lesion regions greater than 1 are traversed, and the lesions are associated with the lesion regions contained in the previous and next CT plain scan images as anchor points to construct a local feature space;

[0015] The in-degree and out-degree of the anchor points in each local feature space are calculated by the degree analysis method. If the out-degree and in-degree of the lesion area are the same, the local feature space is marked as parallel; if the out-degree of the lesion area is greater than the in-degree, the local feature space is marked as bifurcation; if the in-degree of the lesion area is greater than the out-degree, the local feature space is marked as adhesion;

[0016] Traversing all the marks of the local feature space, if there is no bifurcation or adhesion mark, the morphology of the lesion in the CT plain scan image is determined to be a staggered lesion; if there is a bifurcation or adhesion mark, the morphology of the lesion in the CT plain scan image is determined to be a antler-type lesion.

[0017] In some embodiments, the step of constructing a density space matrix using semantic features corresponding to lesions comprises the following steps:

[0018] Calculating the semantic density between the lesion regions according to their three-dimensional semantic coordinates to obtain a density space matrix; wherein the semantic density is used to describe the degree of spatial correlation between the lesion regions;

[0019] The search strategy corresponding to the designed lesion morphology calculates the optimal semantic density in the density space matrix, and then obtains the number of kidney stones through an unsupervised clustering algorithm, including the following steps:

[0020] According to the specific morphology of the lesion, the field-specific morphological structure and the corresponding anchor image sequence number are obtained from the quantity dictionary of the lesion area and recorded in a dictionary manner; wherein the corresponding morphological structure of the staggered lesion is parallel, and the corresponding morphological structure of the antler lesion is bifurcation and adhesion;

[0021] Based on different lesion morphologies and corresponding field-specific morphological structures, the corresponding search objects are calculated;

[0022] The density space matrix is ​​adjusted according to the search object to obtain the target search matrix;

[0023] Based on the specific morphology of the lesion, the target search matrix is ​​traversed to calculate the semantic density difference between the lesion areas. If the semantic density difference exceeds the density search upper limit of the target search matrix, the current density search upper limit is recorded.

[0024] The minimum semantic density is calculated based on the density search upper limit of the current batch, and compared with the optimal semantic density of the previous batch to obtain the optimal semantic density;

[0025] According to the optimal semantic density and lesion characteristics, the lesion areas with density reachable are clustered together to obtain one or more clusters through an unsupervised clustering algorithm, and the number of clusters is the number of lesions; wherein the lesion characteristic is that the lesion exists in at least two consecutive CT plain scan images.

[0026] In some embodiments, the method further comprises the following steps:

[0027] Verify whether the cluster belongs to a kidney stone lesion;

[0028] The number of clusters belonging to kidney stone lesions was statistically verified as the number of kidney stones.

[0029] In some embodiments, the method of realizing automatic volume measurement of kidney stones by using a graphics method based on the results of the morphology and quantity analysis of kidney stones comprises the following steps:

[0030] The pixels of the lesion area belonging to the kidney stone are classified into two categories: foreground and background, and then the coverage ratio between each pixel and the surrounding adjacent pixels in the area belonging to the foreground is calculated by a graphics method; wherein the foreground is the kidney stone and the background is non-kidney stone;

[0031] All pixels of the lesion area belonging to the kidney stone are traversed to obtain the coverage rate of each lesion area, and then the volume of the kidney stone is calculated in combination with the slice thickness and pixel spacing of the CT plain scan image.

[0032] To achieve the above-mentioned purpose, another aspect of the embodiment of the present application provides a kidney stone burden assessment device based on CT plain scan images, the device comprising:

[0033] A data set construction unit, used for automatically parsing and recording the semantic coordinates of each lesion area to construct a structured data set, wherein each lesion area is a semantic boundary of a suspected kidney stone in each CT plain scan image in a CT plain scan image sequence;

[0034] A lesion morphology judgment unit is used to construct a local feature space for the lesion and to judge the lesion morphology by exploring corresponding semantic features in the local feature space through morphological methods;

[0035] The kidney stone quantity determination unit is used to construct a density space matrix using the semantic features corresponding to the lesions, and to design a search strategy corresponding to the lesion morphology to calculate the optimal semantic density in the density space matrix, and then obtain the number of kidney stones through an unsupervised clustering algorithm;

[0036] The kidney stone volume determination unit is used to realize automatic volume measurement of kidney stones by using graphics methods according to the results of kidney stone morphology and quantity analysis.

[0037] To achieve the above objective, another aspect of an embodiment of the present application provides an electronic device, the electronic device comprising a memory and a processor, the memory storing a computer program, and the processor implementing the above method when executing the computer program.

[0038] To achieve the above objective, another aspect of an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program implements the above method when executed by a processor.

[0039] The embodiments of the present application include at least the following beneficial effects:

[0040] This application has realized the automation and high-precision evaluation of the kidney stone load in CT plain scan images by introducing unsupervised machine learning technology and medical clinical knowledge. Specifically, this method can automatically and accurately judge the morphology of kidney stones by analyzing the distribution characteristics and morphological characteristics of the lesion area. In addition, this method uses unsupervised machine learning technology and graphics methods to automatically complete the number and volume evaluation of kidney stones without manual intervention, significantly improves the efficiency of evaluation, and reduces human errors. In summary, the kidney stone load evaluation method based on CT plain scan images proposed in this application and its special device have significantly improved the accuracy and efficiency of kidney stone load evaluation through technological innovation, making the evaluation process more objective and standardized, and providing important technical support for clinical diagnosis and treatment. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0042] Figure 1 A schematic diagram of a process for evaluating kidney stone burden based on CT plain scan images provided in an embodiment of the present application;

[0043] Figure 2 A schematic diagram of the structure of a kidney stone burden assessment device based on CT plain scan images provided in an embodiment of the present application;

[0044] Figure 3 A schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0045] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application is further described in detail below in conjunction with the accompanying drawings and examples. It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the embodiments of the present application. They are only examples of devices and methods consistent with some aspects of the embodiments of the present application as detailed in the attached claims.

[0046] It is understood that the terms "first", "second", etc. used in this application can be used to describe various concepts in this article, but unless otherwise specified, these concepts are not limited by these terms. These terms are only used to distinguish one concept from another concept. For example, without departing from the scope of the embodiment of the present application, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the words "if" and "if" as used herein can be interpreted as "at the time of" or "when" or "in response to determination".

[0047] The terms "at least one", "multiple", "each", "any", etc. used in this application, at least one includes one, two or more, multiple includes two or more, each refers to each of the corresponding multiple, and any refers to any one of the multiple.

[0048] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0049] Before describing the embodiments of the present application in detail, the various kidney stone morphologies involved in the present application are described as follows:

[0050] Solitary kidney stones: limited to a single kidney stone or multiple kidney stones that are not crossed in the spatial dimension and appear as a single lesion area in each CT plain scan image.

[0051] Interlaced kidney stones: composed of multiple kidney stones, but each kidney stone does not branch or attach to other kidney stones. In CT plain scan images, interlaced kidney stones appear as multiple lesion areas in each CT plain scan image, and each lesion area belongs to a different kidney stone.

[0052] Staghorn calculi: Staghorn calculi are similar in morphology to interdigitated calculi, except that bifurcations or adhesions may occur between the calculi themselves and between the calculi. Staghorn calculi appear as multiple lesions in each plain CT scan, which may belong to the same or different calculi.

[0053] The embodiment of the present application provides a method for assessing the burden of kidney stones based on CT plain scan images, and relates to the field of medical image processing technology. The method for assessing the burden of kidney stones based on CT plain scan images provided in the embodiment of the present application can be applied to a terminal, can also be applied to a server, and can also be software running in a terminal or a server. In some embodiments, the terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, a smart speaker, a smart watch, and a car terminal, etc., but is not limited to this; the server side can be configured as an independent physical server, or it can be configured as a server cluster or a distributed system composed of multiple physical servers, and can also be configured to provide cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and cloud servers for basic cloud computing services such as big data and artificial intelligence platforms. The server can also be a node server in a blockchain network; the software can be an application that implements a knowledge extraction method, etc., but is not limited to the above forms.

[0054] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments, in which tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0055] Reference Figure 1 The present application embodiment provides a method for assessing kidney stone burden based on CT plain scan images. The method may include but is not limited to S110 to S140, as follows:

[0056] Before executing S110, this embodiment may further include a step of acquiring a lesion region. For example, this embodiment may identify multiple lesion regions from a CT plain scan image sequence, specifically:

[0057] The lesion boundary constraint model is used to identify and outline the lesion area from the CT plain scan image sequence. The lesion boundary constraint model can be used to roughly divide the lesion area, and the refined lesion area can be further identified by combining morphological analysis.

[0058] Steps to identify the lesion area may include:

[0059] 1. Construct a lesion boundary constraint model based on convolutional neural network (CNN): Use pre-trained deep convolutional neural network to fine-tune specific lesion features in CT plain scan image sequences to identify and accurately outline the lesion area. The lesion boundary constraint model can not only effectively identify the lesion area, but also maintain high-precision segmentation in complex backgrounds. Compared with traditional threshold segmentation or edge detection methods, it has higher robustness and adaptability.

[0060] 2. Combining morphological operations and lesion features to determine attributes: By applying morphological operations (such as opening and closing operations) to the lesion areas identified by the lesion boundary constraint model, the contours of the lesion areas are further refined, and the attributes of each lesion area (stone area or non-stone area) are determined by combining the texture, size and other features of the lesion area. This step not only enhances the clarity of the lesion area boundary, but also provides detailed lesion feature parameters for subsequent load assessment.

[0061] S110: Automatically parse and record the semantic coordinates of each lesion area to construct a structured data set, wherein each lesion area is a semantic boundary of a suspected kidney stone in each CT plain scan image in a CT plain scan image sequence.

[0062] It can be understood that each lesion area can correspond to a two-dimensional semantic coordinate in the plane coordinate system, and the semantic coordinate combined with the CT plain scan image sequence number can correspond to a three-dimensional semantic coordinate in the spatial coordinate system. The three-dimensional semantic coordinates of all lesion areas are combined as a structured data set.

[0063] Furthermore, S110 may include S111-S112:

[0064] S111: measuring the attributes of each lesion region by a morphological method, and then parsing and recording the two-dimensional semantic coordinates of each lesion region;

[0065] The expression of the two-dimensional semantic coordinates is:

[0066] C ij (x c,ij ,y c,ij )=f r (R ij );

[0067] Among them, C ij (x c,ij ,y c,ij ) is the two-dimensional semantic coordinate, x c,ij and c,ij f respectively represent the x and y coordinates of the two-dimensional semantic coordinates of the ith lesion area in the jth CT plain scan image; r Represents the regionprops function in the morphological method; R ij is the i-th lesion area in the j-th CT plain scan image, j=1, 2, ..., E, and E is the total number of the CT plain scan images;

[0068] Specifically, this embodiment can use the regionprops function in the morphological method to determine the semantic coordinates of each lesion region contained in each CT plain scan image in the CT plain scan image sequence, and each lesion region corresponds to a two-dimensional semantic coordinate;

[0069] S112: Expanding the two-dimensional semantic coordinates of each lesion area into three-dimensional semantic coordinates according to the sequence number of the CT plain scan image sequence, and forming a structured data set;

[0070] The expression of the three-dimensional semantic coordinates is:

[0071] Cij (x c,ij ,y c,ij ,z j );

[0072] Among them, z j = j represents the serial number of the CT plain scan image; the data set is represented by D, which is defined as D = {C ij |i=1,2,...,n j ; j = 1, 2, ..., E}, C in D ij is the three-dimensional semantic coordinate; n j It represents the number of the lesion areas identified in the j-th CT plain scan image.

[0073] Specifically, by determining the three-dimensional semantic coordinates of each lesion area, three-dimensional modeling of each lesion area can be performed, thereby providing a data basis for subsequent analysis of the morphology, quantity, and volume of kidney stones.

[0074] S120: construct a local feature space for the lesion, and explore corresponding semantic features in the local feature space through morphological methods to determine the lesion morphology.

[0075] It is understandable that kidney stones may exist in various forms. For the convenience of classification, this embodiment can classify the forms of kidney stones into isolated, interlaced and antler types.

[0076] Kidney stones of different shapes may correspond to different lesion areas, so this embodiment can determine the corresponding kidney stone shape based on the characteristics of each lesion area, such as quantity distribution, morphological structure and other characteristics.

[0077] Furthermore, S120 may include S121 to S123:

[0078] S121: Counting and recording the number of the lesion regions in the CT plain scan image sequence by means of a dictionary; if the maximum number of the lesion regions in the CT plain scan image is less than or equal to 1, determining the morphology of the lesion in the CT plain scan image as an isolated lesion; if the maximum number of the lesion regions in the CT plain scan image is greater than 1, temporarily determining the morphology of the lesion in the CT plain scan image as an interlaced lesion or a staghorn lesion;

[0079] The expression for counting the number of the lesion areas is:

[0080]

[0081] Among them, Dict m is a dictionary recording the number of the lesion areas in the CT plain scan image sequence, is a statistical function indexed by the z-axis, Dz The data set is indexed on the z-axis;

[0082] The expression for preliminarily distinguishing the morphology of kidney stones is:

[0083]

[0084] in, is the maximum search function, is represents isolated kidney stones, ss represents interlaced kidney stones, cs represents staghorn kidney stones; M represents the morphology of kidney stones;

[0085] S122: For lesions tentatively identified as interlaced or antler-shaped, traverse all CT plain scan images with a number of lesion regions greater than 1, and use this as an anchor point to associate it with the lesion regions included in the previous and next CT plain scan images to construct a local feature space;

[0086] The expression of the local feature space is:

[0087] L z =f E (f pd (D z-1 ,D z ,D z+1 ));

[0088] Among them, L z represents the local feature space, f E is the Euclidean distance function, f pd It is the Pandas data constructor;

[0089] S123: calculating the in-degree and out-degree of the anchor points in each local feature space by a degree analysis method; if the out-degree and in-degree of the lesion area are the same, marking the local feature space as parallel; if the out-degree of the lesion area is greater than the in-degree, marking the local feature space as bifurcation; if the in-degree of the lesion area is greater than the out-degree, marking the local feature space as adhesion;

[0090] The expression for calculating the in-degree is:

[0091]

[0092] Where ε is L z The average of the sum of the mean and standard deviation of ; It is a statistical function that counts the number of 0s;

[0093] S124: traversing all the marks of the local feature space, if there is no bifurcation or adhesion mark, the morphology of the lesion in the CT plain scan image is determined to be a staggered lesion; if there is a bifurcation or adhesion mark, the morphology of the lesion in the CT plain scan image is determined to be a staghorn lesion;

[0094] The expression to further distinguish the morphology of kidney stones is:

[0095]

[0096] in, represents the row space of the matrix, represents the column space of the matrix, Represents the value corresponding to the a-th row and b-th column of the matrix;

[0097] This embodiment determines the morphology of kidney stones by analyzing the number of lesion areas contained in each CT plain scan image in the CT plain scan image sequence and the contextual relationship of image matching. This embodiment can improve the efficiency of identifying the morphology of kidney stones and can identify the morphology of kidney stones without manual intervention.

[0098] S130: Construct a density space matrix using semantic features corresponding to the lesions, and design a search strategy corresponding to the lesion morphology to calculate the optimal semantic density in the density space matrix, and then obtain the number of kidney stones through an unsupervised clustering algorithm.

[0099] It is understandable that isolated, interlaced, and staghorn lesions may have one or more. However, based on different morphologies, the way to evaluate the number of kidney stones will be different. For isolated types, a simple judgment is sufficient. For interlaced types, it is necessary to find the CT plain scan image with the largest number of lesion areas, and then start the analysis from that CT plain scan image. For staghorn types, it is necessary to find multiple continuous CT plain scan images in which the number of lesion areas changes, and then start the analysis from the above multiple continuous CT plain scan images.

[0100] Further, S130 may include S131 to S137:

[0101] S131: Calculating the semantic density between the lesion regions according to their three-dimensional semantic coordinates to obtain a density space matrix; wherein the semantic density is used to describe the degree of spatial correlation between the lesion regions;

[0102] The expression of the density space matrix is:

[0103]

[0104] Among them, P i,j represents the semantic density, (x i,y i ,z i ) and (x j ,y j ,z j ) are any two different three-dimensional semantic coordinates; the density space matrix is ​​represented by P, P includes P calculated from each of the three-dimensional semantic coordinates i,j ;

[0105] S132: according to the specific morphology of the lesion, obtaining the domain-specific morphological structure and the corresponding anchor image sequence number from the quantity dictionary of the lesion area and recording them in a dictionary manner; wherein the corresponding morphological structure of the staggered lesion is parallel, and the corresponding morphological structure of the antler lesion is bifurcation and adhesion;

[0106] The expression for recording the unique morphological structure and the corresponding anchor image sequence number in a dictionary manner is:

[0107]

[0108] in, It is a morphological search function, which is used to search for the location of the unique semantic features of the specified morphology in the CT plain scan image sequence;

[0109] S133: based on different lesion morphologies and corresponding field-specific morphological structures, calculate and obtain corresponding search objects;

[0110] The expression of the search object is:

[0111]

[0112] Among them, f p It is a positioning function, which is used to locate the position of the unique semantic features in the CT plain scan image sequence;

[0113] S134: adjusting the density space matrix according to the search object to obtain a target search matrix;

[0114] The expression of the target search matrix is:

[0115]

[0116] Wherein, P′ represents the target search matrix constructed by columns, P″ represents the target search matrix constructed by rows; m and n represent the rows and columns of the density space matrix P, P m,k is a matrix focused on columns k, P k ' ,n is a matrix focused on k rows, sort represents the sorting function;

[0117] S135: based on the specific morphology of the lesion, traverse the target search matrix to calculate the semantic density difference between the lesion areas, and if the semantic density difference exceeds the density search upper limit of the target search matrix, record the current density search upper limit;

[0118] The expression of the density search upper limit is:

[0119] cutoff = f J (DDN(P u ″ +1,k ,P u ' , ' k ),φ)

[0120] Among them, f J represents the contrast function, φ is the average of the mean and variance of the kth column in P″; DDN represents the neighborhood discrete difference function, which is expressed as:

[0121]

[0122] Among them, P u ″ +1,k and P u ' , ' k are the two values ​​that need to be compared, μ is P u ″ +1,k and P u ' , ' k The average value of

[0123] S136: Calculate the minimum semantic density according to the density search upper limit of the current batch, and compare it with the optimal semantic density of the previous batch to obtain the optimal semantic density;

[0124] The expression of the optimal semantic density is:

[0125]

[0126] Among them, EpS represents the semantic density of the current batch; EpS' represents the optimal semantic density of the previous batch; is the minimum search function used to search for the minimum value, is a minimum comparison function used to determine the minimum between two input values;

[0127] S137: according to the optimal semantic density and lesion characteristics, clustering the lesion regions with density reachable together to obtain one or more clusters by an unsupervised clustering algorithm, and the number of clusters is the number of lesions; wherein the lesion characteristic is that the lesion exists in at least two consecutive CT plain scan images;

[0128] The expression for calculating the number of kidney stones is:

[0129] Q=F cluster (D,EpS)

[0130] Among them, F cluster is an unsupervised clustering algorithm, Q is the number of clusters of lesions;

[0131] Specifically, this embodiment performs a clustering operation on each 3D semantic coordinate by calculating the semantic density between each 3D semantic coordinate. When the semantic density is less than the calculated optimal semantic density, it can be considered that each 3D semantic coordinate belongs to the same cluster.

[0132] In order to improve the accuracy of the number of kidney stones, the embodiment of the present application may further include the following steps S138-S139:

[0133] S138: verifying whether the cluster is a kidney stone lesion;

[0134] The expression to be verified is:

[0135]

[0136] Among them, f represents the verification result, υ i is the effective value; when υ i 1 indicates that the object attribute of the lesion area is kidney stones. i 0 means that the lesion area is not a kidney stone;

[0137] S139: Statistically verifying the number of clusters belonging to kidney stone lesions as the number of kidney stones.

[0138] It can be understood that this embodiment verifies whether each cluster is a kidney stone, removes clusters that are not kidney stones, and finally counts the number of clusters verified to be kidney stones to obtain the total number of kidney stones.

[0139] S140: Based on the results of kidney stone morphology and quantity analysis, automatic volume measurement of kidney stones is achieved using graphics methods.

[0140] Furthermore, S140 may specifically include S141-S142:

[0141] S141: Classifying the pixels of the lesion area belonging to the kidney stone into two categories: foreground and background, and then calculating the coverage ratio between each pixel and surrounding adjacent pixels in the foreground area by a graphics method; wherein the foreground is the kidney stone, and the background is non-kidney stone;

[0142] The expression for calculating the coverage is:

[0143]

[0144] Among them, X i,j is the pixel value corresponding to the i-th row and j-th column in the target area;

[0145] S142: traversing all pixels of the lesion area belonging to the kidney stone to obtain the coverage rate of each lesion area, and then calculating the volume of the kidney stone in combination with the slice thickness and pixel spacing of the CT plain scan image;

[0146] The total volume of kidney stones is expressed as:

[0147]

[0148] Where V represents the total volume of kidney stones, and represents the pixel spacing of the kth CT plain scan image, ST k represents the slice thickness of the kth CT plain scan image.

[0149] Specifically, for the volume estimation problem of irregular objects such as kidney stones, this embodiment proposes a volume analysis solution based on graphic combination: kidney stones are regarded as irregular shapes composed of multiple squares and triangles, squares indicate that four pixels are in the area where the target area is located, and triangles indicate that three of the four pixels are in the area where the target area is located. Therefore, this embodiment calculates the volume of irregular kidney stones by calculating the number of squares and triangles in the area where the target area is located.

[0150] In some optional embodiments, the step of calculating the volume may include: 1. First, based on the result of the quantity evaluation, extract the cluster corresponding to each kidney stone, and then extract the corresponding image number and three-dimensional semantic coordinates from the cluster. 2. According to the image number and three-dimensional semantic coordinates, correspond back to the original lesion area, calculate the coverage rate of the lesion area to obtain the area of ​​the lesion area. 3. According to all the numbers and coordinates, as well as the pixel spacing and slice thickness corresponding to the image, the volume of the kidney stone is obtained.

[0151] Next, the solution of the embodiment of the present application will be introduced and explained in detail with reference to specific application examples.

[0152] Optionally, the steps of this embodiment may include obtaining lesion area boundaries and kidney stone burden assessment.

[0153] Step 1: Obtain the boundary of the lesion area.

[0154] The steps for determining the boundaries of the lesion area may include:

[0155] 1. Construct a lesion boundary constraint model based on convolutional neural network (CNN): Use pre-trained deep convolutional neural network to fine-tune specific lesion features in CT plain scan image sequences to identify and accurately outline the lesion area. The lesion boundary constraint model can not only effectively identify the lesion area, but also maintain high-precision segmentation in complex backgrounds. Compared with traditional threshold segmentation or edge detection methods, it has higher robustness and adaptability.

[0156] 2. Combining morphological operations and lesion features to determine attributes: By applying morphological operations (such as opening and closing operations) to the lesion areas identified by the lesion boundary constraint model, the contours of the lesion areas are further refined, and the attributes of each lesion area (stone area or non-stone area) are determined by combining the texture, size and other features of the lesion area. This step not only enhances the clarity of the lesion area boundary, but also provides detailed lesion feature parameters for subsequent load assessment.

[0157] Step 2: Assessment of kidney stone burden. The specific steps are as follows:

[0158] Step 1: 3D modeling: Let the jth CT scan image be Image j , where j = 1, 2, ..., E, E is the total number of CT plain scan images. For the i-th lesion area R in the j-th CT plain scan image ij , use the regionprops function in the morphological method to extract its two-dimensional semantic coordinates C ij (x c,ij ,y c,ij ), the process can be formulated as C ij (x c,ij ,y c,ij ) = f r (R ij ), where x c,ij and c,ij represent the x and y coordinates of the 2D semantic coordinates of the i-th lesion in the j-th CT plain scan image, respectively, and f r In order to use the corresponding CT scan image layer as the z-axis coordinate, each two-dimensional semantic coordinate C ij (x c,ij ,y c,ij ) is expanded to a three-dimensional semantic coordinate C ij (x c,ij ,y c,ij ,z j ), where z j = j represents the serial number of the CT plain scan image. Finally, the three-dimensional semantic coordinates of all lesion areas in all CT plain scan images are collected into a structured data set D, which is defined as D = {C ij|i=1,2,...,n j ; j = 1, 2, ..., E}, where n j represents the number of lesions identified in the jth CT scan image. This dataset D represents the distribution of lesions in three-dimensional space. Each three-dimensional semantic coordinate C ij (x c,ij ,y c,ij ,z j ) indicates the specific location of the lesion in the CT plain scan image sequence.

[0159] Step 2: Morphological analysis: Clinicians usually focus on CT plain scan images with a large number of kidney stone regions or changes in regions, and then judge the kidney stone morphology through the contextual relationship of region matching. Using this diagnostic knowledge, the morphological analysis algorithm proposed in this embodiment can identify the morphology of kidney stones without manual intervention.

[0160] Step 2.1: Local feature space construction: First, the number of lesion areas in each CT plain scan image is counted. It contains key information that is crucial to determine the lesion morphology. The process can be formulated as: Dict m ={z|f s z (D z )}, where f s z It is a statistical function indexed by the z-axis and is used to count the number of lesion areas on each CT plain scan image. In general, the morphology of kidney stones shows local changes. For interdigitated kidney stones, the morphological structure is that the lesions are parallel in space. For staghorn kidney stones, the morphological structure is that the lesions are bifurcated or adhered. For f s z (D z )>1, that is, the CT plain scan image contains multiple lesion areas, and a local feature space L is constructed to reflect the changes in the morphology of kidney stones. The process can be formulated as: L z =f E (f pd (D z-1 ,D z ,D z+1 )), where f E is the Euclidean distance function, f pd Is the Pandas data constructor.

[0161] Step 2.2: Domain-specific semantic feature exploration: For solitary kidney stones, each CT plain scan image contains only a single lesion area, while for staggered and staghorn kidney stones, multiple kidney stone areas may coexist in a single CT plain scan image. This feature can be effectively used to identify solitary kidney stones. The process can be formulated as: in The maximum search function, is represents isolated kidney stones, ss represents interlaced kidney stones, and cs represents staghorn kidney stones. Regarding interlaced and staghorn kidney stones, the former has a unique semantic feature of parallelism, which shows a one-to-one regional correlation in the local feature space, while the latter has a unique semantic feature of bifurcation or adhesion, which may present a one-to-many or many-to-one situation in the local feature space. Therefore, exploring the in-and-out degrees between lesion regions in the local feature space can effectively distinguish them. The process can be formulated as: Where Ι is the indicator function, the formula is: Where ε is L z The average of the sum of the mean and standard deviation of i The total number of It is a statistical function that counts the number of zeros.

[0162] Step 3: Quantity assessment: For different morphologies of kidney stones, clinicians usually choose appropriate assessment methods based on the specific situation. For solitary kidney stones, a comprehensive assessment is usually performed from beginning to end. For staggered and staghorn kidney stones, the focus is usually on areas with unique semantic features. Using this diagnostic knowledge, the proposed quantity analysis algorithm adaptively adopts corresponding strategies to automatically estimate the number of kidney stones.

[0163] Step 3.1: Spatialization of semantic density: Euclidean distance is used to evaluate the semantic density between the three-dimensional semantic coordinates of each lesion area. The formula is: Where (x i ,y i ,z i ) and (x j ,y j ,z j ) are two different three-dimensional semantic coordinates. After the above steps, a density space matrix P reflecting the relationship between each lesion area can be obtained.

[0164] Step 3.2: Semantic density search using clinical knowledge: In clinical settings, the methods used to evaluate kidney stones of different morphologies show significant differences. Faced with various morphologies of kidney stones, fixed semantic density search strategies are no longer flexible. This work proposes a semantic density search strategy specific to lesion morphology from a clinical perspective. This strategy integrates clinical judgment knowledge into the semantic density search process and calculates the optimal semantic density by interacting with the density space matrix and lesion morphology. Therefore, the search process can be summarized into the following steps: construction of the search object, design of the search behavior, and definition of search termination.

[0165] Step 3.2.1: Construction of search objects: The representation of search objects constitutes the initial and critical stage of semantic density search. The search objects of each step are constructed based on the medical perspective. The establishment of search objects involves adjusting the density space matrix based on regions of domain-specific semantic features. The process is formulated as: Where m and n represent the rows and columns of the density space matrix P, P m,k is a matrix focused on columns k, P k ' ,n is a matrix focused on row k, sort represents the sorting function, k is the search object, and the formula is: where f p It is a positioning function used to locate the position of unique semantic features in the CT plain scan image sequence. q It is a dictionary that records unique semantic features and their corresponding image positions. The formula is: It is a morphological search function, which is used to search for the location of the unique semantic features of the specified morphology in the CT plain scan image sequence.

[0166] Step 3.2.2: Design of search behavior: If adjacent 3D semantic coordinates belong to the same cluster, their deviations should remain within a stable range. This knowledge helps calculate the semantic density difference cutoff, which distinguishes the semantic density difference between them by calculating the discrete values ​​of adjacent semantic densities. The process can be formulated as: cutoff = f J (DDN(P″ u+1,k ,P″ u,k ),φ), where f J represents the contrast function, φ is the average of the mean and variance of the kth column in P″, and DDN represents the neighborhood discrete difference function, which can be formulated as: Where P u ″ +1,k and P u ' , ' k are the two values ​​to be compared, μ is P u ″+1,k and P u ' , ' k The average value of . Subsequently, the optimal semantic density Eps can be determined by comparing the optimal semantic density of the current batch with the optimal semantic density of the previous batch. The process can be formulated as: in is a minimum search function used to search for the minimum value in an input list or dictionary, Is a minimum comparison function used to determine the minimum between two input values.

[0167] Step 3.2.3: Definition of search termination: The termination condition of the complete semantic density search process is that the search boundary exceeds the range of the matrix P, which can be determined as: u≥m-1.

[0168] Step 3.3: Number of clusters found: Density-based clustering algorithms are able to find clusters with random shapes without pre-defining the number of clusters. The number of kidney stones can be easily determined by calculating the optimal semantic density through a semantic density search strategy. The algorithm can be formulated as: Q = F cluster (D, EpS), where F cluster It is an unsupervised clustering algorithm.

[0169] Step 3.4: Validity verification: Since the search target includes all areas identified by the adaptive discriminant boundary algorithm, the clustering results include non-stone clusters and stone clusters. In order to distinguish non-stone clusters from stone clusters, a validity check is designed to examine whether there are semantic coordinates belonging to non-stones in a certain cluster. Invalid semantic coordinates mean lesion areas that are judged as non-stones in the lesion boundary constraint model. The designed validity test method can be expressed as: Where f represents the verification result, υ i is a valid value. The only valid values ​​are 1 and 0. The former indicates that the semantic coordinate is a kidney stone area, and the latter indicates a non-kidney stone area. Therefore, for a cluster set, when the verification result is 1, the cluster set is considered to be a kidney stone, except for other cases.

[0170] Step 4: Volume evaluation: Aiming at the problem of volume estimation of irregular objects such as kidney stones, a volume analysis algorithm based on graphic combination is proposed. The algorithm regards kidney stones as irregular shapes composed of multiple squares and triangles. A square means that four pixels are in the area where the target area is located, and a triangle means that three of the four pixels are in the area where the target area is located. Therefore, calculating the volume of this irregular shape mainly requires calculating the number of squares and triangles in the area where the target area is located. In the proposed algorithm, the pixel attributes of the target area are first distinguished, and then the coverage rate between each pixel and its adjacent pixels belonging to kidney stones is calculated, and its expression is: When traversing all pixels, the total volume of kidney stones can be expressed as: in and represents the pixel spacing of the kth CT plain scan image, ST k Represents the slice thickness of the kth CT plain scan image.

[0171] The load assessment of kidney stones in this embodiment can be divided into: kidney stone morphology assessment, kidney stone quantity assessment and kidney stone volume assessment. In the kidney stone morphology assessment, the morphology of the stones is divided into three types, namely isolated, staggered and antler. The morphology assessment uses clinical prior knowledge to construct a local feature space for the variability or high concentration area of ​​kidney stones. Subsequently, a morphological correlation algorithm is designed to explore the regional correlation in the local feature space, thereby realizing the stone morphology analysis. In the kidney stone quantity assessment, an adaptive analysis strategy is designed using the clinical prior knowledge of the actual analysis quantity under different stone morphologies. This strategy combines the domain-specific lesion semantic features to construct a density space, and then uses a discrete neighbor difference function to measure the semantic density difference between lesions in the density space. Through the interaction of semantic density difference information and lesion semantic features, this embodiment can adaptively perform automatic quantitative analysis on stones of different morphologies. In the kidney stone volume assessment, since kidney stones are extremely irregular objects, the regular volume calculation method is not suitable for kidney stone volume assessment, so a graphic combination segmentation algorithm is designed to accurately assess the kidney stone volume. In the designed algorithm, the pixels of kidney stones in a single CT plain scan image section are restored to their actual size based on the pixel spacing and layer thickness in the CT plain scan image. Then, the kidney stones are segmented into irregular cubes composed of multiple prisms and cubes through a graphic combination segmentation algorithm. The sum of the volumes of the prisms and cubes is the volume of the kidney stones in a single CT plain scan image section. Finally, the volume of the kidney stones is calculated based on the connected domain information obtained in the kidney stone quantity assessment.

[0172] The existing kidney stone assessment method is mainly to make a simple judgment on the attribution between the contours of kidney stones in continuous CT images, and calculate the volume using an approximate method. The existing method is only applicable to the scenario where the patient only suffers from kidney stones, and cannot adapt to the actual clinical environment. Moreover, the existing method only focuses on the volume assessment of kidney stones, and lacks research on the morphology and number of kidney stones. Therefore, the kidney stone assessment method implemented by the method of this embodiment comprehensively evaluates the morphology, number and volume of kidney stones, uses professional diagnostic knowledge, customizes a load assessment method that conforms to a clinical perspective for different stone morphologies, and realizes an automated and precise assessment of kidney stone load.

[0173] This embodiment has the following technical features:

[0174] Lesion boundary constraint method: It can automatically identify and outline the lesion boundary contour, and then use morphological operations (such as opening and closing operations) to further refine the lesion boundary, and then combine the texture, size and other characteristics of the lesion to determine the attributes of the lesion area.

[0175] Kidney stone burden assessment method: First, this method uses clinical prior knowledge to design a morphological correlation analysis algorithm for kidney stones to explore the correlation between lesion areas, thereby performing adaptive automated morphological analysis. In addition, this method combines semantic features unique to the field of kidney stones to develop morphologically specific adaptive analysis strategies. These strategies use neighborhood discrete difference functions to measure the semantic density differences between lesion areas, and then combine validity verification methods to screen out clusters that meet the characteristics of stones, so that adaptive automated quantitative analysis of kidney stones with different morphologies can be performed. Furthermore, based on the cluster results of the quantitative analysis of kidney stones, this method uses a graphical combination method to calculate the volume of each lesion area in the cluster, and then calculates the total volume of the entire cluster to achieve the purpose of kidney stone volume assessment.

[0176] Reference Figure 2 The embodiment of the present application further provides a kidney stone burden assessment device based on CT plain scan images, which can implement the above-mentioned kidney stone burden assessment method based on CT plain scan images, and the device includes:

[0177] A data set construction unit, used for automatically parsing and recording the semantic coordinates of each lesion area to construct a structured data set, wherein each lesion area is a semantic boundary of a suspected kidney stone in each CT plain scan image in a CT plain scan image sequence;

[0178] A lesion morphology judgment unit is used to construct a local feature space for the lesion and to judge the lesion morphology by exploring corresponding semantic features in the local feature space through morphological methods;

[0179] The kidney stone quantity determination unit is used to construct a density space matrix using the semantic features corresponding to the lesions, and to design a search strategy corresponding to the lesion morphology to calculate the optimal semantic density in the density space matrix, and then obtain the number of kidney stones through an unsupervised clustering algorithm;

[0180] The kidney stone volume determination unit is used to realize automatic volume measurement of kidney stones by using graphics methods according to the results of kidney stone morphology and quantity analysis.

[0181] It can be understood that the contents of the above method embodiments are all applicable to the present device embodiments, the functions specifically implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0182] The embodiment of the present application also provides an electronic device, the electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the above-mentioned method for assessing kidney stone burden based on CT plain scan images when executing the computer program. The electronic device can be any intelligent terminal including a tablet computer, a car computer, etc.

[0183] It can be understood that the contents of the above method embodiments are all applicable to the present device embodiments, the functions specifically implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0184] See also Figure 3 , Figure 3 The hardware structure of an electronic device of another embodiment is illustrated, and the electronic device includes:

[0185] The processor 301 may be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present application;

[0186] The memory 302 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 302 can store an operating system and other application programs. When the technical solution provided in the embodiment of this specification is implemented by software or firmware, the relevant program code is stored in the memory 302, and the processor 301 calls and executes a method for evaluating the burden of kidney stones based on CT plain scan images in the embodiment of this application;

[0187] Input / output interface 303, used to implement information input and output;

[0188] The communication interface 304 is used to realize the communication interaction between the device and other devices. The communication can be realized through a wired manner (such as USB, network cable, etc.) or a wireless manner (such as mobile network, WIFI, Bluetooth, etc.);

[0189] A bus 305 that transmits information between the various components of the device (e.g., the processor 301, the memory 302, the input / output interface 303, and the communication interface 304);

[0190] The processor 301 , the memory 302 , the input / output interface 303 and the communication interface 304 are connected to each other in communication within the device via the bus 305 .

[0191] An embodiment of the present application also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the above-mentioned method for assessing kidney stone burden based on CT plain scan images.

[0192] It can be understood that the contents of the above method embodiments are all applicable to the present storage medium embodiments, the functions specifically implemented by the present storage medium embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0193] The memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory may optionally include a memory remotely disposed relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0194] The embodiments described in the embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application and do not constitute a limitation on the technical solutions provided in the embodiments of the present application. Those skilled in the art will appreciate that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0195] Those skilled in the art will appreciate that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present application, and may include more or fewer steps than shown in the figures, or a combination of certain steps, or different steps.

[0196] The device embodiments described above are merely illustrative, and the units described as separate components may or may not be physically separated, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0197] Those skilled in the art will appreciate that all or some of the steps in the methods disclosed above, and the functional modules / units in the systems and devices may be implemented as software, firmware, hardware, or a suitable combination thereof.

[0198] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0199] It should be understood that in the present application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0200] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the above units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0201] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0202] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0203] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including multiple instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, referred to as ROM), random access memory (Random Access Memory, referred to as RAM), disk or optical disk and other media that can store programs.

[0204] The preferred embodiments of the present invention are described above with reference to the accompanying drawings, but the scope of the rights of the present invention is not limited thereto. Any modification, equivalent substitution and improvement made by a person skilled in the art without departing from the scope and essence of the present invention should be within the scope of the rights of the present invention.

Claims

1. A method for assessing kidney stone burden based on CT plain scan images, characterized in that: The method comprises the following steps: Automatically parse and record the semantic coordinates of each lesion area to construct a structured data set, where each lesion area is the semantic boundary of the suspected kidney stone in each CT plain scan image in the CT plain scan image sequence; Construct a local feature space for the lesion, and use morphological methods to explore the corresponding semantic features in the local feature space to determine the lesion morphology; The density space matrix was constructed using the semantic features corresponding to the lesions, and a search strategy corresponding to the lesion morphology was designed to calculate the optimal semantic density in the density space matrix, and then the number of kidney stones was obtained through an unsupervised clustering algorithm. According to the results of kidney stone morphology and quantity analysis, the automatic volume measurement of kidney stones is realized by using graphics method.

2. The method for evaluating kidney stone burden based on CT plain scan images according to claim 1, characterized in that: The automatic parsing and recording of the semantic coordinates of each lesion area and the construction of a structured data set include the following steps: Measuring the attributes of each lesion area by a morphological method, and then parsing and recording the two-dimensional semantic coordinates of each lesion area; The two-dimensional semantic coordinates of each of the lesion areas are expanded into three-dimensional semantic coordinates according to the sequence number of the CT plain scan image sequence, and a structured data set is formed.

3. The method for evaluating kidney stone burden based on CT plain scan images according to claim 1, characterized in that: The method of constructing a local feature space for the lesion and exploring corresponding semantic features in the local feature space by a morphological method to determine the lesion morphology comprises the following steps: The number of the lesion areas in the CT plain scan image sequence is counted and recorded in a dictionary manner; if the maximum number of the lesion areas in the CT plain scan image is less than or equal to 1, the morphology of the lesion in the CT plain scan image is determined to be an isolated lesion; if the maximum number of the lesion areas in the CT plain scan image is greater than 1, the morphology of the lesion in the CT plain scan image is temporarily determined to be an interlaced lesion or a staghorn lesion; For lesions tentatively identified as staggered or antler-shaped, all CT plain scan images with a number of lesion regions greater than 1 are traversed, and the lesions are associated with the lesion regions contained in the previous and next CT plain scan images as anchor points to construct a local feature space; The in-degree and out-degree of the anchor points in each local feature space are calculated by the degree analysis method. If the out-degree and in-degree of the lesion area are the same, the local feature space is marked as parallel; if the out-degree of the lesion area is greater than the in-degree, the local feature space is marked as bifurcation; if the in-degree of the lesion area is greater than the out-degree, the local feature space is marked as adhesion; Traversing all the marks of the local feature space, if there is no bifurcation or adhesion mark, the morphology of the lesion in the CT plain scan image is determined to be a staggered lesion; if there is a bifurcation or adhesion mark, the morphology of the lesion in the CT plain scan image is determined to be a antler-type lesion.

4. The method for evaluating kidney stone burden based on CT plain scan images according to claim 1, characterized in that: The method of constructing a density space matrix using semantic features corresponding to the lesions includes the following steps: Calculating the semantic density between the lesion regions according to their three-dimensional semantic coordinates to obtain a density space matrix; wherein the semantic density is used to describe the degree of spatial correlation between the lesion regions; The search strategy corresponding to the designed lesion morphology calculates the optimal semantic density in the density space matrix, and then obtains the number of kidney stones through an unsupervised clustering algorithm, including the following steps: According to the specific morphology of the lesion, the field-specific morphological structure and the corresponding anchor image sequence number are obtained from the quantity dictionary of the lesion area and recorded in a dictionary manner; wherein the corresponding morphological structure of the staggered lesion is parallel, and the corresponding morphological structure of the antler lesion is bifurcation and adhesion; Based on different lesion morphologies and corresponding field-specific morphological structures, the corresponding search objects are calculated; The density space matrix is ​​adjusted according to the search object to obtain the target search matrix; Based on the specific morphology of the lesion, the target search matrix is ​​traversed to calculate the semantic density difference between the lesion areas. If the semantic density difference exceeds the density search upper limit of the target search matrix, the current density search upper limit is recorded. The minimum semantic density is calculated based on the density search upper limit of the current batch, and compared with the optimal semantic density of the previous batch to obtain the optimal semantic density; According to the optimal semantic density and lesion characteristics, the lesion areas with density reachable are clustered together to obtain one or more clusters through an unsupervised clustering algorithm, and the number of clusters is the number of lesions; wherein the lesion characteristic is that the lesion exists in at least two consecutive CT plain scan images.

5. The method for evaluating kidney stone burden based on CT plain scan images according to claim 4, characterized in that: The method further comprises the following steps: Verify whether the cluster belongs to a kidney stone lesion; The number of clusters belonging to kidney stone lesions was statistically verified as the number of kidney stones.

6. The method for evaluating kidney stone burden based on CT plain scan images according to claim 1, characterized in that: The method of realizing automatic volume measurement of kidney stones by using a graphics method according to the results of the morphology and quantity analysis of kidney stones comprises the following steps: The pixels of the lesion area belonging to the kidney stone are classified into two categories: foreground and background, and then the coverage ratio between each pixel and the surrounding adjacent pixels in the area belonging to the foreground is calculated by a graphics method; wherein the foreground is the kidney stone and the background is non-kidney stone; All pixels of the lesion area belonging to the kidney stone are traversed to obtain the coverage rate of each lesion area, and then the volume of the kidney stone is calculated in combination with the slice thickness and pixel spacing of the CT plain scan image.

7. A kidney stone burden assessment device based on CT plain scan images, characterized in that: The device comprises: A data set construction unit, used for automatically parsing and recording the semantic coordinates of each lesion area to construct a structured data set, wherein each lesion area is a semantic boundary of a suspected kidney stone in each CT plain scan image in a CT plain scan image sequence; A lesion morphology judgment unit is used to construct a local feature space for the lesion and to judge the lesion morphology by exploring corresponding semantic features in the local feature space through morphological methods; The kidney stone quantity determination unit is used to construct a density space matrix using the semantic features corresponding to the lesions, and to design a search strategy corresponding to the lesion morphology to calculate the optimal semantic density in the density space matrix, and then obtain the number of kidney stones through an unsupervised clustering algorithm; The kidney stone volume determination unit is used to realize automatic volume measurement of kidney stones by using graphics methods according to the results of kidney stone morphology and quantity analysis.

8. An electronic device, characterized in that: The electronic device comprises a memory and a processor, the memory stores a computer program, and the processor implements the method according to any one of claims 1 to 6 when executing the computer program.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images