Three-dimensional Coordinate Determination Method, System, Device and Storage Medium for Kidney Stones

Abstract

The present invention discloses a method, system, device and storage medium for determining the three-dimensional coordinates of kidney stones. The method includes: inputting multiple two-dimensional CT grayscale images into an improved active contour model, obtaining corresponding improved energy functional values through the improved energy functional, and after the improved energy functional values converge, outputting the information of the pixel points inside the kidney contour. The improved active contour model is constructed from the energy functional of the improved Chan-Vese model, and kidney three-dimensional point cloud data is generated according to the information of the pixel points inside the kidney contour corresponding to each two-dimensional CT grayscale image; based on the kidney stone pixel threshold constraint condition, multiple kidney stone pixel point information is selected from the kidney three-dimensional point cloud data, and the three-dimensional coordinates of the kidney stones are determined according to the multiple kidney stone pixel point information. The present invention uses an improved active contour model that combines texture features and local energy fitting terms to extract the kidney contour, more accurately captures the boundaries of the kidney and stones, and reduces misdiagnosis and missed diagnosis situations.

Description

Technical Field

[0001] The present invention belongs to the technical field of medical image technology processing, and particularly relates to a method, system, device and storage medium for determining the three-dimensional coordinates of kidney stones. Background Art

[0002] Kidney stones are a common urological disease, and early and accurate diagnosis is of great significance for treatment and prevention. Traditional kidney stone detection methods mainly rely on doctors' experience and naked-eye observation, which have problems such as strong subjectivity and high missed diagnosis rate.

[0003] In recent years, with the development of medical imaging technology, automatic kidney stone extraction methods based on three-dimensional CT images have gradually become a research hotspot. However, existing methods still have deficiencies in aspects such as data preprocessing, contour extraction and stone positioning, which affect the accuracy and reliability of diagnosis.

[0004] The above content is only used to assist in understanding the technical solution of the present invention, and does not represent an admission that the above content is prior art. Summary of the Invention

[0005] The main object of the present invention is to provide a method, system, device and storage medium for determining the three-dimensional coordinates of kidney stones, aiming to solve the technical problem of how to efficiently and accurately extract the three-dimensional coordinates of kidney stones.

[0006] To achieve the above object, the present invention provides a method for determining the three-dimensional coordinates of kidney stones, and the method for determining the three-dimensional coordinates of kidney stones includes:

[0007] Obtain the three-dimensional CT image of a kidney stone patient, and perform slice preprocessing on the three-dimensional CT image to obtain multiple two-dimensional CT grayscale images;

[0008] Input the multiple two-dimensional CT grayscale images into an improved active contour model, and obtain the improved energy functional values corresponding to each two-dimensional CT grayscale image through the improved energy functional. The improved active contour model is constructed by the energy functional of the improved Chan-Vese model, and the improved energy functional is constructed by combining a global energy term, a local energy fitting term and a regularization term;

[0009] After the improved energy functional values converge, make the improved active contour model output the internal pixel point information of the kidney contour corresponding to each two-dimensional CT grayscale image;

[0010] Generate kidney three-dimensional point cloud data according to the internal pixel point information of the kidney contour corresponding to each two-dimensional CT grayscale image;

[0011] Select multiple kidney stone pixel point information from the three-dimensional kidney point cloud data based on the pixel threshold constraint conditions of the kidney stones, and determine the three-dimensional coordinates of the kidney stones according to the multiple kidney stone pixel point information.

[0012] Optionally, the step of inputting multiple two-dimensional CT gray-scale images into the improved active contour model and obtaining the improved energy functional values corresponding to each two-dimensional CT gray-scale image through the improved energy functional includes:

[0013] Input multiple two-dimensional CT gray-scale images into the improved active contour model, and calculate the overall energy value, local energy fitting value, and regularization value of each two-dimensional CT gray-scale image;

[0014] Calculate the improved energy functional values of each two-dimensional CT gray-scale image through the improved energy functional according to the overall energy value, the local energy fitting value, and the regularization value.

[0015] Optionally, the step of calculating the overall energy value of each two-dimensional CT gray-scale image includes:

[0016] Select a target CT gray-scale image from multiple two-dimensional CT gray-scale images;

[0017] Determine the initial kidney contour parameters of the target CT gray-scale image, and determine the gray-scale value, average gray-scale value inside the contour, average gray-scale value outside the contour, and pixel point texture feature value of the pixel points in each two-dimensional CT gray-scale image;

[0018] Calculate the overall energy value of each two-dimensional CT gray-scale image through the overall energy term according to the initial kidney contour parameters, the gray-scale value of the pixel points, the average gray-scale value inside the contour, the average gray-scale value outside the contour, and the pixel point texture feature value.

[0019] Optionally, the step of determining the pixel point texture feature value of each two-dimensional CT gray-scale image includes:

[0020] Perform Gaussian blur preprocessing on each two-dimensional CT gray-scale image respectively to obtain multiple two-dimensional smoothed images;

[0021] Perform kidney windowing processing on multiple two-dimensional smoothed images respectively to obtain multiple windowed two-dimensional images;

[0022] Extract the local texture features of each windowed two-dimensional image respectively through the LBP algorithm to obtain multiple LBP feature maps;

[0023] Perform linear combination on multiple two-dimensional smoothed images and multiple LBP feature maps respectively to obtain the pixel point texture feature values corresponding to each two-dimensional CT gray-scale image.

[0024] Optionally, the step of calculating the local energy fitting value of each two-dimensional CT gray-scale image includes:

[0025] Determine the gray value of the pixel points in each two-dimensional CT gray-scale image and the local area mean value of the pixel points;

[0026] Calculate the local energy fitting value of each two-dimensional CT gray-scale image through the local energy fitting term according to the gray value of the pixel point and the local area mean value of the pixel point.

[0027] Optionally, the step of calculating the regularization value of each two-dimensional CT gray-scale image includes:

[0028] Respectively determine the length of the kidney contour balance curve and the area of the kidney contour region corresponding to each two-dimensional CT gray-scale image;

[0029] Calculate the regularization value of each two-dimensional CT gray-scale image through the regularization term according to the length of the kidney contour balance curve and the area of the kidney contour region.

[0030] In addition, to achieve the above object, the present invention also proposes a three-dimensional coordinate determination system for kidney stones, and the three-dimensional coordinate determination system for kidney stones includes:

[0031] A processing module, configured to obtain a three-dimensional CT image of a kidney stone patient, and perform slice preprocessing on the three-dimensional CT image to obtain multiple two-dimensional CT gray-scale images;

[0032] A kidney contour extraction module, configured to input multiple two-dimensional CT gray-scale images into an improved active contour model, and obtain the improved energy functional value corresponding to each two-dimensional CT gray-scale image through the improved energy functional. The improved active contour model is constructed by the energy functional of the improved Chan-Vese model, and the improved energy functional is constructed by combining a global energy term, a local energy fitting term, and a regularization term;

[0033] The kidney contour extraction module is further configured to, after the improved energy functional value converges, enable the improved active contour model to output the information of the pixel points inside the kidney contour corresponding to each two-dimensional CT gray-scale image.

[0034] The processing module is further configured to generate kidney three-dimensional point cloud data according to the information of the pixel points inside the kidney contour corresponding to each two-dimensional CT gray-scale image;

[0035] A coordinate determination module, configured to select multiple kidney stone pixel point information from the kidney three-dimensional point cloud data based on the kidney stone pixel threshold constraint condition, and determine the three-dimensional coordinates of the kidney stones according to the multiple kidney stone pixel point information.

[0036] In addition, to achieve the above object, the present invention also provides a three-dimensional coordinate determination device for kidney stones, the device comprising: a memory, a processor, and a three-dimensional coordinate determination program for kidney stones stored on the memory and executable on the processor, the three-dimensional coordinate determination program for kidney stones being configured to implement the steps of the three-dimensional coordinate determination method for kidney stones as described above.

[0037] In addition, to achieve the above object, the present invention also provides a storage medium, on which a three-dimensional coordinate determination program for kidney stones is stored, and when the three-dimensional coordinate determination program for kidney stones is executed by a processor, the steps of the three-dimensional coordinate determination method for kidney stones as described above are implemented.

[0038] The present invention first obtains three-dimensional CT images of kidney stone patients, preprocesses the three-dimensional CT images by slicing to obtain multiple two-dimensional CT grayscale images, then inputs the multiple two-dimensional CT grayscale images into an improved active contour model, obtains corresponding improved energy functional values through the improved energy functional, and after the improved energy functional values converge, outputs the information of the internal pixel points of the kidney contour corresponding to each two-dimensional CT grayscale image. The improved active contour model is constructed from the energy functional of the improved Chan-Vese model, and the improved energy functional is constructed by combining a global energy term, a local energy fitting term, and a regularization term. Then, kidney three-dimensional point cloud data is generated according to the information of the internal pixel points of the kidney contour corresponding to each two-dimensional CT grayscale image. Finally, based on the kidney stone pixel threshold constraint condition, multiple kidney stone pixel point information is selected from the kidney three-dimensional point cloud data, and the three-dimensional coordinates of the kidney stones are determined according to the multiple kidney stone pixel point information. The present invention combines texture features and local energy fitting techniques, can more accurately capture the boundaries of the kidney and the stones, and by combining the improved active contour model with multi-stage image preprocessing, greatly improves the accuracy and efficiency of kidney stone recognition, and reduces misdiagnosis and missed diagnosis situations. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 is a schematic structural diagram of a three-dimensional coordinate determination device for kidney stones in a hardware operating environment according to an embodiment of the present invention;

[0040] Figure 2 is a schematic flowchart of a first embodiment of the three-dimensional coordinate determination method for kidney stones of the present invention;

[0041] Figure 3 is a structural block diagram of a first embodiment of the three-dimensional coordinate determination system for kidney stones of the present invention.

[0042] The realization, functional features, and advantages of the object of the present invention will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0043] It should be understood that the specific embodiments described herein are merely for explaining the present invention and are not intended to limit the present invention.

[0044] Referring to Figure 1 , Figure 1 FIG. is a schematic structural diagram of a three-dimensional coordinate determination device for kidney stones in the hardware operating environment involved in the embodiment solution of the present invention.

[0045] As Figure 1 shown, the three-dimensional coordinate determination device for kidney stones may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display) and an input unit such as a keyboard (Keyboard). Optionally, the user interface 1003 may further include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a wireless-fidelity (Wi-Fi) interface). The memory 1005 may be a high-speed random access memory (Random Access Memory, RAM) or a stable non-volatile memory (Non-Volatile Memory, NVM), such as a disk memory. Optionally, the memory 1005 may also be a storage system independent of the foregoing processor 1001.

[0046] Those skilled in the art can understand that Figure 1 the structure shown in

[0047] does not constitute a limitation on the three-dimensional coordinate determination device for kidney stones, and may include more or fewer components than shown, or combine some components, or have a different component layout. Figure 1 shown, the memory 1005 as a storage medium may include an operating system, a network communication module, a user interface module, and a three-dimensional coordinate determination program for kidney stones.

[0048] In Figure 1 the three-dimensional coordinate determination device for kidney stones shown, the network interface 1004 is mainly used for data communication with a network server; the user interface 1003 is mainly used for data interaction with a user; the processor 1001 and the memory 1005 in the three-dimensional coordinate determination device for kidney stones of the present invention may be arranged in the three-dimensional coordinate determination device for kidney stones. The three-dimensional coordinate determination device for kidney stones calls the three-dimensional coordinate determination program stored in the memory 1005 through the processor 1001 and executes the three-dimensional coordinate determination method provided by the embodiment of the present invention.

[0049] An embodiment of the present invention provides a method for determining the three-dimensional coordinates of kidney stones. Refer to Figure 2 , Figure 2 which is a schematic flowchart of the first embodiment of the method for determining the three-dimensional coordinates of kidney stones according to the present invention.

[0050] In this embodiment, the method for determining the three-dimensional coordinates of the kidney stones includes the following steps:

[0051] Step S10: Obtain the three-dimensional CT image of the kidney stone patient, and perform slice preprocessing on the three-dimensional CT image to obtain multiple two-dimensional CT grayscale images.

[0052] It is easy to understand that the execution subject of this embodiment can be a three-dimensional coordinate determination system for kidney stones with functions such as data processing, network communication, and program operation, or other computer devices with similar functions. This embodiment does not impose any restrictions.

[0053] In this embodiment, it is necessary to pre-obtain the CT slice file in DICOM format (i.e., DICOM file) of the kidney stone patient, and then use the medical image processing software SimpleITK to parse the CT slice file in DICOM format to obtain the three-dimensional CT image and DICOM metadata, and its DICOM metadata includes detailed information such as patient information, scanning parameters, and the number of CT layers. The specific parameters include the resolution of the image, the size of the scanning area, and the scanning time.

[0054] In specific implementation, it is necessary to resample the three-dimensional CT image to adjust the resolution of the three-dimensional CT image to meet the needs of subsequent processing.

[0055] The resampling process adjusts all images to the same voxel size of 1mm×1mm×1mm to eliminate the influence caused by equipment differences. In addition, perform image normalization processing to adjust the grayscale value of the image to a unified range of 0 to 255, enhance the contrast of the image, and improve the visualization effect.

[0056] Furthermore, since the three-dimensional CT image to be sliced is in DICOM format, it is necessary to convert the three-dimensional CT image in DICOM format into a three-dimensional CT image in PNG format, and then slice the three-dimensional CT image in PNG format according to the number of CT layers (i.e., the number of CT slices), and perform rotation, weakening, and contrast enhancement processing on the sliced multiple CT images (multiple CT images in PNG format) to standardize the image data and optimize the subsequent stone detection performance to obtain multiple two-dimensional CT grayscale images.

[0057] Assume that the number of CT slices is 256, then 256 two-dimensional CT grayscale images are generated.

[0058] It should also be noted that the steps of rotating, weakening, and enhancing the contrast of multiple sliced CT images are as follows:

[0059] First, perform image rotation. All images will be uniformly rotated by 180 degrees to ensure that the heads of the images are always upward, which helps to ensure the consistency of the images during the standardization process. The rotation operation will be performed around the center point of the image;

[0060] Perform image weakening. Apply a 3x3 Gaussian filter to each CT image, where the standard deviation of the Gaussian kernel is set to 1.5, to smooth the image and reduce noise, reducing the recognition error of subsequent algorithms;

[0061] Perform contrast enhancement. Use contrast-limited adaptive histogram equalization (CLAHE) to process the image, with the clipping limit set to 2.0 and the applied grid size of 8x8. It is used to improve the contrast between the stones and the surrounding tissues in the image, making the stones more obvious and easier to identify.

[0062] Step S20: Input multiple two-dimensional CT grayscale images into the improved active contour model, and obtain the improved energy functional values corresponding to each two-dimensional CT grayscale image through the improved energy functional. The improved active contour model is constructed from the energy functional of the improved Chan-Vese model, and the improved energy functional is constructed by combining the global energy term, the local energy fitting term, and the regularization term.

[0063] It should be noted that the improved active contour model improves the global energy functional of the Chan-Vese (CV) model. Instead of simply calculating the average gray values of the inner and outer regions of the image, the difference between the gray value of the image region and its average gray value is directly represented by the square difference, and the saliency map is combined to enhance the edge recognition ability.

[0064] The improved active contour model effectively integrates the global energy term and the local energy fitting term, and enhances the smoothness and self-adaptability of the model through the regularization term. This model can accurately identify the target edge without resetting, especially performing well in medical images with complex backgrounds and uneven gray levels.

[0065] The energy functional of the improved model consists of three parts: the global energy term, the local energy fitting term, and the regularization term.

[0066] Furthermore, input multiple two-dimensional CT grayscale images into the improved active contour model, calculate the global energy value, the local energy fitting value, and the regularization value of each two-dimensional CT grayscale image; calculate the improved energy functional values of each two-dimensional CT grayscale image through the improved energy functional according to the global energy value, the local energy fitting value, and the regularization value.

[0067] The improved energy functional is defined as:

[0068]

[0069] where E is the value of the improved energy functional, is the overall energy value, is the local energy fitting value, is the regularization value, w represents a constant ranging from 0 to 1, which is adjusted according to the degree of gray-scale inhomogeneity. Here, w is initialized to 0.7.

[0070] It should be understood that the pixel point information inside the kidney contour is the gray-scale value of the pixel points inside the kidney contour that are normalized to the range of 0 to 255.

[0071] Furthermore, the processing method for calculating the overall energy term of each two-dimensional CT gray-scale image is to select the target CT gray-scale image from multiple two-dimensional CT gray-scale images; determine the initial kidney contour parameters of the target CT gray-scale image, and determine the gray-scale value, average gray-scale value inside the contour, average gray-scale value outside the contour, and pixel point texture feature value of the pixel points in each two-dimensional CT gray-scale image; calculate the overall energy value of each two-dimensional CT gray-scale image through the overall energy term according to the initial kidney contour parameters, pixel point gray-scale value, average gray-scale value inside the contour, average gray-scale value outside the contour, and pixel point texture feature value.

[0072] It should also be noted that the target CT gray-scale image can be the first two-dimensional CT gray-scale image or the last two-dimensional CT gray-scale image corresponding to the CT cut in the normal order.

[0073] In the specific implementation, the initial contour parameters are first set. For each two-dimensional CT gray-scale image with a resolution of 512×512, the initialized level set contour parameters are represented as two circular contours, where the centers are (320, 170) and (300, 350) respectively, and the radius size is 75 pixels. They respectively correspond to the approximate initial positions of the left and right kidneys of the human body.

[0074] In order to improve the processing ability for gray-scale inhomogeneous images and simplify the calculation process, the calculation of the overall energy term optimizes the global energy term of the simplified CV model. In the calculation, the square difference is directly used, and the difference between the gray-scale value of the image region and its average gray-scale value is directly represented by the square difference, avoiding complex numerical calculations and improving stability.

[0075] The overall energy term is:

[0076]

[0077] where are the initial contour parameters, is the gray value of the pixel position (x, y) in each two-dimensional CT gray image. c1 is the average gray value inside the contour, and c2 is the average gray value outside the contour. and are weight coefficients that control the importance of the energy terms in the inner and outer regions. Among them is set to 0.4, is set to 0.6, is the texture feature value of the pixel position (x, y), which is used to enhance the recognition ability of the target edge.

[0078] Furthermore, the processing method for determining the pixel texture feature values of each two-dimensional CT gray image is to perform Gaussian blur preprocessing on each two-dimensional CT gray image to obtain multiple two-dimensional smoothed images; perform kidney windowing processing on multiple two-dimensional smoothed images to obtain multiple windowed two-dimensional images; extract the local texture features of each windowed two-dimensional image through the LBP algorithm to obtain multiple LBP feature maps; linearly combine multiple two-dimensional smoothed images and multiple LBP feature maps respectively to obtain the pixel texture feature values corresponding to each two-dimensional CT gray image.

[0079] In specific implementation, for each two-dimensional CT gray image perform Gaussian blur preprocessing to obtain multiple smoothed images (i.e., multiple two-dimensional smoothed images).

[0080] It should also be noted that in order to highlight the texture feature information of the kidney, based on the image smoothed by Gaussian blur , kidney windowing processing is performed on the two-dimensional smoothed image: Windowing processing is to adjust the window width and window level of the image based on the CT value range of the kidney, so that the contrast of the kidney tissue is enhanced, while the contrast of non-target tissues is relatively reduced. Based on the CT value range of the kidney itself, the CT value of the kidney is concentrated between -75 and 325 Hu. Therefore, a window width of 390 Hu and a window level of 120 Hu are selected to perform windowing processing on the two-dimensional smoothed image.

[0081] After windowing processing, based on the windowed two-dimensional image, the LBP algorithm is applied to extract local texture features. Among them, the LBP algorithm parameters include the neighborhood size and the sampling radius. The neighborhood size and the sampling radius are both for each pixel point in the windowed image. Here, the neighborhood size parameter is set to 8, the sampling radius parameter is set to 1, and the mode parameter adopts the uniform uniform mode. The output of the LBP algorithm is the LBP feature map .

[0082] Next, linearly combine the smoothed image with the LBP feature map to form the pixel texture feature value α is a weight coefficient used to balance the importance of grayscale information and texture information. Here, α is set to 0.5.

[0083]

[0084] Furthermore, the processing method for calculating the local energy fitting term of each two-dimensional CT grayscale image is to determine the grayscale value of the pixel points in each two-dimensional CT grayscale image and the local area mean of the pixel points; calculate the local energy fitting value of each two-dimensional CT grayscale image through the local energy fitting term according to the grayscale value of the pixel points and the local area mean of the pixel points.

[0085] It should be noted that the feature extraction of the local energy term is achieved through Local Binary Pattern (LBP). Local Binary Pattern is a powerful texture descriptor that can capture local texture information in images. In two-dimensional CT grayscale images, texture information plays a key role in distinguishing kidney tissue from surrounding adhesions in the abdominal cavity. Here, the idea of the Local Binary Pattern (LBP) algorithm is adopted, and the Gaussian kernel function is used to capture the local features of the image.

[0086] It should also be noted that the local energy fitting term can better reflect the local features of the image and contribute to improving the segmentation accuracy of the model.

[0087] The local energy fitting term is:

[0088]

[0089] In the formula, is the grayscale value of the i-th pixel, Ω represents the set of all pixels in the two-dimensional CT grayscale image, is the mean value of the local area where the pixel is located (i.e., the local area mean of the pixel point), is a weight factor dynamically calculated according to the position and grayscale value of the pixel, and the initial value is set to 0.2.

[0090] Furthermore, the processing method for calculating the regularization term of each two-dimensional CT grayscale image is to respectively determine the length of the kidney contour balance curve and the area of the kidney contour region corresponding to each two-dimensional CT grayscale image; calculate the regularization value of each two-dimensional CT grayscale image through the regularization term according to the length of the kidney contour balance curve and the area of the kidney contour region.

[0091] In this embodiment, the regularization term is mainly used to maintain the smoothness of the contour and prevent excessive details from appearing during the curve evolution process. Here, two different regularization strategies are adopted, namely curve length regularization and region area regularization. Curve length regularization encourages a smooth boundary by penalizing the length of the contour, and region area regularization encourages a compact segmentation result by penalizing the area of the region.

[0092] Regularization term:

[0093]

[0094] In the formula, μ and ν are regularization parameters used to balance the influence of the curve length and the region area. Here, μ is set to 0.3 and ν is set to 0.7. is the curve length of the kidney contour for balance, is the region area of the kidney contour.

[0095] Step S30: After the improved energy functional value converges, make the improved active contour model output the information of the internal pixel points of the kidney contour corresponding to each two-dimensional CT gray-scale image.

[0096] In a specific implementation, it is determined whether the values of multiple improved energy functions in the improved active contour model converge. If they do not converge, the number of iterations is continuously increased, and the steps of calculating the overall energy term, the local energy fitting term, and the regularization term are repeated. If they converge, the pixel point information obtained after convergence is output (that is, the information of the internal pixel points of the kidney contour, and the pixel point information includes pixel point position information, pixel point gray value, or HU value).

[0097] Step S40: Generate kidney three-dimensional point cloud data according to the information of the internal pixel points of the kidney contour corresponding to each two-dimensional CT gray-scale image.

[0098] It should be noted that the kidney three-dimensional point cloud data is composed of the information of the pixel points inside the kidney contour.

[0099] Step S50: Select multiple kidney stone pixel point information from the kidney three-dimensional point cloud data based on the kidney stone pixel threshold constraint condition, and determine the three-dimensional coordinates of the kidney stones according to the multiple kidney stone pixel point information.

[0100] In a specific implementation, according to clinical experience and previous research, kidney stones usually show a relatively high CT value in CT images. This is based on the fact that stones are usually harder than the surrounding soft tissues and show a higher density in CT scans.

[0101] The kidney stone pixel threshold constraint condition is to pre-set to select pixel points higher than the kidney stone pixel threshold (for example, 110) from the kidney three-dimensional point cloud data.

[0102] In this embodiment, the threshold condition is set such that the CT value is higher than 300 Hounsfield units (HU). Since the two-dimensional CT grayscale image was normalized above, the CT value was normalized to the range of 0 - 255, and the image grayscale value corresponding to the CT value of the stone here is approximately 110. The grayscale value of each pixel point inside the obtained kidney contour C (i.e., the kidney three-dimensional point cloud data) is examined, and only those points with a grayscale value higher than 110 are retained.

[0103] It should also be noted that pixel points higher than the pixel threshold of kidney stones (e.g., 110) need to be sorted and summarized, and the output three-dimensional coordinates of the stones include the position information of each stone point cloud, which is convenient for directly using in navigation surgical equipment or for further image reconstruction.

[0104] In this embodiment, first, a three-dimensional CT image of a kidney stone patient is obtained, and the three-dimensional CT image is preprocessed by slicing to obtain multiple two-dimensional CT grayscale images. Then, the multiple two-dimensional CT grayscale images are input into an improved active contour model, and the corresponding improved energy functional value is obtained by improving the energy functional. After the improved energy functional value converges, the information of the pixel points inside the kidney contour corresponding to each two-dimensional CT grayscale image is output. The improved active contour model is constructed from the energy functional of the improved Chan-Vese model, and the improved energy functional is constructed by combining a global energy term, a local energy fitting term, and a regularization term. Then, kidney three-dimensional point cloud data is generated based on the information of the pixel points inside the kidney contour corresponding to each two-dimensional CT grayscale image. Finally, multiple kidney stone pixel point information is selected from the kidney three-dimensional point cloud data based on the kidney stone pixel threshold constraint condition, and the three-dimensional coordinates of the kidney stones are determined according to the multiple kidney stone pixel point information. In this embodiment, by combining texture features and local energy fitting techniques, the boundaries of the kidney and the stones can be captured more precisely. By combining the improved active contour model with multi-stage image preprocessing, the accuracy and efficiency of kidney stone recognition are greatly improved, and the situations of misdiagnosis and missed diagnosis are reduced.

[0105] Refer to Figure 3 , Figure 3 which is the structural block diagram of the first embodiment of the three-dimensional coordinate determination system for kidney stones of the present invention.

[0106] As Figure 3 shown, the three-dimensional coordinate determination system for kidney stones proposed in the embodiment of the present invention includes:

[0107] A processing module 3001, configured to obtain a three-dimensional CT image of a kidney stone patient, and preprocess the three-dimensional CT image by slicing to obtain multiple two-dimensional CT grayscale images;

[0108] The kidney contour extraction module 3002 is configured to input multiple two-dimensional CT grayscale images into an improved active contour model, obtain the improved energy functional values corresponding to the respective two-dimensional CT grayscale images through an improved energy functional, where the improved active contour model is constructed from the energy functional of the improved Chan-Vese model, and the improved energy functional is constructed by combining a global energy term, a local energy fitting term, and a regularization term;

[0109] The kidney contour extraction module 3002 is further configured to, after the improved energy functional values converge, cause the improved active contour model to output the information of the internal pixel points of the kidney contour corresponding to each two-dimensional CT grayscale image;

[0110] The processing module 3001 is further configured to generate kidney three-dimensional point cloud data according to the information of the internal pixel points of the kidney contour corresponding to each two-dimensional CT grayscale image;

[0111] The coordinate determination module 3003 is configured to select multiple kidney stone pixel point information from the kidney three-dimensional point cloud data based on the kidney stone pixel threshold constraint condition, and determine the three-dimensional coordinates of the kidney stones according to the multiple kidney stone pixel point information.

[0112] For other embodiments or specific implementation manners of the three-dimensional coordinate determination system for kidney stones of the present invention, reference may be made to the above method embodiments, which will not be elaborated here.

[0113] It should be noted that in this article, the terms "include", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements not only includes those elements, but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article or system. Without further limitation, an element defined by the statement "including one..." does not exclude the existence of another identical element in the process, method, article or system including that element.

[0114] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages and disadvantages of the embodiments.

[0115] Through the description of the above embodiments, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform. Of course, they can also be implemented through hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as a read-only memory / random access memory, magnetic disk, optical disk), and includes several instructions to enable a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in various embodiments of the present invention.

[0116] The above are only the preferred embodiments of the present invention, and do not limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made by using the content of the specification and drawings of the present invention, or directly or indirectly applied in other related technical fields, shall be equally included in the patent protection scope of the present invention.

Claims

1. A method for determining the three-dimensional coordinates of kidney stones, characterized in that, The method for determining the three-dimensional coordinates of kidney stones includes the following steps: Obtain the three-dimensional CT image of a kidney stone patient, and perform slice preprocessing on the three-dimensional CT image to obtain multiple two-dimensional CT grayscale images; Input the multiple two-dimensional CT grayscale images into the improved active contour model, and obtain the improved energy functional values corresponding to each two-dimensional CT grayscale image through the improved energy functional. The improved active contour model is constructed from the energy functional of the improved Chan-Vese model, and the improved energy functional is constructed by combining the global energy term, the local energy fitting term, and the regularization term; After the improved energy functional values converge, make the improved active contour model output the information of the pixel points inside the kidney contour corresponding to each two-dimensional CT grayscale image; Generate kidney three-dimensional point cloud data based on the information of the pixel points inside the kidney contour corresponding to each two-dimensional CT grayscale image; Select multiple kidney stone pixel point information from the kidney three-dimensional point cloud data based on the kidney stone pixel threshold constraint condition, and determine the three-dimensional coordinates of the kidney stones according to the multiple kidney stone pixel point information; The step of inputting the multiple two-dimensional CT grayscale images into the improved active contour model and obtaining the improved energy functional values corresponding to each two-dimensional CT grayscale image through the improved energy functional includes: Input the multiple two-dimensional CT grayscale images into the improved active contour model, and calculate the global energy value, the local energy fitting value, and the regularization value of each two-dimensional CT grayscale image; Calculate the improved energy functional values of each two-dimensional CT grayscale image through the improved energy functional according to the global energy value, the local energy fitting value, and the regularization value; The step of calculating the global energy value of each two-dimensional CT grayscale image includes: Select a target CT grayscale image from the multiple two-dimensional CT grayscale images; Determine the initial kidney contour parameters of the target CT grayscale image, and determine the grayscale value, the average grayscale value inside the contour, the average grayscale value outside the contour, and the pixel point texture feature value of the pixel points in each two-dimensional CT grayscale image; Calculate the global energy value of each two-dimensional CT grayscale image through the global energy term according to the initial kidney contour parameters, the grayscale value of the pixel points, the average grayscale value inside the contour, the average grayscale value outside the contour, and the pixel point texture feature value; The step of determining the pixel point texture feature value of each two-dimensional CT grayscale image includes: Perform Gaussian blur preprocessing on each two-dimensional CT grayscale image respectively to obtain multiple two-dimensional smoothed images; Perform kidney windowing processing on the multiple two-dimensional smoothed images respectively to obtain multiple windowed two-dimensional images; Extract the local texture features of each windowed two-dimensional image respectively through the LBP algorithm to obtain multiple LBP feature maps; Perform linear combination on the multiple two-dimensional smoothed images and the multiple LBP feature maps respectively to obtain the pixel point texture feature values corresponding to each two-dimensional CT grayscale image.

2. The method according to claim 1, wherein The step of calculating the local energy fitting value of each two-dimensional CT grayscale image includes: Determine the grayscale value of the pixel points in each two-dimensional CT grayscale image and the local region mean value of the pixel points; Calculate the local energy fitting value of each two-dimensional CT gray image through the local energy fitting term according to the gray value of the pixel and the local area mean value of the pixel.

3. The method according to claim 1, characterized in that The step of calculating the regularization value of each two-dimensional CT gray image includes: Respectively determine the kidney contour balance curve length and the kidney contour area corresponding to each two-dimensional CT gray image; Calculate the regularization value of each two-dimensional CT gray image through the regularization term according to the kidney contour balance curve length and the kidney contour area.

4. A three-dimensional coordinate determination system for kidney stones, characterized in that, The three-dimensional coordinate determination system of the kidney stone includes: A processing module, configured to obtain a three-dimensional CT image of a kidney stone patient, and perform slice preprocessing on the three-dimensional CT image to obtain multiple two-dimensional CT gray images; A kidney contour extraction module, configured to input multiple two-dimensional CT gray images into an improved active contour model, and obtain an improved energy functional value corresponding to each two-dimensional CT gray image through the improved energy functional. The improved active contour model is constructed by the energy functional of the improved Chan-Vese model, and the improved energy functional is constructed by combining a global energy term, a local energy fitting term, and a regularization term; The kidney contour extraction module is further configured to, after the improved energy functional value converges, cause the improved active contour model to output the pixel point information inside the kidney contour corresponding to each two-dimensional CT gray image; The processing module is further configured to generate kidney three-dimensional point cloud data according to the pixel point information inside the kidney contour corresponding to each two-dimensional CT gray image; A coordinate determination module, configured to select multiple kidney stone pixel point information from the kidney three-dimensional point cloud data based on the kidney stone pixel threshold constraint condition, and determine the three-dimensional coordinates of the kidney stone according to the multiple kidney stone pixel point information; The kidney contour extraction module is further configured to input multiple two-dimensional CT gray images into an improved active contour model, calculate the global energy value, the local energy fitting value, and the regularization value of each two-dimensional CT gray image; calculate the improved energy functional value of each two-dimensional CT gray image through the improved energy functional according to the global energy value, the local energy fitting value, and the regularization value; The kidney contour extraction module is further configured to select a target CT gray image from multiple two-dimensional CT gray images; determine the initial kidney contour parameters of the target CT gray image, and determine the gray value, the average gray value inside the contour, the average gray value outside the contour, and the pixel texture feature value of the pixel points in each two-dimensional CT gray image; calculate the global energy value of each two-dimensional CT gray image through the global energy term according to the initial kidney contour parameters, the gray value of the pixel points, the average gray value inside the contour, the average gray value outside the contour, and the pixel texture feature value; The kidney contour extraction module is further configured to perform Gaussian blur preprocessing on each two-dimensional CT grayscale image respectively to obtain multiple two-dimensional smoothed images; perform kidney windowing processing on the multiple two-dimensional smoothed images respectively to obtain multiple windowed two-dimensional images; extract local texture features of each windowed two-dimensional image respectively through the LBP algorithm to obtain multiple LBP feature maps; perform linear combination on the multiple two-dimensional smoothed images and the multiple LBP feature maps respectively to obtain the pixel point texture feature values corresponding to each two-dimensional CT grayscale image.

5. A three-dimensional coordinate determination device for kidney stones, characterized in that, The device includes: a memory, a processor, and a three-dimensional coordinate determination program for kidney stones stored on the memory and executable on the processor, and the three-dimensional coordinate determination program for kidney stones is configured to implement the steps of the three-dimensional coordinate determination method for kidney stones as described in any one of claims 1 to 3.

6. A storage medium, characterized in that, A three-dimensional coordinate determination program for kidney stones is stored on the storage medium, and when the three-dimensional coordinate determination program for kidney stones is executed by a processor, the steps of the three-dimensional coordinate determination method for kidney stones as described in any one of claims 1 to 3 are implemented.

Images