Method for identifying stone fragments on urethra

Abstract

The invention discloses a calculus fragment identification method on a urethra, and relates to the technical field of image enhancement, and the method comprises the steps: obtaining a urethra CT scanning image sequence of a target patient in a preset window; a urethra CT scanning image identification stone fragment size set sequence and a urethra CT scanning image identification stone fragment position set sequence are obtained; performing mapping fusion risk identification to obtain a fusion risk factor sequence; and determining a stone fragment identification result according to the size of the fusion risk factor in the fusion risk factor sequence. The technical problems that in the prior art, when stone fragments on the urethra are recognized, the dimension is single, and the recognition accuracy and the automation degree are low are solved. The technical effect of stone fragment recognition reliability is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of image processing, and in particular to a method for identifying urethral calculus fragments. Background Art

[0002] Currently, urinary stones are a common urinary tract disease. After treatment, stone fragments may remain in the urethra. If not identified and assessed promptly, these fragments can lead to complications such as urinary tract obstruction and infection. Therefore, how to efficiently and accurately identify stone fragments in the urethra has become an important research direction.

[0003] Existing methods for identifying stone fragments typically rely on physician interpretation of CT scan images. This approach is not only time-consuming and reliant on physician experience, but is also susceptible to subjective factors and can result in inaccurate identification. Furthermore, some automated methods rely solely on single features (such as size or location) to detect fragments, lacking a comprehensive, multi-dimensional analysis. This results in low accuracy in assessing the risk of fragment fusion.

[0004] The existing technology has technical problems such as single dimension, low recognition accuracy and low automation when identifying urethral stone fragments. Summary of the Invention

[0005] The present application provides a method for identifying urethral stone fragments, which is used to solve the technical problems of single dimension, low recognition accuracy and low automation level in the prior art when identifying urethral stone fragments.

[0006] In view of the above problems, the present application provides a method for identifying urethral stone fragments, the method comprising: Acquire a CT scan image sequence of the urethra of a target patient within a preset window; Traversing the urethra CT scan image sequence and performing grayscale water immersion division to obtain a set sequence of stone fragment sizes identified by the urethra CT scan image and a set sequence of stone fragment positions identified by the urethra CT scan image; Performing mapping fusion risk identification on the set sequence of stone fragment sizes identified by the urethra CT scan image and the set sequence of stone fragment positions identified by the urethra CT scan image to obtain a fusion risk factor sequence; Extract the maximum fusion risk factor in the fusion risk factor sequence, and determine whether the maximum fusion risk factor is greater than or equal to the preset fusion risk factor threshold. If not, take the last CT scan image-identified stone fragment size set and the last CT scan image-identified stone fragment position set in the urethra CT scan image-identified stone fragment size set sequence and the urethra CT scan image-identified stone fragment position set sequence as the stone fragment recognition result.

[0007] One or more technical solutions provided in this application have at least the following technical effects or advantages: The present application obtains a urethra CT scan image sequence of a target patient within a preset window, then traverses the urethra CT scan image sequence for grayscale water immersion division, obtains a urethra CT scan image identification stone fragment size set sequence and a urethra CT scan image identification stone fragment position set sequence, then respectively performs mapping fusion risk identification on the urethra CT scan image identification stone fragment size set sequence and the urethra CT scan image identification stone fragment position set sequence, obtains a fusion risk factor sequence, and then extracts the maximum fusion risk factor in the fusion risk factor sequence, determines whether the maximum fusion risk factor is greater than or equal to a preset fusion risk factor threshold, and if not, uses the last CT scan image identification stone fragment size set and the last CT scan image identification stone fragment position set in the urethra CT scan image identification stone fragment size set sequence and the urethra CT scan image identification stone fragment position set sequence as the stone fragment identification result. The technical effect of improving the reliability and accuracy of stone fragment identification is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] Attachment Figure 1 The present invention provides a flowchart of a method for identifying urethral stone fragments.

[0009] Attachment Figure 2 It is a flow chart of obtaining a first divided area set in a method for identifying urethral stone fragments provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0010] Below in conjunction with specific embodiment, further set forth the present invention.Should be understood that these embodiments are only used to illustrate the present invention and are not used in limiting the scope of the present invention.In addition, should be understood that after reading the content taught by the present invention, those skilled in the art can make various changes or modifications to the present invention, and these equivalent forms fall equally within the scope limited by the appended claims of the application.

[0011] It should be noted that the terms "including" and "having" are intended to cover non-exclusive inclusions. For example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or are inherent to these processes, methods, products or devices.

[0012] Examples, such as the attached Figure 1 As shown, the present application provides a method for identifying urethral stone fragments, wherein the method comprises: S1: Acquire a CT scan image sequence of the urethra of the target patient within a preset window; In one possible embodiment, the target patient refers to a patient requiring urethral stone fragment detection. The preset window typically refers to a CT scan image acquisition period within a certain time range. Optionally, the preset window size can be set by a person skilled in the art, such as a postoperative observation period or a specific time interval (e.g., within 24 hours, 48 ​​hours, etc.). A urethral CT scan image sequence refers to a series of urethral images acquired using CT scanning technology within this time window, which are used for subsequent image analysis and stone fragment identification.

[0013] Preferably, the urethra CT scan images of the target patient are collected at a preset sampling frequency within a preset window and arranged in chronological order to obtain the urethra CT scan image sequence. These image sequences can capture the dynamic situation inside the urethra, such as the distribution, size, shape and possible displacement of stone fragments. The role of this step is to provide raw data input for subsequent image processing, ensuring that the system can perform analysis based on continuous image data rather than relying solely on a single image, thereby improving the accuracy and stability of recognition. For example, during postoperative observation, obtaining a set of urethra CT scan images at regular intervals can help doctors determine whether stone fragments are being discharged, moving or forming new obstruction points.

[0014] S2: traversing the urethra CT scan image sequence and performing grayscale water immersion division to obtain a set sequence of stone fragment sizes identified by the urethra CT scan image and a set sequence of stone fragment positions identified by the urethra CT scan image; In one possible embodiment, after obtaining the urethral CT scan image sequence, the urethral CT scan image sequence is traversed, and grayscale value analysis is performed on each urethral CT scan image, with different grayscale values ​​being treated as terrain of different heights. Furthermore, a water immersion simulation is used, starting from the lowest grayscale value point (i.e., the darkest area), to simulate the rising process of water, and regional division is performed using the water immersion demarcation line as the boundary. After regional division, the location of stone fragments is determined and the stone fragments are identified based on the grayscale center value of each region. The size of the stone fragments is then determined based on the regional area, thereby obtaining the urethral CT scan image identified stone fragment size set sequence and the urethral CT scan image identified stone fragment location set sequence. The urethral CT scan image identified stone fragment size set sequence reflects the volume of stone fragments in the target patient's urethra at different times within a preset window. The urethral CT scan image identified stone fragment location set sequence reflects the specific location of stone fragments in the target patient's urethra at different times within the preset window.

[0015] By obtaining the set sequence of stone fragment sizes identified by urethral CT scan images and the set sequence of stone fragment positions identified by urethral CT scan images, the technical effect of providing data support for subsequent fusion risk analysis of stone fragments during movement is achieved.

[0016] Furthermore, the grayscale value water-immersion division is performed on the urethra CT scan image sequence to obtain a set sequence of stone fragment sizes identified by the urethra CT scan image and a set sequence of stone fragment positions identified by the urethra CT scan image. In this embodiment, step S2 further includes: extracting a first urethra CT scan image from the urethra CT scan image sequence; Obtaining a grayscale minimum value of the first urethra CT scan image, using the point at which the grayscale minimum value is located as a first water immersion point, and using the grayscale value as the height of a simulated mountain, performing mountain simulation on the first urethra CT scan image to obtain a first simulated mountain area, wherein the height of the first water immersion point is the grayscale minimum value; Performing grayscale value water immersion segmentation on the first simulated mountainous area to obtain a first segmented area set, and determining a size set of stone fragments identified by the first urethra CT scan image and a location set of stone fragments identified by the first urethra CT scan image based on the first segmented area set; The urethra CT scan image sequence is traversed to perform grayscale water immersion division to obtain a set sequence of stone fragment sizes identified by the urethra CT scan image and a set sequence of stone fragment positions identified by the urethra CT scan image.

[0017] In one possible embodiment, the first CT scan image, i.e., the preliminary reference image, is extracted from the entire urethral CT scan image sequence. The grayscale minimum refers to the lowest grayscale value of a pixel in the first urethral CT scan image, which typically corresponds to the darkest portion of the CT image (usually representing a cavity or water area). The pixel point at this grayscale minimum is then used as the starting point of water immersion and is referred to as the first water immersion point. The grayscale value of this point represents the minimum "height" of the entire image. Preferably, mapping the image's grayscale value to height is equivalent to viewing the CT image as a simulated mountainous area: high grayscale value areas (such as stones) correspond to high simulated mountains, while low grayscale value areas (such as fluid or cavities) correspond to low simulated mountains. This mountain simulation facilitates the identification of object boundaries in CT images. In the watershed algorithm, water gradually fills areas of varying heights, ultimately forming independent segmented regions, i.e., the first set of segmented regions.

[0018] Starting from the first immersion point, simulated water begins to fill the first simulated mountain area. This process simulates the process of water gradually flooding the higher simulated mountains from the lower simulated mountains. When the water level rises to a certain height, the water surface will gradually cover the regional dividing points (i.e., the immersion dividing ridge lines). These areas are the locations of the stone fragments. By generating these ridge lines, the image can be divided into multiple different areas. These areas represent different structures in the CT image. Through grayscale value immersion division, the first divided area set is obtained, and then based on the first divided area set, further analysis is performed to obtain the first urethra CT scan image identified stone fragment size set and the first urethra CT scan image identified stone fragment location set.

[0019] Based on the same principle as obtaining the set of stone fragment sizes and the set of stone fragment locations identified by the first urethral CT scan image, the urethral CT scan image sequence is sequentially segmented by grayscale value immersion, thereby obtaining the set of stone fragment sizes and the set of stone fragment locations identified by the urethral CT scan image. By automatically segmenting the urethral CT scan image, the stone fragments can be accurately located, and subsequent statistical analysis, such as size measurement and position calibration, can be performed. Compared with traditional threshold segmentation, this method is more robust and can more accurately distinguish adjacent tissues or objects with similar density.

[0020] Further, such as Figure 2 As shown, step S2 of the embodiment of the present application also includes: Water is injected into the first simulated mountain area based on the first flooding point. As the water level rises, the simulated mountain located second in the first simulated mountain area, arranged in ascending order of height, is covered. It is determined whether the difference between the simulated mountain and the first flooding point is greater than or equal to a preset height difference threshold. If so, a first flooding demarcation line is generated, wherein the first flooding demarcation line rises as the water level rises. Continue to inject water into the first simulated mountain area until the simulated mountain area corresponding to the maximum height in the first simulated mountain area is submerged, thereby obtaining a set of waterlogged ridge lines; The first urethra CT scan image is divided into regions based on the water-immersion dividing ridge line set to obtain a first divided region set, wherein each first divided region set includes a first divided grayscale value cluster set.

[0021] In one possible embodiment, the water-immersion dividing line is a boundary formed when the height difference between two areas is greater than a certain threshold (preset height difference threshold) during the rising water level, i.e., the watershed line. This line distinguishes different stone fragments or tissue areas. The water-immersion dividing line set is a set composed of multiple water-immersion dividing lines continuously generated during the water immersion process, and is ultimately used to completely segment each area in the first urethra CT scan image. The first divided area set is a set of areas divided by the watershed method, and each area corresponds to a possible stone fragment or other tissue structure. The first divided gray value cluster set is a set obtained by summarizing the gray values ​​of all pixels in each divided area, and each first divided gray value cluster corresponds to a first divided area. The preset height difference threshold is the minimum height difference when generating the water-immersion dividing line, which is pre-set by a person skilled in the art.

[0022] First, the water filling process is simulated starting from the lowest grayscale value (the first flooded point). The water level gradually rises, gradually covering areas with higher grayscale values. When the water reaches the second-highest grayscale value "mountain" (the area with the second-lowest grayscale value), the height difference between it and the starting point is checked. If the difference exceeds a preset threshold, a watershed line is formed between the two areas, serving as the boundary.

[0023] The water level continues to increase, and the water gradually fills the entire CT image area. During the water injection process, when the height difference between the simulated mountain submerged by the water and the previously generated water-soaked demarcation line is greater than or equal to the preset height difference threshold, a new water-soaked demarcation line will be generated again. When the water level reaches the highest point, all watershed lines will form a complete boundary set. Based on these watershed lines, the first urethra CT scan image is divided into multiple regions, each corresponding to an independent tissue or stone fragment. Finally, all the divided regions are organized into a first divided region set, where each first divided region contains a first divided grayscale value cluster for subsequent analysis.

[0024] For example, assume a CT image has a grayscale range of 0-255. Urinary stones typically have higher grayscale values ​​(e.g., 180-220), while the soft tissue surrounding the urethra may have a grayscale value between 100-150. The grayscale distribution of the entire CT image is calculated, the lowest grayscale point (assuming it's 30) is found, and water injection begins. The water level rises to the second lowest grayscale area (assuming it's 35), and the grayscale difference between it and the first point is calculated. If this difference (35 - 30 = 5) is less than a threshold (e.g., a threshold of 10), the water level continues to rise, and no watershed line is formed. When the water level reaches the grayscale area of ​​50, the grayscale difference from the initial point reaches 20 (50 - 30 = 20), exceeding the threshold of 10. A watershed line is formed between 30 and 50, marking the boundary of the stone fragments. Water injection continues until the area with the highest grayscale value (assuming it's 220) is completely filled, ultimately forming a complete segmentation boundary.

[0025] By finely segmenting the first urethra CT scan images, stone fragments can be accurately separated and misjudgment due to similar grayscale values ​​can be avoided. By setting a preset height difference threshold, the technical effect of preventing over-segmentation or under-segmentation and improving the accuracy and robustness of segmentation is achieved.

[0026] Furthermore, step S2 of the embodiment of the present application further includes: Identifying the grayscale center values ​​of the first divided grayscale value cluster sets respectively to obtain a first divided grayscale center value set; Filtering the first divided grayscale center value set according to the grayscale center value threshold of the stone fragments to obtain a first urethra CT scan image-marked stone fragment position set; The size set of stone fragments identified by the first urethra CT scan image is determined according to the area size of the first divided region corresponding to the position set of stone fragments identified by the first urethra CT scan image.

[0027] Furthermore, the grayscale center value of each of the first divided grayscale value cluster sets is identified to obtain a first divided grayscale center value set. In this embodiment of the application, step S2 further includes: Calculating the mean of the first divided grayscale value cluster set to obtain a first divided grayscale mean value set; The first partitioned grayscale mean value set is used as an initial grayscale center value set, and the initial grayscale center value set is iterated in the first partitioned grayscale value cluster set using a center value iteration function until a preset number of iterations is met to obtain the first partitioned grayscale center value set.

[0028] Furthermore, the center value iteration function is: ; in, is the updated grayscale center value of the first partition, is the first gray value cluster, is the i-th first partition grayscale value in the first partition grayscale value cluster, is the initial grayscale center value, is a weight kernel function built based on the Gaussian function.

[0029] In one possible embodiment, the first divided grayscale center value set is respectively the most representative grayscale value in the first divided grayscale value cluster set, reflecting the main grayscale features of the first divided grayscale value cluster set. The grayscale center value threshold of the stone fragment is a grayscale threshold used to distinguish stone fragments from other tissues. A numerical range (such as 180-220) is set. If the grayscale center value of a certain area falls within this range, it is considered to be a stone fragment. The first urethra CT scan image identified stone fragment position set is a stone fragment position set obtained by screening the area that meets the stone grayscale threshold. The first urethra CT scan image identified stone fragment size set is a stone fragment size calculated based on the area corresponding to the stone fragment position.

[0030] Preferably, the mean is calculated for each first partition grayscale value cluster set to obtain a first partition grayscale mean set, which serves as the initial grayscale center value. Then, using a center value iteration function, these center values ​​are continuously optimized until a set number of iterations is reached, ultimately obtaining a first partition grayscale center value set. The center value iteration function primarily optimizes the grayscale center values ​​of the partitioned regions to more accurately represent regional characteristics, reduce noise effects, and improve classification accuracy. The preset number of iterations is a maximum number of iterations pre-set by a person skilled in the art, such as 50 or 100.

[0031] Based on medical imaging data, those skilled in the art will understand that stones typically have a specific grayscale range (e.g., 180-220). The grayscale center value of each first segment is compared with the grayscale center value threshold of the stone, and regions meeting the threshold are screened out. The pixel locations of these regions are stored in the first urethral CT scan image identification stone fragment location set. For the determined stone fragment location, its area in the CT image is calculated and stored in the first urethral CT scan image identification stone fragment size set. This process can use a region growing algorithm or morphological analysis method to calculate the number of pixels of each fragment and convert it into actual size (e.g., square millimeters).

[0032] Because directly calculating the grayscale mean can be affected by noise or boundaries, iterative optimization gradually adjusts the center value to make it more stable. This continuous adjustment of the center value allows for more precise separation of different image regions. For example, stones and normal tissue may have similar grayscale ranges. After iterative optimization, the grayscale center value of stones is more clearly defined, reducing misclassification.

[0033] S3: performing mapping fusion risk identification on the set sequence of stone fragment sizes identified by the urethra CT scan images and the set sequence of stone fragment positions identified by the urethra CT scan images to obtain a fusion risk factor sequence; Furthermore, mapping and fusion risk identification are performed on the set sequence of stone fragment sizes identified by the urethra CT scan image and the set sequence of stone fragment positions identified by the urethra CT scan image to obtain a fusion risk factor sequence. In this embodiment of the application, step S3 further includes: Traversing and calculating the mean of the size of the stone fragments identified in the urethra CT scan image set sequence, to obtain a sequence of the mean of the size of the stone fragments identified in the urethra CT scan image; Comparing the mean values ​​of the sizes of the stone fragments identified by the urethra CT scan images in the mean value sequence of the sizes of the stone fragments identified by the urethra CT scan images with the preset stone fragment size threshold value, respectively, to obtain a stone fragment size risk factor sequence; Randomly extracting M position cluster centers from the position set sequence of stone fragments identified in the urethral CT scan image to obtain a position cluster center set sequence, wherein each position cluster center set includes M position cluster centers, and the distance between any two position cluster centers among the M position cluster centers is greater than or equal to a preset distance threshold, where M is an integer greater than or equal to 1; Using a position collision risk function to perform risk identification on the position cluster center set sequence to obtain a position collision risk factor sequence; A mapping weighted calculation is performed on the stone fragment size risk factor sequence and the position collision risk factor sequence to obtain the fused risk factor sequence.

[0034] Furthermore, step S3 of the embodiment of the present application further includes: Construct a position collision risk function, wherein the position collision risk function is: ; in, is the position collision risk factor, for The first location in the cluster center The urethral CT scan images of the cluster centers identify the location of the stone fragments. for The first location in the cluster center The urethral CT scan images of the cluster centers identify the locations of stone fragments. For the The urethral CT scan image of the cluster center identifies the location of the stone fragments in the set A CT scan of the urethra identifies the location of stone fragments.

[0035] In one possible embodiment, mapping fusion risk identification is to comprehensively analyze the set of stone fragment sizes identified by urethral CT scan images and the set of stone fragment positions identified by urethral CT scan images belonging to the same moment in the set sequence of stone fragment sizes identified by urethral CT scan images and the set of stone fragment positions identified by urethral CT scan images, and perform fusion risk analysis of stone fragments in motion from two dimensions of stone fragment size and stone fragment position to obtain the fusion risk factor sequence. The fusion risk factor sequence reflects the risk level of stone fragment fusion within the preset window for the target patient within the preset window, and the larger the fusion risk factor, the higher the risk level.

[0036] In one embodiment, the mean of the sizes of the identified stone fragments in the set sequence of stone fragment sizes identified by the urethral CT scan images is calculated to obtain a sequence of mean sizes of stone fragments identified by the urethral CT scan images. By calculating the average size of the stone fragments in each urethral CT scan image and comparing it with a preset threshold, the risk of the stone fragments can be assessed. If the fragments are large, the risk of urethral obstruction may be increased, thereby assigning a higher risk factor.

[0037] Preferably, the mean size of each urethral CT scan image-identified stone fragment in the mean size sequence of each urethral CT scan image-identified stone fragment is divided by a preset stone fragment size threshold to obtain a stone fragment size risk factor sequence. The preset stone fragment size threshold is a size tolerance range for normal excretion of stone fragments pre-set by a person skilled in the art.

[0038] M cluster centers are randomly extracted from any set of locations of stone fragments identified by urethral CT scan images in the sequence of locations of stone fragments identified by urethral CT scan images. Preferably, the distance between any two locations of the M cluster centers is greater than or equal to a preset distance threshold to avoid misidentifying stone fragments that are too close together as independent individuals. The preset distance threshold is a minimum distance between two locations and the center when performing clustering, which is preset by a person skilled in the art.

[0039] Furthermore, the position collision risk function is constructed, and the position collision risk function is used to evaluate whether multiple stone fragments are close to each other. If the distance is too close, they may merge into a larger stone mass, increasing the risk of urethral obstruction. The position collision risk function is used to identify the risk of the position cluster center set sequence, thereby obtaining the position collision risk degree at different times within the preset window, and obtaining the position collision risk factor sequence. Furthermore, according to the weight ratio pre-set by a person skilled in the art, the stone fragment size risk factor sequence and the position collision risk factor sequence are mapped and weighted to obtain the fusion risk factor sequence. By calculating the size of the stone and the position collision risk, the risk degree of urethral stone fragment obstruction at different times in the preset window is comprehensively analyzed, thereby providing data support for the subsequent stone fragment identification results.

[0040] S4: Extract the maximum fusion risk factor in the fusion risk factor sequence, and determine whether the maximum fusion risk factor is greater than or equal to the preset fusion risk factor threshold. If not, use the CT scan image-identified stone fragment size set and the urethra CT scan image-identified stone fragment position set located at the last position in the urethra CT scan image-identified stone fragment size set sequence and the urethra CT scan image-identified stone fragment position set sequence as the stone fragment recognition result.

[0041] In one possible embodiment, the maximum fusion risk factor is the highest risk value extracted from the entire fusion risk factor sequence, representing the most severe risk of stone fragmentation during a patient's urethral CT scan. This value is calculated by weighting the stone size risk factor and the location collision risk factor, reflecting the degree of stone blockage risk. The preset fusion risk factor threshold is the minimum fusion risk factor value pre-set by a person skilled in the art that requires continuous monitoring.

[0042] Determine whether the maximum fusion risk factor is greater than or equal to the preset fusion risk factor threshold. If not, it indicates that the risk of complications caused by stone fragments in the target patient is low at this time. At this time, the CT scan image-identified stone fragment size set and the urethra CT scan image-identified stone fragment position set located at the last position in the urethra CT scan image-identified stone fragment size set sequence and the urethra CT scan image-identified stone fragment position set sequence are used as the stone fragment identification result.

[0043] If so, the patient's stone fragments are at high risk of complications, and continuous CT scans of the patient's urethra are necessary within a pre-set, long-term monitoring window to analyze the progression of the stone fragments. This improves the reliability and accuracy of stone fragment identification.

[0044] In summary, the embodiments of the present application have at least the following technical effects: 1. This application adopts the grayscale value immersion segmentation method to accurately segment the stone fragments in the CT image, reduce false detection or missed detection, and by calculating the grayscale center value and performing iterative optimization, the identification of stone fragments is made more stable and reliable.

[0045] 2. By integrating risk factor calculations, the potential risk of urethral obstruction posed by the size and location of stone fragments can be assessed, rather than simply performing image segmentation. This reduces misjudgments and provides stone fragment identification results that are more in line with actual conditions.

[0046] It should be noted that the order in which the embodiments of the present application are presented is for illustrative purposes only and does not necessarily represent the superiority or inferiority of the embodiments. Furthermore, the foregoing descriptions of specific embodiments of this specification are provided. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order or sequential sequence shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0047] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should be included in the scope of protection of the present application.

[0048] This specification and drawings are merely illustrative of the present application and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Obviously, those skilled in the art may make various modifications and variations to this application without departing from the scope of this application. Thus, this application is intended to include such modifications and variations as fall within the scope of this application and its equivalents.

Claims

1. A method for identifying urethral stone fragments, characterized in that: The method comprises: Acquire a CT scan image sequence of the urethra of a target patient within a preset window; Traversing the urethra CT scan image sequence and performing grayscale water immersion division to obtain a set sequence of stone fragment sizes identified by the urethra CT scan image and a set sequence of stone fragment positions identified by the urethra CT scan image; Performing mapping fusion risk identification on the set sequence of stone fragment sizes identified by the urethra CT scan image and the set sequence of stone fragment positions identified by the urethra CT scan image to obtain a fusion risk factor sequence; Extract the maximum fusion risk factor in the fusion risk factor sequence, and determine whether the maximum fusion risk factor is greater than or equal to the preset fusion risk factor threshold. If not, take the last CT scan image-identified stone fragment size set and the last CT scan image-identified stone fragment position set in the urethra CT scan image-identified stone fragment size set sequence and the urethra CT scan image-identified stone fragment position set sequence as the stone fragment recognition result.

2. The method for identifying urethral stone fragments according to claim 1, wherein: Traversing the urethra CT scan image sequence and performing grayscale water immersion division to obtain a set sequence of stone fragment sizes identified by the urethra CT scan image and a set sequence of stone fragment positions identified by the urethra CT scan image, including: extracting a first urethra CT scan image from the urethra CT scan image sequence; Obtaining a grayscale minimum value of the first urethra CT scan image, using the point at which the grayscale minimum value is located as a first water immersion point, and using the grayscale value as the height of a simulated mountain, performing mountain simulation on the first urethra CT scan image to obtain a first simulated mountain area, wherein the height of the first water immersion point is the grayscale minimum value; Performing grayscale value water immersion segmentation on the first simulated mountainous area to obtain a first segmented area set, and determining a size set of stone fragments identified by the first urethra CT scan image and a location set of stone fragments identified by the first urethra CT scan image based on the first segmented area set; The urethra CT scan image sequence is traversed to perform grayscale water immersion division to obtain a set sequence of stone fragment sizes identified by the urethra CT scan image and a set sequence of stone fragment positions identified by the urethra CT scan image.

3. The method for identifying urethral stone fragments according to claim 2, wherein: include: Water is injected into the first simulated mountain area based on the first flooding point. As the water level rises, the simulated mountain located second in the first simulated mountain area, arranged in ascending order of height, is covered. It is determined whether the difference between the simulated mountain and the first flooding point is greater than or equal to a preset height difference threshold. If so, a first flooding demarcation line is generated, wherein the first flooding demarcation line rises as the water level rises. Continue to inject water into the first simulated mountain area until the simulated mountain area corresponding to the maximum height in the first simulated mountain area is submerged, thereby obtaining a set of waterlogged ridge lines; The first urethra CT scan image is divided into regions based on the water-immersion dividing ridge line set to obtain a first divided region set, wherein each first divided region set includes a first divided grayscale value cluster set.

4. The method for identifying urethral stone fragments according to claim 3, characterized in that: include: Identifying the grayscale center values ​​of the first divided grayscale value cluster sets respectively to obtain a first divided grayscale center value set; Filtering the first divided grayscale center value set according to the grayscale center value threshold of the stone fragments to obtain a first urethra CT scan image-marked stone fragment position set; The size set of stone fragments identified by the first urethra CT scan image is determined according to the area size of the first divided region corresponding to the position set of stone fragments identified by the first urethra CT scan image.

5. The method for identifying urethral stone fragments according to claim 4, characterized in that: Identifying the grayscale center values ​​of the first divided grayscale value cluster sets respectively to obtain a first divided grayscale center value set includes: Calculating the mean of the first divided grayscale value cluster set to obtain a first divided grayscale mean value set; The first partitioned grayscale mean value set is used as an initial grayscale center value set, and the initial grayscale center value set is iterated in the first partitioned grayscale value cluster set using a center value iteration function until a preset number of iterations is met to obtain the first partitioned grayscale center value set.

6. The method for identifying urethral stone fragments according to claim 5, characterized in that: The center value iteration function is: ； in, is the updated grayscale center value of the first partition, is the first gray value cluster, is the i-th first partition grayscale value in the first partition grayscale value cluster, is the initial grayscale center value, is a weight kernel function built based on the Gaussian function.

7. The method for identifying urethral stone fragments according to claim 6, characterized in that: Mapping and fusion risk identification is performed on the set sequence of stone fragment sizes identified by the urethra CT scan image and the set sequence of stone fragment positions identified by the urethra CT scan image to obtain a fusion risk factor sequence, including: Traversing and calculating the mean of the size of the stone fragments identified in the urethra CT scan image set sequence, to obtain a sequence of the mean of the size of the stone fragments identified in the urethra CT scan image; Comparing the mean values ​​of the sizes of the stone fragments identified by the urethra CT scan images in the mean value sequence of the sizes of the stone fragments identified by the urethra CT scan images with the preset stone fragment size threshold value, respectively, to obtain a stone fragment size risk factor sequence; Randomly extracting M position cluster centers from the position set sequence of stone fragments identified in the urethral CT scan image to obtain a position cluster center set sequence, wherein each position cluster center set includes M position cluster centers, and the distance between any two position cluster centers among the M position cluster centers is greater than or equal to a preset distance threshold, where M is an integer greater than or equal to 1; Using a position collision risk function to perform risk identification on the position cluster center set sequence to obtain a position collision risk factor sequence; A mapping weighted calculation is performed on the stone fragment size risk factor sequence and the position collision risk factor sequence to obtain the fused risk factor sequence.

8. The method for identifying urethral stone fragments according to claim 1, characterized in that: include: Construct a position collision risk function, wherein the position collision risk function is: ； in, is the position collision risk factor, for The first location in the cluster center The urethral CT scan images of the cluster centers identify the location of the stone fragments. for The first location in the cluster center The urethral CT scan images of the cluster centers identify the locations of stone fragments. For the The urethral CT scan image of the cluster center identifies the location of the stone fragments in the set A CT scan of the urethra identifies the location of stone fragments.

Images