A method of identifying a stone fragment on a urethra

Abstract

The application discloses a urethral stone fragment identification method, and relates to the technical field of image enhancement, and the method comprises the following steps: acquiring a urethral CT scan image sequence of a target patient in a preset window; obtaining a urethral CT scan image identified stone fragment size set sequence and a urethral CT scan image identified stone fragment position set sequence; 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 application solves the technical problem of low recognition accuracy and automation degree and single dimension in the prior art when urethral stone fragments are identified. The technical effect of reliable stone fragment identification is achieved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of image processing, in particular to a urethral stone fragment identification method. BACKGROUND

[0002] Currently, urinary tract stones are a common urological disease. After treatment, there may be residual stone fragments in the urethra. If the risk is not identified and assessed in a timely manner, it may lead to complications such as urinary obstruction and infection. Therefore, how to efficiently and accurately identify stone fragments in the urethra has become an important research direction.

[0003] Existing stone fragment identification methods usually rely on doctors to interpret CT scan images. This method not only takes a long time, but also depends on the experience of doctors and is easily affected by subjective factors, which may lead to insufficient identification accuracy. In addition, some automatic identification methods only detect fragments based on a single feature (such as size or location), lack comprehensive analysis in multiple dimensions, and result in low accuracy in fragment fusion risk assessment.

[0004] The prior art has the technical problem of low identification accuracy and low automation degree when identifying urethral stone fragments. SUMMARY

[0005] The present application provides a urethral stone fragment identification method to solve the technical problem of low identification accuracy and low automation degree when identifying urethral stone fragments in the prior art.

[0006] In view of the above problems, the present application provides a urethral stone fragment identification method, which comprises:

[0007] Obtaining a urethral CT scan image sequence of a target patient within a preset window;

[0008] Performing gray value water immersion division on the urethral CT scan image sequence to obtain a urethral CT scan image identified stone fragment size set sequence and a urethral CT scan image identified stone fragment position set sequence;

[0009] Respectively mapping and fusing the urethral CT scan image identified stone fragment size set sequence and the urethral CT scan image identified stone fragment position set sequence to identify the risk, and obtaining a fusion risk factor sequence;

[0010] extracting a maximum fusion risk factor in the fusion risk factor sequence, judging whether the maximum fusion risk factor is greater than or equal to a preset fusion risk factor threshold, and if not, taking 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 identification result.

[0011] The one or more technical solutions provided in the present application have at least the following technical effects or advantages:

[0012] In the present application, the urethra CT scan image sequence of the target patient in the preset window is obtained, then the urethra CT scan image sequence is traversed to perform gray value immersion division, the urethra CT scan image identified stone fragment size set sequence and the urethra CT scan image identified stone fragment position set sequence are obtained, then the urethra CT scan image identified stone fragment size set sequence and the urethra CT scan image identified stone fragment position set sequence are respectively mapped and fusion risk identification is performed to obtain the fusion risk factor sequence, and then the maximum fusion risk factor in the fusion risk factor sequence is extracted, whether the maximum fusion risk factor is greater than or equal to the preset fusion risk factor threshold is judged, and if not, 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 taken as the stone fragment identification result. The technical effect of improving the stone fragment identification reliability and the identification accuracy is achieved. BRIEF DESCRIPTION OF DRAWINGS

[0013] FIG. 1 is a urethra stone fragment identification method flowchart provided by an embodiment of the present application. Figure 1 FIG. 1 is a urethra stone fragment identification method flowchart provided by an embodiment of the present application.

[0014] FIG. 2 is a flowchart of obtaining a first division region set in the urethra stone fragment identification method provided by the embodiment of the present application. Figure 2 FIG. 2 is a flowchart of obtaining a first division region set in the urethra stone fragment identification method provided by the embodiment of the present application. DETAILED DESCRIPTION

[0015] The present application will be further described below in conjunction with specific embodiments. It should be understood that these embodiments are only used to illustrate the present application and not used to limit the scope of the present application. In addition, it should be understood that after reading the content taught by the present application, those skilled in the art can make various modifications or changes to the present application, and these equivalent forms also fall within the scope of the appended claims of the present application.

[0016] It is to be understood that the terms "including", "comprising", "having" and "with" are meant to be interpreted open-ended, i.e. they are meant to encompass not only the listed steps or units but also other steps or units not explicitly listed. It is also to be understood that, wherever used, the terms "comprising", "including", "with" and "having" are intended to be open-ended and do not exclude other steps or units not explicitly listed.

[0017] Embodiments, as shown in the accompanying drawings Figure 1 The present application provides a method for identifying a urethral stone fragment, wherein the method comprises:

[0018] S1: obtaining a urethral CT scan image sequence of a target patient within a preset window;

[0019] In one possible embodiment, the target patient refers to a patient who needs to be detected for urethral stone fragments. The preset window generally refers to a CT scan image acquisition time period within a certain time range, which can be optionally set by a person skilled in the art, such as a postoperative observation period or a specific time interval (e.g., within 24 hours, within 48 hours, etc.). The urethral CT scan image sequence refers to a series of urethral images obtained by CT scan technology within the time window, which are used for subsequent image analysis and stone fragment identification.

[0020] Preferably, the urethral CT scan images of the target patient are collected within the preset window at a preset sampling frequency and arranged in chronological order to obtain the urethral CT scan image sequence. These image sequences can capture the dynamic conditions inside the urethra, such as the distribution, size, shape and possible displacement of the stone fragments. The purpose of this step is to provide raw data input for subsequent image processing, ensuring that the system can analyze based on continuous image data rather than relying solely on a single image, thereby improving the accuracy and stability of the identification. For example, during the postoperative observation period, a set of urethral CT scan images are obtained at regular intervals, which can help the doctor to determine whether the stone fragments are being expelled, moving or forming new obstruction points.

[0021] S2: traversing the urethral CT scan image sequence to perform gray value water immersion division, obtaining a urethral CT scan image identified stone fragment size set sequence and a urethral CT scan image identified stone fragment position set sequence;

[0022] In a possible embodiment, after obtaining the urethra CT scan image sequence, the urethra CT scan image sequence is traversed, gray value analysis is performed on each urethra CT scan image, and different gray values are regarded as different heights of terrain. Then, water immersion simulation is adopted, the rising process of water is simulated from the point with the lowest gray value (i.e., the darkest region), and regional division is performed by taking the water immersion division ridge line as a boundary. After the regional division is completed, the positions of the stone fragments are determined according to the sizes of the gray center values of different regions, and the stone fragments are identified. Then, the sizes of the stone fragments are determined according to the areas of the regions, so as to obtain the urethra CT scan image stone fragment size set sequence and the urethra CT scan image stone fragment position set sequence. The urethra CT scan image stone fragment size set sequence reflects the volume sizes of the stone fragments in the urethra of the target patient at different moments within a preset window. The urethra CT scan image stone fragment position set sequence reflects the specific positions of the stone fragments in the urethra of the target patient at different moments within the preset window.

[0023] By obtaining the urethra CT scan image stone fragment size set sequence and the urethra CT scan image stone fragment position set sequence, a technical effect of providing data support for subsequent fusion risk analysis of the stone fragments in the movement process is achieved.

[0024] Further, the urethra CT scan image sequence is traversed to perform gray value water immersion division, so as to obtain the urethra CT scan image stone fragment size set sequence and the urethra CT scan image stone fragment position set sequence. The step S2 of the embodiment of the present application further includes:

[0025] extracting a first urethra CT scan image from the urethra CT scan image sequence;

[0026] obtaining the minimum gray value of the first urethra CT scan image, taking the point at which the minimum gray value is located as a first water immersion point, and taking the gray value as the height of a simulated mountain, so as to perform mountain simulation on the first urethra CT scan image, and obtain a first simulated mountain region. The height of the first water immersion point is the minimum gray value.

[0027] performing gray value water immersion division on the first simulated mountain region, to obtain a first division region set, and determining a first urethra CT scan image stone fragment size set and a first urethra CT scan image stone fragment position set based on the first division region set.

[0028] traversing the urethra CT scan image sequence to perform gray value water immersion division, so as to obtain the urethra CT scan image stone fragment size set sequence and the urethra CT scan image stone fragment position set sequence.

[0029] In one possible embodiment, a first CT scan image, i.e., a preliminary reference image, is extracted from the entire urethral CT scan image sequence. The minimum grayscale value refers to the lowest grayscale value of a pixel in the first urethral CT scan image, which typically corresponds to the darkest part in the CT image (usually representing a cavity or water-filled area). The pixel containing this minimum grayscale value is then used as the starting point for immersion, called the first immersion point. The grayscale value of this point represents the minimum "height" of the entire image. Preferably, mapping the image's grayscale values ​​to height is equivalent to viewing the CT image as a simulated mountainous region: high grayscale areas (e.g., stones) correspond to high simulated mountains, and low grayscale areas (e.g., liquid or cavities) correspond to low simulated mountains. This mountainous simulation helps identify object boundaries in the CT image. In the watershed algorithm, water gradually fills regions of different heights, eventually forming independent segmented regions, i.e., the first set of segmented regions.

[0030] Starting from the first immersion point, simulated water begins to fill the first simulated mountain area. This process simulates water gradually submerging higher simulated mountains from lower ones. When the water level rises to a certain height, the water surface gradually covers the regional boundary points (i.e., the immersion ridge lines), which are the locations of the stone fragments. By generating these ridge lines, the image can be divided into multiple different regions. These regions represent different structures in the CT image. By dividing the image using grayscale values, the first set of divided regions is obtained. Then, based on the first set of divided regions, further analysis is performed to obtain the set of stone fragment sizes and the set of stone fragment locations identified in the first urethral CT scan image.

[0031] Based on the same principle as obtaining the set of sizes and locations of the stone fragments identified in the first urethral CT scan image, the urethral CT scan image sequence is sequentially divided by grayscale water immersion to obtain the sets of sizes and locations of the stone fragments identified in the urethral CT scan image. By automatically segmenting the urethral CT scan image, the stone fragments can be accurately located, and subsequent statistical analyses, such as size measurement and location calibration, can be performed. This method is more robust than traditional threshold segmentation and can more accurately distinguish adjacent tissues or objects with similar densities.

[0032] Furthermore, such as Figure 2 As shown, step S2 in this embodiment further includes:

[0033] based on the first water immersion point, water is injected into the first simulated mountain region, and as the water level rises to cover the simulated mountain region with the second highest height, it is determined whether the height difference between the first water immersion point and the simulated mountain region is greater than or equal to a preset height difference threshold, and if so, a first water immersion division ridge line is generated, wherein the first water immersion division ridge line rises as the water level rises;

[0034] Water injection into the first simulated mountain region continues until the simulated mountain region with the maximum height is covered, and a set of water immersion division ridge lines is obtained;

[0035] Based on the set of water immersion division ridge lines, the first urethra CT scan image is regionally divided to obtain a first set of division regions, wherein each first set of division regions includes a first set of division gray value clusters.

[0036] In one possible embodiment, the water immersion division ridge line is a boundary formed when the height difference between two regions exceeds a certain threshold (preset height difference threshold) during the rising of the water level, i.e., a watershed line. This line distinguishes different stone fragments or tissue regions. The set of water immersion division ridge lines is a set composed of multiple water immersion division ridge lines generated during the water immersion process, which is ultimately used to completely segment the regions in the first urethra CT scan image. The first set of division regions is a set of regions divided by the watershed method, each region corresponding to a possible stone fragment or other tissue structure. The first set of division gray value clusters is a set obtained by aggregating the gray values of all pixel points in each division region, each first division gray value cluster corresponding to a first division region. The preset height difference threshold is the minimum height difference set by the person skilled in the art when generating the water immersion division ridge line.

[0037] First, the water filling process is simulated from the lowest gray value (first water immersion point), the water level rises gradually, and the regions with higher gray values are covered in turn. When the water covers the "mountain" with the second lowest gray value (i.e., the region with the second lowest gray value), the height difference between it and the initial point is checked. If the difference exceeds the preset threshold, a watershed line is formed between the two regions as a boundary.

[0038] With the water level continuously increasing, the water gradually fills the entire CT image area, and during the water injection process, when the height difference between the simulated mountain height that is flooded and the height between the last generated water immersion division ridge line is greater than or equal to a preset height difference threshold value, a new water immersion division ridge line is generated again. When the water level reaches the highest point, all the water ridge lines form a complete boundary set. Based on these water ridge lines, the first urethra CT scan image is divided into multiple regions, each of which corresponds to an independent tissue or stone fragment. Finally, all the divided regions are organized into a first division region set, wherein each first division region contains a first division gray value cluster for subsequent analysis.

[0039] For example, assuming that the gray value range of a CT image is 0-255, wherein the gray value of the urethral calculus is usually high (for example, 180-220), and the soft tissue around the urethra can be between 100-150. Calculate the gray value distribution of the entire CT image, find the lowest gray value point (assuming 30), and start water injection. The water level rises to the second lowest area (assuming 35), and the gray value difference between it and the first point is calculated. If the difference (35-30=5) is less than the threshold value (for example, the threshold value is set to 10), continue to rise, and no water ridge line is formed. When the water level rises to the area with a gray value of 50, the gray value difference with the initial point reaches 20 (50-30=20), which exceeds the set threshold value 10, and a water ridge line is formed between 30 and 50, which is marked as the boundary of the stone fragment. Continue to inject water until the area at the highest gray value (assuming 220) is completely filled, and finally form a complete segmentation boundary.

[0040] By finely segmenting the first urethra CT scan image, the stone fragments can be accurately separated, and misjudgments caused by similar gray values are avoided, and by setting a preset height difference threshold value, the technical effects of preventing over-segmentation or under-segmentation, improving the accuracy and robustness of segmentation are achieved.

[0041] Further, the step S2 of the embodiment of the present application further comprises:

[0042] Respectively, the gray center value of the first division gray value cluster set is identified to obtain a first division gray center value set;

[0043] According to the stone fragment gray center value threshold, the first division gray center value set is screened to obtain a first urethra CT scan image stone fragment position set;

[0044] According to the area size of the first division region corresponding to the first urethra CT scan image stone fragment position set, a first urethra CT scan image stone fragment size set is determined.

[0045] Further, the first division gray value cluster set is respectively subjected to gray center value identification to obtain a first division gray center value set. The step S2 of the embodiment of the application further includes:

[0046] The mean value of the first division gray value cluster set is calculated to obtain a first division gray mean value set.

[0047] The first division gray mean value set is taken as an initial gray center value set, and the initial gray center value set is iterated in the first division gray value cluster set by using a center value iteration function until a preset iteration number is met, so as to obtain the first division gray center value set.

[0048] Further, the center value iteration function is:

[0049]

[0050] wherein, is an updated first division gray center value, is a first division gray value cluster, is an i-th first division gray value in the first division gray value cluster, is an initial gray center value, is a weight kernel function constructed based on a Gaussian function.

[0051] In one possible embodiment, the first division gray center value set respectively is a most representative gray value in the first division gray value cluster set, reflecting the main gray feature of the first division gray value cluster set. The stone fragment gray center value threshold is a gray threshold for distinguishing stone fragments and other tissues, and a numerical range (such as 180-220) is set. If the gray center value of a certain region falls within the range, the region 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 regions meeting the stone gray threshold. The first urethra CT scan image identified stone fragment size set is a stone fragment size calculated according to the area of the region corresponding to the stone fragment position.

[0052] Preferably, the mean value of each first division gray value cluster set is calculated to obtain a first division gray mean value set as an initial gray center value. Then, the center value iteration function is used to constantly optimize the center values until a set iteration number is reached, so as to finally obtain the first division gray center value set. The main function of the center value iteration function is to optimize the gray center value of the division region, so that the gray center value more accurately represents the region feature, reduces the noise influence, and improves the classification precision. The preset iteration number is a maximum iteration number set by a person skilled in the art in advance, such as 50 times, 100 times, etc.

[0053] ​The skilled in the art can understand that the stones usually have a specific gray scale range (for example, 180-220) according to the medical image data. The first division gray scale center value is compared with the gray scale center value threshold of the stone, and the regions meeting the threshold are screened out. The pixel positions of these regions are stored in the first urethral CT scan image stone fragment position set. For the determined stone fragment position, its area in the CT image is calculated and stored in the first urethral CT scan image stone fragment size set. This process can use a region growing algorithm or a morphological analysis method to calculate the number of pixels of each fragment and convert it into the actual size (such as square millimeter).

[0054] Since the direct calculation of the gray mean value may be affected by noise or boundary, the center value can be adjusted step by step to make it more stable through iterative optimization. By continuously adjusting the center value, the technical effect of more accurately separating different regions in the image is achieved. For example, the stone and the normal tissue may have similar gray scale range, and after iterative optimization, the gray scale center value of the stone is more clear, reducing misclassification.

[0055] S3: respectively mapping and fusing the urethral CT scan image stone fragment size set sequence and the urethral CT scan image stone fragment position set sequence to perform risk identification, and obtaining a fused risk factor sequence;

[0056] Further, respectively mapping and fusing the urethral CT scan image stone fragment size set sequence and the urethral CT scan image stone fragment position set sequence to perform risk identification, and obtaining a fused risk factor sequence, the step S3 of the embodiment of the application further includes:

[0057] Iteratively calculating the mean value of the urethral CT scan image stone fragment size in the urethral CT scan image stone fragment size set sequence to obtain a urethral CT scan image stone fragment size mean value sequence;

[0058] Respectively comparing the urethral CT scan image stone fragment size mean value in the urethral CT scan image stone fragment size mean value sequence with a preset stone fragment size threshold value to obtain a stone fragment size risk factor sequence;

[0059] Respectively randomly extracting M position clustering centers from the urethral CT scan image stone fragment position set sequence to obtain a position clustering center set sequence, wherein each position clustering center set includes M position clustering centers, the distance between any two position clustering centers in the M position clustering centers is greater than or equal to a preset distance threshold value, and M is an integer greater than or equal to 1;

[0060] Using a position collision risk function to perform risk identification on the position clustering center set sequence to obtain a position collision risk factor sequence;

[0061] mapping weighted calculation is performed on the stone fragment size risk factor sequence and the position collision risk factor sequence to obtain the fusion risk factor sequence.

[0062] Further, the step S3 of the embodiment of the present application further comprises:

[0063] a position collision risk function is constructed, wherein the position collision risk function is:

[0064] ;

[0065] wherein, is a position collision risk factor, is a urethra CT scan image identification stone fragment position set of the i-th cluster center in the K urethra CT scan image identification stone fragment position set of the i-th cluster center in the K is a urethra CT scan image identification stone fragment position of the i-th cluster center in the K urethra CT scan image identification stone fragment position of the i-th cluster center in the K urethra CT scan image identification stone fragment position set of the i-th cluster center in the K urethra CT scan image identification stone fragment position set of the i-th cluster center in the K urethra CT scan image identification stone fragment position set of the i-th cluster center in the K

[0066] In one possible embodiment, the mapping fusion risk identification is to comprehensively analyze the urethra CT scan image identification stone fragment size set and the urethra CT scan image identification stone fragment position set belonging to the same moment in the urethra CT scan image identification stone fragment size set sequence and the urethra CT scan image identification stone fragment position set sequence, to perform fusion risk analysis of the stone fragment in motion from two dimensions of stone fragment size and stone fragment position, to obtain the fusion risk factor sequence. Wherein, the fusion risk factor sequence reflects the risk degree of the stone fragment fusion of the target patient in the preset window within the preset window, and the greater the fusion risk factor, the higher the risk degree.

[0067] In one embodiment, the mean value of the identification stone fragment size of the urethra CT scan image identification stone fragment size set sequence is calculated respectively to obtain the urethra CT scan image identification stone fragment size mean value sequence. By calculating the average size of the stone fragment in each urethra CT scan image and comparing with the preset threshold, the risk of the stone fragment can be evaluated, and if the fragment is larger, the risk of urethral obstruction can be increased, thereby giving a higher risk factor.

[0068] Preferably, the urethra CT scan image is marked in the stone fragment size mean value sequence, and the stone fragment size mean value is greater than or equal to a preset stone fragment size threshold value to obtain a stone fragment size risk factor sequence. The preset stone fragment size threshold value is a size tolerance range of the stone fragment that can be normally discharged, which is preset by a person skilled in the art.

[0069] The urethra CT scan image is marked in the stone fragment position set sequence, and the stone fragment position set is randomly extracted from M position clustering centers. Preferably, the distance between any two position distance centers of the M position clustering centers is greater than or equal to a preset distance threshold value, so as to avoid mistaking the stone fragments that are too close as independent individuals. The preset distance threshold value is the minimum distance between the two position distance centers during clustering, which is preset by a person skilled in the art.

[0070] Further, the position collision risk function is constructed, which is used to evaluate whether the plurality of stone fragments are close to each other. If the distance is too close, the stone fragments may be combined 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 clustering center set sequence, so as to obtain the position collision risk degree at different time points in the preset window, and obtain the position collision risk factor sequence. Further, the stone fragment size risk factor sequence and the position collision risk factor sequence are mapped and weighted according to the weight ratio preset by a person skilled in the art, to obtain the fusion risk factor sequence. By calculating the size and position collision risk of the stone, the risk degree of the urethral stone fragment obstruction at different time points in the preset window is comprehensively analyzed, so as to provide data support for subsequent stone fragment identification results.

[0071] 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 a preset fusion risk factor threshold value. If not, the CT scan image marking stone fragment size set and the urethra CT scan image marking stone fragment position set located at the last position in the urethra CT scan image marking stone fragment size set sequence and the urethra CT scan image marking stone fragment position set sequence are taken as the stone fragment identification result.

[0072] 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 serious stone fragment risk in the urethra CT scan process of the patient. The value is obtained by weighted calculation of the stone size risk factor and the position collision risk factor, and reflects the degree of obstruction risk of the stone. The preset fusion risk factor threshold value is the minimum size of the fusion risk factor that needs to be continuously observed, which is preset by a person skilled in the art.

[0073] If no, it indicates that the risk degree of the target patient's stone fragment to produce complications is low at this time, and the CT scan image identified stone fragment size set and the CT scan image identified stone fragment position set in the last position in the set sequence of the urethra CT scan image identified stone fragment size set and the set sequence of the urethra CT scan image identified stone fragment position set are taken as the stone fragment identification result.

[0074] If yes, it indicates that the risk degree of the target patient's stone fragment to produce complications is high at this time, and the urethra of the target patient needs to be continuously scanned by CT in a preset long-term continuous monitoring window to analyze the development of the stone fragment. Thus, the technical effect of improving the reliability of the stone fragment identification result and improving the identification accuracy is achieved.

[0075] In summary, the embodiments of the present application have at least the following technical effects:

[0076] 1. The present application can accurately segment the stone fragment in the CT image by using the gray value immersion division method, reduce false positives or false negatives, and through calculating the gray center value and iterative optimization, the identification of the stone fragment is more stable and reliable.

[0077] 2. Through the fusion risk factor calculation, the size and position of the stone fragment can be evaluated for the potential risk of blocking the urethra, not just simple image segmentation, thereby reducing misjudgment and providing a more realistic stone fragment identification result.

[0078] It should be noted that the above sequence of the embodiments of the present application is only for description, and does not represent the advantages and disadvantages of the embodiments. And the above describes the specific embodiments of the present application. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multi-task processing and parallel processing are also possible or can be advantageous.

[0079] The above only describes the preferred embodiments of the present application, and does not limit the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

[0080] The present application and the drawings are only exemplary descriptions of the present application, and are considered to cover any and all modifications, changes, combinations or equivalents within the scope of the present application. Obviously, those skilled in the art can make various modifications and changes to the present application without departing from the scope of the present application. Thus, if these modifications and changes of the present application belong to the scope of the present application and its equivalent technology, the present application intends to include these modifications and changes.

Claims

1. A method for identifying fragments of stones in the urethra, characterized in that, The method comprises: acquiring a urethra CT scan image sequence of a target patient within a preset window; traversing the urethra CT scan image sequence to perform gray value water immersion division, to obtain a urethra CT scan image identified stone fragment size set sequence and a urethra CT scan image identified stone fragment position set sequence; respectively performing mapping fusion risk identification on the urethra CT scan image identified stone fragment size set sequence and the urethra CT scan image identified stone fragment position set sequence, to obtain a fusion risk factor sequence; extracting a maximum fusion risk factor in the fusion risk factor sequence, and judging whether the maximum fusion risk factor is greater than or equal to a preset fusion risk factor threshold value, if not, taking a CT scan image identified stone fragment size set and a urethra CT scan image identified stone fragment position set 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 a stone fragment identification result; wherein traversing the urethra CT scan image sequence to perform gray value water immersion division, to obtain a urethra CT scan image identified stone fragment size set sequence and a urethra CT scan image identified stone fragment position set sequence comprises: extracting a first urethra CT scan image from the urethra CT scan image sequence; acquiring a gray minimum value of the first urethra CT scan image, taking a point position where the gray minimum value is located as a first water immersion point position, and taking a gray value as a height of a simulated mountain, to perform mountain simulation on the first urethra CT scan image, to obtain a first simulated mountain region, wherein the height of the first water immersion point position is the gray minimum value; performing gray value water immersion division on the first simulated mountain region, to obtain a first division region set, and determining a first urethra CT scan image identified stone fragment size set and a first urethra CT scan image identified stone fragment position set based on the first division region set; traversing the urethra CT scan image sequence to perform gray value water immersion division, to obtain a urethra CT scan image identified stone fragment size set sequence and a urethra CT scan image identified stone fragment position set sequence; based on the first water immersion point position, water is injected into the first simulated mountain region, and as the water surface rises to cover a simulated mountain with a height arranged at the second position from small to large in the first simulated mountain region, it is judged whether a difference between the height of the first water immersion point position and the height of the simulated mountain is greater than or equal to a preset height difference threshold value, if yes, a first water immersion division ridge line is generated, wherein the first water immersion division ridge line rises as the water surface rises; water continues to be injected into the first simulated mountain region until a simulated mountain region corresponding to a maximum height in the first simulated mountain region is covered, to obtain a water immersion division ridge line set; based on the water immersion division ridge line set, region division is performed on the first urethra CT scan image, to obtain a first division region set, wherein each first division region set comprises a first division gray value cluster set.

2. A method of identifying a stone fragment on a urethra as claimed in claim 1, wherein, comprises: respectively performing gray center value identification on the first division gray value cluster set, to obtain a first division gray center value set; Screening the first division gray center value set according to the stone fragment gray center value threshold, to obtain a first urethra CT scan image stone fragment position set; According to the area size of the first division region corresponding to the first urethra CT scan image stone fragment position set, the first urethra CT scan image stone fragment size set is determined.

3. A method of identifying a stone fragment on a urethra as claimed in claim 2, wherein, Respectively, the first division gray value cluster set is identified by the gray center value, and the first division gray center value set is obtained, including: The mean value of the first division gray value cluster set is calculated to obtain the first division gray mean value set; The first division gray mean value set is used as the initial gray center value set, and the center value iteration function is used to iterate the initial gray center value set in the first division gray value cluster set until the preset iteration number is met, to obtain the first division gray center value set.

4. A method of identifying a stone fragment on a urethra as claimed in claim 3, wherein, The center value iteration function is: ； wherein, is the updated first partitioned gray center value, is the first partitioned gray value cluster, is the i-th first partitioned gray value in the first partitioned gray value cluster, is the initial gray center value, is the weight kernel function constructed based on the Gaussian function.

5. A method of identifying a stone fragment on a urethra as claimed in claim 4, wherein, Respectively, the urethra CT scan image stone fragment size set sequence and the urethra CT scan image stone fragment position set sequence are mapped and fused to identify the risk, to obtain a fused risk factor sequence, including: The mean value of the urethra CT scan image stone fragment size set sequence is calculated to obtain a urethra CT scan image stone fragment size mean value sequence; Respectively, the urethra CT scan image stone fragment size mean value in the urethra CT scan image stone fragment size mean value sequence is greater than the preset stone fragment size threshold, to obtain a stone fragment size risk factor sequence; Respectively, M position clustering centers are randomly extracted from the urethra CT scan image stone fragment position set sequence to obtain a position clustering center set sequence, wherein each position clustering center set includes M position clustering centers, and the distance between any two position clustering centers in the M position clustering centers is greater than or equal to a preset distance threshold, and M is an integer greater than or equal to 1; The position clustering center set sequence is identified by using a position collision risk function to obtain a position collision risk factor sequence; The stone fragment size risk factor sequence and the position collision risk factor sequence are mapped and weighted to obtain the fused risk factor sequence.

6. A method of identifying a stone fragment on a urethra as claimed in claim 1, wherein, Including: The position collision risk function is constructed, wherein the position collision risk function is: ； wherein, is a position collision risk factor, is is a urethra CT scan image of the is a set of stone fragment positions identified by the is is a urethra CT scan image of the is a stone fragment position identified by the is a set of stone fragment positions identified by the is a stone fragment position identified by the urethra CT scan image of the

Images