Image processing method for urinary calculus scene and urinary calculus ablation system

Abstract

The invention discloses an image processing method for a urinary calculus scene and a urinary calculus ablation system, and the method comprises the steps: obtaining a first to-be-detected image of a target region; performing classification detection on the first to-be-detected image based on the target detection model to determine a first detection result; when the first detection result comprises at least one of the component type of at least one urinary calculus and the corresponding probability information and the position information of the bounding box characteristics, determining a target urinary calculus based on the position information of the bounding box characteristics of each urinary calculus; determining the ablation distance of the target urinary calculus based on the first detection result; the output parameters of the calculus ablation equipment are determined based on the component type and the ablation distance of the target urinary calculus, accurate determination of the output parameters of the calculus ablation equipment is achieved, and accurate data support is provided for subsequent analysis and processing.

Description

Technical Field

[0001] This invention relates to the field of image processing technology, and in particular to image processing methods and urinary stone ablation systems for urinary stone scenarios. Background Technology

[0002] Urinary tract stones are a common disease that can be treated with stone ablation devices. The output parameters of these devices affect the ablation effect. Currently, the composition of the urinary tract stones is manually determined, and the output parameters of the ablation device are then determined based on this composition. However, manually determining these parameters relies on experience and is prone to inaccuracies. Summary of the Invention

[0003] This invention provides an image processing method and a urinary stone ablation system for urinary stone scenarios, so as to achieve accurate determination of the output parameters of the stone ablation device.

[0004] According to one aspect of the present invention, an image processing method for a urinary calculus scene is provided, the method comprising:

[0005] Obtain the first image of the target region to be detected;

[0006] The first image to be detected is classified and detected based on the object detection model to determine the first detection result;

[0007] When the first detection result includes at least one of the composition type of at least one urinary stone and the corresponding probability information and the location information of the bounding box feature, the target urinary stone is determined based on the location information of the bounding box feature of each urinary stone.

[0008] The ablation distance of the target urinary stone is determined based on the initial detection results;

[0009] The output parameters of the stone ablation device are determined based on the composition and ablation distance of the target urinary stone.

[0010] According to another aspect of the present invention, a urinary stone ablation system is provided, comprising an endoscope, a processing unit, and a stone ablation device;

[0011] The endoscope is used to acquire a first image to be detected and to transmit the first image to be detected to the processing unit;

[0012] The processing unit is used to classify and detect the first image to be detected based on the target detection model, and determine the first detection result; when the first detection result includes at least one of the composition type of at least one urinary stone and the corresponding probability information and the location information of the bounding box feature, the processing unit determines the target urinary stone based on the location information of the bounding box feature of each urinary stone; determines the ablation distance of the target urinary stone based on the first detection result; determines the output parameters of the stone ablation device based on the composition type and ablation distance of the target urinary stone; and sends an ablation command to the stone ablation device based on the output parameters.

[0013] Stone ablation equipment is used to ablate target urinary stones in response to ablation commands.

[0014] The technical solution of this invention provides data support for subsequent analysis and processing by acquiring a first image of the target area, ensuring efficient and accurate execution of various tasks. It classifies and detects the first image based on a target detection model to determine the first detection result, achieving accurate determination of the first detection result and providing accurate data support for subsequent analysis and processing. When the first detection result includes at least one of the following: the composition type of at least one urinary stone and its corresponding probability information and the location information of the bounding box feature, the target urinary stone is determined based on the location information of the bounding box feature of each urinary stone, achieving accurate determination of the target urinary stone. The ablation distance of the target urinary stone is determined based on the first detection result, achieving accurate determination of the target urinary stone's ablation distance and providing accurate data support for subsequent analysis and processing. The output parameters of the stone ablation device are determined based on the composition type and ablation distance of the target urinary stone, solving the problem of inaccurate determination of the output parameters of the stone ablation device caused by manual determination, achieving automatic and accurate determination of the output parameters of the stone ablation device, and providing accurate data support for subsequent analysis and processing.

[0015] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1This is a flowchart of an image processing method for a urinary calculus scenario provided in Embodiment 1 of the present invention;

[0018] Figure 2 This is a flowchart of an image processing method for a urinary calculus scenario provided in Embodiment 2 of the present invention;

[0019] Figure 3 This is a flowchart of an image processing method for a urinary calculus scenario provided by an embodiment of the present invention;

[0020] Figure 4 This is a schematic diagram of the structure of a urinary stone ablation system provided in Embodiment 3 of the present invention;

[0021] Figure 5 This is a schematic diagram of the structure of an image processing device for a urinary calculus scenario provided in Embodiment 4 of the present invention;

[0022] Figure 6 This is a schematic diagram of the structure of an electronic device provided in Embodiment 5 of the present invention. Detailed Implementation

[0023] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0024] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0025] Example 1

[0026] Figure 1This is a flowchart of an image processing method for a urinary calculus scenario provided in Embodiment 1 of the present invention. This embodiment is applicable to situations where the output parameters of a urinary calculus ablation device are determined. This method can be executed by a urinary calculus ablation system, which can be implemented in hardware and / or software. Figure 1 As shown, the method includes:

[0027] S110. Obtain the first image to be detected in the target area.

[0028] The target area refers to the spatial extent of the urinary system and its surrounding anatomical structures. The target area can be selected based on actual needs and is not limited here. The first image to be detected is an image obtained by acquiring images of the urinary system using an image acquisition device. Image acquisition devices include, but are not limited to, endoscopes. The first image to be detected can be acquired in real-time by the image acquisition device or obtained from an image database. The image database can store images of different objects; by matching the object's unique identification information within the image database, the first data to be detected for that object can be obtained.

[0029] Specifically, the image database is matched based on the object's unique identification information to obtain the first data to be detected for the object, providing data support for subsequent analysis and processing, and ensuring that various tasks are executed efficiently and accurately.

[0030] S120. Classify and detect the first image to be detected based on the target detection model, and determine the first detection result.

[0031] The target detection model is a deep learning model used to classify and detect the first image to be detected. The target detection model includes, but is not limited to, the initial YOLO model and its variants; for example, the target detection model can be the YOLOv11 model. The first detection result is used to characterize whether urinary stones are present in the acquired image of the urinary system. For example, the first detection result can be that urinary stones are not present. Optionally, when urinary stones are detected in the first image to be detected, the first detection result can include at least one of the composition type of the urinary stone and the location information of the bounding box feature. Optionally, the first detection result is a detection image, which is determined by at least one of the following: marking the bounding box feature of the first image to be detected and identifying the composition. Since the target detection model processes image data, the corresponding first detection result can be a detection image. Specifically, the detection image can be obtained by marking the urinary stones in the first image to be detected with bounding box features; it can also be obtained by marking the composition type of the urinary stones. The composition types of urinary stones include, but are not limited to, calcium oxalate monohydrate, uric acid, calcium phosphate, cystine, and infection stones. The bounding box is the circumscribed polygon of a urinary calculus, including but not limited to quadrilaterals. Optionally, the smallest bounding rectangle of the urinary calculus can be used as the bounding box. Bounding box features describe the geometric properties of the bounding box. For example, bounding box features include, but are not limited to, the vertices of the bounding box. The positional information of the bounding box features includes, but is not limited to, the two-dimensional coordinates of multiple vertices of the bounding box in the first detection result. The first image to be detected is input into a trained object detection model for classification processing to obtain the first detection result.

[0032] Specifically, the first image to be detected is input into the trained target detection model for classification processing to obtain the first detection result, thus achieving accurate determination of the first detection result and providing accurate data support for subsequent analysis and processing.

[0033] S130. When the first detection result includes at least one of the composition type of at least one urinary stone and the corresponding probability information and the location information of the bounding box feature, the target urinary stone is determined based on the location information of the bounding box feature of each urinary stone.

[0034] Specifically, when the first detection result includes at least one of the following: the composition type of at least one urinary stone and the corresponding probability information and the location information of the bounding box feature, it indicates that a urinary stone exists in the target region corresponding to the first image to be detected. The probability information is data characterizing the composition type of the urinary stone. The target urinary stone is the urinary stone that needs to be ablated. The target urinary stone can be determined based on the location information of the bounding box feature of each urinary stone. When the first image to be detected includes one urinary stone, that urinary stone can be directly used as the target urinary stone; when the first image to be detected includes multiple urinary stones, the location information of the bounding box feature of each urinary stone can be input into a trained stone determination model for processing to obtain the target urinary stone among at least one urinary stone.

[0035] Specifically, by inputting the location information of the bounding box features of each urinary stone into the trained stone identification model for processing, the target urinary stone is identified from at least one urinary stone, thus achieving accurate identification of the target urinary stone.

[0036] Optionally, the target urinary stone is determined based on the location information of the bounding box features of each urinary stone, specifically including: for any urinary stone, determining the distance information of the urinary stone relative to a reference position based on the location information of the bounding box features of each urinary stone, and determining the area information based on the location information of the bounding box features; and determining the target urinary stone based on the distance information and area information of at least one urinary stone relative to the reference position.

[0037] The reference position includes, but is not limited to, the position of the origin of the coordinate system in the first detection result, and can be set according to requirements. Distance information represents the distance between the urinary stone and the reference position. Since the bounding box feature of each urinary stone can have multiple positional information, the sum of the distances between the multiple positional information of the bounding box feature of each urinary stone and the reference position can be calculated and used as the distance information of the urinary stone relative to the reference position. Area information represents the area of ​​the bounding box. The area information can be determined based on the positional information of the bounding box feature. Taking the minimum bounding rectangle of the urinary stone as an example, the length and width of the rectangle are determined based on the positional information of the bounding box feature, and the product of the length and width is calculated to obtain the area of ​​the rectangle, which is used as the area information. The target urinary stone can also be determined based on the distance information and area information of at least one urinary stone relative to the reference position. For example, the urinary stone corresponding to the minimum distance information and the maximum area information of at least one urinary stone relative to the reference position can be used as the target urinary stone.

[0038] Specifically, by calculating the sum of multiple location information of the bounding box features of each urinary stone and the distance between the reference position, the sum of the above distances is used as the distance information of the urinary stone relative to the reference position. The urinary stone corresponding to the minimum distance information and the maximum area information of at least one urinary stone relative to the reference position is selected as the target urinary stone, thus realizing the determination of the target urinary stone and providing accurate data support for subsequent analysis and processing.

[0039] In some embodiments of the present invention, there are cases where the urinary stones corresponding to the minimum distance information and the maximum area information are different urinary stones, and the urinary stone corresponding to the maximum area is taken as the target urinary stone.

[0040] Optionally, the first detection result also includes the confidence level corresponding to the bounding box of at least one urinary stone; before determining the target urinary stone based on the location and area information of the bounding box features of each urinary stone, the method further includes: filtering the first detection result based on the confidence level to obtain the filtered first detection result.

[0041] Here, confidence level represents the degree to which the object within the bounding box is a urinary calculus. The first detection result can be filtered based on confidence level. For example, a preset confidence threshold can be set. When the confidence level for urinary calculus is less than the preset threshold, it indicates that the object within the bounding box corresponding to that confidence level is not a urinary calculus, meaning the bounding box corresponding to that confidence level is not a urinary calculus. The bounding box corresponding to that confidence level can be removed from the first detection result, and only the first detection results with a confidence level greater than or equal to the preset confidence threshold are retained. For example, a confidence screening model can be used to screen the confidence of urinary stones. The confidence range of the confidence screening model can be [0,1], and the preset confidence threshold of the confidence screening model can be set to 0.75. The first detection result is input into the trained confidence screening model for screening. The first detection result corresponding to the confidence score less than 0.75 is removed, and the first detection result corresponding to the confidence score greater than or equal to 0.75 is retained. The confidence screening model includes, but is not limited to, algorithmic models and neural network models. For example, the algorithmic model can be the model corresponding to the Non-Maximum Suppression (NMS) algorithm.

[0042] Specifically, by filtering the first detection results based on confidence level, the first detection results with a confidence level greater than or equal to the preset confidence threshold are retained. This can reduce the interference of first detection results with a confidence level less than the preset confidence threshold, while also reducing the amount of data and improving processing speed.

[0043] Optionally, after determining the target urinary stone based on the location and area information of the bounding box features of each urinary stone, the image processing method for the urinary stone scene further includes: detecting the probability information corresponding to the component type of the target urinary stone to obtain a second detection result, wherein the second detection result is used to characterize whether the probability information corresponding to the component type of the target urinary stone is greater than or equal to a preset probability threshold.

[0044] The detection of probability information corresponding to the component type of the target urinary stone can be achieved by comparing this probability information with a preset probability threshold to determine whether the probability information is greater than or equal to the preset probability threshold. The preset probability threshold can be set to 0.95, and this invention does not impose any limitations on the setting of the preset probability threshold. The second detection result is information indicating whether the probability information corresponding to the component type of the target urinary stone is greater than or equal to the preset probability threshold. For example, the second detection result could be that the probability information corresponding to the component type of the target urinary stone is greater than or equal to the preset probability threshold. Another example is that the second detection result could be that the probability information corresponding to the component type of the target urinary stone is less than the preset probability threshold.

[0045] Specifically, the probability information corresponding to the composition type of the target urinary stone is compared with a preset probability threshold to obtain a second detection result, which provides data support for subsequent decision-making.

[0046] For example, the process of detecting the probability information corresponding to the component type of the target urinary stone is as follows: the probability detection range is set to [0,1], and the preset probability threshold is set to 0.95; the probability information corresponding to the component type of the target urinary stone is compared with the preset probability threshold; when the probability information corresponding to the component type of the target urinary stone is greater than or equal to the preset probability threshold, the second detection result is that the probability information corresponding to the component type of the target urinary stone is greater than or equal to the preset probability threshold; when the probability information corresponding to the component type of the target urinary stone is less than the preset probability threshold, the second detection result is that the probability information corresponding to the component type of the target urinary stone is less than the preset probability threshold.

[0047] In some embodiments of the present invention, when the first detection result does not include urinary stones, the target area is redefined, and a first image of the redefined target area is obtained.

[0048] When the first detection result does not include urinary stones, it indicates that the target area does not require urinary stone ablation, and the target area can be redefined. For example, multiple areas can be pre-set, each with a different priority, and the target area can be redefined according to the priority from high to low. After the target area is redefined, an image acquisition device is used to acquire images of the redefined target area, obtaining the first image to be detected for the redefined target area, until urinary stones are detected in the first image to be detected. When the first detection result does not include urinary stones, the target area is redefined, and the first image to be detected for the redefined target area is obtained, until urinary stones are detected in the first image to be detected. This process of redefining the target area and acquiring the first image to be detected provides data support for the identification of the target urinary stones.

[0049] S140. Determine the ablation distance of the target urinary stone based on the first detection result.

[0050] Here, the ablation distance represents the distance between the target urinary stone and the stone ablation device, including but not limited to the distance between the working end of the stone ablation device and the target urinary stone. The ablation distance can be determined based on the first detection result. For example, the location information of the bounding box feature of the target urinary stone in the first detection result can be input into a trained ablation distance determination model for processing to obtain the ablation distance of the target urinary stone. The ablation distance determination model includes, but is not limited to, mathematical models and neural network models, and is not limited here.

[0051] Specifically, by inputting the location information of the bounding box features of the target urinary calculus in the first detection result into the trained ablation distance determination model for processing, the ablation distance of the target urinary calculus is obtained, thus achieving accurate determination of the ablation distance of the target urinary calculus and providing accurate data support for subsequent analysis and processing.

[0052] S150. Determine the output parameters of the stone ablation device based on the composition type and ablation distance of the target urinary stone.

[0053] The stone ablation device is used to ablate urinary stones. Stone ablation devices include, but are not limited to, laser-type, ultrasonic-type, and pneumatic ballistic-type stone ablation devices; the appropriate device can be selected based on actual needs. This invention uses a laser-type stone ablation device as an example. Output parameters are the operating parameters of the stone ablation device. Output parameters include, but are not limited to, output power, output frequency, and pulse width. Optionally, this invention uses output power as the output parameter. The output parameters of the stone ablation device can be determined based on the composition type and ablation distance of the target urinary stone. For example, the composition type and ablation distance of the target urinary stone can be input into a trained processing model for processing to obtain the output parameters of the stone ablation device. The processing model includes, but is not limited to, mathematical models and neural network models. Alternatively, the output parameters can be obtained by matching the composition type and ablation distance of the target urinary stone in an output parameter lookup table. The output parameter lookup table can store the output parameters of stone ablation devices corresponding to different composition types and ablation distances.

[0054] Specifically, by inputting the composition type and ablation distance of the target urinary stone into a trained processing model, the output parameters of the stone ablation device are obtained. This enables the automatic and accurate determination of the output parameters of the stone ablation device, providing precise data support for subsequent analysis and processing.

[0055] Optionally, after determining the output parameters of the stone ablation device based on the composition type and ablation distance of the target urinary stone, the image processing method for the urinary stone scene further includes: when the confidence level of the target urinary stone is less than a preset probability threshold, sending the output parameters to the review end to obtain the review result.

[0056] The preset probability threshold is used to determine whether the output parameters need to be reviewed. The preset probability threshold can be set according to requirements; for example, it can be set to 0.95. The review result is the result of the reviewer reviewing the output parameters of the stone ablation device. The review result can be used to characterize the degree of compatibility between the output parameters of the stone ablation device and the target urinary stone. For example, a review result of "review passed" indicates that the output parameters of the stone ablation device are compatible with the target urinary stone.

[0057] Specifically, when the confidence level of the target urinary stone is less than the preset probability threshold, the output parameters are sent to the review end for review, and the review results are obtained, which is beneficial to the accuracy of the output parameters of the stone ablation device.

[0058] Optionally, after determining the output parameters of the stone ablation device based on the composition type and ablation distance of the target urinary stone, the image processing method for the urinary stone scene further includes: when the probability information corresponding to the composition type of the target urinary stone is greater than or equal to a preset probability threshold, transmitting the output parameters to the stone ablation device.

[0059] Specifically, when the probability information corresponding to the composition type of the target urinary stone is greater than or equal to the preset probability threshold, the output parameters can be transmitted to the stone ablation device. The stone ablation device can then ablate the target urinary stone according to the transmitted output parameters, thus realizing the automatic transmission of output parameters and providing accurate data support for the ablation of the target urinary stone.

[0060] The technical solution of this embodiment acquires a first image of the target area to be detected, providing data support for subsequent analysis and processing, ensuring that various tasks are executed efficiently and accurately; classifies and detects the first image based on a target detection model to determine the first detection result, achieving accurate determination of the first detection result and providing accurate data support for subsequent analysis and processing; when the first detection result includes at least one of the composition type of at least one urinary stone and the location information of the bounding box feature, the target urinary stone is determined based on the location information of the bounding box feature of each urinary stone, achieving accurate determination of the target urinary stone; the ablation distance of the target urinary stone is determined based on the first detection result, achieving accurate determination of the target urinary stone ablation distance and providing accurate data support for subsequent analysis and processing; the output parameters of the stone ablation device are determined based on the composition type and ablation distance of the target urinary stone, achieving automatic and accurate determination of the output parameters of the stone ablation device, providing accurate data support for subsequent analysis and processing.

[0061] Example 2

[0062] Figure 2 This is a flowchart of an image processing method for a urinary calculus scene provided in Embodiment 2 of the present invention. This embodiment is a refinement of the above embodiments. Based on the foregoing embodiments, it provides a detailed explanation of determining the ablation distance of the target urinary calculus based on the first detection result. For specific implementation details, please refer to the technical solution of this embodiment. Technical terms that are the same as or corresponding to those in the above embodiments will not be repeated here. Figure 2 As shown, the method includes:

[0063] S210. Obtain the first image to be detected in the target area.

[0064] S220. Classify and detect the first image to be detected based on the target detection model, and determine the first detection result.

[0065] S230. When the first detection result includes at least one of the composition type of at least one urinary stone and the corresponding probability information and the location information of the bounding box feature, the target urinary stone is determined based on the location information of the bounding box feature of each urinary stone.

[0066] S240. Obtain ablation depth data of the target urinary calculus, including a preset minimum ablation distance and a preset maximum ablation distance; perform depth detection on the detection image marked with bounding box features based on the depth estimation model to obtain a relative depth image, which includes first relative depth information corresponding to multiple pixels in the detection image; determine the weight information of the ablation depth data based on the first relative depth information corresponding to a preset number of pixels; determine the ablation distance based on the ablation depth data and the weight information of the ablation depth data.

[0067] The ablation depth data consists of a pre-set distance range used to constrain the range of ablation distance values. The ablation depth data includes a preset minimum ablation distance and a preset maximum ablation distance. These preset minimum and maximum ablation distances can be set according to actual needs; for example, the preset minimum ablation distance can be set to 0.2 mm, and the preset maximum ablation distance can be set to 0.6 mm. The depth estimation model is a model for depth detection on detection images marked with bounding box features. The depth estimation model includes, but is not limited to, convolutional neural network models and their variants. The relative depth image is an image describing the distance between a pixel and a reference point. The relative depth image can be a grayscale image. The greater the distance between a pixel and a reference point, the greater the grayscale value of that pixel; conversely, the smaller the distance, the smaller the grayscale value. First relative depth information characterizes the distance between a pixel and a reference point. Weight information characterizes the importance of the distance between a pixel and a reference point. The weight information can be determined based on the first relative depth information corresponding to a preset number of pixels. For example, the center of the smallest bounding rectangle of the target urinary calculus in the relative depth image is determined, and multiple pixels within a 9×9 area centered on the center of the smallest bounding rectangle are identified. The pixel mean of the first relative depth information corresponding to these pixels is used as the weight information of the ablation depth data. The ablation distance can also be determined based on the ablation depth data and its weight information. For example, the ablation depth data and its weight information can be input into a trained ablation distance determination model for processing to obtain the ablation distance of the target urinary calculus. The ablation distance determination model includes, but is not limited to, mathematical models and neural network models.

[0068] Specifically, the preset minimum and maximum ablation distances of the target urinary calculus are obtained. The detection image marked with bounding box features is input into the depth estimation model for depth detection, resulting in a relative depth image that includes first relative depth information corresponding to multiple pixels in the detection image. The center of the minimum bounding rectangle of the target urinary calculus in the relative depth image is determined, and multiple pixels within a 9×9 range centered on the center of the minimum bounding rectangle are determined. The pixel mean of the first relative depth information corresponding to the above pixels is used as the weight information of the ablation depth data. The ablation depth data and the weight information of the ablation depth data are input into the trained ablation distance determination model for processing to obtain the ablation distance of the target urinary calculus. This achieves accurate determination of the ablation distance of the target urinary calculus and provides accurate data support for determining the output parameters of the stone ablation device.

[0069] In some embodiments of the present invention, a relative depth image can also be obtained by downsampling the first image to be detected and inputting the downsampled first image to be detected into a depth estimation model for depth detection.

[0070] For example, the formula for calculating the ablation distance is as follows:

[0071] ;

[0072] in, Indicates the ablation distance of the target urinary stone; Indicates the preset minimum ablation distance; This indicates the weighting information for the ablation depth data; This indicates the preset maximum ablation distance.

[0073] S250. Determine the output parameters of the stone ablation device based on the composition type and ablation distance of the target urinary stone.

[0074] The greater the ablation distance of urinary stones, the greater the energy loss of the stone ablation equipment during the stone ablation process. Therefore, the output power of the stone ablation equipment can be compensated.

[0075] Optionally, the output parameters of the stone ablation device are determined based on the composition type and ablation distance of the target urinary stone, including: determining the expected output power of the stone ablation device based on the composition type of the target urinary stone; determining the power compensation coefficient based on the ablation distance of the target urinary stone; and determining the output power of the stone ablation device based on the expected output power and the power compensation coefficient.

[0076] The expected output power is the pre-set basic energy output of the stone ablation device. For example, the expected output power can be the output power of the target urinary stone and the ablation device's working end at a preset minimum ablation distance. Different urinary stone composition types correspond to different expected output powers. For example, see Table 1, which is a comparison table of the composition types of urinary stones and expected output powers provided in this embodiment of the invention. The power compensation coefficient is used to dynamically adjust the output power of the stone ablation device, ensuring that the adjusted output power can ablate the stone without damaging surrounding body tissues. The power compensation coefficient can be determined based on the ablation distance of the target urinary stone. For example, the power compensation coefficient is obtained by looking up the ablation distance in the ablation distance-power compensation coefficient comparison table. For example, see Table 2, which is a comparison table of partial ablation distances and power compensation coefficients provided in this embodiment of the invention. The output power of the stone ablation device can be determined based on the expected output power and the power compensation coefficient. For example, the product between the expected output power and the power compensation coefficient can be calculated, and this product can be used as the output power of the stone ablation device.

[0077] Table 1

[0078]

[0079] Table 2

[0080]

[0081] Specifically, based on the composition type of the target urinary stone, the expected output power of the stone ablation device is determined by referring to a table of urinary stone composition types and expected output power. Based on the ablation distance of the target urinary stone, the power compensation coefficient is determined by referring to a table of ablation distance and power compensation coefficient. The product between the expected output power and the power compensation coefficient is calculated, and this product is taken as the output power of the stone ablation device. This achieves accurate determination of the output power of the stone ablation device, providing precise data support for subsequent analysis and processing.

[0082] Optionally, the image processing method for the urinary calculus scenario further includes: acquiring multiple frames of ablation images generated during the ablation process of the target urinary calculus by the stone ablation device based on the output parameters; determining the component type and second relative depth information corresponding to each frame of ablation image; determining the ablation result based on the component type corresponding to the last frame of ablation image and the component type corresponding to the non-last frame of ablation image in the multiple frames of ablation images, wherein the ablation result characterizes the degree of state change of the target urinary calculus before and after the ablation process; and, if the ablation result meets the set conditions, re-acquiring the second image to be detected after ablation processing, and re-determining the output parameters of the stone ablation device based on the second image to be detected.

[0083] The ablation image refers to the image of the target urinary stone during the ablation process using a stone ablation device. The ablation result characterizes the degree of change in the state of the target urinary stone before and after the ablation process. The ablation result can be determined based on the component type corresponding to the last ablation image and the component types corresponding to each non-last ablation image. For example, if the component type corresponding to the last ablation image and the component type corresponding to each non-last ablation image are different, it indicates that the state of the target urinary stone has changed, and the output parameters of the stone ablation device cannot ablate the target urinary stone, requiring a re-determination of the output parameters of the stone ablation device. The second image to be detected is the image of the target urinary stone after ablation. The second image to be detected can be acquired by an image acquisition device, including but not limited to an endoscope.

[0084] It should be noted that the process of re-determining the output parameters of the stone ablation device based on the second image to be detected is as follows: The second image to be detected is classified and detected based on the target detection model to determine the first detection result, which includes at least one of the composition type and bounding box feature location information for each urinary stone; a new target urinary stone is determined based on the location information of the bounding box feature of each urinary stone; the ablation distance of the new target urinary stone is determined based on the first detection result; and the output parameters of the stone ablation device are re-determined based on the composition type and ablation distance of the new target urinary stone.

[0085] It should also be noted that the process of re-determining the output parameters of the stone ablation device based on the second image to be detected is the same as the process of re-determining the output parameters of the stone ablation device based on the first image to be detected.

[0086] Specifically, multiple ablation images of the target urinary tract stone are acquired via endoscopy during the ablation process using a stone ablation device. Each ablation image is then classified and detected using a target detection model to determine the component type corresponding to each image. When the component type corresponding to the last ablation image differs from that of any of the subsequent ablation images, a second image is acquired after ablation processing. The output parameters of the stone ablation device are then redefined based on this second image, providing accurate data support for subsequent analysis and processing.

[0087] Optionally, the image processing method for the urinary calculus scenario further includes: acquiring multiple frames of ablation images generated during the ablation process of the target urinary calculus by the stone ablation device based on the output parameters; determining the component type and second relative depth information corresponding to each frame of ablation image; determining the ablation result based on the second relative depth information corresponding to the last frame of ablation image and the second relative depth information corresponding to the non-last frame of ablation image in the multiple frames of ablation images, wherein the ablation result characterizes the degree of state change of the target urinary calculus before and after the ablation process; and, if the ablation result meets the set conditions, re-acquiring the second image to be detected after ablation processing, and re-determining the output parameters of the stone ablation device based on the second image to be detected.

[0088] The second relative depth information is the distance between a pixel and a reference point in the image representing the ablated target urinary stone. This second relative depth information can be determined from the ablation image. For example, the second relative depth information can be obtained by inputting the ablation image into a depth estimation model. The ablation result can also be determined based on the second relative depth information corresponding to each frame of the ablation image. For example, the offset between the relative depth information corresponding to the last frame of the ablation image and the relative depth information corresponding to each non-last frame of the ablation image is calculated. When the offset between the relative depth information corresponding to the last frame of the ablation image and the relative depth information corresponding to each non-last frame of the ablation image exceeds a preset relative depth threshold, it indicates that the state of the target urinary stone has changed, and the output parameters of the stone ablation device are insufficient to ablate the target urinary stone, requiring a re-determination of the output parameters of the stone ablation device.

[0089] Specifically, multiple frames of ablation images of the target urinary tract stone are acquired using an endoscope during the ablation process. Depth detection is performed on each frame of the ablation image based on a depth estimation model to determine the second relative depth information corresponding to each frame. The offset between the second relative depth information corresponding to the last frame and the second relative depth information corresponding to each non-last frame is calculated. When the offset exceeds a preset relative depth threshold, a second image to be detected after ablation is acquired. The output parameters of the stone ablation device are re-determined based on the second image to be detected, providing accurate data support for subsequent analysis and processing.

[0090] Optionally, the image processing method for the urinary calculus scenario further includes: acquiring multiple frames of ablation images generated during the ablation process of the target urinary calculus by the stone ablation device based on the output parameters; determining the component type and second relative depth information corresponding to each frame of ablation image; determining the ablation result based on the component type corresponding to the last frame of ablation image and the component type corresponding to the non-last frame of ablation image in the multiple frames of ablation images; and determining the ablation result based on the second relative depth information corresponding to the last frame of ablation image and the second relative depth information corresponding to the non-last frame of ablation image in the multiple frames of ablation images, wherein the ablation result characterizes the degree of state change of the target urinary calculus before and after the ablation process; and, if the ablation result meets the set conditions, re-acquiring the second image to be detected after ablation processing, and re-determining the output parameters of the stone ablation device based on the second image to be detected.

[0091] Specifically, multiple frames of ablation images of the target urinary tract stone are acquired via endoscopy during the ablation process using a stone ablation device. Each frame is classified and detected using a target detection model to determine the component type corresponding to each frame. Depth detection is performed on each frame using a depth estimation model to determine the second relative depth information corresponding to each frame. The offset between the second relative depth information corresponding to the last frame and the second relative depth information corresponding to each non-last frame is calculated. When the component type corresponding to the last frame and the component type corresponding to each non-last frame are different, and when the offset between the second relative depth information corresponding to the last frame and the second relative depth information corresponding to each non-last frame exceeds a preset relative depth threshold, a second image to be detected after ablation is re-acquired. The output parameters of the stone ablation device are re-determined based on the second image to be detected, thus providing accurate data support for subsequent analysis and processing. For example, see [link to example]. Figure 3 , Figure 3 This is a flowchart of an image processing method for a urinary calculus scenario provided by an embodiment of the present invention.

[0092] The technical solution of this embodiment acquires a first image of the target area to be detected, providing data support for subsequent analysis and processing, ensuring that various tasks are executed efficiently and accurately; it classifies and detects the first image based on a target detection model to determine the first detection result, achieving accurate determination of the first detection result and providing accurate data support for subsequent analysis and processing; when the first detection result includes at least one of the composition type of at least one urinary stone and the location information of the bounding box feature, the target urinary stone is determined based on the location information of the bounding box feature of each urinary stone, achieving accurate determination of the target urinary stone; it acquires ablation depth data of the target urinary stone, including a preset minimum ablation distance and a preset maximum ablation distance. This paper describes a method for determining the ablation depth of a target urinary calculus. The method involves using a depth estimation model to perform depth detection on the detected image marked with bounding box features, resulting in a relative depth image. This image includes first relative depth information corresponding to multiple pixels in the detected image. Weights for the ablation depth data are determined based on a preset number of pixels and their weights. This method accurately determines the ablation distance for the target urinary calculus, providing accurate data support for determining the output parameters of the ablation device. Furthermore, the method determines the output parameters of the ablation device based on the composition and ablation distance of the target urinary calculus, enabling automatic and accurate determination of these parameters and providing precise data support for subsequent analysis and processing.

[0093] Example 3

[0094] Figure 4 This is a schematic diagram of a urinary stone ablation system provided in Embodiment 3 of the present invention. Figure 4 As shown, the urinary stone ablation system includes an endoscope 310, a processing unit 320, and a stone ablation device 330.

[0095] The endoscope 310 is used to acquire a first image to be detected of the target area and transmit the first image to be detected to the processing unit 320. The processing unit 320 is used to classify and detect the first image to be detected based on the target detection model and determine a first detection result. When the first detection result includes at least one of the composition type of at least one urinary stone and the corresponding probability information and the location information of the bounding box feature, the target urinary stone is determined based on the location information of the bounding box feature of each urinary stone. The ablation distance of the target urinary stone is determined based on the first detection result. The output parameters of the stone ablation device are determined based on the composition type and ablation distance of the target urinary stone. An ablation command is sent to the stone ablation device 330 based on the output parameters. The stone ablation device 330 is used to perform ablation treatment on the target urinary stone in response to the ablation command.

[0096] Optionally, the processing unit 320 is further configured to: generate an image re-acquisition command when the first detection result does not include urinary stones, and transmit the image re-acquisition command to the endoscope 310; the endoscope 310 is further configured to: acquire a first image to be detected of the redefined target area in response to the image re-acquisition command.

[0097] Optionally, the processing unit 320 is further configured to: for any urinary stone, determine the distance information of the urinary stone relative to a reference position based on the position information of the bounding box features of each urinary stone, and determine the area information based on the position information of the bounding box features; and determine a target urinary stone based on the distance information and area information of at least one urinary stone relative to the reference position.

[0098] Optionally, the first detection result also includes the confidence level of each urinary stone; the processing unit 320 is further configured to: filter the first detection result based on the confidence level before determining the target urinary stone based on the location information and area information of the bounding box features of each urinary stone, and obtain the filtered first detection result.

[0099] Optionally, the processing unit 320 is further configured to: after determining the target urinary stone based on the location information and area information of the bounding box features of each urinary stone, detect the probability information corresponding to the component type of the target urinary stone to obtain a second detection result, the second detection result being used to characterize whether the probability information corresponding to the component type of the target urinary stone is greater than or equal to a preset probability threshold.

[0100] Optionally, the urinary stone ablation system also includes a review unit; the processing unit 320 is further configured to: after determining the output parameters of the stone ablation device based on the composition type and ablation distance of the target urinary stone, when the probability information corresponding to the composition type of the target urinary stone is less than a preset probability threshold, send the output parameters to the review unit; the review unit is specifically configured to: review the output parameters and obtain the review result.

[0101] Optionally, the processing unit 320 is further configured to: send an ablation command to the stone ablation device 330 based on the output parameters when the probability information corresponding to the composition type of the target urinary stone is greater than or equal to a preset probability threshold; the stone ablation device 330 is configured to perform ablation treatment on the target urinary stone in response to the ablation command.

[0102] Optionally, the first detection result is a detection image, which is determined by at least one of marking bounding box features and identifying component classification on the first image to be detected.

[0103] Optionally, the processing unit 320 is further configured to: acquire ablation depth data of the target urinary calculus, the ablation depth data including a preset minimum ablation distance and a preset maximum ablation distance; perform depth detection on the detection image marked with bounding box features based on a depth estimation model to obtain a relative depth image, the relative depth image including first relative depth information corresponding to multiple pixels in the detection image; determine weight information of the ablation depth data based on the first relative depth information corresponding to a preset number of pixels; and determine the ablation distance based on the ablation depth data and the weight information of the ablation depth data.

[0104] Optionally, the endoscope 310 is further configured to acquire multiple frames of ablation images generated during the ablation process of the stone ablation device on the target urinary stone based on the output parameters, and send the multiple frames of ablation images to the processing unit 320; the processing unit 320 is further configured to: determine the component type and second relative depth information corresponding to each frame of ablation image respectively, determine the ablation result based on the component type corresponding to the last frame of ablation image and the component type corresponding to the non-last frame of ablation image in the multiple frames of ablation images, and / or, determine the ablation result based on the relative depth information corresponding to the last frame of ablation image and the relative depth information corresponding to the non-last frame of ablation image in the multiple frames of ablation images, the ablation result characterizing the degree of state change of the target urinary stone before and after the ablation process; if the ablation result meets the set conditions, generate a re-acquisition command and send the re-acquisition command to the endoscope 310; the endoscope 310 is further configured to: re-acquire the second image to be detected after ablation processing and send the second image to be detected to the processing unit 320; the processing unit 320 is further configured to: re-determine the output parameters of the stone ablation device based on the second image to be detected.

[0105] Optionally, the output parameters include output power; the processing unit 320 is also used to: determine the expected output power of the stone ablation device based on the composition type of the target urinary stone; determine the power compensation coefficient based on the ablation distance of the target urinary stone; and determine the output power of the stone ablation device based on the expected output power and the power compensation coefficient.

[0106] The technical solution of this embodiment is a urinary stone ablation system, including an endoscope, a processing unit, and a stone ablation device. The endoscope acquires a first image of the target area to be detected and transmits it to the processing unit, providing data support for subsequent analysis and processing, ensuring efficient and accurate execution of various tasks. The processing unit classifies and detects the first image based on a target detection model to determine a first detection result, achieving accurate determination of the first detection result and providing accurate data support for subsequent analysis and processing. When the first detection result includes at least one of the following: the composition type of at least one urinary stone and its corresponding probability information and the location information of the bounding box feature, the system further classifies the image based on the location information of the bounding box feature of each urinary stone. The system accurately identifies the target urinary calculus; it determines the ablation distance of the target urinary calculus based on the initial detection results, providing accurate data support for subsequent analysis and processing; it automatically and accurately determines the output parameters of the stone ablation device based on the composition and ablation distance of the target urinary calculus; it sends ablation commands to the stone ablation device based on the output parameters; and the stone ablation device responds to the ablation commands to perform ablation treatment on the target urinary calculus. This solves the problem of inaccurate output parameter determination caused by manual determination of the stone ablation device's output parameters, achieving precise ablation of urinary calculi.

[0107] Example 4

[0108] Figure 5 This is a schematic diagram of the structure of an image processing device for a urinary calculus scenario provided in Embodiment 4 of the present invention. Figure 5 As shown, the image processing device for the urinary calculus scenario includes a first image acquisition module 410, a first detection result determination module 420, a target urinary calculus determination module 430, an ablation distance determination module 440, and an output parameter determination module 450.

[0109] The system includes: a first image acquisition module for acquiring a first image of the target region; a first detection result determination module for classifying and detecting the first image based on a target detection model to determine a first detection result; a target urinary stone determination module for determining a target urinary stone based on the location information of the bounding box features of each urinary stone when the first detection result includes at least one of the following: the composition type of at least one urinary stone and its corresponding probability information and the location information of the bounding box feature; an ablation distance determination module for determining the ablation distance of the target urinary stone based on the first detection result; and an output parameter determination module for determining the output parameters of the stone ablation device based on the composition type and ablation distance of the target urinary stone.

[0110] The technical solution of this embodiment acquires a first image of the target region through a first image acquisition module, providing data support for subsequent analysis and processing, and ensuring that various tasks are executed efficiently and accurately. A first detection result determination module classifies and detects the first image based on a target detection model, determining the first detection result and achieving accurate determination of the first detection result, providing accurate data support for subsequent analysis and processing. A target urinary stone determination module, when the first detection result includes at least one of the composition type of at least one urinary stone and the location information of its bounding box features, determines the target urinary stone based on the location information of the bounding box features of each urinary stone. The system accurately identifies the target urinary calculus. The ablation distance determination module, based on the initial detection results, determines the ablation distance of the target urinary calculus, providing accurate data support for subsequent analysis and processing. The output parameter determination module, based on the composition and ablation distance of the target urinary calculus, determines the output parameters of the stone ablation device. This solves the problem of inaccurate output parameter determination caused by manual determination, achieving automatic and accurate determination of the device's output parameters and providing precise data support for subsequent analysis and processing.

[0111] Based on the above embodiments, optionally, the target urinary stone determination module 430 is further configured to: for any urinary stone, determine the distance information of the urinary stone relative to the reference position based on the position information of the bounding box feature of each urinary stone, and determine the area information based on the position information of the bounding box feature; and determine the target urinary stone based on the distance information and area information of at least one urinary stone relative to the reference position.

[0112] Optionally, the first detection result also includes the confidence level of each urinary stone; the first detection result determination module 420 is further configured to: after determining the target urinary stone based on the location information and area information of the bounding box features of each urinary stone, detect the probability information corresponding to the component type of the target urinary stone to obtain a second detection result, the second detection result being used to characterize whether the probability information corresponding to the component type of the target urinary stone is greater than or equal to a preset probability threshold.

[0113] Optionally, the output parameter determination module 450 is also used to: after determining the output parameters of the stone ablation device based on the composition type and ablation distance of the target urinary stone, when the probability information corresponding to the composition type of the target urinary stone is less than a preset probability threshold, send the output parameters to the review end to obtain the review result.

[0114] Optionally, the output parameter determination module 450 is also used to: after determining the output parameters of the stone ablation device based on the composition type and ablation distance of the target urinary stone, transmit the output parameters to the stone ablation device when the probability information corresponding to the composition type of the target urinary stone is greater than or equal to a preset probability threshold.

[0115] Optionally, the first detection result is a detection image, which is determined by at least one of marking bounding box features and identifying component classification on the first image to be detected.

[0116] Optionally, the ablation distance determination module 440 is further configured to: acquire ablation depth data of the target urinary calculus, the ablation depth data including a preset minimum ablation distance and a preset maximum ablation distance; perform depth detection on the detection image marked with bounding box features based on a depth estimation model to obtain a relative depth image, the relative depth image including first relative depth information corresponding to multiple pixels in the detection image; determine weight information of the ablation depth data based on the first relative depth information corresponding to a preset number of pixels; and determine the ablation distance based on the ablation depth data and the weight information of the ablation depth data.

[0117] Optionally, the device further includes an output parameter re-determination module, used for: acquiring multiple frames of ablation images generated during the ablation process of the stone ablation device on the target urinary stone based on the output parameters; determining the component type and second relative depth information corresponding to each frame of ablation image; determining the ablation result based on the component type corresponding to the last frame of ablation image and the component type corresponding to the non-last frame of ablation image in the multiple frames of ablation images, and / or, determining the ablation result based on the relative depth information corresponding to the last frame of ablation image and the relative depth information corresponding to the non-last frame of ablation image in the multiple frames of ablation images; the ablation result characterizes the degree of state change of the target urinary stone before and after the ablation process; and, if the ablation result meets the set conditions, re-acquiring the second image to be detected after ablation processing, and re-determining the output parameters of the stone ablation device based on the second image to be detected.

[0118] Optionally, the output parameters include the output power; the output parameter determination module 450 is also used to: determine the expected output power of the stone ablation device based on the composition type of the target urinary stone; determine the power compensation coefficient based on the ablation distance of the target urinary stone; and determine the output power of the stone ablation device based on the expected output power and the power compensation coefficient.

[0119] Optionally, the image processing device for the urinary calculus scenario further includes an image re-acquisition module, used to: when the first detection result does not include urinary calculus, redetermine the target area and acquire a first image to be detected of the redetermined target area.

[0120] The image processing device for urinary calculi scenes provided in the embodiments of the present invention can execute an image processing method for urinary calculi scenes provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the method.

[0121] Example 5

[0122] Figure 6 This is a schematic diagram of the structure of an electronic device provided in Embodiment 5 of the present invention. The electronic device 10 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0123] like Figure 6 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 may also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0124] Multiple components in electronic device 10 are connected to input / output (I / O) interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of monitors, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0125] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as an image processing method for a urinary calculi scenario.

[0126] In some embodiments, an image processing method for a urinary calculus scene can be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on electronic device 10 via read-only memory (ROM) 12 and / or communication unit 19. When the computer program is loaded into random access memory (RAM) 13 and executed by processor 11, one or more steps of the image processing method for a urinary calculus scene described above can be performed. Alternatively, in other embodiments, processor 11 can be configured to perform an image processing method for a urinary calculus scene by any other suitable means (e.g., by means of firmware).

[0127] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transferring data and instructions to the storage system, the at least one input device, and the at least one output device.

[0128] A computer program for implementing an image processing method for a urinary calculus scenario according to the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The computer program can be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0129] Example 6

[0130] Embodiment 6 of the present invention also provides a computer-readable storage medium storing computer instructions for causing a processor to execute an image processing method for a urinary calculus scene, the method comprising:

[0131] Acquire a first image of the target region to be detected; classify and detect the first image based on the target detection model to determine a first detection result; when the first detection result includes at least one of the composition type of at least one urinary stone and its corresponding probability information and the location information of the bounding box feature, determine the target urinary stone based on the location information of the bounding box feature of each urinary stone; determine the ablation distance of the target urinary stone based on the first detection result; determine the output parameters of the stone ablation device based on the composition type and ablation distance of the target urinary stone.

[0132] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0133] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0134] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0135] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0136] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0137] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. An image processing method of a urinary stone scene, characterized by, The method comprises: acquiring a first to-be-detected image of a target region; performing classification detection on the first to-be-detected image based on a target detection model to determine a first detection result; when the first detection result comprises at least one of component type and corresponding probability information of a urinary calculus and position information of a bounding box feature, determining a target urinary calculus based on the position information of the bounding box feature of each urinary calculus; determining an ablation distance of the target urinary calculus based on the first detection result; determining an output parameter of a calculus ablation device based on the component type of the target urinary calculus and the ablation distance.

2. The method of claim 1, wherein, The determination of the target urinary calculus based on the position information of the bounding box feature of each urinary calculus comprises: for any urinary calculus, determining distance information of the urinary calculus relative to a reference position based on the position information of the bounding box feature of each urinary calculus, and determining area information based on the position information of the bounding box feature; determining the target urinary calculus based on the distance information and the area information of the at least one urinary calculus relative to the reference position respectively.

3. The method of claim 2, wherein, The first detection result further comprises confidence of the bounding box corresponding to at least one of the urinary calculi; Before determining the target urinary calculus based on the position information of the bounding box feature of each urinary calculus and the area information, the method further comprises: screening the first detection result based on the confidence to obtain a screened first detection result.

4. The method of claim 2, wherein, After determining the target urinary calculus based on the position information of the bounding box feature of each urinary calculus and the area information, the method further comprises: detecting the probability information corresponding to the component type of the target urinary calculus to obtain a second detection result, wherein the second detection result is used to represent whether the probability information corresponding to the component type of the target urinary calculus is greater than or equal to a preset probability threshold.

5. The method of claim 4, wherein, After determining the output parameter of the calculus ablation device based on the component type of the target urinary calculus and the ablation distance, the method further comprises: when the probability information of the target urinary calculus is less than the preset probability threshold, transmitting the output parameter to a review end to obtain a review result.

6. The method of claim 4, wherein, After determining the output parameter of the calculus ablation device based on the component type of the target urinary calculus and the ablation distance, the method further comprises: when the probability information of the target urinary calculus is greater than or equal to the preset probability threshold, transmitting the output parameter to the calculus ablation device.

7. The method of claim 1, wherein, The first detection result is a detection image, and the detection image comprises at least one of the bounding box feature marking and the component classification identification determined by the first to-be-detected image.

8. The method of claim 7, wherein, The determination of the ablation distance of the target urinary calculus based on the first detection result comprises: acquiring ablation depth data of the target urinary calculus, wherein the ablation depth data comprises a preset minimum ablation distance and a preset maximum ablation distance; performing depth detection on the detection image marked with the bounding box feature based on a depth estimation model to obtain a relative depth image, wherein the relative depth image comprises first relative depth information corresponding to a plurality of pixel points in the detection image respectively; determine weight information of the ablation depth data based on first relative depth information corresponding to a preset number of pixel points; determine the ablation distance based on the ablation depth data and the weight information of the ablation depth data.

9. The method of claim 7, wherein, The method further comprises: acquire a plurality of ablation images generated in an ablation process of the target urinary calculus by the calculus ablation device based on the output parameter; determine a component type and second relative depth information corresponding to each of the ablation images, respectively; determine an ablation result based on the component type corresponding to the last one of the ablation images and the component type corresponding to the non-last one of the ablation images, and / or determine the ablation result based on the second relative depth information corresponding to the last one of the ablation images and the second relative depth information corresponding to the non-last one of the ablation images, the ablation result representing a state change degree of the target urinary calculus before and after the ablation process; in a case where the ablation result meets a set condition, re-acquire a second to-be-detected image after the ablation treatment, and re-determine the output parameter of the calculus ablation device based on the second to-be-detected image.

10. The method of claim 1, wherein, The output parameter comprises an output power; The determination of the output parameter of the calculus ablation device based on the component type of the target urinary calculus and the ablation distance comprises: determining an expected output power of the calculus ablation device based on the component type of the target urinary calculus; determining a power compensation coefficient based on the ablation distance of the target urinary calculus; determining an output power of the calculus ablation device based on the expected output power and the power compensation coefficient.

11. The method of claim 1, wherein, The method further comprises: when the first detection result does not include the urinary calculus, re-determine the target region, and acquire a first to-be-detected image of the re-determined target region.

12. A urinary stone ablation system, comprising: comprise an endoscope, a processing unit, and a calculus ablation device; the endoscope is configured to acquire a first to-be-detected image and transmit the first to-be-detected image to the processing unit; the processing unit is configured to perform classification detection on the first to-be-detected image based on a target detection model, determine a first detection result, determine a target urinary calculus based on at least one of probability information corresponding to a component type of at least one urinary calculus and position information of a bounding box feature when the first detection result includes the at least one, determine an ablation distance of the target urinary calculus based on the first detection result, and determine an output parameter of the calculus ablation device based on the component type of the target urinary calculus and the ablation distance; send an ablation instruction to the calculus ablation device based on the output parameter; the calculus ablation device is configured to perform ablation treatment on the target urinary calculus in response to the ablation instruction.

13. The system of claim 12, wherein, the processing unit is further configured to generate an image re-acquisition instruction and transmit the image re-acquisition instruction to the endoscope when the first detection result does not include the urinary calculus; the endoscope is further configured to acquire a first to-be-detected image of a re-determined target region in response to the image re-acquisition instruction.

Images