Percutaneous nephrolithotripsy navigation control system and method

Abstract

The embodiment of the invention provides a navigation control system and method for percutaneous nephrolithotripsy. The method is executed by a processor and comprises the following steps: acquiring an intraoperative real-time X-ray image, a preoperative CT image and an intraoperative real-time ultrasonic image; based on the intraoperative real-time X-ray image and the preoperative CT image, obtaining fused image data; based on the intraoperative real-time ultrasonic image, correcting the fused image data, and determining target image data; based on the target image data, the real-time position of the puncture needle is determined, auxiliary navigation information and recommended navigation parameters are generated, and the target image data, the auxiliary navigation information and the recommended navigation parameters are sent to an interaction screen. The system comprises an image acquisition module, an image processing module, a control module and an interactive screen. The image acquisition module comprises at least one of an X-ray imaging acquisition module, a CT image acquisition module and an ultrasonic image acquisition module. The method is operated after a computer instruction stored in a computer readable storage medium is read.

Description

Technical Field

[0001] The present invention relates to the technical field of percutaneous nephrolithotomy, and in particular to a navigation control system and method for percutaneous nephrolithotomy. Background Art

[0002] Percutaneous nephrolithotomy (PCNL) is a surgical method that creates an artificial channel from the skin to the renal collecting system, inserts an endoscope and lithotripsy and stone removal instruments through the channel, and clears stones in the renal collecting system and (or) ureter. In the treatment of upper urinary tract stones, PCNL, together with ureteroscopic lithotripsy and extracorporeal shock wave lithotripsy, has become the main modern treatment method, which has completely changed the traditional open surgical treatment of upper urinary tract stones. Through comprehensive treatment methods such as percutaneous nephrolithotomy, ureteroscopic lithotripsy and extracorporeal shock wave lithotripsy, more than 90% of kidney stones can be exempted from open surgery.

[0003] Bleeding is one of the most common complications of percutaneous nephrolithotomy. Bleeding can occur during puncture, channel establishment, and the entire process of surgery. For example, improper selection of puncture points and angles, deviation from the original puncture path during channel expansion, and laser burning of the renal pelvis and calyces may all lead to intraoperative bleeding. How to prevent the puncture needle from accidentally touching the blood vessels and causing bleeding in patients, and then reasonably avoid potential bleeding risks, has become an issue that needs to be solved urgently.

[0004] Therefore, it is necessary to propose a navigation control system and method for percutaneous nephrolithotomy, which can improve the accuracy of kidney stone positioning and reduce the risk of bleeding without increasing CT or X-ray radiation through reasonable medical image processing. Summary of the invention

[0005] One or more embodiments of the present specification provide a navigation control system for percutaneous nephrolithotomy, the system comprising: an image acquisition module, an image processing module, a control module, and an interactive screen, wherein the image processing module and the control module are integrated in a processor. The image acquisition module comprises at least one of an X-ray imaging acquisition module, a CT image acquisition module, and an ultrasound image acquisition module; the image acquisition module is configured to: acquire intraoperative real-time X-ray images based on the X-ray imaging acquisition module, the intraoperative real-time X-ray images comprising image data after imaging kidney stones and puncture needles; acquire preoperative CT images based on the CT image acquisition module, the preoperative CT images comprising image data after imaging kidney stones and blood vessels and kidney tissues; and acquire intraoperative real-time ultrasound images based on the ultrasound image acquisition module, the intraoperative real-time ultrasound images comprising image data after imaging kidney stones, puncture needles, renal collecting systems, and organs surrounding the kidneys. The control module is configured to: control the image processing module to fuse and correct at least one image data to obtain target image data, including: fusing the preoperative CT image with one or two of the intraoperative real-time X-ray image and the intraoperative real-time ultrasound image to obtain fused image data; based on the intraoperative real-time ultrasound image, correcting at least one parameter of the fused image data to determine target image data, the target image data including the corrected image data including kidney shape, position, kidney stone position, and distribution information; based on the target image data, determining the real-time position of the puncture needle, generating auxiliary navigation information and recommended navigation parameters, and sending the target image data, the auxiliary navigation information and the recommended navigation parameters to the interactive screen, the auxiliary navigation information and the recommended navigation parameters including information and parameters instructing the puncture needle to navigate.

[0006] One or more embodiments of the present specification provide a percutaneous nephrolithotomy navigation control method, which is implemented based on a processor. Based on the X-ray imaging acquisition module, an intraoperative real-time X-ray image is acquired, and the intraoperative real-time X-ray image includes image data after imaging the kidney stones and the puncture needle; based on the CT image acquisition module, a preoperative CT image is acquired, and the preoperative CT image includes image data after imaging the kidney stones and blood vessels and kidney tissue; based on the ultrasound image acquisition module, an intraoperative real-time ultrasound image is acquired, and the intraoperative real-time ultrasound image includes image data after imaging the kidney stones, the puncture needle, the renal collecting system, and the organs around the kidney; based on the preoperative CT image and one or both of the intraoperative real-time X-ray image and the intraoperative real-time ultrasound image, a real-time ultrasound image is acquired. The method comprises the steps of: performing fusion to obtain fused image data; based on the real-time intraoperative ultrasound image, correcting at least one parameter of the fused image data to determine target image data, wherein the target image data includes the corrected image data including the shape, position, position and distribution information of the kidney, and the position of kidney stones; based on the target image data, determining the real-time position of the puncture needle, generating auxiliary navigation information and recommended navigation parameters, and sending the target image data, the auxiliary navigation information and the recommended navigation parameters to the interactive screen, wherein the auxiliary navigation information and the recommended navigation parameters include information and parameters instructing the puncture needle to perform navigation.

[0007] One or more embodiments of the present specification provide a percutaneous nephrolithotomy navigation control device, which includes at least one processor and at least one memory; the at least one memory is used to store computer instructions; the at least one processor is used to execute at least part of the computer instructions to implement the percutaneous nephrolithotomy navigation control method.

[0008] One or more embodiments of the present specification provide a computer-readable storage medium, wherein the storage medium stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the percutaneous nephrolithotomy navigation control method. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] This specification will be further described in the form of exemplary embodiments, which will be described in detail by the accompanying drawings. These embodiments are not restrictive, and in these embodiments, the same number represents the same structure, wherein:

[0010] Figure 1 is an exemplary flow chart of a percutaneous nephrolithotomy navigation control method according to some embodiments of the present specification;

[0011] Figure 2 is an exemplary schematic diagram of controlling the emergency stop of a puncture needle according to some embodiments of this specification;

[0012] Figure 3 It is an exemplary schematic diagram of a bleeding feature recognition model according to some embodiments of the present specification. DETAILED DESCRIPTION

[0013] In order to more clearly illustrate the technical solutions of the embodiments of this specification, the following is a brief introduction to the drawings required for the description of the embodiments. Obviously, the drawings described below are only some examples or embodiments of this specification. For ordinary technicians in this field, this specification can also be applied to other similar scenarios based on these drawings without creative work. Unless it is obvious from the language environment or otherwise explained, the same reference numerals in the figures represent the same structure or operation.

[0014] It should be understood that the "system", "device", "unit" and / or "module" used herein are a method for distinguishing different components, elements, parts, portions or assemblies at different levels. However, if other words can achieve the same purpose, the words can be replaced by other expressions.

[0015] As shown in this specification and claims, unless the context clearly indicates an exception, the words "a", "an", "an" and / or "the" do not refer to the singular and may also include the plural. Generally speaking, the terms "comprise" and "include" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0016] Flowcharts are used in this specification to illustrate the operations performed by the system according to the embodiments of this specification. It should be understood that the preceding or following operations are not necessarily performed precisely in order. Instead, the steps may be processed in reverse order or simultaneously. At the same time, other operations may also be added to these processes, or one or more operations may be removed from these processes.

[0017] The embodiment of the present specification provides a percutaneous nephrolithotomy navigation control system, which includes: an image acquisition module, an image processing module, a control module, and an interactive screen.

[0018] In some embodiments, the image acquisition module is used to acquire at least one type of image data. For example, the image acquisition module can be used to acquire medical images such as CT images, X-ray images, and ultrasound images.

[0019] In some embodiments, the image acquisition module includes: at least one of an X-ray imaging acquisition module, a CT image acquisition module, and an ultrasound image acquisition module.

[0020] The X-ray imaging acquisition module is a module for acquiring X-ray images. In some embodiments, an X-ray imaging device (XR) is integrated in the X-ray imaging acquisition module. Exemplary X-ray imaging devices include a general X-ray machine (GXR) and an interventional X-ray machine (IXR), wherein the GXR includes conventional digital X-ray imaging (DR) equipment, mobile DR, breast machine, gastrointestinal machine, etc., and the IXR includes a C-arm X-ray machine, etc.

[0021] The CT image acquisition module is a module for acquiring CT images. In some embodiments, a computer tomography device (CT machine) is integrated into the CT image acquisition module. Common CT machines include rotary CT machines, spiral CT machines, dual-energy CT machines, etc.

[0022] The ultrasonic image acquisition module is a module for acquiring ultrasonic images. In some embodiments, an ultrasonic imaging device is integrated into the ultrasonic image acquisition module. Exemplary ultrasonic imaging devices include type A ultrasonic imaging devices, type B ultrasonic imaging devices, and the like.

[0023] In some embodiments, the image acquisition module is configured to: acquire intraoperative real-time X-ray images based on the X-ray imaging acquisition module, acquire preoperative CT images based on the CT image acquisition module, and acquire intraoperative real-time ultrasound images based on the ultrasound image acquisition module. For more information about intraoperative real-time X-ray images, preoperative CT images, and intraoperative real-time ultrasound images, please refer to the relevant description below.

[0024] In some embodiments, the image processing module is used to process at least one type of image data. For example, the image processing module can perform multi-planar reconstruction on preoperative CT images, or perform denoising on intraoperative real-time X-ray images.

[0025] In some embodiments, the control module can be used to control the image processing module and the image acquisition module. For example, the control module can control the image acquisition module to acquire at least one image data. For another example, the processing module can control the image processing module to process at least one image data.

[0026] In some embodiments, the control module is configured to: obtain fused image data based on the fusion of preoperative CT images with one or both of intraoperative real-time X-ray images and intraoperative real-time ultrasound images; modify at least one parameter of the fused image data based on the intraoperative real-time ultrasound image to determine the target image data; determine the real-time position of the puncture needle based on the target image data, generate auxiliary navigation information and recommended navigation parameters; and send the target image data, auxiliary navigation information and recommended navigation parameters to the interactive screen. For more information about this embodiment, please refer to the relevant description below.

[0027] In some embodiments, the control module is further configured to obtain the optical imaging data and the vital sign monitoring data of the patient based on the optical imaging device and the vital sign monitoring device outside the system. For more information about this embodiment, please refer to the relevant description below.

[0028] In some embodiments, the percutaneous nephrolithotomy navigation control system may further include a bleeding risk assessment module. The bleeding risk assessment module is used to assess the patient's bleeding risk. In some embodiments, the bleeding risk module is configured to determine bleeding data based on intraoperative real-time ultrasound images. In some embodiments, the bleeding risk module is further configured to determine the estimated bleeding risk of multiple areas of the patient in the overall area of ​​the percutaneous nephrolithotomy based on intraoperative real-time X-ray images, preoperative CT images, and intraoperative real-time ultrasound images. For more information about this embodiment, see the relevant description below.

[0029] In some embodiments, the image processing module, the control module and the bleeding risk assessment module may be integrated in a processor. The processor may control the above modules to perform corresponding operations in response to computer instructions.

[0030] Figure 1 1 is a flowchart of a percutaneous nephrolithotomy navigation control method according to some embodiments of this specification. In some embodiments, process 100 can be implemented based on a processor. Figure 1 As shown, the following steps are included.

[0031] Step 110: Acquire real-time intraoperative X-ray images based on an X-ray imaging acquisition module.

[0032] Intraoperative real-time X-ray images refer to X-ray images of the area to be operated on that are acquired by an X-ray imaging device during the operation. For example, an X-ray image of the patient's kidney and surrounding area acquired before percutaneous nephrolithotomy. The X-ray image can be a planar image. In some embodiments, the intraoperative real-time X-ray image includes image data after imaging the kidney stone and the puncture needle.

[0033] By collecting X-ray images, we can obtain basic information such as the location and number of kidney stones, thereby understanding the basic condition of the patient.

[0034] Step 120: acquiring a preoperative CT image based on the CT image acquisition module.

[0035] Preoperative CT images refer to CT images of the area to be operated on that are acquired by CT imaging equipment before the operation. For example, CT images of the patient's kidneys and surrounding areas acquired before percutaneous nephrolithotomy. The CT images may be tomographic images. In some embodiments, the imaging range of the preoperative CT radiographic images includes image data after imaging of kidney stones, blood vessels, and kidney tissues. In some embodiments, the imaging range of the intraoperative real-time X-ray images may be the same as or different from the imaging range of the preoperative CT radiographic images.

[0036] By collecting CT images, we can obtain more detailed and accurate information about kidney stones, such as the size, shape, density, number, distribution, etc. of kidney stones, and have a deeper and more accurate understanding of the patient's condition.

[0037] Step 130: Acquire intraoperative real-time ultrasound images based on the ultrasound image acquisition module.

[0038] Intraoperative real-time ultrasound images refer to ultrasound images acquired by ultrasound equipment during surgery. For example, ultrasound images collected and presented in real time during percutaneous nephrolithotomy. During the operation, an ultrasound probe sends an ultrasound beam to the affected part, and then the reflected sound wave signal is converted into an image and displayed on the interactive screen, so that the position, size, shape and other information of organs and kidney stones in the surgical area can be observed in real time. In some embodiments, intraoperative real-time ultrasound images include image data after imaging kidney stones, puncture needles, renal collecting systems (such as renal pelvis, renal calyces), and organs around the kidneys.

[0039] Step 140 , fusing the preoperative CT image with one or both of the intraoperative real-time X-ray image and the intraoperative real-time ultrasound image to obtain fused image data.

[0040] Fusion image data refers to the image data obtained by combining image data obtained by different imaging technologies. For example, by combining the CT images obtained before surgery with the X-ray images and ultrasound images obtained in real time during surgery, a fusion image can be obtained that contains both high-resolution images of bone structure and organ morphology (provided by CT) and real-time information on the position and morphological changes of organs and kidney stones. Fusion images can provide more accurate spatial positioning in surgical navigation, help doctors accurately locate kidney stones, and guide the puncture needle for precise operation.

[0041] Step 150: Based on the intraoperative real-time ultrasound image, at least one parameter of the fused image data is corrected to determine the target image data.

[0042] The target image data refers to the image data obtained by correcting the fused image data.

[0043] In some embodiments, the target image data includes the image data of the corrected kidney, kidney stones and percutaneous renal passage. In some embodiments, the target image data may include the image data of the corrected kidney shape, position, detailed position and distribution of kidney stones.

[0044] During the operation, the patient's kidney morphology will change as the patient moves (for example, slight changes in body position, etc.), breathes, etc. Therefore, the patient's fused image data can be corrected based on the medical image data acquired in real time during the operation.

[0045] In some embodiments, the control module or processor may modify the fused image data in a variety of ways based on the intraoperative real-time ultrasound image to determine the target image data.

[0046] In some embodiments, the control module or processor may compare the fused image data with the intraoperative real-time ultrasound image to determine whether the position, size, shape and other information of the region of interest (e.g., kidney stones, lesions, etc.) in the fused image data are respectively consistent with the position, size, shape and other information of the region of interest displayed in the intraoperative real-time ultrasound image; in response to inconsistency, the intraoperative real-time ultrasound image is used as a real-time guide to correct the fused image data, thereby obtaining more accurate fused image data. For example, when the position of the region of interest displayed by the intraoperative real-time ultrasound image is inconsistent with the fused image data, the processor or doctor may perform correction processing such as rotation, scaling, and movement on the fused image data. As an example only, when the intraoperative real-time ultrasound image shows that the kidney stone is located in the upper part of the renal pelvis, but the kidney stone in the fused image data is located in the middle part of the renal pelvis, the processor or doctor may make corresponding corrections to the fused image data and adjust the position of the kidney stone upward so that the position of the kidney stone in the fused image data is always consistent with the intraoperative real-time ultrasound image.

[0047] In some embodiments, the control module or processor may also evaluate the imaging quality of the intraoperative real-time ultrasound image, and when the imaging quality of the intraoperative real-time ultrasound image meets certain conditions, the fused image data is corrected. For more description of this embodiment, see the relevant description of the following steps 151 to 154.

[0048] Step 151, based on the optical imaging device and the vital sign monitoring device, obtain the patient's optical imaging data and vital sign monitoring data.

[0049] Optical imaging data refers to the patient's body picture or video data. Optical imaging data can be collected in real time or at regular intervals by an optical imaging device. The optical imaging device can include a camera or a laser scanner, etc.

[0050] In some embodiments, the control module or processor can determine the change characteristics of the optical imaging data based on the optical imaging data collected at the current moment and the previous historical moment. In some embodiments, the change characteristics of the optical imaging data can include the patient's body position movement distance, the position movement distance of the region of interest (e.g., the kidney and its surrounding area). For example, the control module or processor can calculate the patient's body position movement distance and the position movement distance of the region of interest based on the optical imaging data collected at the two moments.

[0051] Vital sign monitoring data refers to the patient's physiological monitoring parameters. For example, heart rate, respiration, blood oxygen, blood pressure and other data. Vital sign monitoring data can be collected in real time or at regular intervals through a vital sign monitoring device. Vital sign monitoring devices can include electrocardiographs, ventilators and other equipment.

[0052] In some embodiments, the control module or processor can determine whether the patient's physiological state is stable based on the vital sign monitoring data collected at least two time points. For example, the control module or processor can calculate and determine the degree of fluctuation of the vital sign monitoring data based on the vital sign monitoring data collected at least two time points. When the degree of fluctuation of the vital sign change data is greater than the corresponding fluctuation threshold, the patient's physiological state is judged to be unstable, otherwise it is judged to be stable. Among them, the fluctuation threshold corresponding to the vital sign change data can be obtained by the system or manually preset. It should be noted that for each vital sign monitoring sub-data in the vital sign monitoring data, the degree of fluctuation corresponding to each vital sign monitoring sub-data can be determined. When it is judged that the degree of fluctuation of the vital sign monitoring sub-data is greater than the corresponding fluctuation threshold, it can be judged that the patient's physiological state is unstable.

[0053] Step 152: Evaluate the imaging quality of the intraoperative real-time ultrasound image based on the optical imaging data and the vital sign monitoring data.

[0054] The imaging quality of intraoperative real-time ultrasound images refers to the quality of ultrasound images. The imaging quality can be measured by data, for example, a score from 0 to 1 can be used to quantify the imaging quality, and a higher score indicates better imaging quality.

[0055] In some embodiments, the imaging quality of ultrasound images is related to the clarity, delay time, etc. of ultrasound imaging. When performing an ultrasound examination, factors such as the patient's body position and blood flow velocity will affect the echo intensity and echo time of the ultrasound signal, thereby affecting the imaging quality. For example, the stronger the echo intensity of the ultrasound signal, the clearer the ultrasound imaging; the shorter the echo time of the ultrasound signal, the shorter the delay time of the ultrasound imaging. When performing an ultrasound examination, the patient's physiological indicators can also affect the imaging quality. For example, if the patient has abnormal physiological indicators such as a drop in blood pressure, the quality of ultrasound imaging may be reduced.

[0056] In some embodiments, the control module or processor can evaluate the imaging quality through an imaging quality evaluation model based on the optical imaging data and the vital sign monitoring data. The imaging quality evaluation model can be a computer algorithm or rule for evaluating the imaging quality. The feature point distance refers to the distance between one or more feature points (e.g., lesions) corresponding to the intraoperative real-time ultrasound image and the fused image data in the same reference coordinate system.

[0057] In some embodiments, the imaging quality assessment model may include: calculating the imaging quality according to a first score corresponding to the optical imaging data, a second score corresponding to the vital sign monitoring data, and a third score corresponding to the feature point distance.

[0058] Exemplarily, the calculation formula of the imaging quality assessment model is shown in the following formula (1): Q=w1a1+w2a2+w3a3 (1)

[0059] Among them, Q is the imaging quality, a1 is the first score corresponding to the optical imaging data, a2 is the second score corresponding to the vital sign monitoring data, a3 is the third score corresponding to the feature point distance, w1 is the weight of the first score, w2 is the weight of the second score; w3 is the weight of the third score. Among them, w1, w2, and w3 can be set manually. The larger the weight value, the more important the data is.

[0060] In some embodiments, the first score corresponding to the optical imaging data may be negatively correlated with the degree of change in the patient's body position, and negatively correlated with the degree of change in the color of the patient's affected area, pixel distribution, etc.

[0061] In some embodiments, the second score corresponding to the vital sign monitoring data can be the weighted sum of the corresponding sub-scores of multiple vital sign monitoring sub-data (such as heart rate, respiration, blood oxygen, blood pressure, etc.). The weight of each vital sign monitoring sub-data is related to the patient's condition. For example, when the patient has problems such as arrhythmia, the weight of the vital sign monitoring sub-data corresponding to the heart rate can be set to a larger value. The weights of each vital sign monitoring sub-data of different patients can be pre-set by the doctor based on experience. The higher the second score corresponding to the vital sign monitoring data, the more stable the patient's vital signs are and the smaller the imaging image is.

[0062] The feature point distance can reflect the degree of change in the patient's body position, the location and size of the affected area, etc. In some embodiments, the feature point distance can be represented by the average distance, the maximum distance, the minimum distance, and the distance distribution on the image, etc. In some embodiments, the third score corresponding to the feature point distance can be positively correlated with the feature point distance.

[0063] Step 153: in response to the imaging quality of the intraoperative real-time ultrasound image being greater than a first preset threshold, the fused image data is corrected.

[0064] The first preset threshold is a threshold for judging whether the imaging quality reaches a threshold that can be used to correct the fused image data. The first preset threshold can be obtained by the system or manually preset.

[0065] In some embodiments, when the imaging quality of the intraoperative real-time ultrasound image is greater than a first preset threshold, the control module or processor may correct the fused image data based on the intraoperative real-time ultrasound image. When the imaging quality is greater than the first preset threshold, it means that the imaging quality of the intraoperative real-time ultrasound image is good and can be used to correct the fused image data. In some embodiments, when the imaging quality of the intraoperative real-time ultrasound image is greater than the first preset threshold, the control module or processor may perform correction processing such as rotation, scaling, and movement on the fused image data. For more information about this embodiment, please refer to the relevant description above.

[0066] In some embodiments, the control module or processor may correct the fused image data at a preset correction frequency. The correction frequency refers to the frequency at which the fused image data is corrected. For example, once every 10 seconds, 10 times per minute, etc. In some embodiments, the correction frequency may be preset and determined by the processor or manually based on historical data or prior knowledge.

[0067] In some embodiments, the control module or the processor may adjust the preset correction frequency during surgery, and correct the fused image data based on the adjusted correction frequency.

[0068] In some embodiments, the control module or processor may adjust the preset correction frequency based on at least one of the bleeding data, optical imaging data, and vital sign monitoring data obtained during the operation. Bleeding data refers to data related to bleeding during the operation of the patient. Bleeding data may include the bleeding location, amount of bleeding, and cause of bleeding in the surgical area. For more information about bleeding data, see Figure 2 and its related description.

[0069] In some embodiments, the control module or processor can determine the adjustment mode of the preset correction frequency based on the bleeding volume, bleeding position and bleeding volume threshold in the bleeding data. Wherein, the bleeding volume threshold can include a bleeding volume lower limit threshold and a bleeding volume upper limit threshold, and the bleeding volume threshold can be pre-set by the processor or manually based on historical data or prior knowledge. The adjustment mode of the preset correction frequency can include keeping unchanged, reducing or increasing, etc.

[0070] In some embodiments, when the amount of bleeding is less than the lower limit threshold of bleeding, the preset correction frequency can be kept unchanged. When the amount of bleeding is greater than the upper limit threshold of bleeding and the bleeding location is in the surgical area, the control module or processor can reduce the preset correction frequency to ensure that the doctor has sufficient time to deal with abnormal conditions such as bleeding and reduce surgical risks.

[0071] In some embodiments, the control module or processor can determine the adjustment method for the preset correction frequency based on the imaging quality of the optical imaging data, the vital sign monitoring data and the intraoperative real-time ultrasound image. For example, if the imaging quality of the intraoperative real-time ultrasound image is greater than the preset quality threshold, and the body position movement distance and / or the position movement distance of the affected part in the optical imaging data is less than the corresponding distance threshold, and the fluctuation degree of the vital sign monitoring data is less than the corresponding fluctuation threshold, the correction frequency can be increased to enable the doctor to operate more accurately and improve the efficiency of the operation. For another example, when the patient has shortness of breath, abnormal blood pressure or other abnormal physiological changes, the correction frequency can be appropriately reduced, or the doctor can determine whether the correction frequency needs to be adjusted based on the vital sign monitoring data.

[0072] In some embodiments of the present specification, by adjusting the correction frequency in real time during the operation, it is possible to balance the surgical efficiency and surgical risks, so that the patient can receive more effective treatment.

[0073] In some embodiments, the control module or processor may also estimate the correction time (hereinafter referred to as the next correction time) for correcting the fused image data based on the next intraoperative real-time ultrasound image based on at least one of the bleeding data, the changing characteristics of the optical imaging data, and the degree of fluctuation of the vital sign monitoring data. Among them, the next intraoperative real-time ultrasound image may be the intraoperative real-time ultrasound image acquired after the current correction is completed. The next correction time may be the time point of the next correction or the time interval between the current correction time. In some embodiments, the control module or processor may determine the next correction time based on the influence value corresponding to at least one of the bleeding data, the changing characteristics of the optical imaging data, and the degree of fluctuation of the vital sign monitoring data, based on the influence value and the last correction time. For example, the control module or processor may determine the next correction time by the following formula (2): T next = k × W change +(1-k)×W remain (2)

[0074] Among them, T next is the next correction time, or the time interval between the current correction; W change is the influence value W corresponding to at least one of the bleeding data, the change characteristics of the optical imaging data, and the fluctuation degree of the vital sign monitoring data. change is a positive value; W remain is the preset correction time or the last correction time; k is a weight parameter, which is used to represent the influence of the change characteristics of bleeding data, optical imaging data, and the fluctuation amplitude of vital sign monitoring data on the correction time, and can be manually set to a value of 0-1.

[0075] In some embodiments, the impact value may reflect the influence of at least one of the change characteristics of the bleeding data, the optical imaging data, and the fluctuation degree of the vital sign monitoring data on the correction time. The impact value is a positive value. The larger the impact value, the greater the influence of at least one of the change characteristics of the bleeding data, the optical imaging data, and the fluctuation degree of the vital sign monitoring data on the correction time. For example, when the influence of the change characteristics of the bleeding data, the optical imaging data, and the fluctuation degree of the vital sign monitoring data on the correction time is too large, W change will increase, thus prolonging the time for the next correction; when the change characteristics of bleeding data, optical imaging data, and the fluctuation degree of vital sign monitoring data have little effect on the correction time, W remain will decrease, resulting in a shorter time for the next correction.

[0076] In some embodiments, the influence of bleeding data on the correction time can be determined based on the amount of bleeding and the bleeding location. For example, when the amount of bleeding is greater than the upper threshold of the amount of bleeding and the bleeding location is located in the surgical area, it can be determined that the influence of bleeding data on the correction time is greater, and the influence value is greater at this time; when the amount of bleeding is less than the lower threshold of the amount of bleeding, it can be determined that the influence of bleeding data on the correction time is less, and the influence value is smaller at this time.

[0077] In some embodiments, the influence of the change characteristics of the optical imaging data on the correction time can be determined based on the body position movement distance and / or the position movement distance of the affected part. For example, when the body position movement distance and / or the position movement distance of the affected part is less than the corresponding distance threshold, it can be determined that the change characteristics of the optical imaging data have little influence on the correction time, and the influence value is small at this time.

[0078] In some embodiments, the influence of the fluctuation degree of the vital sign monitoring data on the correction time can be determined based on the relationship between the fluctuation degree and the corresponding fluctuation threshold. For example, when the fluctuation degree of the vital sign change data is greater than the corresponding fluctuation threshold, it can be determined that the fluctuation degree of the vital sign monitoring data has a greater influence on the correction time, and the influence value is greater at this time.

[0079] In some embodiments of the present specification, by estimating the next correction time, doctors can have a psychological expectation of the change time of the fused image data, thereby preventing the sudden correction of the fused image data from causing the doctor to make a wrong judgment.

[0080] Step 154 ​​, in response to the imaging quality of the intraoperative real-time ultrasound image being less than a second preset threshold, adjusting the ultrasound imaging parameters of the ultrasound image acquisition module, and sending the adjusted ultrasound imaging parameters to the ultrasound image acquisition module.

[0081] The second preset threshold is a threshold for judging whether the imaging quality reaches a threshold that can be used to adjust the ultrasonic imaging parameters. The second preset threshold can be obtained by the system or manually preset. The second preset threshold is less than the first preset threshold.

[0082] Ultrasound imaging parameters refer to equipment parameters of ultrasound equipment.

[0083] In some embodiments, the ultrasound imaging parameters include at least one of beam width, sensitivity, imaging depth, and probe position.

[0084] Beam width refers to the transverse resolution dimension of the cross section perpendicular to the beam axis. Beam width can indicate the diameter of the ultrasound during propagation. Sensitivity refers to the ability of the ultrasound imaging module to detect the smallest stones. Imaging depth refers to the maximum depth of ultrasound propagation in tissue. Probe position refers to the location of the ultrasound sensor.

[0085] In some embodiments, when the imaging quality of the intraoperative real-time ultrasound image is less than the second preset threshold, the ultrasound imaging parameters may be adjusted according to a preset method. In some embodiments, the preset method may be a preset means of adjusting the ultrasound imaging parameters. For example, the preset method may be to appropriately increase the sensitivity to improve the signal-to-noise ratio, etc.

[0086] In some embodiments, when the imaging quality of the intraoperative real-time ultrasound image is less than a second preset threshold, the control module or the processor can analyze the quality impact type of the intraoperative real-time ultrasound image, and adjust at least one of the beam width, sensitivity, imaging depth, and probe position based on the quality impact type.

[0087] In some embodiments, the quality impact type may include but is not limited to shallow imaging depth, deep imaging depth, low sensitivity, deviation between the imaging range and the lesion area, low image clarity, etc. In some embodiments, the control module or processor may determine the quality impact type of the intraoperative real-time ultrasound image by analyzing the intraoperative real-time ultrasound image. The embodiments of this specification do not specifically limit the manner in which the intraoperative real-time ultrasound image is analyzed, and operations familiar to those skilled in the art may be used.

[0088] In some embodiments, when the quality impact type is a shallow imaging depth, the sound beam width can be reduced; when the quality impact type is a deep imaging depth, the sound beam width can be increased. When the quality impact type is a deviation between the imaging range and the lesion area, the probe position can be adjusted. When the quality impact type is low sensitivity, the sensitivity can be appropriately increased. When the quality impact type is low image clarity, the imaging depth can be adjusted. In some embodiments, the control module or processor can adjust the imaging depth based on tissue depth, severity of the affected area, and the like. For example, the deeper the tissue depth and the more severe the affected area, the deeper the imaging depth can be to improve the clarity of the ultrasound image.

[0089] In some embodiments of this specification, the patient's body position changes and physiological characteristics are obtained by monitoring the patient's physiological state data and optical imaging data, so as to more comprehensively evaluate the quality of ultrasound imaging, thereby making the fusion image data more accurately corrected, so that doctors can make more accurate judgments during surgery. At the same time, the ultrasound imaging parameters are adjusted according to the ultrasound imaging quality, so that the ultrasound equipment can obtain clearer ultrasound images.

[0090] Step 160 , generating auxiliary navigation information and recommended navigation parameters based on the target image data, and sending the target image data, the auxiliary navigation information and the recommended navigation parameters to the interactive screen.

[0091] The auxiliary navigation information is information that guides the doctor to more accurately locate and operate the surgical area. In some embodiments, the auxiliary navigation information may include information that instructs the puncture needle to navigate. For example, the auxiliary navigation information may include information that indicates the specific position and orientation of the puncture needle in the kidney. In some embodiments, the auxiliary navigation information may also include the tissue structure and blood vessel distribution of the patient's kidney and its surrounding area.

[0092] In some embodiments, the control module or processor may perform image analysis on the target image data to obtain auxiliary navigation information. For example, the image analysis method may include image registration, feature detection, or deep learning.

[0093] The recommended navigation parameters are suggested parameters for guiding the movement and operation of the puncture needle. In some embodiments, the recommended navigation parameters may include the movement speed, depth, direction and strength of the puncture needle.

[0094] In some embodiments, the control module or processor can obtain recommended navigation parameters in a variety of ways based on the target image data. For example, the control module or processor can plan multiple intervention positions and targets based on the target image data, determine the surgical path based on the intervention position and target, and then plan the path navigation parameters according to the surgical path. Among them, the intervention position refers to the position point that the puncture needle must pass through during the interventional treatment process. The target refers to the target area to be treated or the position point when the puncture needle reaches the target area. In some embodiments, the intervention position and target can be automatically planned by the control module or processor based on the target image data. In some embodiments, the doctor can also review and adjust the automatic planning results of the control module or processor (i.e., the intervention position and target automatically planned by the control module or processor) to determine the intervention position and target. For another example, the control module or processor can determine the real-time coordinates of the puncture needle, as well as the moving direction and moving speed of the puncture needle based on the target image data, so that the puncture needle can accurately puncture the target calyx.

[0095] In some embodiments of the present specification, by constructing fused image data, it is possible to provide doctors with richer and more intuitive lesion information about the patient's kidneys and surrounding areas, thereby improving the accuracy of diagnosis; by combining intraoperative real-time X-ray images and preoperative CT images to construct fused image data, it is possible to combine the advantages of low radiation of X-ray imaging and the advantages of CT imaging in assessing the complexity and surgical difficulty of kidney stones more accurately and comprehensively, thereby reducing the radiation dose to the patient while ensuring the accuracy of information acquisition; by using real-time ultrasound images during surgery, the fused image data can be corrected, thereby obtaining a more accurate three-dimensional imaging of the patient's surgical area during surgery, thereby making the acquired auxiliary navigation information and recommended navigation parameters more accurate, making the movement path of the puncture needle safer, and reducing the risk of bleeding during surgery.

[0096] Figure 2 It is an exemplary schematic diagram of controlling the emergency stop of the puncture needle according to some embodiments of the present specification.

[0097] In some embodiments, the percutaneous nephrolithotomy navigation control system may further include a bleeding risk assessment module, which may assess the bleeding risk during surgery.

[0098] In some embodiments, Figure 2 As shown, the bleeding risk assessment module or processor can determine bleeding data 240 based on the intraoperative real-time ultrasound image 210; determine patient physiological data 270 based on the optical imaging data 250 and the vital sign monitoring data 260; respond to the bleeding data 240 and the patient physiological data 270. When the first warning condition is met, a first warning message 291 is issued, and the puncture needle is controlled to stop urgently.

[0099] Bleeding data refers to data related to bleeding during surgery of a patient. In some embodiments, the bleeding data may include at least one of bleeding location, bleeding amount, and bleeding cause.

[0100] The bleeding location refers to the location of the ruptured blood vessel of the patient. For example, the bleeding location may include the absolute coordinates of the bleeding location in the real-time ultrasound image during the operation, or the relative position of the bleeding location and the puncture needle.

[0101] The cause of bleeding is the cause of the rupture of the patient's blood vessels. For example, the cause of bleeding may include accidental needle contact, the actual need for surgical incision, or bleeding caused by organ or tissue lesions.

[0102] The bleeding risk assessment module or processor can determine the bleeding data in a variety of ways based on the real-time ultrasound image during the operation. Since the ultrasound image can show the blood flow during the imaging process, it can provide information on the bleeding location and blood flow rate. Therefore, the ultrasound image can contain information on the blood flow location and blood flow rate. The bleeding risk assessment module can determine whether there is a bleeding location among the multiple blood flow locations displayed in the real-time ultrasound image during the operation based on the reference ultrasound image in the absence of bleeding. For example, the real-time ultrasound image during the operation is compared with the reference ultrasound image in the absence of bleeding to determine the bleeding location, and then determine the amount of bleeding by calculation.

[0103] In some embodiments, Figure 3 As shown, the bleeding risk assessment module or processor may determine bleeding data based on the intraoperative real-time ultrasound image 310 through a bleeding feature recognition model 320 .

[0104] The bleeding feature recognition model refers to a machine learning model for identifying bleeding data. In some embodiments, the bleeding feature recognition model can be a machine learning model of a custom structure as described below, or a machine learning model of other structures. For example, a neural network model (NN), a deep neural network (DNN), a convolutional neural network (CNN), etc. or any combination thereof.

[0105] In some embodiments, Figure 3 As shown, the bleeding feature recognition model 320 may include a bleeding feature prediction layer 320-1 and a bleeding cause prediction layer 320-2. The input of the bleeding feature prediction layer 320-1 may include the intraoperative real-time ultrasound image 320, and the output of the bleeding feature prediction layer 320-1 may include a bleeding location 330 and a bleeding amount 340. The input of the bleeding cause prediction layer 320-2 may include surgical operation feature data 350 within a preset time period and the output of the bleeding feature prediction layer 320-1 (i.e., the bleeding location 330 and the bleeding amount 340), and the output of the bleeding cause prediction layer 320-2 may include a bleeding cause 380.

[0106] In some embodiments, the bleeding feature prediction layer may be a convolutional neural network (CNN). In some embodiments, the bleeding cause prediction layer may be a convolutional neural network (CNN).

[0107] The preset time period may be a period of time before the acquisition time point of the intraoperative real-time ultrasound image. The surgical operation characteristic data is data related to the doctor's operation when performing surgical treatment. In some embodiments, the surgical operation characteristic data may include: the use of the puncture needle (for example, the size and number of the puncture needle), the duration of the operation, and the treatment process data (for example, the intervention path, intervention speed, and intervention direction of the puncture needle). In some embodiments, the bleeding risk assessment module or processor can obtain the surgical operation characteristic data of the preset time period based on the surgical process monitoring record. The surgical process monitoring record can be automatically generated by the system or manually generated by the system.

[0108] In some embodiments, Figure 3 As shown, the input of the bleeding cause prediction layer 320-2 may also include the patient's optical imaging data 360 and vital sign monitoring data 370. For more information about optical imaging data and vital sign monitoring data, see Figure 1 In some embodiments, the input of the bleeding cause prediction layer may further include the patient's age, gender, medical history, medication history, condition, etc. By inputting more comprehensive data into the model, a more accurate and reliable bleeding cause analysis can be achieved.

[0109] In some embodiments, the bleeding feature prediction layer can be obtained by separate training based on a large number of first training samples with a first label through various feasible methods. An exemplary separate training process may include: training based on a gradient descent method. As an example only, a plurality of first training samples with a first label can be input into an initial bleeding feature prediction layer, a loss function is constructed by the first label and the result of the initial bleeding feature prediction layer, and the parameters of the initial bleeding feature prediction layer are iteratively updated based on the loss function. When the loss function of the initial bleeding feature prediction layer meets a preset condition, the model training is completed, and a trained bleeding feature prediction layer is obtained. Among them, the preset condition can be that the loss function converges, the number of iterations reaches a threshold, etc.

[0110] In some embodiments, the first training sample may include historical intraoperative ultrasound images in which bleeding occurred, and the first label may include historical actual bleeding locations and historical actual bleeding volumes corresponding to the first training sample. The first training label may be obtained by consulting historical diagnosis reports.

[0111] In some embodiments, the bleeding cause prediction layer can be obtained by joint training with the bleeding feature prediction layer. The second training sample of the bleeding cause prediction layer can include feature data of surgical operations within a historical preset period, historical actual bleeding locations and historical actual bleeding volumes output by the bleeding feature prediction layer. The second training label can be the historical actual bleeding cause corresponding to the second training sample. The second training label can be obtained by consulting manual records.

[0112] An exemplary joint training process may include: inputting a first training sample into an initial bleeding feature prediction layer to obtain the historical actual bleeding position and the historical actual bleeding volume output by the initial bleeding feature prediction layer; inputting the output of the initial bleeding feature prediction layer and the second training sample into the initial bleeding cause prediction layer to obtain the historical actual bleeding cause output by the initial bleeding cause prediction layer. A loss function is constructed based on the output of the initial bleeding cause prediction layer and the second label, and the parameters of the initial bleeding feature prediction layer and the initial bleeding cause prediction layer are synchronously updated using the loss function. By updating the parameters, a trained bleeding feature recognition model is obtained. In some embodiments, the loss functions of the two layers of training can be added to obtain a total loss function for joint training.

[0113] In some embodiments, the second training sample may include historical surgical operation feature data within a historical preset period. In some embodiments, the second training sample may also include historical optical imaging data and historical vital sign monitoring data. The second label may be the historical actual bleeding cause corresponding to the second training sample. The second label may be obtained by consulting manual records.

[0114] Patient physiological data refers to data related to the patient's physiological state. In some embodiments, the patient's physiological data includes index data (e.g., heart rate, respiratory rate, body temperature, blood oxygen saturation, blood pressure, blood sugar, blood lipids, blood calcium, etc.), medical image data (e.g., electrocardiogram, electroencephalogram, etc.), skin data (e.g., skin color, skin temperature, etc.), and surgical area data (e.g., the shape, color, temperature, etc. of the surgical area).

[0115] In some embodiments, the bleeding risk assessment module or processor can perform feature fusion of the optical imaging data and the vital sign monitoring data to obtain the patient's physiological data. The processor can use a variety of algorithms to achieve feature fusion, such as weighted average, feature splicing, etc.

[0116] In some embodiments, the bleeding risk assessment module or processor may perform feature extraction on the optical imaging data and the vital sign monitoring data respectively, assign different weights to the extracted features, and then obtain the patient's physiological data through weighted averaging.

[0117] In some embodiments, the bleeding risk assessment module or processor can directly stitch together the extracted features corresponding to the optical imaging data and the vital sign monitoring data in a preset order through a feature stitching method to obtain the patient's physiological data.

[0118] The first warning condition refers to a condition for determining whether to issue a warning based on the patient's current bleeding condition and / or current physiological condition. The first warning information refers to a warning information issued when the first warning condition is met. The first warning information can be used to prompt the patient's current bleeding condition to be abnormal, etc. The first warning information can also be used to prompt the patient's current physiological condition to be abnormal, etc.

[0119] In some embodiments, the warning method of issuing the warning information may include sending the warning information to the user (eg, a doctor, etc.) in the form of text, voice, image, video, tactile alarm, etc. or any combination thereof.

[0120] In some embodiments, the first warning condition may be that the patient's bleeding severity level is greater than a severity level threshold, and / or the patient has an abnormal physiological condition.

[0121] In some embodiments, the bleeding risk assessment module or processor can assess the patient's bleeding severity level based on the patient's bleeding data; in response to the bleeding severity level being greater than the severity level threshold, the bleeding data is judged to meet the first warning condition. Among them, the severity level threshold can be a system default value, an experience value, a manually preset value, etc. or any combination thereof, which can be set according to actual needs, and this specification does not limit this. The first warning condition can be set according to actual needs, and is not limited here.

[0122] In some embodiments, the bleeding risk assessment module or processor can determine the bleeding severity level by vector retrieval based on the bleeding location, bleeding amount, and bleeding cause. For example, the bleeding risk assessment module or processor can construct a vector to be matched based on the bleeding location, bleeding amount, and bleeding cause; retrieve the vector to be matched in the vector database based on the vector to be matched, obtain a reference vector whose vector distance with the vector to be matched meets the distance condition, and determine the reference bleeding severity level corresponding to the reference vector as the bleeding severity level corresponding to the vector to be matched. Among them, the vector database is used to store a number of reference vectors and their corresponding reference bleeding severity levels. Among them, the reference vector can be constructed based on the historical bleeding location, historical bleeding amount, and historical bleeding cause, and the reference bleeding severity level corresponding to the reference vector can be determined by the doctor's annotation.

[0123] In some embodiments, the bleeding risk assessment module or processor can determine whether the patient has an abnormal physiological condition based on the patient's physiological data and the reference physiological data; in response to the patient having an abnormal physiological condition, determine that the patient's physiological data meets the first warning condition. When the patient's physiological data does not match the reference physiological data, determine that the patient has an abnormal physiological condition. The reference physiological data can be preset by the doctor.

[0124] In some embodiments, the bleeding risk assessment module or processor may determine that the bleeding data and the patient's physiological data meet the first warning condition in response to the bleeding severity level being greater than the severity level threshold and the patient having an abnormal physiological condition.

[0125] In some embodiments of the present specification, the patient's current bleeding data and / or the patient's physiological data can be used to more accurately analyze whether the patient's current state is abnormal, so as to issue early warning information in time and control the puncture needle to stop suddenly, thereby reducing the risk of bleeding, ensuring patient safety, and reducing surgical risks.

[0126] In some embodiments, Figure 2 As shown, the bleeding risk assessment module or processor is further configured to: determine the estimated bleeding risk 280 of the patient in multiple areas of the overall percutaneous nephroscopic surgery area based on the intraoperative real-time X-ray image 220, the preoperative CT image 230, and the intraoperative real-time ultrasound image 210; in response to the estimated bleeding risk and the patient's physiological data satisfying the second warning condition, issue a second warning message 291 and control the puncture needle to stop urgently. For more information about intraoperative real-time X-ray images, preoperative CT images, and intraoperative real-time ultrasound images, see Figure 1 And related instructions.

[0127] In some embodiments, the processor can divide the whole percutaneous nephroscopic surgery area into a plurality of unit surgery areas in a variety of ways. For example, the processor can divide the whole percutaneous nephroscopic surgery area into a kidney area and a peripheral area based on the physiological structure. The kidney area can include a calyx area, a renal parenchyma area, etc., and the peripheral area can include a subcostal vascular area, other organ areas, etc.

[0128] The estimated bleeding risk refers to the pre-estimated risk of bleeding in a certain area during surgery. For example, the risk that the puncture needle may touch the blood vessel and cause bleeding if the distance from the blood vessel to the puncture needle path is within a preset range. The estimated bleeding risk can be expressed in numbers (for example, numbers 0-10, etc.). The larger the number, the higher the estimated bleeding risk. The estimated bleeding risk can also be expressed by risk level, such as level 1, level 2, etc., or in other ways. The higher the risk level (the larger the level number), the higher the estimated bleeding risk.

[0129] In some embodiments, the bleeding risk assessment module or processor can determine the estimated bleeding risk of multiple areas of the patient in the overall area of ​​percutaneous nephroscopic surgery in a variety of ways based on intraoperative real-time X-ray images, preoperative CT images, and intraoperative real-time ultrasound images.

[0130] In some embodiments, the bleeding risk assessment module or processor can determine the estimated bleeding risk of the current unit surgical area based on the location and distribution of blood vessels in adjacent unit surgical areas. The more complex the distribution of blood vessels and tissues between adjacent areas, the higher the risk of bleeding during surgery. For example, when a surgical operation is performed in unit surgical area 1, and there are a large number of blood vessels connected to unit surgical area 1 and adjacent unit surgical area 2, the estimated bleeding risk of adjacent unit surgical area 2 is higher while the operation is performed in unit surgical area 1.

[0131] In some embodiments, the bleeding risk assessment module or processor can determine the estimated bleeding risk of multiple areas of the patient in the overall area of ​​percutaneous nephroscopic surgery through a bleeding risk prediction model based on intraoperative real-time X-ray images, preoperative CT images, and intraoperative real-time ultrasound images.

[0132] The bleeding risk prediction model is a model for estimating the bleeding risk. The bleeding risk prediction model can be a machine learning model, such as a Graph Neural Network (GNN) model.

[0133] In some embodiments, the input of the bleeding risk prediction model may be a surgical area atlas, and the output may be an estimated bleeding risk of multiple unit surgical areas, wherein the node output in the GNN corresponds to the estimated bleeding risk of the unit surgical area.

[0134] The bleeding risk prediction model can also be other graph models, such as a graph convolutional neural network model (GCNN), or other processing layers can be added to the graph neural network model, its processing method can be modified, etc.

[0135] In some embodiments, the surgical area map is a data structure composed of nodes and edges, where the edges connect the nodes, and the nodes and edges may have attributes. Among the multiple nodes in the surgical area map, each node represents a different unit surgical area. In some embodiments, the node attributes may include the area of ​​the unit surgical area, the characteristics of the stones contained in the unit surgical area, etc. Among them, the stone characteristics may include the size of the stone, the number of stones, and the distribution of the stones, etc.

[0136] In some embodiments, the node attributes of the surgical area atlas may also include image features of the unit surgical area. Image features refer to the features of the image of the unit surgical area. In some embodiments, the image features may include the correction amount of the intraoperative real-time ultrasound image of the unit surgical area to the fused image data. For more information about the correction of fused image data, please refer to Figure 1 And related instructions.

[0137] In some embodiments, the node attributes of the surgical area atlas may also include the progress characteristics of the puncture needle in the unit surgical area. The progress characteristics of the puncture needle refer to the characteristics of the movement and operation of the puncture needle, including the movement speed, depth, direction and force of the puncture needle in the unit surgical area.

[0138] In some embodiments, the edges of the surgical area atlas can be used to connect adjacent unit surgical areas. The edges of the surgical area atlas are undirected edges. In some embodiments, the edge attributes of the surgical area atlas can include the location and distribution of blood vessels in adjacent unit surgical areas. The location and distribution of blood vessels in adjacent unit surgical areas can be represented by numbers between 0 and 10. For example, the closer the location of blood vessels in the adjacent unit surgical area is to the current unit surgical area and the denser the distribution of blood vessels is, the larger the number is used to represent the location and distribution of blood vessels corresponding to the adjacent unit surgical area.

[0139] In some embodiments, the bleeding risk assessment module or processor may construct a surgical area map and determine node attributes and edge attributes in the surgical area map based on intraoperative real-time X-ray images, preoperative CT images, and intraoperative real-time ultrasound images.

[0140] In some embodiments, the bleeding risk assessment module or processor can be trained by various methods based on the third training sample with the third label to obtain a trained bleeding risk prediction model. The training method of the bleeding risk prediction model is similar to the method of separate training of the bleeding feature prediction layer, which will not be repeated here.

[0141] In some embodiments, the third training sample includes a sample surgical area atlas constructed at the first sample moment, and the third label is the actual bleeding data (including bleeding volume and bleeding duration, etc.) of each unit surgical area in the sample surgical area at the second sample moment after the first sample moment. The first sample moment and the second sample moment are both historical moments, and the second sample moment is after the first sample moment. In some embodiments, the third label and the third training sample can be obtained based on historical data.

[0142] In some embodiments, the bleeding risk assessment module or processor can mark the third label based on the actual bleeding data of different unit surgical areas in the historical surgical area atlas. The third label can be represented by a number between 0 and 1. For example, for a unit surgical area in the surgical area atlas at historical moment A, bleeding occurs at a later historical moment B, then the third label is marked according to the length of the interval between historical moment A and historical moment B. The shorter the interval, the closer the third label is to 1.

[0143] In some embodiments of the present specification, the bleeding risk of different surgical areas is predicted by a bleeding risk prediction model, which can more accurately locate the specific locations of areas with higher bleeding risks, thereby facilitating doctors to take corresponding measures to prevent the occurrence of bleeding and increase in bleeding volume, thereby ensuring surgical safety.

[0144] The second warning condition is a condition for determining whether to issue a warning based on the patient's estimated bleeding condition and current physiological condition. The second warning information refers to the warning information issued when the second warning condition is met. The second warning information can be used to prompt the patient that the estimated bleeding condition is more serious. In some embodiments, the warning content of the second warning information may be different from the warning content of the first warning information, and the warning method of the second warning information may be the same as the warning method of the first warning information. The warning content may be current bleeding abnormalities, estimated high bleeding risk, etc. For more information about the warning method, please refer to the relevant description above.

[0145] In some embodiments, the second warning condition may be that the patient's estimated bleeding risk is greater than a risk threshold, and that the patient has an abnormal physiological condition. Accordingly, the bleeding risk assessment module or processor may determine whether the patient's estimated bleeding risk is greater than the risk threshold, and whether the patient has an abnormal physiological condition; in response to the estimated bleeding risk being greater than the risk threshold and the patient having an abnormal physiological condition, the estimated bleeding risk and the patient's physiological data are determined to meet the second warning condition. For more information on determining whether the physiological condition is abnormal, see the relevant description above.

[0146] In some embodiments, the second warning condition may be that the patient's estimated bleeding risk is greater than a risk threshold. Accordingly, the bleeding risk assessment module or processor may also determine that the estimated bleeding risk meets the second warning condition in response to the patient's estimated bleeding risk being greater than the risk threshold.

[0147] In some embodiments of this specification, by dividing the overall percutaneous nephroscopic surgery area into multiple areas and estimating the bleeding risk for each area separately, the area with a higher estimated bleeding risk can be more accurately located. When the estimated bleeding risk and the patient's physiological data do not meet the requirements, early warning information is issued and the puncture needle is controlled to stop suddenly, which can reduce the bleeding risk, ensure patient safety, and reduce surgical risks.

[0148] Some embodiments of the present specification provide a percutaneous nephrolithotomy navigation control device, comprising at least one processor and at least one memory. The at least one memory is used to store computer instructions; the at least one processor is used to execute at least part of the computer instructions to implement the percutaneous nephrolithotomy navigation control method described in any one of the embodiments of the present specification.

[0149] Some embodiments of the present specification provide a computer-readable storage medium, wherein the storage medium stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the percutaneous nephrolithotomy navigation control method described in any one of the embodiments of the present specification.

[0150] The basic concepts have been described above. Obviously, for those skilled in the art, the above detailed disclosure is only for example and does not constitute a limitation of this specification. Although not explicitly stated here, those skilled in the art may make various modifications, improvements and corrections to this specification. Such modifications, improvements and corrections are suggested in this specification, so such modifications, improvements and corrections still belong to the spirit and scope of the exemplary embodiments of this specification.

[0151] At the same time, this specification uses specific words to describe the embodiments of this specification. For example, "one embodiment", "an embodiment", and / or "some embodiments" refer to a certain feature, structure or characteristic related to at least one embodiment of this specification. Therefore, it should be emphasized and noted that "one embodiment" or "an embodiment" or "an alternative embodiment" mentioned twice or more in different positions in this specification does not necessarily refer to the same embodiment. In addition, certain features, structures or characteristics in one or more embodiments of this specification can be appropriately combined.

[0152] In addition, unless explicitly stated in the claims, the order of the processing elements and sequences described in this specification, the use of alphanumeric characters, or the use of other names are not intended to limit the order of the processes and methods of this specification. Although the above disclosure discusses some invention embodiments that are currently considered useful through various examples, it should be understood that such details are only for illustrative purposes, and the attached claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that are consistent with the essence and scope of the embodiments of this specification. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only by software solutions, such as installing the described system on an existing server or mobile device.

[0153] Similarly, it should be noted that in order to simplify the description disclosed in this specification and thus help understand one or more embodiments of the invention, in the above description of the embodiments of this specification, multiple features are sometimes combined into one embodiment, figure or description thereof. However, this disclosure method does not mean that the features required by the subject matter of this specification are more than the features mentioned in the claims. In fact, the features of the embodiments are less than all the features of the single embodiment disclosed above.

[0154] In some embodiments, numbers describing the number of components and attributes are used. It should be understood that such numbers used in the description of the embodiments are modified by the modifiers "about", "approximately" or "substantially" in some examples. Unless otherwise specified, "about", "approximately" or "substantially" indicate that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which may change according to the required features of individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and adopt the general method of retaining digits. Although the numerical domains and parameters used to confirm the breadth of their range in some embodiments of this specification are approximate values, in specific embodiments, the setting of such numerical values ​​is as accurate as possible within the feasible range.

[0155] The entire contents of this specification are hereby incorporated into this specification by reference for each patent, patent application, patent application disclosure and other materials cited in this specification. Except for application historical documents that are inconsistent with or conflict with the contents of this specification, and also for documents that have limited the widest scope of the claims of this specification. It should be noted that if the description, definition, and / or use of the terms in the accompanying materials of this specification are inconsistent or conflicting with the contents of this specification, the description, definition, and / or use of the terms of this specification shall prevail.

[0156] Finally, it should be understood that the embodiments described in this specification are only used to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, as an example and not a limitation, alternative configurations of the embodiments of this specification may be considered consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly introduced and described in this specification.

Claims

1. A navigation control system for percutaneous nephrolithotomy, characterized in that: The system comprises: an image acquisition module, an image processing module, a control module, and an interactive screen, wherein the image processing module and the control module are integrated in a processor; The image acquisition module includes at least one of an X-ray imaging acquisition module, a CT imaging acquisition module, and an ultrasound imaging acquisition module; the image acquisition module is configured as follows: Acquire intraoperative real-time X-ray images based on the X-ray imaging acquisition module, the intraoperative real-time X-ray images include image data after imaging kidney stones and puncture needles; acquire preoperative CT images based on the CT image acquisition module, the preoperative CT images include image data after imaging kidney stones, blood vessels and kidney tissues; and acquire intraoperative real-time ultrasound images based on the ultrasound image acquisition module, the intraoperative real-time ultrasound images include image data after imaging kidney stones, puncture needles, renal collecting system, and organs around the kidneys; The control module is configured to: Controlling the image processing module to fuse and correct at least one image data to obtain target image data, including: Obtaining fused image data based on fusing the preoperative CT image with one or both of the intraoperative real-time X-ray image and the intraoperative real-time ultrasound image; Based on the intraoperative real-time ultrasound image, at least one parameter of the fused image data is corrected to determine the target image data; the target image data includes the corrected image data including kidney shape, position, kidney stone position, and distribution information; Based on the target image data, the real-time position of the puncture needle is determined, auxiliary navigation information and recommended navigation parameters are generated, and the target image data, the auxiliary navigation information and the recommended navigation parameters are sent to the interactive screen. The auxiliary navigation information and the recommended navigation parameters include information and parameters instructing the puncture needle to navigate.

2. The system according to claim 1, characterized in that The control module is further configured to: Based on the optical imaging device and the vital sign monitoring device, acquiring the optical imaging data and the vital sign monitoring data of the patient; Based on the optical imaging data and the vital sign monitoring data, evaluating the imaging quality of the intraoperative real-time ultrasound image; In response to the imaging quality of the intraoperative real-time ultrasound image being greater than a first preset threshold, modifying the fused image data; In response to the imaging quality of the intraoperative real-time ultrasound image being less than a second preset threshold, the ultrasound imaging parameters of the ultrasound image acquisition module are adjusted, and the adjusted ultrasound imaging parameters are sent to the ultrasound image acquisition module.

3. The system according to claim 1, characterized in that The system further comprises a bleeding risk assessment module, which is integrated in the processor and configured to: Determining bleeding data based on the intraoperative real-time ultrasound image, wherein the bleeding data includes at least one of a bleeding location, a bleeding amount, and a bleeding cause; Determine the patient's physiological data based on the optical imaging data and the vital sign monitoring data; In response to the bleeding data and / or the patient's physiological data satisfying a first warning condition, a first warning message is issued, and the puncture needle is controlled to stop urgently.

4. The system according to claim 3, characterized in that The bleeding risk assessment module is further configured to: Determining the estimated bleeding risk of multiple areas of the patient in the overall percutaneous nephroscopic surgery area based on the intraoperative real-time X-ray image, the preoperative CT image, and the intraoperative real-time ultrasound image; In response to the estimated bleeding risk and the patient's physiological data satisfying a second warning condition, a second warning message is issued and the puncture needle is controlled to stop urgently.

5. A navigation control method for percutaneous nephrolithotomy, characterized in that: The method is implemented based on a processor and includes: Acquiring intraoperative real-time X-ray images based on an X-ray imaging acquisition module, wherein the intraoperative real-time X-ray images include image data after imaging the kidney stones and the puncture needle; Acquire a preoperative CT image based on a CT image acquisition module, wherein the preoperative CT image includes image data of kidney stones, blood vessels, and kidney tissues; Acquiring intraoperative real-time ultrasound images based on an ultrasound image acquisition module, wherein the intraoperative real-time ultrasound images include image data of kidney stones, puncture needles, renal collecting system, and organs surrounding the kidneys; Obtaining fused image data based on fusing the preoperative CT image with one or both of the intraoperative real-time X-ray image and the intraoperative real-time ultrasound image; Based on the intraoperative real-time ultrasound image, at least one parameter of the fused image data is corrected to determine the target image data, wherein the target image data includes the corrected image data including kidney shape, position, kidney stone position, and distribution information; Based on the target image data, the real-time position of the puncture needle is determined, auxiliary navigation information and recommended navigation parameters are generated, and the target image data, the auxiliary navigation information and the recommended navigation parameters are sent to the interactive screen. The auxiliary navigation information and the recommended navigation parameters include information and parameters instructing the puncture needle to navigate.

6. The method according to claim 5, characterized in that The method further comprises: Based on the optical imaging device and the vital sign monitoring device, acquiring the optical imaging data and the vital sign monitoring data of the patient; Based on the optical imaging data and the vital sign monitoring data, evaluating the imaging quality of the intraoperative real-time ultrasound image; In response to the imaging quality of the intraoperative real-time ultrasound image being greater than a first preset threshold, modifying the fused image data; In response to the imaging quality of the intraoperative real-time ultrasound image being less than a second preset threshold, the ultrasound imaging parameters of the ultrasound image acquisition module are adjusted, and the adjusted ultrasound imaging parameters are sent to the ultrasound image acquisition module.

7. The method according to claim 5, characterized in that The method further comprises: Determining bleeding data based on the intraoperative real-time ultrasound image, wherein the bleeding data includes at least one of a bleeding location, a bleeding amount, and a bleeding cause; Determine the patient's physiological data based on the optical imaging data and the vital sign monitoring data; In response to the bleeding data and / or the patient's physiological data satisfying a first warning condition, a first warning message is issued, and the puncture needle is controlled to stop urgently.

8. The method according to claim 7, characterized in that The method further comprises: Determining the estimated bleeding risk of multiple areas of the patient in the overall percutaneous nephroscopic surgery area based on the intraoperative real-time X-ray image, the preoperative CT image, and the intraoperative real-time ultrasound image; In response to the estimated bleeding risk and the patient's physiological data, if a second warning condition is met, a second warning message is issued, and the puncture needle is controlled to stop urgently.

9. A navigation control device for percutaneous nephrolithotomy, characterized in that: The apparatus comprises at least one processor and at least one memory; The at least one memory is used to store computer instructions; The at least one processor is used to execute at least part of the computer instructions to implement the percutaneous nephrolithotomy navigation control method as described in any one of claims 5-8.

10. A computer-readable storage medium, wherein the storage medium stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the percutaneous nephrolithotomy navigation control method as described in any one of claims 5 to 8.

Images