Intelligent auxiliary navigation system for improving safety of urinary surgery operation

Abstract

The invention relates to the technical field of surgical auxiliary navigation, in particular to an intelligent auxiliary navigation system for improving the safety of urinary surgery. The method comprises the following steps: determining an instrument region of a urinary tract cross-sectional image according to a change trend of an instrument matching condition of the same organ region in the urinary tract cross-sectional image in an analysis period of each moment; determining an instrument posture offset moment according to the offset degree of the instrument area of the urinary tract cross-sectional image at each moment and the adjacent moment, and determining a tissue extrusion moment according to the change degree of the same tactile data in the analysis period of each moment; and further assisting in surgical instrument navigation according to the correlation between the instrument posture offset moment and the tissue extrusion moment. According to the system, related analysis is carried out on instrument deviation and tissue extrusion, the real-time extrusion condition of the surgical instrument on the tissue in the operation is monitored in real time, early warning is carried out on the surgical instrument in time, and then the safety of the urinary surgery operation is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of surgical operation auxiliary navigation, and in particular to an intelligent auxiliary navigation system for improving the safety of urological surgery. Background Art

[0002] Urological surgery includes radical prostatectomy, percutaneous nephrolithotomy and partial nephrectomy. Laparoscopy is a commonly used surgical method in urological surgery, especially in kidney, prostate and bladder surgery. Minimally invasive surgery brings significant advantages, such as reducing pain, shortening recovery time and reducing complications. By introducing artificial intelligence technology, it is possible to more accurately identify the location and anatomical structure of lesions, effectively avoid important blood vessels and nerves, reduce the incidence of surgical errors and complications, shorten the operation time, and significantly improve the safety of surgery.

[0003] Minimally invasive surgery uses an endoscope to provide vision and clarity for the penetration of surgical instruments, but it cannot fully reflect the position and posture of surgical instruments, causing the instruments themselves to deviate from the predetermined path during penetration and squeeze other tissues. In robot-assisted surgical navigation, the robot system relies on preoperative images and high-precision robotic arm control to achieve navigation, but the real-time tissue deformation monitoring capability during surgery is limited, making it difficult to dynamically feedback the interaction status between instruments and tissues; in multimodal image fusion navigation, ultrasound tracking of three-dimensional deformation of soft tissues still has delays, and cannot reflect the tissue squeezing status caused by instrument operation in real time; resulting in insufficient monitoring of real-time squeezing of tissues by surgical instruments during surgery, thereby reducing the safety of urological surgery. Summary of the invention

[0004] In order to solve the technical problem that the real-time monitoring capability of surgical instruments on tissue compression during surgery is insufficient, the purpose of the present invention is to provide an intelligent auxiliary navigation system that improves the safety of urological surgery. The technical solutions adopted are as follows: The present invention proposes an intelligent auxiliary navigation system for improving the safety of urological surgery, the system comprising: A data acquisition module, used to respectively acquire urinary tract tomographic images and different types of tactile data of the instrument in real time; An instrument region selection module is used to determine the instrument region of the urinary tract tomographic image at each moment according to the changing trend of the instrument matching situation of the same organ region in the urinary tract tomographic image within the analysis period at each moment; The offset squeezing analysis module is used to determine the time of device posture offset according to the offset degree of the device area of ​​the urinary tract tomographic image at each moment and its adjacent moments; and to determine the time of tissue squeezing according to the degree of change of the same tactile data within the analysis period at each moment; An instrument-assisted navigation module, which is used to assist instrument navigation in urological surgery according to the correlation between the instrument attitude offset moment and the tissue compression moment.

[0005] Further, the determining the instrument area of the urinary tract tomographic image at each moment includes: Determining the organ area of the urinary tract tomographic image; Obtaining the instrument matching degree of the organ area according to the difference between the area of the overlapping part of the organ area of the urinary tract tomographic image and the instrument template and the maximum area length; Denoting the cumulative sum of the differences in the instrument matching degrees of the same organ area at all adjacent two moments within the analysis period at each moment as the instrument trend index of each organ area of the urinary tract tomographic image at each moment; Calculating the cumulative sum of the differences in the instrument matching degrees of each organ area of the urinary tract tomographic image at each moment with the other organ areas respectively as the instrument significance index corresponding to each organ area; Obtaining the instrument possible index of each organ area of the urinary tract tomographic image at each moment according to the instrument trend index and the instrument significance index; selecting the instrument area from the urinary tract tomographic image based on the instrument possible index.

[0006] Further, the determining the instrument attitude offset moment includes: Determining the feature points of the instrument area of the urinary tract tomographic image; Performing optical flow tracking on the feature points of the urinary tract tomographic image, and denoting the concentration value of the angles between the line segments formed by every two feature points among all the feature points of the urinary tract tomographic image at the previous moment at each moment and the line segments formed by the corresponding optical flow matching points of every two feature points in the urinary tract tomographic image at each moment as the direction offset index at each moment; Denoting the concentration value of the absolute values of the differences between the distances between every two feature points among all the feature points of the urinary tract tomographic image at the previous moment at each moment and the distances between the corresponding optical flow matching points of every two feature points in the urinary tract tomographic image at each moment as the distance offset index at each moment; Obtaining the instrument offset index at each moment according to the direction offset index and the distance offset index; determining the instrument attitude offset moment based on the instrument offset index.

[0007] Further, the determining the tissue compression moment includes: Calculating the cumulative sum of the differences between each moment and all moments of the same kind of tactile data within its analysis period to obtain the enhancement index of each kind of tactile data at each moment; Obtaining the instantaneous change index of each kind of tactile data at each moment according to the difference between each kind of tactile data at each moment and its tactile preset value and the enhancement index; Normalize the cumulative product of the instantaneous change indexes of all types of tactile data at each moment to obtain the tactile anomaly index at each moment; determine the tissue extrusion moment based on the tactile anomaly index.

[0008] Further, the assisting in instrument navigation during urological surgery according to the correlation between the instrument attitude deviation moment and the tissue extrusion moment includes: Perform a negative correlation mapping on the time interval between each tissue extrusion moment and its previous tissue extrusion moment, and normalize the product of the mapping result and the time interval between each tissue extrusion moment and its adjacent previous instrument attitude deviation moment to obtain the warning coefficient at each tissue extrusion moment; Adjust the machine at the tissue extrusion moment when the warning coefficient is greater than the preset warning threshold.

[0009] Further, the selecting the instrument area from the urinary tract tomographic image based on the possible instrument index includes: Record the organ area corresponding to the largest possible instrument index in the urinary tract tomographic image as the instrument area.

[0010] Further, the determining the instrument attitude deviation moment based on the instrument deviation index includes: Record the moment when the instrument deviation index is greater than the preset deviation threshold as the instrument attitude deviation moment.

[0011] Further, the determining the tissue extrusion moment based on the tactile anomaly index includes: Record the moment when the tactile anomaly index is greater than the preset tactile threshold as the tissue extrusion moment.

[0012] Further, the method for determining the feature points of the instrument area in the urinary tract tomographic image is the Harris algorithm.

[0013] Further, the central value is the mean value.

[0014] The present invention has the following beneficial effects: In the embodiment of the present invention, the instrument is positioned in real time through the real-time urinary tract tomographic image during the operation to determine the instrument area; the attitude deviation is analyzed respectively through the deviation degree of the instrument area, and the instrument tactile anomaly is analyzed through the real-time feature change degree of the same type of tactile data to determine the instrument attitude deviation moment and the tissue extrusion moment; since there is a causal relationship between the mechanical attitude deviation and the extrusion of the tissue blood vessel, the risk of tissue extrusion caused by the instrument operation during the operation is predicted by analyzing the correlation between the instrument attitude deviation moment and the tissue extrusion moment in real time, the intraoperative feedback mechanism is improved and the automated decision-making ability is optimized, and the relevant personnel are assisted in instrument navigation, effectively improving the navigation safety during urological surgery. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the following will briefly introduce the accompanying drawings required for the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0016] Figure 1 The system structure diagram of an intelligent auxiliary navigation system for improving the safety of urological surgery provided by an embodiment of the present invention; Figure 2 The schematic diagram of a computer device of an intelligent auxiliary navigation device for improving the safety of urological surgery provided by an embodiment of the present invention. Detailed implementation manners

[0017] In order to further elaborate on the technical means and effects adopted by the present invention to achieve the intended invention purpose, the following, in combination with the accompanying drawings and preferred embodiments, will detail the specific implementation manners, structures, features, and effects of an intelligent auxiliary navigation system for improving the safety of urological surgery proposed according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0018] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which the present invention belongs.

[0019] The following will specifically describe the specific solution of an intelligent auxiliary navigation system for improving the safety of urological surgery provided by the present invention in conjunction with the accompanying drawings.

[0020] Embodiment 1: Please refer to Figure 1 , which shows the system block diagram of an intelligent auxiliary navigation system for improving the safety of urological surgery provided by an embodiment of the present invention. The system includes: a data acquisition module 110, an instrument area selection module 120, an offset extrusion analysis module 130, and an instrument assisted navigation module 140.

[0021] The data acquisition module 110 is used to respectively and real-time obtain different types of tactile data of the urinary tract tomographic image and the instrument.

[0022] The various components of the urinary system are mainly located in the abdominal region of the human body. To more accurately and comprehensively measure the real-time state of surgical instruments during the insertion process, a computed tomography (CT) scanner is used to take tomographic images of the abdomen of the patient to be measured, which are recorded as urinary tract tomographic images. The urinary tract tomographic images provide detailed cross-sectional images of the urinary system and can clearly show the position and insertion state of the surgical instruments. At the same time, multiple integrated sensors are set on the surface of the surgical instruments to collect all kinds of tactile data at each moment through the sensors. The operation risk is warned by combining the real-time insertion situation of the surgical instruments with the tactile feedback characteristics, and the insertion path of the surgical instruments is adjusted in real time.

[0023] If the surgical instrument squeezes tissues and blood vessels, the pressure and temperature applied to the sensors will change, and slight compression or movement of the tissues will cause changes in acceleration. In the embodiments of the present invention, the sensors integrated on the surgical instrument include a pressure sensor, a temperature sensor, and an acceleration sensor, and the types of tactile data include: pressure data, temperature data, and acceleration data.

[0024] It should be noted that the sampling frequencies of the urinary tract tomographic images and the tactile data are the same. In this embodiment, the sampling frequency is set to once per second, and the implementer can set it according to the specific situation. The urinary tract tomographic images at different moments are tomographic images of the same position of the abdomen of the patient to be measured. Before performing urological surgery, it is necessary to perform three-dimensional reconstruction on the tomographic images of different positions of the abdomen of the patient to be measured to obtain a three-dimensional model of the urinary system, determine the positions of blood vessels, nerves, and lesions, and the doctor designs the insertion path of the surgical instrument from the surgical incision position to the lesion position according to experience. During the operation, the surgical instrument inserts into the lesion position according to the insertion path. Among them, a multi-planar image reconstruction algorithm is selected for three-dimensional reconstruction.

[0025] The instrument area selection module 120 is configured to determine the instrument area of the urinary tract tomographic image at each moment according to the change trend of the instrument matching situation in the same organ area in the urinary tract tomographic image within the analysis period at each moment.

[0026] In the initial stage of the surgical operation, the insertion position of the surgical instrument is relatively shallow, and only a small part of the instrument exists in the urinary tract tomographic image. As the instrument inserts deeper, the doctor will insert the surgical instrument into the corresponding organ, so that the surgical instrument will gradually appear completely in the corresponding organ area in the urinary tract tomographic image. The more complete the surgical instrument appears in the organ area, the greater the instrument matching degree of the organ area. Therefore, the instrument matching degree in the same organ area shows a gradually increasing trend within a period of time, and the possibility of the surgical instrument appearing in the organ area is greater, and then the instrument area is determined.

[0027] Preferably, in some possible implementation manners of the embodiments of the present invention, the method for obtaining the instrument area includes: determining the organ area of the urinary tract tomographic image; obtaining the instrument matching degree of the organ area according to the difference between the area of the overlapping part of the organ area of the urinary tract tomographic image and the instrument template and the maximum area length; taking the sum of the differences in the instrument matching degrees of the same organ area at all adjacent two moments within each analysis period at each moment as the instrument trend index of each organ area of the urinary tract tomographic image at each moment; calculating the sum of the differences in the instrument matching degrees of each organ area of the urinary tract tomographic image at each moment with the other organ areas respectively as the instrument significant index corresponding to each organ area; obtaining the instrument possible index of each organ area of the urinary tract tomographic image at each moment according to the instrument trend index and the instrument significant index; and selecting the instrument area from the urinary tract tomographic image based on the instrument possible index.

[0028] During the surgical process, each tissue and organ will not change significantly in the urinary tract tomographic image. In the embodiments of the present invention, a neural network is used to obtain an organ area corresponding to each organ in the abdomen in the urinary tract tomographic image. Since the surgical instruments for the urinary system are generally long and narrow, the length of the surgical instrument is an important feature for analyzing the matching degree between the organ area and the surgical instrument. If the difference in the maximum area length between the organ area and the instrument template is smaller and the area of the overlapping part is larger, it indicates that the shape of the organ area is more similar to that of the surgical instrument, and the possibility that the organ area is the surgical instrument is greater, so the instrument matching degree is greater. Therefore, there is a positive correlation between the area of the overlapping part of the organ area of the urinary tract tomographic image and the instrument template and the instrument matching degree, and there is a negative correlation between the absolute value of the difference in the maximum area length between the organ area of the urinary tract tomographic image and the instrument template and the instrument matching degree. For each organ area of the urinary tract tomographic image, the instrument matching degree Z of the organ area is expressed by the formula: ; In the formula, is the area of the overlapping part of the organ area and the instrument template; L is the maximum area length of the organ area; is the maximum area length of the instrument template; is the absolute value function; is a preset positive number, taking an empirical value of 0.01, and its function is to prevent the fraction from being meaningless due to the denominator being zero. It should be noted that the maximum area length of the instrument template refers to the maximum area length of the instrument area in the instrument template.

[0029] The method for obtaining the instrument template is as follows: Obtain the urinary tract tomographic images when the surgical instrument reaches the same lesion position as the patient to be measured during the historical surgical procedure, use semantic segmentation to remove the irrelevant regions, and take the remaining instrument region as the instrument template. It should be noted that the images are collected using the same device, so that the sizes of the urinary tract tomographic images and the instrument template are the same, and the two can be in the same coordinate system, enabling the analysis of the overlapping part between the organ regions of the urinary tract tomographic images and the instrument template.

[0030] In one implementation manner of the embodiment of the present invention, the method for determining the maximum region length of the region is as follows: Obtain the minimum bounding rectangle of the region, and take the length of the minimum bounding rectangle as the maximum region length of the region.

[0031] If the instrument trend index and the instrument significant index are larger, it indicates that the upward trend of the instrument matching degree in the same organ region of the urinary tract tomographic images during each analysis period at each moment is more obvious, and the instrument matching degree of each organ region in the urinary tract tomographic images at each moment is larger compared to other organ regions. Then, the possibility of a surgical instrument appearing in each organ region is greater, and the instrument probability index is larger. Therefore, both the instrument significant index and the instrument trend index have a positive correlation with the organ probability index. In the embodiment of the present invention, the sum value of the instrument trend index and the instrument significant index of each organ region of the urinary tract tomographic images at each moment is normalized to obtain the instrument probability index of the corresponding organ region.

[0032] In the embodiment of the present invention, the correlation relationship between the instrument trend index, the instrument significant index, and the instrument probability index can also be constructed through other basic mathematical operations, such as multiplication, which will not be limited and elaborated herein.

[0033] In a specific implementation manner of the embodiment of the present invention, the instrument probability index of the organ region is expressed by the formula: ; In the formula, is the instrument probability index of the ath organ region of the urinary tract tomographic images at each moment; M is the total number of moments during each analysis period at each moment; is the instrument matching degree of the ath organ region in the urinary tract tomographic images at the mth moment during each analysis period at each moment; is the instrument matching degree of the ath organ region in the urinary tract tomographic images at the (m + 1)th moment during each analysis period at each moment; N is the total number of organ regions in the urinary tract tomographic images at each moment; is the instrument matching degree of the ath organ region in the urinary tract tomographic images at each moment; is the instrument matching degree of the nth organ region other than the ath organ region in the urinary tract tomographic images at each moment; The instrument trend index of the a-th organ region in the urinary tract tomographic image at each moment; The instrument significant index of the a-th organ region in the urinary tract tomographic image at each moment; Norm is a normalization function. It should be noted that the same organ region in different urinary tract tomographic images represents the same organ.

[0034] Select the organ region corresponding to the maximum instrument possible index in the urinary tract tomographic image at each moment as the instrument region to complete the real-time positioning of the surgical instrument.

[0035] In a specific implementation manner of the embodiment of the present invention, each moment is the last moment within its analysis period, and the analysis period contains 5 moments.

[0036] The offset extrusion analysis module 130 is used to determine the instrument attitude offset moment according to the offset degree of the instrument region in the urinary tract tomographic images of each moment and its adjacent moment; and determine the tissue extrusion moment according to the change degree of the same kind of tactile data within the analysis period of each moment.

[0037] During the surgical process, the staff needs to operate the surgical instrument to gradually penetrate into the lesion site. The surgical instrument may deviate from the predetermined path during the penetration process, resulting in squeezing other tissues and blood vessels. By analyzing the offset degree of the instrument region and the tactile feedback situation, the instrument attitude offset moment and the tissue extrusion moment are determined, so as to issue a risk alarm.

[0038] Preferably, in some possible implementation manners of the embodiment of the present invention, the method for obtaining the instrument attitude offset moment includes: determining the feature points of the instrument region in the urinary tract tomographic image; performing optical flow tracking on the feature points of the urinary tract tomographic image, and recording the concentration value of the included angles between the line segments formed by every two feature points among all the feature points in the urinary tract tomographic image of the previous moment of each moment and the line segments formed by the corresponding optical flow matching points of every two feature points in the urinary tract tomographic image of each moment as the direction offset index of each moment; recording the concentration value of the absolute value of the difference between the distances between every two feature points among all the feature points in the urinary tract tomographic image of the previous moment of each moment and the distances between the corresponding optical flow matching points of every two feature points in the urinary tract tomographic image of each moment as the distance offset index of each moment; obtaining the instrument offset index of each moment according to the direction offset index and the distance offset index; and determining the instrument attitude offset moment based on the instrument offset index.

[0039] Generally, surgical instruments will penetrate into the lesion location in a fixed posture. A change in the advancing posture of the surgical instrument indicates that it may deviate, and further, the relative positions of the feature points in the instrument area will change. The degree of deviation of the surgical instrument is determined by the degree of change in the direction and distance of the line segments formed by different feature points at adjacent moments. If the angle and length differences between the line segments formed by every two feature points among all the feature points of the previous urinary tract tomographic image at each moment and the line segments formed by the corresponding optical flow matching points of every two feature points in the urinary tract tomographic image at each moment are smaller, the smaller the attitude deviation degree of the instrument area at each moment, and the smaller the instrument deviation index. Therefore, the direction deviation index, the distance deviation index, and the instrument deviation index are positively correlated. In the embodiments of the present invention, the product of the direction deviation index and the distance deviation index at each moment is normalized to obtain the instrument deviation index. In the embodiments of the present invention, the Norm function is used for normalization. In the embodiments of the present invention, other normalization methods can also be selected, such as function transformation, maximum-minimum normalization, etc. The normalization method is not limited herein.

[0040] In the embodiments of the present invention, the correlation relationship between the direction deviation index, the distance deviation index, and the instrument deviation index can also be constructed through other basic mathematical operations, which are not limited and elaborated herein.

[0041] It should be noted that indicators such as the mean, median, and mode can all reflect the central level of a set of data. The overall deviation degree of the instrument area is analyzed through the deviation degree of pairwise feature points. In the embodiments of the present invention, the central value is the mean, and the mean can also be replaced with indicators such as the median or mode.

[0042] In the embodiments of the present invention, the Harris algorithm is selected to obtain the feature points in the urinary tract tomographic image, and the Lucas-Kanade method is used for optical flow tracking; in other embodiments, the Shi-Tomasi algorithm and other corner detection algorithms can also be selected to select the feature points, and optical flow algorithms such as the Horn-Schunck optical flow algorithm are used for optical flow tracking.

[0043] The greater the instrument deviation index of the surgical instrument, the greater the possibility of attitude deviation at that moment. The moments when the instrument deviation index is greater than the preset deviation threshold are recorded as the instrument attitude deviation moments.

[0044] In an implementation manner of the embodiments of the present invention, the preset deviation threshold is set to 0.9, and the implementer can set it according to the specific situation.

[0045] During the operation, if the surgical instrument exerts pressure on tissues and blood vessels, the pressure and temperature on the surface of the surgical instrument gradually increase, and the tissues will undergo slight compression or movement. Especially at the moment of initial contact or pressure application, it will cause an instantaneous increase in acceleration. Therefore, according to the degree of change of the same type of tactile data within a period of time, it is determined whether the surgical instrument squeezes the tissue at each moment, and then the tissue squeezing moment is determined.

[0046] Preferably, in some possible implementation manners of the embodiments of the present invention, the method for obtaining the tactile anomaly index includes: calculating the cumulative sum of the differences between each moment and all moments within its analysis period of the same type of tactile data to obtain the enhancement index of each type of tactile data at each moment; obtaining the instantaneous change index of each type of tactile data at each moment according to the difference between each type of tactile data at each moment and its tactile preset value, and the enhancement index; normalizing the product of the instantaneous change indexes of all types of tactile data at each moment to obtain the tactile anomaly index at each moment.

[0047] If the difference between each moment and the moments within its analysis period of the same type of tactile data is greater, the degree of improvement of each type of tactile data is more significant, and the degree of change is greater; the tactile preset value is the normal value of each type of tactile data. If the difference between the tactile data at each moment and the normal value is greater, and each type of tactile data changes more compared to the normal value, then the tactile feedback of the surgical instrument at each moment is more abnormal. Therefore, the difference between each type of tactile data at each moment and its tactile preset value, and the enhancement index are both positively correlated with the instantaneous change index. By comprehensively analyzing the changes of all types of tactile data, the tactile anomaly degree of the surgical instrument at each moment can be analyzed more accurately to obtain the tactile anomaly index. It should be noted that in the embodiments of the present invention, the tactile preset value of each type of tactile data is set to the tactile data of each type when the surgical instrument just enters the body of the patient to be measured.

[0048] In a specific implementation manner of the embodiments of the present invention, the tactile anomaly index is expressed by the formula: ; In the formula, C is the tactile anomaly index at each moment; K is the number of types of tactile data; is the k-th type of tactile data at each moment; is the tactile preset value of the k-th type of tactile data; is the instantaneous change index of the k-th type of tactile data at each moment; M is the total number of moments within the analysis period at each moment; is the k-th type of tactile data at the m-th moment other than the last moment within the analysis period at each moment; is the enhancement index of the k-th type of tactile data at each moment.

[0049] The greater the tactile anomaly index of the surgical instrument, the greater the likelihood of squeezing the body tissue at that moment. The moment when the tactile anomaly index is greater than the preset tactile threshold is recorded as the tissue squeezing moment.

[0050] In an implementation manner of the embodiment of the present invention, the preset tactile threshold is set to 0.9, and the implementer can set it according to specific circumstances.

[0051] The instrument-assisted navigation module 140 is used to assist in the instrument navigation during urological surgery according to the correlation between the instrument attitude deviation moment and the tissue squeezing moment.

[0052] The purpose of this solution is to give an early warning of the situation of tissue squeezing caused by the deviation of the surgical instrument during the surgical process. However, it is not certain that the abnormal deviation of the surgical instrument will cause tissue squeezing, nor is it certain that the squeezing of other tissues is caused by the abnormal deviation of the surgical instrument. Therefore, it is necessary to analyze the correlation between the instrument attitude deviation moment and the tissue squeezing moment and give an early warning at the moment of tissue squeezing.

[0053] Preferably, in some possible implementation manners of the embodiment of the present invention, the method for obtaining the warning coefficient includes: performing a negative correlation mapping on the time interval between each tissue squeezing moment and the previous tissue squeezing moment, and normalizing the product of the mapping result and the time interval between each tissue squeezing moment and the adjacent previous instrument attitude deviation moment to obtain the warning coefficient for each tissue squeezing moment.

[0054] Since there is a causal relationship between the mechanical attitude deviation and the squeezing of the tissue, the mechanical attitude deviation is the cause and the squeezing of the tissue is the result. There is a sequential order between the two moments, so the mechanical attitude deviation and the squeezing of the tissue are in one-to-one correspondence and there is a delay in the occurrence moment. If the time interval between each tissue squeezing moment and the previous tissue squeezing moment is smaller, the greater the influence of the squeezing generated by the previous tissue squeezing moment on the surgical instrument at each tissue squeezing moment, the greater the likelihood of the surgical instrument squeezing the tissue at each moment, and the greater the need for early warning; if the time interval between each tissue squeezing moment and the adjacent previous instrument attitude deviation moment is smaller, the greater the likelihood of being in the delay between the two situations, the smaller the likelihood of the surgical instrument squeezing the tissue at each moment, and the smaller the need for early warning.

[0055] In the embodiment of the present invention, the ratio of the time interval between each tissue squeezing moment and the adjacent previous instrument attitude deviation moment to the time interval between each tissue squeezing moment and the previous tissue squeezing moment is normalized to obtain the warning coefficient. The normalization process is performed using the Norm function, and other normalization methods can also be used, which will not be elaborated here.

[0056] Since tissue extrusion will occur when the surgical instrument is at the tissue extrusion moment with the warning coefficient greater than the preset warning threshold, a warning is issued at the tissue extrusion moment with the warning coefficient greater than the preset warning threshold, so as to assist in reminding the staff to adjust the penetration path of the surgical instrument in real time when the surgical instrument squeezes the tissue, and prompting the doctor to pay attention to adjusting the operation direction or force of the surgical instrument. There may be other situations during the operation that can also cause the instrument to squeeze the tissue, and this solution does not analyze the above other situations.

[0057] In one implementation manner of the embodiment of the present invention, the preset warning threshold is set to 0.8, and the implementer can set it by himself according to the specific situation.

[0058] To improve the safety of urological surgery, a robot such as the da Vinci Surgical System can be used to assist the doctor in performing delicate surgical operations. The robot uses devices such as a high-definition 3D imaging system to magnify the surgical field in the patient's body and clearly present it on the screen in front of the doctor, while reducing the tremors of the doctor's hand; through augmented reality (AR) glasses or mixed reality (MR) headsets, virtual information such as the location of the lesion and the course of blood vessels is superimposed on the real surgical field to assist the doctor in precise positioning.

[0059] The intelligent assisted navigation system realizes the goal of "precision surgery" centered on the patient by deeply integrating the doctor's experience and the precision of the machine through the full-process support of "precision planning - real-time navigation - intelligent warning".

[0060] So far, the present invention is completed.

[0061] Embodiment 2: Figure 2 It is a schematic diagram of a computer device of an intelligent assisted navigation device for improving the safety of urological surgery provided by an embodiment of the present invention. Exemplarily, as Figure 2 shown, the computer device includes: a memory 201, a processor 202, and a computer program 203 stored in the memory 201 and running on the processor 202. When the processor 202 executes the computer program 203, the computer device can execute any of the intelligent assisted navigation systems for improving the safety of urological surgery introduced above.

[0062] In addition, an embodiment of the present application also protects a device, which may include a memory and a processor. The memory stores executable program code, and the processor is used to call and execute the executable program code to execute an intelligent assisted navigation system for improving the safety of urological surgery provided by an embodiment of the present application.

[0063] In this embodiment, the device can be divided into functional modules according to the above method examples. For example, it can correspond to each functional module, or two or more functions can be integrated into one processing module. The above integrated module can be implemented in the form of hardware. It should be noted that the division of modules in this embodiment is illustrative, only a logical function division, and there can be other division methods in actual implementation.

[0064] It should be understood that the device provided in this embodiment is used to execute the above intelligent auxiliary navigation system for improving the safety of urological surgery, so the same effects as the above implementation method can be achieved.

[0065] In the case of adopting an integrated unit, the device can include a processing module and a storage module. Among them, when the device is applied to a device, the processing module can be used to control and manage the actions of the device. The storage module can be used to support the device to execute mutual program codes, etc.

[0066] Among them, the processing module can be a processor or a controller, which can implement or execute various exemplary logical blocks, modules, and circuits described in combination with the disclosure of this application. The processor can also be a combination that realizes computing functions, such as including a combination of one or more microprocessors, a combination of digital signal processing (DSP) and a microprocessor, etc. The storage module can be a memory.

[0067] Embodiment 3: This embodiment also provides a computer-readable storage medium, in which computer program code is stored. When the computer program code runs on a computer, it causes the computer to execute the above-related method steps to implement an intelligent auxiliary navigation system for improving the safety of urological surgery provided in the above embodiment.

[0068] Among them, the device and the computer-readable storage medium provided in this embodiment are both used to execute the corresponding system provided above. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding system provided above, and will not be elaborated here.

[0069] It should be noted that the above sequence of embodiments of the present invention is only for description and does not represent the superiority or inferiority of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0070] Each embodiment in this specification is described in a progressive manner. The same or similar parts between each embodiment can be referred to each other, and the key points of each embodiment are the differences from other embodiments.

[0071] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. An intelligent auxiliary navigation system for improving the safety of urological surgery, characterized in that: The system includes: A data acquisition module, used to respectively acquire urinary tract tomographic images and different types of tactile data of the instrument in real time; An instrument region selection module is used to determine the instrument region of the urinary tract tomographic image at each moment according to the changing trend of the instrument matching situation of the same organ region in the urinary tract tomographic image within the analysis period at each moment; The offset squeezing analysis module is used to determine the time of device posture offset according to the offset degree of the device area of ​​the urinary tract tomographic image at each moment and its adjacent moments; and to determine the time of tissue squeezing according to the degree of change of the same tactile data within the analysis period at each moment; The instrument-assisted navigation module is used to assist instrument navigation in urological surgery based on the correlation between the instrument posture deviation moment and the tissue compression moment.

2. The intelligent auxiliary navigation system for improving the safety of urological surgery according to claim 1, characterized in that: The method of determining the device area of ​​the urinary tract tomographic image at each moment includes: Determine organ regions in cross-sectional images of the urinary tract; Obtaining the device matching degree of the organ region according to the difference in the area of ​​the overlapping part and the maximum region length between the organ region of the urinary tract tomographic image and the device template; The cumulative sum of the differences of the instrument matching degrees of the same organ region at two adjacent moments in the analysis period at each moment is recorded as the instrument trend index of each organ region of the urinary tract tomographic image at each moment; Calculate the cumulative sum of the differences between the instrument matching degrees of each organ region of the urinary tract tomographic image at each moment and the remaining organ regions as the instrument significance index corresponding to each organ region; According to the instrument trend index and the instrument significant index, the instrument possible index of each organ region in the urinary tract tomographic image at each moment is obtained; and the instrument region is selected from the urinary tract tomographic image based on the instrument possible index.

3. The intelligent auxiliary navigation system for improving the safety of urological surgery according to claim 1, characterized in that: Determining the time of deviation of the apparatus posture comprises: determining feature points of the device region of the urinary tract cross-sectional image; Perform optical flow tracking on the feature points of the urinary tract tomographic image, and record the concentrated value of the angle between the line segment formed by every two feature points of all feature points of the urinary tract tomographic image at the previous moment and the line segment formed by the corresponding optical flow matching points of every two feature points in the urinary tract tomographic image at each moment as the direction deviation index at each moment; The concentrated value of the absolute value of the difference between the distance between every two feature points of all feature points of the urinary tract tomographic image at the previous moment and the distance between every two feature points and the corresponding optical flow matching points in the urinary tract tomographic image at each moment is recorded as the distance offset index at each moment; According to the direction offset index and the distance offset index, the instrument offset index at each moment is obtained; and based on the instrument offset index, the instrument posture offset moment is determined.

4. The intelligent auxiliary navigation system for improving the safety of urological surgery according to claim 1, characterized in that: Determining the tissue squeezing moment comprises: Calculate the cumulative sum of the differences between each moment and the same type of tactile data at all moments in the analysis period to obtain an enhancement index for each type of tactile data at each moment; According to the difference between each type of tactile data at each moment and its preset tactile value, and the enhancement index, an instantaneous change index of each type of tactile data at each moment is obtained; The cumulative product of the instantaneous change indexes of all kinds of tactile data at each moment is normalized to obtain the abnormal tactile index at each moment; and the tissue compression moment is determined based on the abnormal tactile index.

5. The intelligent auxiliary navigation system for improving the safety of urological surgery according to claim 1, characterized in that: The method of assisting instrument navigation in urological surgery based on the correlation between the instrument posture deviation moment and the tissue squeezing moment includes: A negative correlation mapping is performed on the time interval between each tissue squeezing moment and its previous tissue squeezing moment, and the product of the mapping result and the time interval between each tissue squeezing moment and its adjacent previous instrument posture deviation moment is normalized to obtain the warning coefficient of each tissue squeezing moment; The machine is adjusted at the tissue compression moment when the warning coefficient is greater than the preset warning threshold.

6. The intelligent auxiliary navigation system for improving the safety of urological surgery according to claim 2, characterized in that: The selecting of the device region from the urinary tract tomographic image based on the possible indicators of the device comprises: The organ region corresponding to the largest possible instrument indicator in the urinary tract tomographic image is recorded as the instrument region.

7. The intelligent auxiliary navigation system for improving the safety of urological surgery according to claim 3, characterized in that: The step of determining the device posture deviation time based on the device deviation index comprises: The moment when the instrument deviation index is greater than a preset deviation threshold is recorded as the instrument posture deviation moment.

8. The intelligent auxiliary navigation system for improving the safety of urological surgery according to claim 4, characterized in that: The step of determining the tissue squeezing time based on the abnormal tactile sensation index comprises: The moment when the abnormal tactile index is greater than the preset tactile threshold is recorded as the tissue compression moment.

9. The intelligent auxiliary navigation system for improving the safety of urological surgery according to claim 3, characterized in that: The method for determining the feature points of the instrument area of ​​the urinary tract cross-sectional image is the Harris algorithm.

10. The intelligent auxiliary navigation system for improving the safety of urological surgery according to claim 3, characterized in that: The central value is the mean value.

Images