A method and system for lesion confirmation in endoscopic surgery

Abstract

The present invention provides a method and system for lesion confirmation in laparoscopic surgery, which relates to the technical field of lesion localization. By obtaining a scanned image of a lesion organ; then performing three-dimensional modeling on the lesion organ according to the scanned image of the lesion organ; then inputting the scanned image of the lesion organ into a preset bed adjustment model, generating and adjusting the operating bed according to the bed angle information; then obtaining and adjusting the three-dimensional model of the lesion organ according to the real-time picture information of the visual laparoscope rod, so that the display angle of view of the three-dimensional model of the lesion organ is consistent with the angle of view of the real-time picture; finally obtaining and calculating the relative position between the positioning laparoscope rod and the preliminary positioning lesion position according to the current position of the positioning laparoscope rod and the preliminary positioning lesion position, so as to control the positioning laparoscope rod and the visual laparoscope rod to determine the lesion position, thereby assisting the doctor to determine the lesion position without spending much time adjusting the operating bed and shortening the operation time.

Description

Technical Field

[0001] The present invention relates to the technical field of lesion localization, and in particular, to a method and system for lesion confirmation in laparoscopic surgery. Background Art

[0002] Laparoscopic surgery is a newly developed minimally invasive method and an inevitable trend in the development of future surgical methods. As a common minimally invasive surgery, it has been rapidly popularized clinically in recent years. Laparoscopic surgery can replace traditional open surgery in some specific situations and rely on special surgical instruments to complete the surgical treatment of in-vivo lesion tissues through a smaller incision. The surgical injury is small and the postoperative recovery is fast.

[0003] During the process of doctors searching for lesions, they often need to adjust the position of the operating table for easy observation. Some lesions are located in hard-to-detect positions, so it takes more time to adjust the operating table to determine the position of the lesions. Summary of the Invention

[0004] The purpose of the present invention is to provide a method and system for lesion confirmation in laparoscopic surgery to improve the problem that in the existing technology, some lesions are located in hard-to-detect positions and it takes more time to adjust the operating table.

[0005] In a first aspect, an embodiment of the present application provides a method for lesion confirmation in laparoscopic surgery, including the following steps:

[0006] Obtain a scanned image of a lesion organ, where the scanned image includes a preliminary localization of the lesion position;

[0007] Perform three-dimensional modeling on the lesion organ according to the scanned image of the lesion organ to obtain a three-dimensional model of the lesion organ, where the three-dimensional model of the lesion organ includes a preliminary localization of the lesion position;

[0008] Input the scanned image of the lesion organ into a preset bed position adjustment model, generate and adjust the operating table according to the bed angle information;

[0009] Obtain and adjust the three-dimensional model of the lesion organ according to the real-time picture information of the visual laparoscope rod, so that the display angle of view of the three-dimensional model of the lesion organ is consistent with the angle of view of the real-time picture;

[0010] Obtain and calculate the relative position between the positioning laparoscope rod and the preliminary localization of the lesion position according to the current position of the positioning laparoscope rod and the preliminary localization of the lesion position, so as to control the positioning laparoscope rod and the visual laparoscope rod to determine the lesion position.

[0011] In the above implementation process, by obtaining the scanned image of the diseased organ, the preliminary lesion position is included in the scanned image, so that the scanned image can display the preliminary lesion position; then, based on the scanned image of the diseased organ, a three-dimensional model of the diseased organ is built to obtain a three-dimensional model of the diseased organ, and the preliminary lesion position is included in the three-dimensional model of the diseased organ, which helps the doctor observe the diseased organ; then, the scanned image of the diseased organ is input into a preset bed adjustment model to generate and adjust the operating table according to the bed angle information. The most suitable bed angle information can be obtained through the preset bed adjustment model, and then the operating table is adjusted, thus saving the operating table adjustment time; then, the three-dimensional model of the diseased organ is adjusted according to the real-time picture information of the vision endoscope rod, so that the display angle of the three-dimensional model of the diseased organ is consistent with the angle of the real-time picture to assist the doctor in observing the lesion; finally, the relative position between the positioning endoscope rod and the preliminary lesion position is calculated based on the current position of the positioning endoscope rod and the preliminary lesion position to control the positioning endoscope rod and the vision endoscope rod to determine the lesion position. A control signal is generated through the relative position to control the positioning endoscope rod and the vision endoscope rod to determine the lesion position, thereby assisting the doctor in quickly confirming the lesion position, so that the doctor does not need to spend a lot of time adjusting the operating table and can assist the doctor in determining the lesion position, shortening the operation time.

[0012] Based on the first aspect, in some embodiments of the present invention, the following steps are further included:

[0013] Input the scanned image of the diseased organ into a preset surgical parameter pre-adjustment model to generate the optimal bed angle information, the optimal positioning endoscope rod parameter information, and the optimal vision endoscope rod parameter information.

[0014] Based on the first aspect, in some embodiments of the present invention, the following steps are further included:

[0015] Obtain the patient information corresponding to the scanned image of the diseased organ;

[0016] Match according to the gender information in the patient information in a preset bed adjustment model library to obtain the corresponding bed adjustment model.

[0017] Based on the first aspect, in some embodiments of the present invention, the following steps are further included:

[0018] Obtain and use the final operating table angle information and the corresponding scanned image information of the diseased organ of multiple endoscopic surgeries as sample information;

[0019] Train the sample information using a neural network algorithm to obtain a bed adjustment model.

[0020] Based on the first aspect, in some embodiments of the present invention, the following steps are further included:

[0021] Obtain and use the final operating table angle information of multiple laparoscopic surgeries and the scanned image information of the corresponding lesion organs as initial samples;

[0022] Obtain the medical record information of each laparoscopic surgery;

[0023] Classify the initial samples according to the preset classification rules based on the medical record information to obtain sub-sample information of multiple categories;

[0024] Train the sub-sample information of each category separately using a neural network algorithm to obtain bed adjustment models of multiple categories, so as to form a bed adjustment model library.

[0025] Based on the first aspect, in some embodiments of the present invention, the steps for obtaining a scanned image of a lesion organ, where the scanned image includes preliminarily locating the lesion position, include the following steps:

[0026] Obtain lesion organ information;

[0027] Scan the lesion organ according to the lesion organ information to obtain a scanned image of the lesion organ, where the scanned image includes preliminarily locating the lesion position.

[0028] Based on the first aspect, in some embodiments of the present invention, the steps for performing three-dimensional modeling on the lesion organ according to the scanned image of the lesion organ to obtain a three-dimensional model of the lesion organ, where the three-dimensional model of the lesion organ includes preliminarily locating the lesion position, include the following steps:

[0029] Obtain an image sequence of multiple angles according to the scanned image of the lesion organ;

[0030] Perform three-dimensional modeling according to the image sequence of multiple angles to obtain a three-dimensional model of the lesion organ, where the three-dimensional model of the lesion organ includes preliminarily locating the lesion position.

[0031] In a second aspect, an embodiment of the present application provides a lesion confirmation system for laparoscopic surgery, including:

[0032] A scanned image acquisition module for acquiring a scanned image of a lesion organ, where the scanned image includes preliminarily locating the lesion position;

[0033] A three-dimensional modeling module for performing three-dimensional modeling on the lesion organ according to the scanned image of the lesion organ to obtain a three-dimensional model of the lesion organ, where the three-dimensional model of the lesion organ includes preliminarily locating the lesion position;

[0034] A bed angle adjustment module for inputting the scanned image of the lesion organ into a preset bed adjustment model, generating and adjusting the operating table according to the bed angle information;

[0035] A visual adjustment module, configured to obtain and adjust a three-dimensional model of a diseased organ based on real-time image information of a visual endoscope rod, so that the display view angle of the three-dimensional model of the diseased organ is consistent with the view angle of the real-time image;

[0036] A lesion determination module, configured to obtain and calculate the relative position between the positioning endoscope rod and the preliminarily positioned lesion position based on the current position of the positioning endoscope rod and the preliminarily positioned lesion position, so as to control the positioning endoscope rod and the visual endoscope rod to determine the lesion position.

[0037] In the above implementation process, a scanning image acquisition module is used to acquire a scanning image of a diseased organ, and the scanning image includes the preliminarily positioned lesion position, so that the scanning image can display the preliminarily positioned lesion position; a three-dimensional modeling module performs three-dimensional modeling on the diseased organ according to the scanning image of the diseased organ to obtain a three-dimensional model of the diseased organ, and the three-dimensional model of the diseased organ includes the preliminarily positioned lesion position, and the three-dimensional model helps doctors observe the diseased organ; a bed angle adjustment module inputs the scanning image of the diseased organ into a preset bed adjustment model, generates and adjusts the operating bed according to the bed angle information, and the most suitable bed angle information can be obtained through the preset bed adjustment model, and then the operating bed is adjusted, thereby saving the operating bed adjustment time; the visual adjustment module obtains and adjusts the three-dimensional model of the diseased organ according to the real-time image information of the visual endoscope rod, so that the display view angle of the three-dimensional model of the diseased organ is consistent with the view angle of the real-time image to assist doctors in observing the lesion; the lesion determination module obtains and calculates the relative position between the current positioning endoscope rod position and the preliminarily positioned lesion position to control the positioning endoscope rod and the visual endoscope rod to determine the lesion position, and generates a control signal according to the relative position to control the positioning endoscope rod and the visual endoscope rod to determine the lesion position, thereby assisting doctors in quickly confirming the lesion position, so that it is not necessary to spend a lot of time adjusting the operating bed, and the position of the lesion can be assisted to be determined by doctors, shortening the operation time.

[0038] In a third aspect, an embodiment of the present application provides an electronic device, which includes a memory for storing one or more programs; a processor. When the one or more programs are executed by the processor, the method according to any one of the first aspects above is implemented.

[0039] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the method according to any one of the first aspects above is implemented.

[0040] The embodiments of the present invention have at least the following advantages or beneficial effects:

[0041] An embodiment of the present invention provides a method and system for lesion confirmation in laparoscopic surgery. By acquiring a scanned image of a lesion organ, the scanned image includes a preliminary localization of the lesion position, such that the scanned image can display the preliminary localization of the lesion position; then, a three-dimensional model of the lesion organ is constructed based on the scanned image of the lesion organ to obtain a three-dimensional model of the lesion organ, and the three-dimensional model of the lesion organ includes the preliminary localization of the lesion position, and the three-dimensional model helps a doctor to observe the lesion organ; then, the scanned image of the lesion organ is input into a preset operating table adjustment model to generate and adjust the operating table according to the bed angle information. The most suitable bed angle information can be obtained through the preset operating table adjustment model, and then the operating table is adjusted, thereby saving the operating table adjustment time; then, the three-dimensional model of the lesion organ is adjusted according to the real-time picture information of the visual laparoscope rod, such that the display angle of the three-dimensional model of the lesion organ is consistent with the angle of view of the real-time picture to assist the doctor in observing the lesion; finally, the relative position between the positioning laparoscope rod and the preliminary localization of the lesion position is calculated based on the current position of the positioning laparoscope rod and the preliminary localization of the lesion position to control the positioning laparoscope rod and the visual laparoscope rod to determine the lesion position. A control signal is generated through the relative position to control the positioning laparoscope rod and the visual laparoscope rod to determine the lesion position, thereby assisting the doctor in quickly confirming the lesion position, so that the doctor does not need to spend a lot of time adjusting the operating table and can assist the doctor in determining the lesion position, shortening the operation time. By matching the corresponding operating table adjustment model, the obtained bed angle information better meets the surgical requirements, further shortening the operating table adjustment time. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] To more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for use in the embodiments. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as limiting the scope. For those of ordinary skill in the art, other related drawings can be obtained based on these drawings without creative efforts.

[0043] Figure 1 It is a flowchart of a method for lesion confirmation in laparoscopic surgery provided by an embodiment of the present invention;

[0044] Figure 2 It is a flowchart of the steps for matching an operating table adjustment model according to an organ provided by an embodiment of the present invention;

[0045] Figure 3 It is a flowchart of the steps for matching an operating table adjustment model according to gender provided by an embodiment of the present invention;

[0046] Figure 4 It is a block diagram of the structure of a system for lesion confirmation in laparoscopic surgery provided by an embodiment of the present invention;

[0047] Figure 5 A structural block diagram of an electronic device provided by an embodiment of the present invention.

[0048] Icons: 110 - Scanning image acquisition module; 120 - 3D modeling module; 130 - Bed position angle adjustment module; 140 - Visual adjustment module; 150 - Lesion determination module; 101 - Memory; 102 - Processor; 103 - Communication interface. Detailed implementation manners

[0049] To make the objectives, technical solutions, and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are some, but not all, of the embodiments of the present application. Components of the embodiments of the present application usually described and illustrated in the accompanying drawings here can be arranged and designed in various different configurations.

[0050] Therefore, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the present application claimed, but merely represents selected embodiments of the present application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts fall within the scope of protection of the present application.

[0051] Embodiment

[0052] The following will describe in detail some implementation manners of the present application with reference to the accompanying drawings. Without conflict, the following embodiments and the features in the embodiments can be combined with each other.

[0053] Please refer to Figure 1 , Figure 1 A flowchart of a method for lesion confirmation in endoscopic surgery provided by an embodiment of the present invention. The method for lesion confirmation in endoscopic surgery includes the following steps:

[0054] Step S110: Obtain a scanning image of the lesion organ, where the scanning image includes a preliminary location of the lesion; the above scanning image can be image data output by medical imaging devices such as CT and MRI. In this embodiment, the organ can be preliminarily examined before scanning, and a lesion location identifier can be set, which can be specifically completed through the following steps:

[0055] First, when a lesion is detected through an endoscope, a positioning hook with an identification function is clamped on the lesion to obtain lesion organ information. For example, during a gastroscopy operation, the positioning hook is clamped on the lesion inside the gastric wall. The above-mentioned positioning hook can be mounted through an endoscope and clamped on the inner side of the gastric wall through an endoscopic operation. It has the characteristics of small size, light weight, safety, and non-toxicity. A positioning label with a positioning and recognition function is equipped at the gripper of the hook, and there are two implementation methods: the first is a micro RFID tag, and for identification, a positioning antenna needs to be installed on the positioning endoscope rod; the second is a small permanent magnet, and a magnetic sensor can be used on the endoscope rod for positioning and recognition. It is also possible to use both technologies for double guarantee.

[0056] Then, the lesion organ is scanned according to the lesion organ information to obtain a scanned image of the lesion organ, and the scanned image includes the preliminary positioning of the lesion location. Since the metal components in the hook will have a high-brightness imaging in the scanned image such as a CT image, the high-brightness position in the image is the preliminary positioning of the lesion location. By obtaining the scanned image of the target organ with the preliminary positioning of the lesion location, the preliminary positioning of the lesion location can be achieved.

[0057] Step S120: Perform three-dimensional modeling on the lesion organ according to the scanned image of the lesion organ to obtain a three-dimensional model of the lesion organ, and the three-dimensional model of the lesion organ includes the preliminary positioning of the lesion location. Since the metal components in the hook will have a high-brightness imaging in the CT image, there will also be an obvious high-brightness mark at the lesion location in the obtained three-dimensional model of the stomach. The above-mentioned three-dimensional modeling can be performed through volume rendering or surface rendering. The above-mentioned three-dimensional reconstruction can be performed using the Visualization Toolkit (VTK) for rendering. Based on VTK, there are mainly two types of three-dimensional image reconstructions: surface rendering and volume rendering. The ray casting algorithm belongs to volume rendering. Volume rendering faces the entire volume data and processes each voxel in the volume data field, making the reconstruction effect more accurate. The marching cubes algorithm belongs to surface rendering. Surface rendering extracts the surface contour information of the part to be reconstructed in the image for three-dimensional rendering, and only reconstructs the surface of the object. Since surface rendering processes part of the data in the volume data field, it has the advantages of small computational workload and fast speed. The steps for surface rendering can include the following:

[0058] First, obtain image sequences at multiple angles according to the scanned image of the lesion organ. To obtain the image sequences at multiple angles, first calculate the pixel values of each converted pixel point according to the obtained scanned image and the corresponding image parameters, then construct a new image based on the pixel values of each converted pixel point, and perform binary processing and median filtering on the new image to obtain a basic CT image; then calculate the similarity between adjacent basic CT images to obtain a CT image sequence at multiple angles of the part to be processed.

[0059] Then, three-dimensional modeling is performed based on the image sequences from multiple angles to obtain a three-dimensional model of the lesion organ, and the three-dimensional model of the lesion organ includes the preliminary localization of the lesion position. The above modeling is first to calculate the pixel intervals included in each CT image in the image sequences from each angle, and based on the pixel intervals, use the marching cubes algorithm to establish a three-dimensional model of the part to be processed. The marching cubes algorithm belongs to the prior art and will not be elaborated here.

[0060] Step S130: Input the scanned image of the lesion organ into a pre-set bed adjustment model, generate and adjust the operating bed according to the bed angle information; the above operating bed can be an operating bed that can automatically control the adjustment of the angle and height, and the above pre-set bed adjustment model can be a model trained by using a neural network model based on historical bed data, and this model can calculate the corresponding bed angle information through the input scanned image. When the above bed adjustment model is calculating, first, it calculates the lesion position information in the scanned image of the lesion organ, and then obtains the bed angle information according to the lesion position information. The bed angle information includes the tilt angle of the operating bed. The above lesion position information can be coordinate information, and a coordinate system can be established on the lesion organ to determine the lesion position information. The above adjustment of the operating bed can first obtain the current angle information through the angle sensor on the operating bed, then calculate the adjustment angle according to the bed angle information and the current angle information, and then generate an angle adjustment command according to the adjustment angle to adjust the operating bed. The above bed adjustment model can be obtained through the following steps:

[0061] First, obtain and use the final operating bed angle information and the corresponding scanned image information of the lesion organ in multiple laparoscopic surgeries as sample information; the above sample information includes the information of multiple completed surgeries, including the final surgical angle information, the corresponding scanned image information of the lesion organ, etc. For the scanned image information of the lesion organ, it includes image information, lesion position information, etc., and the above lesion position information can be coordinate information.

[0062] Then, use the neural network algorithm to train the sample information to obtain a bed adjustment model. When the above training is performed, first, it extracts the lesion position information in the scanned image information of the lesion organ in each sample information, and then uses the neural network algorithm to train the multiple lesion position information and the corresponding final operating bed angle information to obtain a bed adjustment model. The above neural network algorithm belongs to the prior art and will not be elaborated here.

[0063] Step S140: Obtain and adjust the three-dimensional model of the diseased organ according to the real-time picture information of the vision endoscope rod, so that the display perspective of the three-dimensional model of the diseased organ is consistent with the perspective of the real-time picture; the above real-time picture information can be obtained by means of wired transmission, using the angle information of the vision endoscope rod monitored in real time by the displacement sensor at the tail of the vision endoscope rod, and the real-time vision information collected by the bevel camera at the head of the vision endoscope rod; in this step, the head of the vision endoscope rod is equipped with a bevel camera, and its imaging angle forms a 30-degree angle with the vision endoscope rod. During the movement and rotation of the vision endoscope rod, its distance from the lesion, the rotation detection angle, and the zoom factor of the camera will be monitored in real time by the displacement sensor at the tail and sent to the main control unit for processing, so as to know the relative distance between the current vision endoscope rod and the lesion position, as well as the current perspective direction, providing a basis for subsequent adjustment of the three-dimensional model so that its display perspective is synchronized with the current display perspective of the vision endoscope rod. Adjust and transform the three-dimensional model according to the angle information and vision information of the vision endoscope rod, so that the display perspective of the three-dimensional model is consistent with the perspective of the return vision picture of the vision endoscope rod. The above adjustment and transformation include rotation, scaling, etc.

[0064] Step S150: Obtain and calculate the relative position between the positioning endoscope rod and the preliminarily positioned lesion position according to the current position of the positioning endoscope rod and the preliminarily positioned lesion position, so as to control the positioning endoscope rod and the vision endoscope rod to determine the lesion position. Establish a three-dimensional coordinate system with the lesion as the center, monitor the real-time position information of the positioning endoscope rod through the displacement sensor on the positioning endoscope rod, update the coordinates of the positioning endoscope rod in real time, and send them to the main control unit for processing through wired transmission, so as to obtain the current position of the positioning endoscope rod. The position information of the current positioning endoscope rod can be projected onto the three-dimensional image, and then the relative position between the current position of the positioning endoscope rod and the preliminarily positioned lesion position can be calculated. According to the relative position, corresponding control commands can be generated and sent to the positioning endoscope rod to control the movement of the positioning endoscope rod and the vision endoscope rod, so as to assist the doctor in quickly determining the lesion position.

[0065] In the above implementation process, by obtaining the scanned image of the diseased organ, the scanned image includes the preliminary localization of the lesion position, so that the scanned image can display the preliminary localization of the lesion position; then, based on the scanned image of the diseased organ, a three-dimensional model of the diseased organ is built to obtain a three-dimensional model of the diseased organ, and the preliminary localization of the lesion position is included in the three-dimensional model of the diseased organ, which helps the doctor to observe the diseased organ; then, the scanned image of the diseased organ is input into a preset bed adjustment model to generate and adjust the operating table according to the bed angle information. The most suitable bed angle information can be obtained through the preset bed adjustment model, and then the operating table is adjusted, thus saving the time for adjusting the operating table; then, the three-dimensional model of the diseased organ is adjusted according to the real-time picture information of the visual endoscope rod, so that the display angle of the three-dimensional model of the diseased organ is consistent with the angle of the real-time picture to assist the doctor in observing the lesion; finally, the relative position between the positioning endoscope rod and the preliminary localization of the lesion position is calculated based on the current position of the positioning endoscope rod and the preliminary localization of the lesion position, so as to control the positioning endoscope rod and the visual endoscope rod to determine the lesion position. A control signal is generated through the relative position to control the positioning endoscope rod and the visual endoscope rod to determine the lesion position, thus assisting the doctor to quickly confirm the lesion position, so that the doctor does not need to spend much time adjusting the operating table, and the position of the lesion can be assisted to be determined, shortening the operation time.

[0066] Among them, the scanned image of the diseased organ can also be input into a preset surgical parameter pre-adjustment model to generate the optimal bed angle information, the optimal positioning endoscope rod parameter information, and the optimal visual endoscope rod parameter information. The above-mentioned preset surgical parameter pre-adjustment model can be a model trained by using a neural network model based on historical surgical data. This model can calculate the optimal bed angle information, the optimal positioning endoscope rod parameter information, and the optimal visual endoscope rod parameter information through the input scanned image. The above-mentioned historical surgical data includes the scanned image during the operation, the bed parameter information, the positioning endoscope rod parameter information, and the visual endoscope rod parameter information when the lesion position is finally determined. The historical surgical data is trained by using a neural network model, and the surgical parameter pre-adjustment model is obtained through machine learning. The above-mentioned optimal bed angle information includes the optimal tilt angle of the operating table, the optimal height information of the operating table, etc. The above-mentioned optimal positioning endoscope rod parameter information includes the optimal insertion length of the positioning endoscope rod, the optimal insertion angle of the positioning endoscope rod, etc. The above-mentioned optimal visual endoscope rod parameter information includes the optimal insertion length of the visual endoscope rod, the optimal insertion of the visual endoscope rod, etc.

[0067] Before the operation, the operating table, the positioning endoscope rod, and the visual endoscope rod can be adjusted respectively according to the obtained optimal bed angle information, the optimal positioning endoscope rod parameter information, and the optimal visual endoscope rod parameter information, so that the doctor can quickly find the lesion during the operation, further saving the operation time.

[0068] Among them, to further make the bed angle information meet the surgical requirements, the pre-set bed adjustment model can also be matched. Please refer to Figure 2 , Figure 2 which is the flowchart of the steps for matching the bed adjustment model according to the organ provided by the embodiment of the present invention. Specifically, it includes the following steps:

[0069] First, obtain the organ information corresponding to the scanned image of the diseased organ; the above organ information refers to the organ that needs surgery, such as the stomach, intestine, etc.

[0070] Then, match according to the organ information in the pre-set bed adjustment model library to obtain the corresponding bed adjustment model. The above pre-set bed adjustment model library includes various types of bed adjustment models, which can be different bed adjustment models for different organs. The above matching is to find the bed adjustment model for the corresponding organ. By matching the bed adjustment model for the corresponding organ, the obtained bed angle information better meets the surgical requirements and further shortens the operation bed adjustment time.

[0071] Among them, to further make the bed angle information meet the surgical requirements, the pre-set bed adjustment model can also be matched through the patient information. Please refer to Figure 3 , Figure 3 which is the flowchart of the steps for matching the bed adjustment model according to the gender provided by the embodiment of the present invention. Specifically, it includes the following steps:

[0072] First, obtain the patient information corresponding to the scanned image of the diseased organ; the above patient information includes information such as name, age, gender, etc.

[0073] Then, match according to the gender information in the patient information in the pre-set bed adjustment model library to obtain the corresponding bed adjustment model. The above pre-set bed adjustment model library includes various types of bed adjustment models, which can be divided into a bed adjustment model applicable to men and a bed adjustment model applicable to women according to gender. The above matching is to find the bed adjustment model applicable to the corresponding gender, so that the obtained bed angle information better meets the surgical requirements and further shortens the operation bed adjustment time. At the same time, the corresponding bed adjustment models can also be set separately according to different age groups. Similar to the above, it will not be elaborated here.

[0074] Among them, the bed adjustment model library can be obtained through the following steps:

[0075] First, obtain and use the final operation bed angle information of multiple laparoscopic surgeries and the corresponding scanned image information of the diseased organ as the initial samples;

[0076] Then, obtain the medical record information of each laparoscopic surgery; the above medical record information includes patient information, diseased organ information, etc.

[0077] Then, classify the initial samples according to the preset classification rules based on the medical record information to obtain sub-sample information of multiple categories; the above classification rules can be classification according to the gender information in the patient information, or classification according to the lesion organ information, etc. Specifically, it can be set according to the bed adjustment model library established according to actual needs. By classifying the initial samples, sub-sample information of multiple categories can be obtained, which is convenient for separately training to obtain the corresponding bed adjustment model library later.

[0078] Finally, train the sub-sample information of each category using the neural network algorithm to obtain bed adjustment models of multiple categories, so as to form a bed adjustment model library. When performing the above training, first extract the lesion position information in the scanned image information of each lesion organ in the sub-sample information, and then use the neural network algorithm to train the multiple lesion position information and the corresponding final operating table angle information to obtain the bed adjustment model. The above neural network algorithm belongs to the prior art and will not be elaborated here. By classifying the initial samples and separately training each sub-sample information, different bed adjustment models are obtained to form a bed adjustment model library.

[0079] Based on the same inventive concept, the present invention also proposes a lesion confirmation system for laparoscopic surgery. Please refer to Figure 4 , Figure 4 which is a structural block diagram of a lesion confirmation system for laparoscopic surgery provided by an embodiment of the present invention. The lesion confirmation system for laparoscopic surgery includes:

[0080] A scanned image acquisition module 110, configured to acquire a scanned image of a lesion organ, and the scanned image includes a preliminary positioning of the lesion position;

[0081] A three-dimensional modeling module 120, configured to perform three-dimensional modeling on the lesion organ according to the scanned image of the lesion organ to obtain a three-dimensional model of the lesion organ, and the three-dimensional model of the lesion organ includes a preliminary positioning of the lesion position;

[0082] A bed angle adjustment module 130, configured to input the scanned image of the lesion organ into a preset bed adjustment model, generate and adjust the operating table according to the bed angle information;

[0083] A visual adjustment module 140, configured to acquire and adjust the three-dimensional model of the lesion organ according to the real-time picture information of the visual laparoscope rod, so that the display angle of the three-dimensional model of the lesion organ is consistent with the angle of the real-time picture;

[0084] A lesion determination module 150 is configured to obtain and calculate the relative position between the positioning endoscope rod and the preliminarily positioned lesion position based on the current position of the positioning endoscope rod and the preliminarily positioned lesion position, so as to control the positioning endoscope rod and the vision endoscope rod to determine the lesion position.

[0085] In the above implementation process, the scanning image acquisition module 110 acquires the scanning image of the lesion organ, and the preliminarily positioned lesion position is included in the scanning image, so that the scanning image can display the preliminarily positioned lesion position; the three-dimensional modeling module 120 performs three-dimensional modeling on the lesion organ according to the scanning image of the lesion organ to obtain a three-dimensional model of the lesion organ, and the preliminarily positioned lesion position is included in the three-dimensional model of the lesion organ, and the three-dimensional model helps the doctor to observe the lesion organ; the bed angle adjustment module 130 inputs the scanning image of the lesion organ into a preset bed adjustment model, generates and adjusts the operating bed according to the bed angle information. The most suitable bed angle information can be obtained through the preset bed adjustment model, and then the operating bed is adjusted, thus saving the operating bed adjustment time; the vision adjustment module 140 obtains and adjusts the three-dimensional model of the lesion organ according to the real-time image information of the vision endoscope rod, so that the display angle of the three-dimensional model of the lesion organ is consistent with the angle of the real-time image, to assist the doctor in observing the lesion; the lesion determination module 150 obtains and calculates the relative position between the current positioning endoscope rod position and the preliminarily positioned lesion position to control the positioning endoscope rod and the vision endoscope rod to determine the lesion position. A control signal is generated through the relative position to control the positioning endoscope rod and the vision endoscope rod to determine the lesion position, thereby assisting the doctor to quickly confirm the lesion position, so that the doctor can be assisted to determine the lesion position without spending a lot of time adjusting the operating bed, shortening the operation time.

[0086] Please refer to Figure 5 , Figure 5 which is a schematic structural block diagram of an electronic device provided by an embodiment of the present application. The electronic device includes a memory 101, a processor 102, and a communication interface 103. The memory 101, the processor 102, and the communication interface 103 are directly or indirectly electrically connected to each other to achieve data transmission or interaction. For example, these components can be electrically connected to each other through one or more communication buses or signal lines. The memory 101 can be used to store software programs and modules, such as program instructions / modules corresponding to a lesion confirmation system for endoscopic surgery provided by an embodiment of the present application. The processor 102 executes various functional applications and data processing by executing the software programs and modules stored in the memory 101. The communication interface 103 can be used for signaling or data communication with other node devices.

[0087] Among them, the memory 101 can be, but is not limited to, Random Access Memory (RAM), Read Only Memory (ROM), Programmable Read-Only Memory (PROM), Erasable Programmable Read-Only Memory (EPROM), Electric Erasable Programmable Read-Only Memory (EEPROM), etc.

[0088] The processor 102 can be an integrated circuit chip with signal processing capabilities. The processor 102 can be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0089] It can be understood that Figure 5 the structure shown is only schematic, and the electronic device may also include more or fewer components than those shown Figure 5 in the figure, or have a different configuration from that shown Figure 5 in the figure. Figure 5 Each component shown in the figure can be implemented using hardware, software, or a combination thereof.

[0090] In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architectures, functions, and operations of devices, methods, and computer program products according to multiple embodiments of the present application. In this regard, each block in the flowchart or block diagram may represent a module, a program segment, or a part of code, and the module, program segment, or part of code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order from that marked in the accompanying drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, as well as the combination of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system for performing the specified functions or actions, or can be implemented by a combination of dedicated hardware and computer instructions.

[0091] In addition, in each embodiment of the present application, the various functional modules can be integrated together to form an independent part, or each module can exist separately, or two or more modules can be integrated to form an independent part.

[0092] If the above functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in each embodiment of the present application. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disks, or optical discs that can store program codes.

[0093] The foregoing is only the preferred embodiment of the present application and is not used to limit the present application. For those skilled in the art, the present application can have various changes and modifications. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included within the protection scope of the present application.

[0094] It is obvious to those skilled in the art that the present application is not limited to the details of the above-mentioned exemplary embodiments, and the present application can be implemented in other specific forms without departing from the spirit or basic characteristics of the present application. Therefore, from any point of view, the embodiments should be regarded as exemplary and non-limiting. The scope of the present application is defined by the appended claims rather than the above description. Therefore, all changes falling within the meaning and scope of the equivalent elements of the claims are intended to be included in the present application. Any reference signs in the claims should not be construed as limiting the claims concerned.

Claims

1. A lesion confirmation system for endoscopic surgery, characterized in that, Comprising: A scanning image acquisition module, configured to acquire a scanning image of a lesion organ, where the preliminary lesion position is included in the scanning image; A three-dimensional modeling module, configured to perform three-dimensional modeling on the lesion organ according to the scanning image of the lesion organ to obtain a three-dimensional model of the lesion organ, where the preliminary lesion position is included in the three-dimensional model of the lesion organ; A bed angle adjustment module, configured to input the scanning image of the lesion organ into a preset bed adjustment model. When the bed adjustment model performs calculations, it first calculates the lesion position information in the scanning image of the lesion organ, then obtains the bed angle information according to the lesion position information, and finally adjusts the operating bed according to the bed angle information; A visual adjustment module, configured to, during the movement and rotation of the visual endoscope rod, the distance from the lesion, the rotation detection angle, and the zoom factor of the camera are monitored in real time by a displacement sensor at the tail and sent to the main control unit for processing to obtain the relative distance between the current visual endoscope rod and the lesion position and the current viewing direction, and obtain and adjust the three-dimensional model of the lesion organ according to the real-time image information of the visual endoscope rod, so that the display viewing angle of the three-dimensional model of the lesion organ is consistent with the viewing angle of the real-time image; A lesion determination module, configured to obtain and calculate the relative position between the current positioning endoscope rod position and the preliminary lesion position according to the preliminary lesion position, so as to control the positioning endoscope rod and the visual endoscope rod to determine the lesion position.

2. An electronic device, characterized in that, Comprising: A memory, configured to store one or more programs; A processor; When the one or more programs are executed by the processor, a method for lesion confirmation in endoscopic surgery is implemented. The method includes the following steps: Acquire a scanning image of a lesion organ, where the preliminary lesion position is included in the scanning image; Perform three-dimensional modeling on the lesion organ according to the scanning image of the lesion organ to obtain a three-dimensional model of the lesion organ, where the preliminary lesion position is included in the three-dimensional model of the lesion organ; Input the scanning image of the lesion organ into a preset bed adjustment model. When the bed adjustment model performs calculations, it first calculates the lesion position information in the scanning image of the lesion organ, then obtains the bed angle information according to the lesion position information, and finally adjusts the operating bed according to the bed angle information; During the movement and rotation of the visual endoscope rod, the distance from the lesion, the rotation detection angle, and the zoom factor of the camera are monitored in real time by a displacement sensor at the tail and sent to the main control unit for processing to obtain the relative distance between the current visual endoscope rod and the lesion position and the current viewing direction, and obtain and adjust the three-dimensional model of the lesion organ according to the real-time image information of the visual endoscope rod, so that the display viewing angle of the three-dimensional model of the lesion organ is consistent with the viewing angle of the real-time image; Obtain and calculate the relative position between the current positioning endoscope rod position and the preliminary lesion position according to the preliminary lesion position, so as to control the positioning endoscope rod and the visual endoscope rod to determine the lesion position.

3. An electronic device according to claim 2, characterized in that, The method for lesion confirmation in endoscopic surgery implemented further includes the following steps: Input the scanned image of the diseased organ into a preset surgical parameter pre-adjustment model to generate the optimal bed angle information, the optimal positioning endoscope rod parameter information, and the optimal visual endoscope rod parameter information.

4. An electronic device according to claim 2, characterized in that, A method for lesion confirmation in endoscopic surgery also includes the following steps: Obtain the patient information corresponding to the scanned image of the diseased organ; Match according to the gender information in the patient information in a preset bed adjustment model library to obtain the corresponding bed adjustment model.

5. An electronic device according to claim 2, characterized in that, A method for lesion confirmation in endoscopic surgery also includes the following steps: Obtain and use the final operating bed angle information of multiple endoscopic surgeries and the corresponding scanned image information of the diseased organ as sample information; Train the sample information using a neural network algorithm to obtain a bed adjustment model.

6. An electronic device according to claim 2, wherein A method for lesion confirmation in endoscopic surgery also includes the following steps: Obtain and use the final operating bed angle information of multiple endoscopic surgeries and the corresponding scanned image information of the diseased organ as the initial sample; Obtain the medical record information of each endoscopic surgery; Classify the initial sample according to the preset classification rules based on the medical record information to obtain sub-sample information of multiple categories; Train the sub-sample information of each category using a neural network algorithm respectively to obtain bed adjustment models of multiple categories, so as to form a bed adjustment model library.

7. An electronic device according to claim 2, characterized in that The step of obtaining the scanned image of the diseased organ, where the scanned image includes the step of preliminarily locating the lesion position includes the following steps: Obtain the diseased organ information; Scan the diseased organ according to the diseased organ information to obtain the scanned image of the diseased organ, and the scanned image includes the preliminarily located lesion position.

8. An electronic device according to claim 2, characterized in that, The step of performing three-dimensional modeling on the diseased organ according to the scanned image of the diseased organ to obtain a three-dimensional model of the diseased organ, where the three-dimensional model of the diseased organ includes the step of preliminarily locating the lesion position includes the following steps: Obtain an image sequence of multiple angles according to the scanned image of the diseased organ; Perform three-dimensional modeling according to the image sequence of multiple angles to obtain a three-dimensional model of the diseased organ, and the three-dimensional model of the diseased organ includes the preliminarily located lesion position.

Images