Method, system and storage medium for guiding interventional surgery

Abstract

The present disclosure provides a method, system and storage medium for guiding interventional surgery. The method includes: collecting a number of images of the target object within a preset time period, wherein the image images include an intracardiac echocardiogram (ICE); performing image analysis on the image images to obtain image analysis results, and generating an interventional surgery planning scheme based on the image analysis results to guide the execution of the interventional surgery. The present disclosure performs image analysis on the intracardiac echocardiogram (ICE) to plan the interventional surgery before puncture, find the best puncture angle, distance and timing for puncture, guide the interventional surgery, and perform real-time detection and tracking of the puncture process, identify and mitigate potential risks during the operation, improve the success rate of the operation, and continuously evaluate and manage possible complications through postoperative evaluation, comprehensively reduce the risks of interventional surgery, and improve the effect and safety of puncture surgery.

Description

Technical Field

[0001] The present disclosure relates to the field of image processing technology, and in particular to a method, system and storage medium for guiding interventional surgery. Background Art

[0002] In recent years, percutaneous interventional therapy has been widely used in the treatment of heart and vascular diseases. Among them, percutaneous interventional procedures include left heart catheter ablation, left atrial appendage (LAA) occlusion, and percutaneous mitral valvuloplasty, which usually require access to the left atrium through the vein for treatment. In order to minimize the risk, interventional devices usually enter through the vein, first through the right atrium, and then penetrate the atrial septum to enter the left side of the heart and other anatomical structures.

[0003] During percutaneous intervention, accurate puncture location is crucial to reduce procedural complications. And the optimal puncture location may vary depending on subsequent treatment and procedure type. For example, a posterior puncture location may be ideal for LAA occlusion, and puncturing through the central position of the atrial septum can provide more space in the left atrium, thereby facilitating the placement of a left ventricular assist device. Among them, X-rays are usually used to guide atrial septal puncture, and emerging imaging technologies such as transesophageal echocardiography (TEE) and intracardiac echocardiography (ICE) provide real-time monitoring and visualization without exposure to X-rays, and have become a better choice in medical imaging diagnosis.

[0004] However, current TEE or ICE images are usually two-dimensional and lack spatial information, which makes it challenging to accurately locate the target puncture point and track the catheter tip. Summary of the invention

[0005] The technical problem to be solved by the present disclosure is to overcome the defect in the prior art that the target puncture point cannot be accurately located and the catheter tip cannot be tracked based on TEE or ICE images, and to provide a method, system and storage medium for guiding interventional surgery.

[0006] The present invention solves the above technical problems through the following technical solutions:

[0007] According to a first aspect of the present disclosure, a method for guiding an interventional procedure is provided, the method comprising:

[0008] Collecting a plurality of images of the target object within a preset time period, wherein the images include an intracardiac echocardiogram (ICE);

[0009] Perform image analysis on a plurality of the image images to obtain image analysis results, and generate an interventional surgery planning scheme based on the image analysis results to guide the execution of the interventional surgery.

[0010] Preferably, the step of performing image analysis on a plurality of the image images to obtain image analysis results, and generating an interventional surgery planning scheme based on the image analysis results comprises:

[0011] Using a preset target detection algorithm to perform target detection on a plurality of the image images to obtain a target puncture area on the target object;

[0012] The interventional surgery planning plan is generated according to the target puncture area.

[0013] Preferably, the target object includes a heart, and the target puncture area includes the fossa ovalis on the heart;

[0014] The step of generating the interventional surgery planning scheme according to the target puncture area comprises:

[0015] Simulating geometric changes of the oval fossa caused by different puncture positions on the oval fossa;

[0016] When a preset puncture index appears in the geometric change of the oval fossa, the puncture position is determined as the target puncture position;

[0017] The interventional surgery planning plan is generated according to the target puncture position.

[0018] Preferably, when a preset puncture index appears in the geometric change of the oval fossa, the step of determining the puncture position as the target puncture position includes:

[0019] Determine whether a tent sign appears in the geometric change of the oval fossa, wherein the tent sign indicates that a tent-like dome pointing to the left atrium is generated at the atrial septum before the actual puncture occurs;

[0020] If the tent sign appears, determine whether the tent sign and the puncture needle are in the coaxial position;

[0021] If so, the location of the tent sign is used as the target puncture location.

[0022] Preferably, the interventional surgery planning scheme includes at least one of a target puncture angle, a target puncture timing, and a target puncture distance.

[0023] Preferably, the method further comprises:

[0024] Based on the plurality of image images, a three-dimensional anatomical model or a stereoscopic anatomical model of the target object is constructed.

[0025] Preferably, the method further comprises:

[0026] The target puncture position is marked on the three-dimensional anatomical model or the stereoscopic anatomical model corresponding to the target object.

[0027] Preferably, before the step of performing image analysis on the plurality of images, the method further comprises:

[0028] Merging a plurality of the image images to obtain a first image, wherein the field of view of the first image is larger than that of the image images;

[0029] The step of performing image analysis on a plurality of the image images to obtain image analysis results, and generating an interventional surgery planning scheme based on the image analysis results comprises:

[0030] Performing image analysis on the first image to obtain a first image analysis result, and generating the interventional surgery planning plan based on the first image analysis result.

[0031] Preferably, before the step of performing target detection on a plurality of the image images using a preset target detection algorithm, the method further comprises:

[0032] Segmenting the plurality of image images using a preset image segmentation algorithm to obtain a plurality of second images;

[0033] The step of using a preset target detection algorithm to perform target detection on a plurality of image images comprises:

[0034] Perform target detection on the plurality of second images and / or the plurality of video images based on the preset target detection algorithm.

[0035] Preferably, the preset target detection algorithm includes a target detection large model.

[0036] Preferably, the method further comprises:

[0037] Collecting surgery-related data during an interventional surgery, wherein the interventional surgery is performed based on the interventional surgery planning scheme;

[0038] A postoperative evaluation result of the interventional surgery is obtained based on the plurality of image images and the surgery-related data.

[0039] Preferably, after the step of collecting surgery-related data during the interventional surgery, the method further comprises:

[0040] identifying surgical risks based on the surgery-related data;

[0041] When the surgical risk meets the warning condition, a warning is issued.

[0042] Preferably, before the step of guiding the interventional surgery based on the interventional surgery planning scheme, the method further comprises:

[0043] receiving modification parameters of the interventional surgery planning scheme;

[0044] A new interventional surgery planning plan is obtained based on the modified parameter update.

[0045] Preferably, the step of receiving the modification parameters of the interventional surgery planning scheme includes:

[0046] The modification parameter inputted from external interaction is received.

[0047] Preferably, the step of receiving the modification parameters of the interventional surgery planning scheme includes:

[0048] The modification parameters generated by the preset large model are received.

[0049] Preferably, the step of performing image analysis on a plurality of the image images to obtain image analysis results, and generating an interventional surgery planning scheme based on the image analysis results to guide the execution of the interventional surgery includes:

[0050] Segmenting the plurality of image images using a preset image segmentation algorithm to obtain a plurality of second images;

[0051] Performing image analysis on the second image, and combining the image with the video image to obtain corresponding target quantitative analysis results and / or display results;

[0052] Based on the target quantitative analysis result and / or the display result, the interventional surgery planning scheme is generated to guide the execution of the interventional surgery.

[0053] According to a second aspect of the present disclosure, there is provided a system for guiding an interventional procedure, the system comprising an interface and a processor;

[0054] The interface is used to collect a number of images of the target object within a preset time period;

[0055] The processor is used to perform image analysis on a plurality of the image images to obtain image analysis results, and generate an interventional surgery planning scheme based on the image analysis results to guide the execution of the interventional surgery.

[0056] Preferably, the processor is further used to perform target detection on a plurality of the image images using a preset target detection algorithm to obtain a target puncture area on the target object;

[0057] The processor is also used to generate the interventional surgery planning plan according to the target puncture area.

[0058] Preferably, the target object includes a heart, and the target puncture area includes an oval fossa on the heart; the processor is further used to simulate geometric changes of the oval fossa caused by different puncture positions on the oval fossa; when a preset puncture index appears in the geometric change of the oval fossa, the puncture position is determined as the target puncture position;

[0059] The processor is also used to generate the interventional surgery planning plan according to the target puncture position.

[0060] Preferably, the processor is also used to determine whether a tent sign appears in the geometric changes of the oval fossa, wherein the tent sign indicates that a tent-like dome pointing to the left atrium is generated at the atrial septum before the actual puncture occurs; if the tent sign appears, it is determined whether the tent sign and the puncture needle are in a coaxial position; if so, the position of the tent sign is used as the target puncture position.

[0061] Preferably, the interventional surgery planning scheme includes at least one of a target puncture angle, a target puncture timing, and a target puncture distance.

[0062] Preferably, the processor is further used to construct a three-dimensional anatomical model or a stereoscopic anatomical model of the target object based on a plurality of the image images.

[0063] Preferably, the processor is further used to mark the target puncture position on the three-dimensional anatomical model or the stereoscopic anatomical model corresponding to the target object.

[0064] Preferably, the processor is further used to merge a plurality of the image images to obtain a first image, wherein the field of view of the first image is larger than that of the image images;

[0065] The processor is further configured to perform image analysis on the first image to obtain a first image analysis result, and generate the interventional surgery planning plan based on the first image analysis result.

[0066] Preferably, the processor is further used to segment the plurality of image images using a preset image segmentation algorithm to obtain a plurality of second images;

[0067] The processor is further configured to perform target detection on a plurality of the second images and / or a plurality of the video images based on the preset target detection algorithm.

[0068] Preferably, the preset target detection algorithm includes a target detection large model.

[0069] Preferably, the interface is also used to collect surgery-related data during an interventional surgery, and the interventional surgery is performed based on the interventional surgery planning scheme;

[0070] The processor is also used to obtain a postoperative evaluation result of the interventional surgery based on a plurality of the image images and the surgery-related data.

[0071] Preferably, the processor is further used to identify surgical risks based on the surgery-related data; and issue a warning when the surgical risks meet warning conditions.

[0072] Preferably, the interface is also used to receive modification parameters of the interventional surgery planning scheme;

[0073] The processor is further configured to update the new interventional surgery planning plan based on the modified parameters.

[0074] Preferably, the interface is also used to receive the modification parameters inputted from external interactions.

[0075] Preferably, the interface is also used to receive the modification parameters generated by the preset large model.

[0076] Preferably, the processor is further used to segment the plurality of image images using a preset image segmentation algorithm to obtain a plurality of second images;

[0077] The processor is also used to perform image analysis on the second image, and combine it with the image to obtain corresponding target quantitative analysis results and / or display results; based on the target quantitative analysis results and / or the display results, generate the interventional surgery planning plan to guide the execution of the interventional surgery.

[0078] According to a third aspect of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the method described in the first aspect of the present disclosure is implemented.

[0079] On the basis of being in accordance with the common sense in the art, the above-mentioned preferred conditions can be arbitrarily combined to obtain the preferred embodiments of the present disclosure.

[0080] The positive progressive effects of the present disclosure are: by performing image analysis on the intracardiac echocardiogram (ICE), interventional surgery planning is performed before puncture, the optimal puncture angle, distance and timing of the puncture are found, the interventional surgery is guided, and the puncture process is detected and tracked in real time, potential risks during the operation are identified and alleviated, and the success rate of the operation is improved. At the same time, postoperative evaluation is also performed to provide continuous evaluation and management of any possible adverse effects or complications, comprehensively reduce the risks of interventional surgery, and improve the effect and safety of puncture surgery. BRIEF DESCRIPTION OF THE DRAWINGS

[0081] Figure 1 This is a first flow chart of a method for guiding an interventional procedure according to Embodiment 1 of the present disclosure;

[0082] Figure 2 This is a flow chart of step S2 of the method for guiding interventional surgery in embodiment 1 of the present disclosure;

[0083] Figure 3 This is a schematic diagram of positioning the oval fossa and the target puncture position in Example 1 of the present disclosure;

[0084] Figure 4 This is a second flow chart of the method for guiding interventional surgery according to Embodiment 1 of the present disclosure;

[0085] Figure 5 It is a schematic diagram of the tent-shaped dome before puncture and the catheter tip after puncture in Example 1 of the present disclosure;

[0086] Figure 6 A schematic diagram of the structure of the system for guiding interventional surgery in Embodiment 2 of the present disclosure DETAILED DESCRIPTION

[0087] The present disclosure is further described below by way of examples, but the present disclosure is not limited to the scope of the examples.

[0088] Prefixes such as "first" and "second" are used in the embodiments of the present disclosure only to distinguish different description objects, and have no limiting effect on the position, order, priority, quantity or content of the described objects. The use of prefixes such as ordinal numbers to distinguish description objects in the embodiments of the present disclosure does not constitute a limitation on the described objects. For the statement of the described objects, please refer to the description in the context of the claims or embodiments, and no unnecessary limitation should be constituted due to the use of such prefixes. In addition, in the description of the present embodiment, unless otherwise specified, the meaning of "plurality" is two or more.

[0089] In the embodiments of the present disclosure, the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0090] Example 1

[0091] In a specific embodiment of the present disclosure, a method for guiding an interventional procedure is provided, such as Figure 1 As shown, the method includes:

[0092] S1, collecting a number of images of the target object within a preset time period, the images including intracardiac echocardiogram (ICE);

[0093] S2. Perform image analysis on a plurality of images to obtain image analysis results, and generate an interventional surgery planning plan based on the image analysis results to guide the execution of the interventional surgery.

[0094] Specifically, step S1 can collect real-time intracardiac echocardiogram (ICE), transesophageal echocardiogram (TEE), or integrated images of ICE and TEE of the target object through a catheter ultrasound imaging device. These images can be the original underlying data of the catheter ultrasound imaging device, DICOM (Digital Imaging and Communications in Medicine) images or videos, or preoperative images, such as two-dimensional, three-dimensional or four-dimensional computed tomography (CT), computed tomography angiography (CTA), in vitro ultrasound images, and magnetic resonance images (MRI).

[0095] Of course, inputs regarding the type of procedure (e.g., LAA occlusion) and device information (e.g., device type and size) can also be collected. This information can also be used to suggest appropriate imaging procedures. For example, although the imaging catheter is usually inserted through the femoral vein, in transaortic valve replacement (TAVR), other veins such as the internal jugular vein can be cannulated, which not only improves image quality but also provides operational convenience.

[0096] For step S2, various image processing algorithms, such as image segmentation algorithms, target detection algorithms, image tracking technology, image stitching technology, etc., can be used to integrate and analyze the collected images to obtain information about the current puncture catheter (angle, position, etc.), and then determine at least one of the optimal puncture angle, distance and timing based on the information of the current puncture catheter, and generate an interventional surgery planning plan including at least one of the target puncture angle, target puncture timing and target puncture distance based on the optimal puncture angle, distance and timing, so as to guide the catheter operation to perform the interventional surgery according to the optimal puncture angle, distance and timing in the plan.

[0097] This specific implementation method performs image analysis of the intracardiac echocardiogram (ICE) to plan interventional surgery before puncture, find the best puncture angle, distance and timing for puncture, and guide the interventional surgery.

[0098] In a specific embodiment, Figure 2 As shown, step S2 includes:

[0099] S21, performing target detection on a plurality of images using a preset target detection algorithm to obtain a target puncture area on the target object;

[0100] S22. Generate an initial interventional surgery planning plan based on the target puncture area.

[0101] Specifically, for interventional surgeries on different target objects, the selection of puncture areas is different, and for different individuals, the puncture risks and surgical success rates corresponding to different puncture positions in the same puncture area are also different.

[0102] The catheter position and anatomical structure provided by the real-time ICE or TEE image are tracked in real time through a preset target detection algorithm (e.g., a large target detection model), and the target puncture area and vascular area on the target object are identified and marked to help doctors identify complications. By detecting the target puncture area, multiple target puncture positions that meet the preset puncture indicators are determined, and the corresponding interventional surgery planning scheme is generated. The possibility of damage to blood vessels or valves after puncture, as well as whether there is enough space to place interventional surgery devices, etc., are evaluated for the target puncture positions. According to the interventional surgery planning scheme corresponding to the least possible damage to blood vessels or valves after puncture and sufficient space to place interventional surgery devices, the interventional surgery is guided.

[0103] In one specific embodiment, the target object includes a heart, and the target puncture area includes the fossa ovalis on the heart;

[0104] Step S22 includes:

[0105] The geometric changes of the oval fossa caused by different puncture positions were simulated;

[0106] When the preset puncture index appears in the geometric change of the oval fossa, the puncture position is determined as the target puncture position;

[0107] Generate an interventional surgery planning plan based on the target puncture location.

[0108] In a specific embodiment, when a preset puncture index appears in the geometric change of the oval fossa, the step of determining the puncture position as the target puncture position includes:

[0109] Determine whether the tent sign appears in the geometric changes of the oval fossa. The tent sign indicates that before the actual puncture occurs, a tent-like dome is generated in the atrial septum pointing to the left atrium;

[0110] If a tent sign is present, determine whether the tent sign and the puncture needle are in the coaxial position;

[0111] If so, the location of the tent sign was used as the target puncture site.

[0112] Specifically, for cardiac interventional surgery, the fossa oval is usually used as the target puncture area. By simulating the geometric changes caused by different puncture positions on the fossa oval, it is determined whether a tent-like dome pointing to the left atrium (i.e., tent sign) is generated at the atrial septum. If the tent sign appears, it is further determined whether the tent sign and the puncture needle are in the same axis. If the tent sign and the puncture needle are in the same axis, it can be determined that the puncture position can be used as the target puncture position, so as to generate an interventional surgery planning plan according to the target puncture position. Figure 3 Shown, examples of localization of the fossa ovalis are shown with optimal puncture locations highlighted, which are marked with bounding boxes.

[0113] During this process, the best image view can be detected in an automated, semi-automated, or fully manual manner. For example, after the tip of an imaging catheter enters the heart, images can be continuously captured and guidance can be provided to the clinician to help him find the best view for appropriate catheter manipulation.

[0114] In one embodiment, the method further comprises:

[0115] Based on a number of image images, a three-dimensional anatomical model or a stereoscopic anatomical model of the target object is constructed.

[0116] Specifically, the three-dimensional anatomical model can be directly reconstructed from the two-dimensional ICE and TEE images acquired from different angles and positions. If the acquired imaging images include preoperative three-dimensional images, an image fusion algorithm can be executed to generate / reconstruct a three-dimensional anatomical model with a larger field of view and a collection shape as a high-quality image, and the three-dimensional anatomical model can be a four-dimensional anatomical model.

[0117] In one embodiment, the method further comprises:

[0118] The target puncture position is marked on a three-dimensional anatomical model or a stereoscopic anatomical model corresponding to the target object.

[0119] Specifically, after obtaining the three-dimensional anatomical model or stereoscopic anatomical model corresponding to the target object, the corresponding position of the determined target puncture position on the three-dimensional anatomical model or stereoscopic anatomical model can be marked to more clearly and unambiguously show the specific position of the target puncture position in the target object.

[0120] In a specific embodiment, before step S2, the method further includes:

[0121] A plurality of image images are combined to obtain a first image, wherein the field of view of the first image is larger than that of the image images.

[0122] Step S2 includes:

[0123] Perform image analysis on the first image to obtain a first image analysis result, and generate an interventional surgery planning plan based on the first image analysis result.

[0124] Specifically, multiple images from ICE or TEE images can be merged using image stitching technology to create a new image (ie, the first image) with a larger field of view, and then image analysis is performed on the new image to obtain a corresponding analysis result.

[0125] In a specific embodiment, before step S21, the method further includes:

[0126] Segmenting a plurality of image images using a preset image segmentation algorithm to obtain a plurality of second images;

[0127] Step S21 includes:

[0128] Target detection is performed on the plurality of second images and / or the plurality of video images based on a preset target detection algorithm.

[0129] Specifically, the image segmentation algorithm can be used to segment the anatomical structure from the preoperative image, and the entire heart can be segmented, and the fine anatomical structure, such as the atrium and ventricle (both sides), valves, major blood vessels (pulmonary artery and vein, aorta, etc.) and coronary artery and vein, can be segmented. After obtaining the segmented second image, the preset target detection algorithm can be used to perform target detection on the segmented second image. Of course, the preset target detection algorithm can also be used to perform target detection on the original image. The specific target detection image can be selected according to actual needs, and this embodiment does not specifically limit this.

[0130] In a specific embodiment, Figure 4 As shown, the method also includes:

[0131] S3, collecting surgery-related data during the interventional surgery, wherein the interventional surgery is performed based on the interventional surgery planning scheme;

[0132] S4. Obtain postoperative evaluation results of the interventional surgery based on a number of imaging images and surgery-related data.

[0133] Specifically, during the procedure, real-time patient data (such as electrocardiogram, blood pressure curve, invasive or non-invasive blood pressure, cardiac output (CO), blood oxygen saturation (SpO2), etc.) are collected and integrated to improve tracking accuracy. A four-dimensional beating heart model corresponding to the patient is established based on the patient data to predict target motion and provide guidance to clinicians during catheter operation. In addition, the tent sign of the atrial septum is detected and tracked during the puncture, such as Figure 5 as shown to ensure accurate positioning of the catheter.

[0134] After the procedure, the accuracy of device placement is evaluated, any complications are identified, and whether further intervention is needed by analyzing postoperative images and patient data. Imaging images and patient data are used to predict surgical outcomes and provide continuous assessment and management of any adverse effects or complications that may occur to evaluate the success and safety of the puncture procedure.

[0135] In a specific embodiment, after step S3, the method further includes:

[0136] Identify surgical risks based on surgical-related data;

[0137] When the surgical risk meets the warning conditions, a warning will be issued.

[0138] Specifically, by conducting a risk assessment on the images collected before the operation and the patient's real-time physiological information during the puncture process, potential risks during the operation, such as vascular damage or valve damage, are identified, and warnings and prompts are immediately issued when the risks meet the warning conditions, so as to provide real-time assistance during the puncture process.

[0139] In a specific embodiment, before step S3, the method further includes:

[0140] receiving modified parameters of the interventional surgery planning plan;

[0141] A new interventional surgery planning plan is obtained based on the modified parameter update.

[0142] Specifically, after generating an interventional surgery planning plan, clinicians can adjust and modify information about parameters such as the optimal puncture site and puncture direction according to actual conditions. This information can be input through external interactions, such as mouse clicks, text input, gestures, or voice prompts, or it can be automatically generated through a preset large model, for example, a generative artificial intelligence model automatically generates corresponding modification parameters.

[0143] In a specific embodiment, step S2 includes:

[0144] Segmenting a plurality of image images using a preset image segmentation algorithm to obtain a plurality of second images;

[0145] Performing image analysis on the second image, and combining the image with the video image, obtaining corresponding target quantitative analysis results and / or display results;

[0146] Based on the target quantitative analysis results and / or display results, an interventional surgery planning plan is generated to guide the execution of the interventional surgery.

[0147] Specifically, an image segmentation algorithm can be used to segment the anatomical structure from the preoperative image. After obtaining the segmented second image, the second image can be analyzed and combined with the image to obtain the corresponding target quantitative analysis results and / or display results. For example, the diaphragm thickness, vascular geometry, valve measurement, etc. can be quantitatively measured from the segmented mask. Of course, the quantitative measurement can also be calculated directly from the original image. At the same time, the target detection and classification algorithm is used to detect abnormalities in the anatomical structure in the second image, such as aneurysms, to provide valuable information for clinicians to consider. This valuable information can be fed back to clinicians through different colors, shapes, symbols, and texts, which effectively serves as a warning.

[0148] The surgical situation is intelligently evaluated based on the obtained target quantitative analysis results and / or display results, and an interventional surgery planning plan is generated. Of course, the segmented content in the second image can also assist in risk identification during surgery, risk assessment after surgery, and treatment recommendations.

[0149] It should be noted that the above-mentioned method of guiding interventional surgery can be fully automatically, semi-automatically or manually executed through a large basic model (for example, a large language model, a large visual model or a large multimodal model) using few-shot learning or smart editing.

[0150] This embodiment performs image analysis of the intracardiac echocardiogram (ICE) to plan interventional surgery before puncture, find the best puncture angle, distance and timing for puncture, guide the interventional surgery, and perform real-time detection and tracking of the puncture process to identify and mitigate potential risks during the operation and improve the success rate of the operation. At the same time, postoperative evaluation is also performed to provide continuous evaluation and management of any adverse effects or complications that may occur, thereby comprehensively reducing the risks of interventional surgery and improving the effectiveness and safety of puncture surgery.

[0151] Example 2

[0152] According to a second aspect of the present disclosure, a system for guiding interventional surgery is provided. Figure 6 As shown, the system includes an interface 100 and a processor 200;

[0153] The interface 100 is used to collect a number of images of a target object within a preset period of time;

[0154] The processor 200 is used to perform image analysis on a plurality of image images to obtain image analysis results, and generate an interventional surgery planning scheme based on the image analysis results to guide the execution of the interventional surgery.

[0155] In a specific embodiment, the processor 200 is further configured to perform target detection on a plurality of image images using a preset target detection algorithm to obtain a target puncture area on the target object;

[0156] The processor 200 is also used to generate an interventional surgery planning plan based on the target puncture area.

[0157] In a specific embodiment, the target object includes a heart, and the target puncture area includes the fossa ovalis on the heart;

[0158] The processor 200 is also used to simulate the geometric changes of the oval fossa caused by different puncture positions on the oval fossa; when a preset puncture index appears in the geometric changes of the oval fossa, the puncture position is determined as the target puncture position;

[0159] The processor 200 is also used to generate an interventional surgery planning plan based on the target puncture position.

[0160] In a specific embodiment, the processor 200 is also used to determine whether a tent sign appears in the geometric changes of the oval fossa. The tent sign indicates that before the actual puncture occurs, a tent-like dome pointing to the left atrium is generated at the atrial septum; if the tent sign appears, it is determined whether the tent sign and the puncture needle are in a coaxial position; if so, the position of the tent sign is used as the target puncture position.

[0161] In a specific embodiment, the interventional surgery planning scheme includes at least one of a target puncture angle, a target puncture timing, and a target puncture distance.

[0162] In a specific implementation, the processor 200 is further configured to construct a three-dimensional anatomical model or a stereoscopic anatomical model of the target object based on a plurality of image images.

[0163] In a specific embodiment, the processor 200 is further configured to mark a target puncture position on a three-dimensional anatomical model or a stereoscopic anatomical model corresponding to the target object.

[0164] In a specific implementation, the processor 200 is further used to merge the plurality of image images to obtain a first image, wherein the field of view of the first image is larger than that of the image images;

[0165] The processor 200 is further configured to perform image analysis on the first image to obtain a first image analysis result, and to generate an interventional surgery planning plan based on the first image analysis result.

[0166] In a specific implementation, the processor 200 is further configured to segment the plurality of image images using a preset image segmentation algorithm to obtain a plurality of second images;

[0167] The processor 200 is further configured to perform target detection on the plurality of second images and / or the plurality of video images based on a preset target detection algorithm.

[0168] In a specific implementation, the preset target detection algorithm includes a target detection large model.

[0169] In a specific embodiment, the interface 100 is also used to collect surgery-related data during an interventional surgery, and the interventional surgery is performed based on the interventional surgery planning scheme;

[0170] The processor 200 is also used to obtain a postoperative evaluation result of the interventional surgery based on a plurality of image images and surgery-related data.

[0171] In a specific embodiment, the processor 200 is further configured to identify surgical risks based on surgery-related data, and issue a warning when the surgical risks meet the warning conditions.

[0172] In a specific embodiment, the interface 100 is also used to receive modification parameters of the interventional surgery planning scheme;

[0173] The processor 200 is further configured to obtain a new interventional surgery planning plan based on the modified parameter update.

[0174] In a specific implementation, the interface 100 is also used to receive modification parameters inputted from external interactions.

[0175] In a specific implementation, the interface 100 is also used to receive modification parameters for generating a preset large model.

[0176] In a specific implementation, the processor 200 is further configured to segment the plurality of image images using a preset image segmentation algorithm to obtain a plurality of second images;

[0177] The processor 200 is also used to perform image analysis on the second image, and combine the image to obtain corresponding target quantitative analysis results and / or display results; based on the target quantitative analysis results and / or display results, generate an interventional surgery planning plan to guide the execution of the interventional surgery.

[0178] As for the system embodiment, since it basically corresponds to the method embodiment, the relevant parts can refer to the partial description of the method embodiment. The system embodiment described above is only illustrative, wherein the units described as separate components may or may not be physically separated, and the components as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the disclosed solution.

[0179] This embodiment performs image analysis of the intracardiac echocardiogram (ICE) to plan interventional surgery before puncture, find the best puncture angle, distance and timing for puncture, guide the interventional surgery, and perform real-time detection and tracking of the puncture process to identify and mitigate potential risks during the operation and improve the success rate of the operation. At the same time, postoperative evaluation is also performed to provide continuous evaluation and management of any adverse effects or complications that may occur, thereby comprehensively reducing the risks of interventional surgery and improving the effectiveness and safety of puncture surgery.

[0180] Example 3

[0181] The present disclosure also provides a computer-readable storage medium having a computer program stored thereon, and when the program is executed by a processor, the method for guiding interventional surgery provided by any of the above embodiments is implemented.

[0182] The readable storage medium may include but is not limited to: a portable disk, a hard disk, a random access memory, a read-only memory, an erasable programmable read-only memory, an optical storage device, a magnetic storage device or any suitable combination of the above.

[0183] Although the specific embodiments of the present disclosure are described above, those skilled in the art should understand that this is only an example, and the protection scope of the present disclosure is defined by the appended claims. Those skilled in the art may make various changes or modifications to these embodiments without departing from the principles and essence of the present disclosure, but these changes and modifications all fall within the protection scope of the present disclosure.

Claims

1. A method for guiding interventional surgery, characterized in that: The method comprises: Collecting a plurality of images of the target object within a preset time period, wherein the images include an intracardiac echocardiogram (ICE); Performing image analysis on a plurality of the image images to obtain image analysis results, and generating an interventional surgery planning scheme based on the image analysis results to guide the execution of the interventional surgery; The step of performing image analysis on a plurality of the image images to obtain image analysis results, and generating an interventional surgery planning scheme based on the image analysis results comprises: Using a preset target detection algorithm to perform target detection on a plurality of the image images to obtain a target puncture area on the target object; generating the interventional surgery planning scheme according to the target puncture area; The target object includes a heart, and the target puncture area includes the fossa ovalis on the heart; The step of generating the interventional surgery planning scheme according to the target puncture area comprises: Simulating geometric changes of the oval fossa caused by different puncture positions on the oval fossa; When a preset puncture index appears in the geometric change of the oval fossa, the puncture position is determined as the target puncture position; generating the interventional surgery planning scheme according to the target puncture position; The step of determining the puncture position as the target puncture position when a preset puncture index appears in the geometric change of the oval fossa comprises: Determine whether a tent sign appears in the geometric change of the oval fossa, wherein the tent sign indicates that a tent-like dome pointing to the left atrium is generated at the atrial septum before the actual puncture occurs; If the tent sign appears, determine whether the tent sign and the puncture needle are in the coaxial position; If so, the location of the tent sign is used as the target puncture location.

2. The method according to claim 1, characterized in that The interventional surgery planning scheme includes at least one of a target puncture angle, a target puncture timing, and a target puncture distance.

3. The method according to claim 1, characterized in that The method further comprises: Based on the plurality of image images, a three-dimensional anatomical model or a four-dimensional anatomical model of the target object is constructed.

4. The method according to claim 3, characterized in that The method further comprises: The target puncture position is marked on the three-dimensional anatomical model or the four-dimensional anatomical model corresponding to the target object.

5. The method according to any one of claims 1 to 4, characterized in that Before the step of performing image analysis on the plurality of images, the method further comprises: Merging a plurality of the image images to obtain a first image, wherein the field of view of the first image is larger than that of the image images; The step of performing image analysis on a plurality of the image images to obtain image analysis results, and generating an interventional surgery planning scheme based on the image analysis results comprises: Performing image analysis on the first image to obtain a first image analysis result, and generating the interventional surgery planning plan based on the first image analysis result.

6. The method according to any one of claims 1 to 4, characterized in that Before the step of performing target detection on the plurality of image images using a preset target detection algorithm, the method further includes: Segmenting the plurality of image images using a preset image segmentation algorithm to obtain a plurality of second images; The step of using a preset target detection algorithm to perform target detection on a plurality of image images comprises: Perform target detection on the plurality of second images and / or the plurality of video images based on the preset target detection algorithm.

7. The method according to any one of claims 1 to 4, characterized in that The preset target detection algorithm includes a target detection large model.

8. The method according to any one of claims 1 to 4, characterized in that The method further comprises: Based on the plurality of image pictures and surgery-related data, a postoperative evaluation result of the interventional surgery is obtained.

9. The method according to claim 8, characterized in that Before performing the interventional surgery based on the interventional surgery planning scheme, the method further includes: receiving modification parameters of the interventional surgery planning scheme; A new interventional surgery planning plan is obtained based on the modified parameter update.

10. The method according to claim 9, characterized in that The step of receiving the modification parameters of the interventional surgery planning scheme comprises: The modification parameter inputted from external interaction is received.

11. The method according to claim 9, characterized in that The step of receiving the modification parameters of the interventional surgery planning scheme comprises: The modification parameters generated by the preset large model are received.

12. The method according to claim 1, characterized in that The step of performing image analysis on a plurality of the image images to obtain image analysis results, and generating an interventional surgery planning scheme based on the image analysis results to guide the execution of the interventional surgery comprises: Segmenting the plurality of image images using a preset image segmentation algorithm to obtain a plurality of second images; Performing image analysis on the second image, and combining the image with the video image to obtain corresponding target quantitative analysis results and / or display results; Based on the target quantitative analysis result and / or the display result, the interventional surgery planning scheme is generated to guide the execution of the interventional surgery.

13. A system for guiding interventional surgery, characterized in that: The system includes an interface and a processor; The interface is used to collect a number of images of the target object within a preset time period; The processor is used to perform image analysis on a plurality of the image images to obtain image analysis results, and generate an interventional surgery planning scheme based on the image analysis results to guide the execution of the interventional surgery; The processor is also used to perform target detection on the plurality of image images using a preset target detection algorithm to obtain a target puncture area on the target object; The processor is also used to generate the interventional surgery planning scheme according to the target puncture area; The target object includes a heart, and the target puncture area includes the fossa ovalis on the heart; The processor is also used to simulate the geometric changes of the oval fossa caused by different puncture positions on the oval fossa; when a preset puncture index appears in the geometric changes of the oval fossa, the puncture position is determined as the target puncture position; and the interventional surgery planning scheme is generated according to the target puncture position; The processor is further used to determine whether a tent sign appears in the geometric change of the oval fossa, wherein the tent sign indicates that a tent-like dome pointing to the left atrium is generated at the atrial septum before the actual puncture occurs; If the tent sign appears, it is determined whether the tent sign and the puncture needle are in a coaxial position; if so, the position of the tent sign is used as the target puncture position.

14. The system according to claim 13, characterized in that The processor is also used to construct a three-dimensional anatomical model or a four-dimensional anatomical model of the target object based on a plurality of the image images; The processor is further configured to mark the target puncture position on the three-dimensional anatomical model or the four-dimensional anatomical model corresponding to the target object.

15. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 12 is implemented.

Images