CN118634033B

CN118634033B - Method, system and storage medium for guiding interventional procedures

Info

Publication number: CN118634033B
Application number: CN202410726474.8A
Authority: CN
Inventors: 张吉宏; 贺黎钢; 刘思朦
Original assignee: Shanghai Bingzuo Jingyi Technology Co ltd
Current assignee: Shanghai Bingzuo Jingyi Technology Co ltd
Priority date: 2024-06-05
Filing date: 2024-06-05
Publication date: 2025-05-16
Anticipated expiration: 2044-06-05
Also published as: CN118634033A

Abstract

The present disclosure provides a method, system, and storage medium for guiding interventional procedures. The method comprises the steps of collecting a plurality of image images of a target object in a preset period, wherein the image images comprise intracardiac echocardiography ICE, carrying out image analysis on the image images to obtain an image analysis result, and generating an interventional operation planning scheme based on the image analysis result so as to guide the interventional operation to be executed. According to the method, the image analysis is carried out on the intracardiac echocardiogram ICE, the interventional operation planning is carried out before puncture, the optimal puncture angle, distance and time of puncture are found, guidance of the interventional operation is achieved, the puncture process is detected and tracked in real time, potential risks in the operation process are identified and relieved, the success rate of the operation is improved, complications which possibly occur are continuously evaluated and managed through postoperative evaluation, the risk of the interventional operation is comprehensively reduced, and the effect and safety of the puncture operation are improved.

Description

Method, system and storage medium for guiding interventional procedures

Technical Field

The present disclosure relates to the field of image processing technology, and in particular, to a method, system, and storage medium for guiding interventional procedures.

Background

In recent years, percutaneous interventions have found widespread use in the treatment of heart and vascular diseases. Among other procedures for percutaneous interventional procedures, left heart catheter ablation, left Atrial Appendage (LAA) occlusion, percutaneous mitral valve angioplasty, etc., typically require transvenous access to the left atrium for treatment. While to minimize risk, interventional devices are typically accessed intravenously, first through the right atrium, and then through the septum of the penetrating atrium to access the left side of the heart and other anatomical structures.

During percutaneous interventional procedures, accurate puncture location is critical to reducing surgical complications. And the optimal puncture location may vary depending on the subsequent treatment and type of procedure. For example, a posterior puncture location may be a desirable choice for LAA occlusion, and by puncturing at a central location in the atrial septum, more space may be provided in the left atrium, thereby facilitating placement of left ventricular assist devices. Among them, X-rays are commonly used to guide atrial septal punctures, and emerging imaging techniques such as transesophageal echocardiography (TEE) and intracardiac echocardiography (ICE) provide real-time monitoring and visualization without exposure to X-rays, have become a better choice in medical imaging diagnostics.

However, current TEE or ICE images are typically two-dimensional, lacking spatial information, which makes it challenging to accurately locate target puncture points and track catheter tips.

Disclosure of Invention

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

The technical problems are solved by the following technical scheme:

According to a first aspect of the present disclosure, there is provided a method of guiding an interventional procedure, the method comprising:

Collecting a plurality of image images of a target object in a preset period, wherein the image images comprise an intracardiac echocardiogram ICE;

And carrying out image analysis on a plurality of image images to obtain an image analysis result, and generating an interventional operation planning scheme based on the image analysis result so as to guide the interventional operation to be executed.

Preferably, the step of performing image analysis on the plurality of image images to obtain an image analysis result, and generating the interventional operation planning scheme based on the image analysis result includes:

Performing target detection on a plurality of image images by adopting a preset target detection algorithm to obtain a target puncture area on the target object;

And generating the interventional operation planning scheme according to the target puncture area.

Preferably, the target object comprises a heart and the target penetration region comprises an fossa ovalis on the heart;

the step of generating the interventional procedure planning scheme according to the target puncture area comprises the following steps:

Simulating geometric changes of the fossa ovalis caused by different puncture positions on the fossa ovalis;

when a preset puncture index appears in the geometric change of the fossa ovalis, determining the puncture position as a target puncture position;

And generating the interventional operation planning scheme according to the target puncture position.

Preferably, the step of determining the puncture position as the target puncture position when the preset puncture index appears in the geometric change of the fossa ovalis comprises:

judging whether tent symptoms occur in the geometric change of the fossa ovalis, wherein the tent symptoms represent that a dome similar to tent is generated at the room septum and points to the left atrium before the actual puncture action occurs;

If the tent sign appears, judging whether the tent sign and the puncture needle are in the coaxial position or not;

If yes, the tent sign position is taken as the target puncture position.

Preferably, the interventional operation planning scheme comprises at least one of a target puncture angle, a target puncture time and a target puncture distance.

Preferably, the method further comprises:

And constructing a three-dimensional anatomical model or a stereoscopic anatomical model of the target object based on a plurality of image images.

Preferably, the method further comprises:

And identifying the target puncture position on the three-dimensional anatomical model or the stereoscopic anatomical model corresponding to the target object.

Preferably, before the step of performing image analysis on the plurality of image images, the method further includes:

Combining 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;

the step of performing image analysis on the plurality of image images to obtain an image analysis result and generating an interventional operation planning scheme based on the image analysis result comprises the following steps:

And carrying out image analysis on the first image to obtain a first image analysis result, and generating the interventional operation planning scheme based on the first image analysis result.

Preferably, before the step of performing object detection on the plurality of image images by using a preset object detection algorithm, the method further includes:

dividing a plurality of image images by using a preset image dividing algorithm to obtain a plurality of second images;

The step of performing target detection on a plurality of image images by adopting a preset target detection algorithm comprises the following steps:

And carrying out target detection on a plurality of second images and/or a plurality of image images based on the preset target detection algorithm.

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

Preferably, the method further comprises:

collecting operation related data in an interventional operation process, wherein the interventional operation is executed based on the interventional operation planning scheme;

and obtaining postoperative evaluation results of the interventional operation according to the plurality of image images and the operation related data.

Preferably, after the step of collecting surgical related data during the interventional procedure, the method further comprises:

identifying a surgical risk based on the surgical related data;

And when the surgical risk meets the early warning condition, early warning is carried out.

Preferably, before the step of guiding the intervention based on the intervention planning scheme, the method further comprises:

receiving modification parameters of the interventional procedure planning scheme;

And updating the modified parameters to obtain a new interventional operation planning scheme.

Preferably, the step of receiving modification parameters of the interventional procedure planning scheme comprises:

The modification parameters of the external interaction input are received.

And receiving the modification parameters generated by the preset large model.

Preferably, the step of performing image analysis on the plurality of image images to obtain an image analysis result, and generating an interventional operation planning scheme based on the image analysis result to guide the execution of the interventional operation includes:

Performing image analysis on the second image, and combining the image images to obtain a corresponding target quantitative analysis result and/or a display result;

based on the target quantitative analysis result and/or the display result, the interventional procedure planning scheme is generated to guide the interventional procedure to be performed.

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;

The interface is used for collecting a plurality of image images of the target object in a preset period;

The processor is used for carrying out image analysis on a plurality of image images to obtain image analysis results, and generating an interventional operation planning scheme based on the image analysis results so as to guide the interventional operation to be executed.

Preferably, the processor is further configured to perform target detection on a plurality of image images by using a preset target detection algorithm, so as to obtain a target puncture area on the target object;

the processor is further configured to generate the interventional procedure planning scheme based on the target penetration region.

Preferably, the target object comprises a heart, the target puncture area comprises a fossa ovalis on the heart, the processor is further used for simulating fossa ovalis geometric changes caused by different puncture positions on the fossa ovalis, and when a preset puncture index appears in the fossa ovalis geometric changes, the puncture position is determined to be the target puncture position;

the processor is further configured to generate the interventional procedure planning scheme based on the target puncture location.

Preferably, the processor is further configured to determine whether a tent sign occurs in the geometric change of the fossa ovalis, where the tent sign indicates that a dome similar to a tent is generated at a septum of a room pointing to a left atrium before an actual puncturing operation occurs, determine whether the tent sign and the puncture needle are in a coaxial position if the tent sign occurs, and use a position where the tent sign is located as the target puncture position if the tent sign occurs.

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

Preferably, the processor is further configured to identify the target puncture location on the three-dimensional anatomical model or the stereoscopic anatomical model corresponding to the target object.

Preferably, the processor is further configured to combine the plurality of image images to obtain a first image, where a field of view of the first image is larger than that of the image images;

The processor is also used for carrying out image analysis on the first image to obtain a first image analysis result, and generating the interventional operation planning scheme based on the first image analysis result.

Preferably, the processor is further configured to segment the plurality of image images by using a preset image segmentation algorithm to obtain a plurality of second images;

The processor is further used for carrying out target detection on a plurality of second images and/or a plurality of image images based on the preset target detection algorithm.

Preferably, the interface is further configured to collect surgical related data during an interventional procedure, the interventional procedure being performed based on the interventional procedure planning scheme;

the processor is also used for obtaining postoperative evaluation results of the interventional operation according to the plurality of image images and the operation related data.

Preferably, the processor is further used for identifying surgical risks based on the surgical related data, and performing early warning when the surgical risks meet early warning conditions.

Preferably, the interface is further configured to receive modification parameters of the interventional procedure planning scheme;

the processor is further configured to update a new interventional procedure planning scheme based on the modification parameters.

Preferably, the interface is further configured to receive the modification parameters of the external interaction input.

Preferably, the interface is further configured to receive the modification parameter generated by the preset large model.

The processor is further used for carrying out image analysis on the second image and combining the image to obtain a corresponding target quantitative analysis result and/or a display result, and generating the interventional operation planning scheme based on the target quantitative analysis result and/or the display result so as to guide the interventional operation to be executed.

According to a third aspect of the present disclosure, there is provided a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the method of the first aspect of the present disclosure.

On the basis of conforming to the common knowledge in the art, the preferred conditions can be arbitrarily combined to obtain the preferred examples of the disclosure.

The method has the positive progress effects that through image analysis of the intracardiac echocardiogram ICE, interventional operation planning is conducted before puncture, the optimal puncture angle, distance and opportunity of puncture are found, guidance of interventional operation is achieved, real-time detection and tracking are conducted on the puncture process, potential risks in the operation process are identified and relieved, the success rate of operation is improved, meanwhile, postoperative evaluation is conducted, continuous evaluation and management of any adverse effects or complications possibly occurring are provided, risks of interventional operation are comprehensively reduced, and the effect and safety of the puncture operation are improved.

Drawings

FIG. 1 is a first flow chart of a method of guiding an interventional procedure according to embodiment 1 of the present disclosure;

FIG. 2 is a flowchart of method step S2 of guiding an interventional procedure according to embodiment 1 of the present disclosure;

FIG. 3 is a schematic view of fossa ovalis positioning and target puncture location positioning in embodiment 1 of the present disclosure;

FIG. 4 is a second flowchart of a method of guiding an interventional procedure according to embodiment 1 of the present disclosure;

FIG. 5 is a schematic view of a tent dome prior to puncture and a catheter tip after puncture in example 1 of the present disclosure;

fig. 6 is a schematic structural view of a system for guiding an interventional procedure according to embodiment 2 of the present disclosure

Detailed Description

The present disclosure is further illustrated by way of examples below, but is not thereby limited to the scope of the examples described.

Prefix words such as "first" and "second" are used in the embodiments of the present disclosure, and are merely for distinguishing between different description objects, and there is no limitation on the location, order, priority, number, content, or the like of the described objects. The use of ordinal words and the like in embodiments of the present disclosure to distinguish between the prefix words describing the object does not limit the described object, and statements of the described object are to be taken in the claims or in the context of the embodiments and should not be construed as unnecessary limitations due to the use of such prefix words. In addition, in the description of the present embodiment, unless otherwise specified, the meaning of "a plurality" is two or more.

In the embodiment of the disclosure, the related processes of collecting, storing, using, processing, transmitting, providing, disclosing and the like of the personal information of the user accord with the rules of related laws and regulations, and do not violate the public order colloquial.

Example 1

In one embodiment of the present disclosure, a method of guiding an interventional procedure is provided, as shown in fig. 1, the method comprising:

s1, acquiring a plurality of image images of a target object in a preset period, wherein the image images comprise an intracardiac echocardiogram ICE;

s2, performing image analysis on the plurality of image images to obtain an image analysis result, and generating an interventional operation planning scheme based on the image analysis result so as to guide the interventional operation to be executed.

Specifically, step S1 may acquire a real-time intracardiac echocardiogram ICE, a transesophageal echocardiogram TEE, or an image integration of ICE and TEE of the target object by a catheter ultrasound imaging device. These image images may be raw underlying data, DICOM (DIGITAL IMAGING AND Communications IN MEDICINE ) images or video of a catheter ultrasound imaging device, as well as pre-operative images such as two-, three-or four-dimensional Computed Tomography (CT), computed Tomography Angiography (CTA), in vitro ultrasound images and Magnetic Resonance Images (MRI).

Of course, inputs may also be collected regarding the type of procedure (e.g., LAA occlusion) and device information (e.g., device type and size). Such information may also be used to suggest an appropriate imaging procedure, for example, although the imaging catheter is typically inserted through the femoral vein, in aortic valve replacement (TAVR) other veins such as the internal jugular vein may be selected for catheterization, which may not only improve image quality, but also provide operational convenience.

For step S2, the acquired image may be integrated and image analyzed by using various image processing algorithms, such as an image segmentation algorithm, a target detection algorithm, an image tracking technology, an image stitching technology, etc., to obtain information (angle, position, etc.) about the current puncture catheter, and then determine at least one of an optimal puncture angle, distance, and timing according to the information of the current puncture catheter, and generate an interventional procedure planning scheme including at least one of a target puncture angle, a target puncture timing, and a target puncture distance based on the optimal puncture angle, distance, and timing, so as to guide catheter operation to perform an interventional procedure according to the optimal puncture angle, distance, and timing in the scheme.

According to the specific embodiment, the image analysis is carried out on the intracardiac echocardiography ICE, the interventional operation planning is carried out before the puncture, the optimal puncture angle, distance and time of the puncture are found, and the guidance of the interventional operation is realized.

In one embodiment, as shown in fig. 2, step S2 includes:

S21, performing target detection on a plurality of image images by adopting a preset target detection algorithm to obtain a target puncture area on a target object;

S22, generating an interventional initial operation planning scheme according to the target puncture area.

Specifically, for interventional operations of different target objects, the puncture areas are selected differently, and for different individuals, the puncture risks and the operation success rates corresponding to different puncture positions in the same puncture area are also different.

The catheter position and anatomy provided by the real-time ICE or TEE image is tracked in real-time by a preset target detection algorithm (e.g., a large target detection model), and the target puncture area and the blood vessel area on the target object are identified and marked to help the physician identify complications. By detecting the target puncture area, a plurality of target puncture positions meeting preset puncture indexes are determined, a corresponding intervention operation planning scheme is generated, the possibility of damage to blood vessels, valves and the like after puncture is evaluated according to the target puncture positions, an intervention operation device (device) and the like are placed in a sufficient space, and the intervention operation is guided to be executed according to the intervention operation planning scheme which has the minimum possibility of damage to the blood vessels, the valves and the like after puncture and corresponds to the intervention operation device placed in the sufficient space.

In one embodiment, the target object comprises a heart and the target penetration area comprises an fossa ovalis on the heart;

Step S22 includes:

When a preset puncture index appears in geometric change of the fossa ovalis, determining the puncture position as a target puncture position;

and generating an interventional operation planning scheme according to the target puncture position.

In one embodiment, when the preset puncture index appears in the geometric change of the fossa ovalis, the step of determining the puncture position as the target puncture position includes:

Judging whether tent symptoms occur in geometric changes of the fossa ovalis, wherein the tent symptoms represent that a dome similar to tent pointing to a left atrium is generated at a room space before actual puncture actions occur;

if yes, the position where the tent sign is located is taken as a target puncture position.

Specifically, for cardiac interventional operations, the fossa ovalis is generally used as a target puncture area, whether a tent-like dome (i.e., tent sign) pointing to the left atrium is generated at the interatrial septum is judged by simulating geometric changes caused by different puncture positions on the fossa ovalis, if the tent sign is generated, whether the tent sign and the puncture needle are in the coaxial position is further judged, if the tent sign and the puncture needle are in the coaxial position, the puncture position can be determined as the target puncture position, so that an interventional operation planning scheme is generated according to the target puncture position, and as shown in fig. 3, a positioning example of the fossa ovalis displayed together with the highlighted optimal puncture position, and the positions are marked by boundary boxes.

In this process, the optimal image view may be detected in an automatic, semi-automatic or fully manual manner. For example, after the imaging catheter tip enters the heart, images may be continuously captured and guidance provided to the clinician to help it find the best view under the proper catheter procedure.

In one embodiment, the method further comprises:

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

In particular, two-dimensional ICE and TEE images acquired from different angles and positions may be reconstructed directly from the three-dimensional anatomical model. If preoperative three-dimensional images are included in the acquired image, an image fusion algorithm may be performed to generate/reconstruct a stereoscopic anatomical model, which may be a four-dimensional anatomical model, with a larger field of view, in aggregate shape as a high quality image.

In one embodiment, the method further comprises:

Specifically, after the three-dimensional anatomical model or the three-dimensional anatomical model corresponding to the target object is obtained, the corresponding position of the determined target puncture position on the three-dimensional anatomical model or the three-dimensional anatomical model can be identified, so that the specific position of the target puncture position in the target object can be clearly and clearly displayed.

In a specific embodiment, before step S2, the method further comprises:

And combining 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.

The step S2 comprises the following steps:

and carrying out image analysis on the first image to obtain a first image analysis result, and generating an interventional operation planning scheme based on the first image analysis result.

In particular, multiple images from ICE or TEE images may be combined using image stitching techniques to create a new image (i.e., a first image) with a larger field of view. And further carrying out image analysis on the new image to obtain a corresponding analysis result.

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

The step S21 includes:

and carrying out target detection on the second images and/or the image images based on a preset target detection algorithm.

In particular, the image segmentation algorithm may be used to segment anatomical structures from pre-operative images, both the whole heart and fine anatomical structures such as the atria and ventricles (both sides), valves, major blood vessels (pulmonary artery and vein, aorta, etc.), and coronary arteries and veins. And after the segmented second image is obtained, performing target detection on the segmented second image by using a preset target detection algorithm. Of course, the original image may be subjected to target detection by using a preset target detection algorithm, and a specific target detection image may be selected according to actual needs, which is not particularly limited in this embodiment.

In one embodiment, as shown in fig. 4, the method further comprises:

s3, acquiring operation related data in an interventional operation process, wherein the interventional operation is executed based on the interventional operation planning scheme;

S4, obtaining postoperative evaluation results of the interventional operation according to the plurality of image images and the operation related data.

Specifically, during surgery, real-time patient data (e.g., electrocardiogram, blood pressure curve, invasive or non-invasive blood pressure, cardiac Output (CO), blood oxygen saturation (SpO 2), etc.) are acquired and integrated to improve tracking accuracy, and a four-dimensional beating heart model corresponding to the patient is built from the patient data to predict target motion, providing guidance to the clinician during catheter operation. In addition, tenting of the atrial septum is detected and tracked during the puncture procedure, as shown in FIG. 5, to ensure accurate catheter positioning.

After the operation is finished, the accuracy of the placement of the device is evaluated, any complications are identified, whether further intervention is needed is determined, and the operation result is predicted by utilizing the image and the patient data, so that continuous evaluation and management of any adverse effect or complications possibly occurring are provided to evaluate the success and safety of the puncture process.

In a specific embodiment, after step S3, the method further comprises:

Identifying a surgical risk based on the surgical related data;

Specifically, risk assessment is performed on the image collected before operation and real-time physiological information of a patient in the puncture process, potential risks in the operation process, such as vascular injury or valve injury, are identified, and warning and prompt are immediately sent out when the risks meet the early warning conditions, so that real-time assistance is provided in the puncture process.

In a specific embodiment, before step S3, the method further comprises:

receiving modification parameters of an interventional procedure planning scheme;

And updating based on the modified parameters to obtain a new interventional operation planning scheme.

Specifically, after the interventional operation planning scheme is generated, a clinician can adjust and modify information about parameters such as an optimal puncture position, a puncture direction and the like according to actual conditions, the information can be input in an external interaction mode, such as mouse clicking, text input, gesture or voice prompt and the like, and the information can also be automatically generated through a preset large model, for example, a generated artificial intelligent model automatically generates corresponding modification parameters.

In one embodiment, step S2 includes:

based on the target quantitative analysis results and/or the display results, an interventional procedure planning scheme is generated to guide the performance of the interventional procedure.

Specifically, the anatomical structure may be segmented from the preoperative image by using an image segmentation algorithm, and after the segmented second image is obtained, image analysis may be performed on the second image, and a corresponding target quantitative analysis result and/or display result may be obtained by combining the image, for example, quantitative measurement may be performed on the thickness of the diaphragm, the geometric measure of the blood vessel, the valve measurement, etc. from the segmented mask, and of course, the quantitative measurement may also be directly calculated from the original image. At the same time, anomaly detection of anatomical structures in the second image, such as aneurysms, using target detection and classification algorithms provides valuable information for the clinician to consider. The valuable information can be fed back to the clinician through different colors, shapes, symbols and characters, so that the function of warning is effectively achieved.

And intelligently evaluating the operation condition according to the obtained target quantitative analysis result and/or the display result, and generating an interventional operation planning scheme. Of course, the segmentation content in the second image can also assist in risk identification during surgery, postoperative risk assessment, treatment advice and the like.

It should be noted that the above method for guiding the interventional operation may be performed fully automatically, semi-automatically or manually by using a large basic model, for example, a large language model, a large visual model or a large multi-modal model, and using a small amount of sample Learning (Few-Shot Learning) or intelligent editing (SMART EDITING) or the like.

According to the embodiment, through carrying out image analysis on the intracardiac echocardiogram ICE, interventional operation planning is carried out before puncture, the optimal puncture angle, distance and time of puncture are found, guidance of interventional operation is achieved, real-time detection and tracking are carried out on the puncture process, potential risks in the operation process are identified and relieved, the success rate of the operation is improved, meanwhile, postoperative evaluation is also carried out, continuous evaluation and management on any adverse effects or complications possibly occurring are provided, risks of the interventional operation are comprehensively reduced, and the effect and safety of the puncture operation are improved.

Example 2

According to a second aspect of the present disclosure, there is provided a system for guiding an interventional procedure, as shown in fig. 6, the system comprising an interface 100 and a processor 200;

the interface 100 is used for collecting a plurality of image images of a target object within a preset period;

The processor 200 is configured to perform image analysis on the plurality of image images to obtain an image analysis result, and generate an interventional procedure planning scheme based on the image analysis result, so as to guide the interventional procedure to be performed.

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

the processor 200 is also configured to generate an interventional procedure planning scheme based on the target penetration region.

the processor 200 is further configured to simulate geometric changes of the fossa ovalis caused by different puncture positions on the fossa ovalis;

The processor 200 is also configured to generate an interventional procedure planning scheme based on the target puncture location.

In one embodiment, the processor 200 is further configured to determine whether a tent symptom occurs in the geometric change of the fossa ovalis, wherein the tent symptom is characterized in that a dome similar to a tent is generated at the atrial septum and points to the left atrium before the actual puncturing operation occurs, determine whether the tent symptom and the puncture needle are in the coaxial position if the tent symptom occurs, and take the position of the tent symptom as the target puncture position if the tent symptom occurs.

In one embodiment, the interventional procedure planning scheme includes at least one of a target penetration angle, a target penetration timing, a target penetration distance.

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

In a specific embodiment, the processor 200 is further configured to identify the target puncture location on a three-dimensional anatomical model or a volumetric anatomical model corresponding to the target object.

In a specific embodiment, the processor 200 is further configured to combine the plurality of image images to obtain a first image, where a field of view of the first image is larger than that of the image images;

The processor 200 is further configured to perform image analysis on the first image to obtain a first image analysis result, and generate an interventional procedure planning scheme based on the first image analysis result.

In a specific embodiment, the processor 200 is further configured to segment the plurality of image images by using a preset image segmentation algorithm to obtain a plurality of second images;

the processor 200 is further configured to perform object detection on the plurality of second images and/or the plurality of image images based on a preset object detection algorithm.

In one embodiment, the preset target detection algorithm includes a large target detection model.

In one embodiment, the interface 100 is further configured to collect surgical-related data during an interventional procedure, the interventional procedure being performed based on an interventional procedure planning scheme;

The processor 200 is further configured to obtain a post-operation evaluation result of the interventional operation according to the plurality of image images and the operation association data.

In one embodiment, the processor 200 is further configured to identify a surgical risk based on the surgical related data, and perform an early warning when the surgical risk satisfies an early warning condition.

In one embodiment, the interface 100 is further configured to receive modification parameters of the interventional procedure planning scheme;

the processor 200 is also configured to derive a new interventional procedure planning scheme based on the modified parameter updates.

In one embodiment, the interface 100 is also configured to receive modification parameters of an external interaction input.

In a specific embodiment, the interface 100 is further configured to receive modification parameters generated by the pre-defined large model.

The processor 200 is further configured to perform image analysis on the second image, combine the image images to obtain a corresponding target quantitative analysis result and/or a display result, and generate an interventional operation planning scheme based on the target quantitative analysis result and/or the display result to guide the interventional operation to be performed.

For system embodiments, reference is made to the description of method embodiments for the relevant points, since they essentially correspond to the method embodiments. The system embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the objectives of the disclosed solution.

Example 3

The disclosed embodiments also provide a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the method of guiding an interventional procedure provided by any of the embodiments described above.

More specifically, a readable storage medium may include, but is not limited to, a portable disk, hard disk, random access memory, read only memory, erasable programmable read only memory, optical storage device, magnetic storage device, or any suitable combination of the foregoing.

While specific embodiments of the present disclosure have been described above, it will be appreciated by those skilled in the art that this is by way of example only, and the scope of the disclosure is defined by the appended claims. Various changes and modifications to these embodiments may be made by those skilled in the art without departing from the principles and spirit of the disclosure, but such changes and modifications fall within the scope of the disclosure.

Claims

1. A method of guiding an interventional procedure, the method comprising:

performing image analysis on a plurality of image images to obtain an image analysis result, and generating an interventional operation planning scheme based on the image analysis result so as to guide the interventional operation to be executed;

Generating the interventional operation planning scheme according to the target puncture area;

the target object comprises a heart, and the target puncture area comprises an oval fossa on the heart;

generating the interventional operation planning scheme according to the target puncture position;

The step of determining the puncture position as the target puncture position when the preset puncture index appears in the geometric change of the fossa ovalis comprises the following steps:

If yes, the tent sign position is taken as the target puncture position.

2. The method of claim 1, wherein the interventional procedure planning scheme includes at least one of a target penetration angle, a target penetration timing, a target penetration distance.

3. The method according to claim 1, wherein the method further comprises:

And constructing a three-dimensional anatomical model or a four-dimensional anatomical model of the target object based on a plurality of the image images.

4. A method according to claim 3, characterized in that the method further comprises:

And identifying the target puncture position 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, wherein prior to the step of image analysis of a number of said photographic images, the method further comprises:

6. The method according to any one of claims 1 to 4, wherein prior to the step of performing object detection on a plurality of said photographic images using a predetermined object detection algorithm, the method further comprises:

7. The method according to any one of claims 1 to 4, wherein the preset target detection algorithm comprises a target detection large model.

8. The method according to any one of claims 1 to 4, further comprising:

9. The method of claim 8, wherein prior to performing an interventional procedure based on the interventional procedure planning scheme, the method further comprises:

10. The method of claim 9, wherein the step of receiving modification parameters of the interventional procedure planning scheme comprises:

The modification parameters of the external interaction input are received.

11. The method of claim 9, wherein the step of receiving modification parameters of the interventional procedure planning scheme comprises:

And receiving the modification parameters generated by the preset large model.

12. The method of claim 1, wherein the steps of performing an image analysis on the plurality of image images to obtain an image analysis result, and generating an interventional procedure planning scheme based on the image analysis result to guide the performing of the interventional procedure include:

13. A system for guiding an interventional procedure, the system comprising an interface and a processor;

the processor is used for carrying out image analysis on a plurality of image images to obtain an image analysis result, and generating an interventional operation planning scheme based on the image analysis result so as to guide the interventional operation to be executed;

The processor is also used for carrying out target detection on a plurality of image images by adopting a preset target detection algorithm to obtain a target puncture area on the target object;

The processor is further configured to generate the interventional procedure planning scheme according to the target puncture region;

The processor is also used for simulating geometric changes of the fossa ovalis caused by different puncture positions on the fossa ovalis, determining the puncture position as a target puncture position when a preset puncture index appears in the geometric changes of the fossa ovalis;

the processor is also used for judging whether tent symptoms occur in geometric changes of the fossa ovalis, wherein the tent symptoms represent that a dome similar to a tent shape pointing to a left atrium is generated at a room space before actual puncture actions occur, judging whether the tent symptoms and a puncture needle are in the coaxial position if the tent symptoms occur, and taking the position where the tent symptoms are located as the target puncture position if the tent symptoms occur.

14. The system of claim 13, wherein the processor is further configured 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 identify the target puncture location on the three-dimensional anatomical model or the four-dimensional anatomical model corresponding to the target object.

15. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the method of any one of claims 1 to 12.